From 87ca2b9125237e8a409f6ceca29bc2f0ba6d71a4 Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Fri, 15 Aug 2025 13:18:38 +0000
Subject: [PATCH 01/74] feat: Adding filter_cdx and warc_by_cdx commands

---
 cdx_toolkit/cli.py                 |  91 ++++++++++++++++
 cdx_toolkit/filter_cdx/__init__.py | 167 +++++++++++++++++++++++++++++
 cdx_toolkit/filter_cdx/args.py     |  64 +++++++++++
 cdx_toolkit/filter_cdx/matcher.py  |  67 ++++++++++++
 setup.py                           |   3 +
 5 files changed, 392 insertions(+)
 create mode 100644 cdx_toolkit/filter_cdx/__init__.py
 create mode 100644 cdx_toolkit/filter_cdx/args.py
 create mode 100644 cdx_toolkit/filter_cdx/matcher.py

diff --git a/cdx_toolkit/cli.py b/cdx_toolkit/cli.py
index 6ffa393..4d0ae13 100644
--- a/cdx_toolkit/cli.py
+++ b/cdx_toolkit/cli.py
@@ -4,9 +4,14 @@
 import sys
 import json
 import os
+from typing import Iterable
+
+import smart_open
 
 import cdx_toolkit
 from cdx_toolkit.commoncrawl import normalize_crawl
+from cdx_toolkit.filter_cdx import run_filter_cdx
+from cdx_toolkit.filter_cdx.args import add_filter_cdx_args
 
 LOGGER = logging.getLogger(__name__)
 
@@ -54,6 +59,20 @@ def main(args=None):
     warc.add_argument('url')
     warc.set_defaults(func=warcer)
 
+    warc_by_cdx = subparsers.add_parser('warc_by_cdx', help='iterate over capture content based on an CDX index file, creating a warc')
+    warc_by_cdx.add_argument('--prefix', default='TEST', help='prefix for the warc filename')
+    warc_by_cdx.add_argument('--subprefix', type=str, default=None, help='subprefix for the warc filename, default None')
+    warc_by_cdx.add_argument('--size', type=int, default=1000000000, help='target for the warc filesize in bytes')
+    warc_by_cdx.add_argument('--creator', action='store', help='creator of the warc: person, organization, service')
+    warc_by_cdx.add_argument('--operator', action='store', help='a person, if the creator is an organization')
+    warc_by_cdx.add_argument('--warc-download-prefix', action='store', help='prefix for downloading content, automatically set for CC')
+    warc_by_cdx.add_argument('index_path')
+    warc_by_cdx.set_defaults(func=warcer_by_cdx)
+
+    filter_cdx = subparsers.add_parser('filter_cdx', help='Filter CDX files based on SURT prefixes whitelist')
+    add_filter_cdx_args(filter_cdx)
+    filter_cdx.set_defaults(func=run_filter_cdx)
+
     size = subparsers.add_parser('size', help='imprecise count of how many results are available')
     size.add_argument('--details', action='store_true', help='show details of each subindex')
     size.add_argument('url')
@@ -214,8 +233,80 @@ def warcer(cmd, cmdline):
         writer.write_record(record)
 
 
+
+def warcer_by_cdx(cmd, cmdline):
+    """Like warcer but fetches WARC records based on an CDX index file.
+    
+    Approach:
+    - Iterate over CDX file to extract capture object (file, offset, length)
+    - Fetch WARC record based on capture object
+    - Write to new WARC file with metadata
+    """
+    cdx, kwargs = setup(cmd)
+
+    ispartof = cmd.prefix
+    if cmd.subprefix:
+        ispartof += '-' + cmd.subprefix
+
+    info = {
+        'software': 'pypi_cdx_toolkit/'+get_version(),
+        'isPartOf': ispartof,
+        'description': 'warc extraction generated with: '+cmdline,
+        'format': 'WARC file version 1.0',  # todo: if we directly read a warc, have this match the warc
+        # TODO add information from the index file
+    }
+    if cmd.creator:
+        info['creator'] = cmd.creator
+    if cmd.operator:
+        info['operator'] = cmd.operator
+
+    kwargs_writer = {}
+    if 'size' in kwargs:
+        kwargs_writer['size'] = kwargs['size']
+        del kwargs['size']
+
+    writer = cdx_toolkit.warc.get_writer(cmd.prefix, cmd.subprefix, info, **kwargs_writer)
+
+    def get_caputure_objects_from_index_file(index_path: str, warc_download_prefix=None) -> Iterable[cdx_toolkit.CaptureObject]:
+        """Read CDX index file and generate CaptureObject objects."""
+        with smart_open.open(index_path) as f:
+            for line in enumerate(f):
+                cols = line.split(" ", maxsplit=2)
+
+                if len(cols) == 3:
+                    # TODO can there be a different format?
+                    # surt, timestamp, json_data = cols 
+                    data = json.loads(cols[2])
+                    data["timestamp"] = cols[1]
+                else:
+                    raise ValueError(f"Cannot parse line: {line}")
+                
+                yield cdx_toolkit.CaptureObject(
+                    data=data, wb=None, warc_download_prefix=warc_download_prefix
+                )
+
+    # TODO probably we should support multiple indices as input
+
+    # The index file holds all the information to download specific objects (file, offset, length etc.)
+    for obj in get_caputure_objects_from_index_file(index_path=cmd.index_path, warc_download_prefix=cmd.warc_download_prefix):
+        url = obj['url']
+
+        timestamp = obj['timestamp']
+        try:
+            record = obj.fetch_warc_record()
+        except RuntimeError:  # pragma: no cover
+            LOGGER.warning('skipping capture for RuntimeError 404: %s %s', url, timestamp)
+            continue
+        if obj.is_revisit():
+            LOGGER.warning('revisit record being resolved for url %s %s', url, timestamp)
+        writer.write_record(record)
+
 def sizer(cmd, cmdline):
     cdx, kwargs = setup(cmd)
 
     size = cdx.get_size_estimate(cmd.url, **kwargs)
     print(size)
+
+
+if __name__ == "__main__":
+    main()
diff --git a/cdx_toolkit/filter_cdx/__init__.py b/cdx_toolkit/filter_cdx/__init__.py
new file mode 100644
index 0000000..1b7437c
--- /dev/null
+++ b/cdx_toolkit/filter_cdx/__init__.py
@@ -0,0 +1,167 @@
+
+import logging
+import time
+import os
+import sys
+import glob
+
+from cdx_toolkit.filter_cdx.args import validate_args
+from cdx_toolkit.filter_cdx.matcher import TupleMatcher, TrieMatcher
+
+try:
+    import smart_open
+    smart_open_installed = True
+except ImportError:
+    smart_open_installed = True
+
+logger = logging.getLogger(__name__)
+
+def run_filter_cdx(args, cmdline: str):
+    """Filter CDX index files based on a given SURT whitelist. 
+
+    - A index entry's SURT must start with one of the SURTs from the whiteliste to be considered.
+    - All other index entries are discarded.
+    - All input/output paths can be local or remote paths (S3, ...) and compressed (*.gz).
+    """
+
+    validate_args(args)
+    
+    # Resolve input and output paths using glob pattern
+    # TODO this should support glob via S3 (e.g., to fetch the indices from s3://commoncrawl/cc-index/collections/* ...)
+    input_paths, output_paths = resolve_paths(args)
+    validate_resolved_paths(output_paths, args.overwrite)
+
+    logger.info("Filtering CDX files based on whitelist")
+    logger.info(f"Found {len(input_paths)} files matching pattern: {os.path.join(args.input_base_path, args.input_glob)}")
+    
+    # Ensure output directories exist
+    # TODO make sure this works with remote paths as well!
+    ensure_output_directories(output_paths)
+    
+    # Start timing
+    start_time = time.time()
+
+    # Load SURT prefixes
+    with optional_smart_open(args.surts_file) as input_f:
+        include_surt_prefixes = [line.strip() for line in input_f.readlines()]
+
+    # Create matcher based on selected approach
+    matcher_classes = {
+        "trie": TrieMatcher,
+        "tuple": TupleMatcher,
+    }
+
+    matcher = matcher_classes[args.matching_approach](include_surt_prefixes)
+
+    logger.info(
+        f"Loaded {len(include_surt_prefixes):,} surts using {args.matching_approach} approach"
+    )
+
+    # Process each input/output file pair
+    total_lines_n = 0
+    total_included_n = 0
+
+    for input_path, output_path in zip(input_paths, output_paths):
+        logger.info("Reading index from %s", input_path)
+        logger.info("Writing filter output to %s", output_path)
+
+        lines_n = 0
+        included_n = 0
+
+        with optional_smart_open(output_path, "w") as output_f:
+            with optional_smart_open(input_path) as input_f:
+                for i, line in enumerate(input_f):
+                    surt_length = line.find(
+                        " "
+                    )  # we do not need to parse the full line
+                    record_surt = line[:surt_length]
+                    lines_n += 1
+
+                    # Use matcher
+                    include_record = matcher.matches(record_surt)
+
+                    if include_record:
+                        output_f.write(line)
+                        included_n += 1
+
+                    if (i % 100_000) == 0:
+                        logger.info(f"Lines completed: {i:,}")
+
+        logger.info(
+            f"File statistics for {input_path}: included_n={included_n}; lines_n={lines_n}; ratio={included_n/lines_n:.4f}"
+        )
+        total_lines_n += lines_n
+        total_included_n += included_n
+
+    logger.info(
+        f"Total statistics: included_n={total_included_n}; lines_n={total_lines_n}; ratio={total_included_n/total_lines_n:.4f}"
+    )
+
+    # End timing and log execution time
+    end_time = time.time()
+    execution_time = end_time - start_time
+
+    logger.info(
+        f"Script execution time: {execution_time:.3f} seconds"
+    )
+
+def optional_smart_open(*args, **kwargs):
+    """Helper function to make `smart_open` an optional dependency."""
+    if smart_open_installed:
+        return smart_open.open(*args, **kwargs)
+    else:
+        return open(*args, **kwargs)
+    
+def resolve_paths(args):
+    """Resolve input paths from glob pattern and generate corresponding output paths."""
+    # Construct full glob pattern
+    full_glob_pattern = os.path.join(args.input_base_path, args.input_glob)
+    
+    # Get input files from glob pattern
+    input_files = glob.glob(full_glob_pattern, recursive=True)
+    if not input_files:
+        logger.error(f"No files found matching glob pattern: {full_glob_pattern}")
+        sys.exit(1)
+    
+    # Sort for consistent ordering
+    input_files.sort()
+    
+    # Generate corresponding output paths
+    output_files = []
+    for input_path in input_files:
+        # Get relative path from input_base_path
+        rel_path = os.path.relpath(input_path, args.input_base_path)
+        
+        # Create corresponding output path
+        output_path = os.path.join(args.output_base_path, rel_path)
+        output_files.append(output_path)
+    
+    return input_files, output_files
+
+
+def ensure_output_directories(output_paths):
+    """Ensure all output directories exist, creating them if necessary."""
+    created_dirs = set()
+    for output_path in output_paths:
+        output_dir = os.path.dirname(output_path)
+        if output_dir and output_dir not in created_dirs:
+            os.makedirs(output_dir, exist_ok=True)
+            created_dirs.add(output_dir)
+    
+    if created_dirs:
+        logger.info(f"Created {len(created_dirs)} output directories")
+
+
+
+def validate_resolved_paths(output_paths, overwrite):
+    """Validate resolved output paths."""
+    # Check if output files exist and overwrite flag
+    if not overwrite:
+        for output_path in output_paths:
+            if os.path.exists(output_path):
+                logger.error(
+                    f"Output file already exists: {output_path}. "
+                    "Use --overwrite to overwrite existing files."
+                )
+                sys.exit(1)
+
diff --git a/cdx_toolkit/filter_cdx/args.py b/cdx_toolkit/filter_cdx/args.py
new file mode 100644
index 0000000..af2a8f8
--- /dev/null
+++ b/cdx_toolkit/filter_cdx/args.py
@@ -0,0 +1,64 @@
+import os
+import sys
+import logging
+import argparse
+
+
+logger = logging.getLogger(__name__)
+
+
+def add_filter_cdx_args(parser: argparse.ArgumentParser):
+    """Add command line arguments."""
+    parser.add_argument(
+        "input_base_path",
+        help="Base directory path for input files"
+    )
+    
+    parser.add_argument(
+        "input_glob",
+        help="Glob pattern relative to input_base_path (e.g., '**/*.cdx.gz' or 'collections/*/indexes/*.gz')"
+    )
+    
+    parser.add_argument(
+        "output_base_path",
+        help="Base directory path for output files (directory structure will be replicated from input_base_path)"
+    )
+
+    parser.add_argument(
+        "--surts_file",
+        required=True,
+        help="Path to file containing SURT prefixes to match (one per line)",
+    )
+
+    parser.add_argument(
+        "--matching_approach",
+        choices=["trie", "tuple"],
+        default="trie",
+        help="Matching approach to use (default: trie)",
+    )
+
+    parser.add_argument(
+        "--overwrite",
+        action="store_true",
+        help="Allow overwriting existing output files",
+    )
+
+    return parser
+
+
+
+def validate_args(args):
+    """Validate command line arguments."""
+    # Check that surts file exists
+    if not os.path.exists(args.surts_file):
+        logger.error(f"SURT file not found: {args.surts_file}")
+        sys.exit(1)
+    
+    # Check that input_base_path exists
+    if not os.path.exists(args.input_base_path):
+        logger.error(f"Input base path not found: {args.input_base_path}")
+        sys.exit(1)
+    
+    if not os.path.isdir(args.input_base_path):
+        logger.error(f"Input base path is not a directory: {args.input_base_path}")
+        sys.exit(1)
diff --git a/cdx_toolkit/filter_cdx/matcher.py b/cdx_toolkit/filter_cdx/matcher.py
new file mode 100644
index 0000000..75c8af0
--- /dev/null
+++ b/cdx_toolkit/filter_cdx/matcher.py
@@ -0,0 +1,67 @@
+import logging
+from abc import ABC, abstractmethod
+
+logger = logging.getLogger(__name__)
+
+
+class Matcher(ABC):
+    """Base class for all matching approaches."""
+
+    @abstractmethod
+    def __init__(self, prefixes: tuple[str] | list[str]):
+        """Initialize the matcher with a list of prefixes."""
+        pass
+
+    @abstractmethod
+    def matches(self, text: str) -> bool:
+        """Check if text starts with any of the prefixes."""
+        pass
+
+
+class TrieNode:
+    def __init__(self):
+        self.children = {}
+        self.is_end = False
+
+
+class TrieMatcher(Matcher):
+    """Trie-based matching approach."""
+
+    def __init__(self, prefixes: tuple[str] | list[str]):
+        logger.info(f"Building trie matcher based on {len(prefixes):,} inputs")
+        self.root = self._build_trie(prefixes)
+
+    def _build_trie(self, prefixes: tuple[str] | list[str]):
+        """Build a trie from a collection of prefixes."""
+        root = TrieNode()
+        for prefix in prefixes:
+            node = root
+            for char in prefix:
+                if char not in node.children:
+                    node.children[char] = TrieNode()
+                node = node.children[char]
+            node.is_end = True
+        return root
+
+    def matches(self, text: str) -> bool:
+        """Check if text starts with any prefix in the trie."""
+        node = self.root
+        for char in text:
+            if char not in node.children:
+                return False
+            node = node.children[char]
+            if node.is_end:
+                return True
+        return False
+
+
+class TupleMatcher(Matcher):
+    """Tuple-based matching approach using startswith."""
+
+    def __init__(self, prefixes: tuple[str] | list[str]):
+        logger.info(f"Building tuple matcher based on {len(prefixes):,} inputs")
+        self.prefixes_tuple = tuple(prefixes)
+
+    def matches(self, text: str) -> bool:
+        """Check if text starts with any prefix in the tuple."""
+        return text.startswith(self.prefixes_tuple)
diff --git a/setup.py b/setup.py
index bceaefb..3b30256 100755
--- a/setup.py
+++ b/setup.py
@@ -16,9 +16,12 @@
 
 package_requirements = ['twine', 'setuptools', 'setuptools-scm']
 
+warc_by_cdx_requirements = ['smart-open']
+
 extras_require = {
     'test': test_requirements,  # setup no longer tests, so make them an extra
     'package': package_requirements,
+    'warc_by_cdx': warc_by_cdx_requirements,  # extra for the "warc_by_cdx command
 }
 
 scripts = ['scripts/cdx_size', 'scripts/cdx_iter']

From e331beeeb5897ce762d0ea507ff5103dc54939e2 Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Tue, 19 Aug 2025 17:04:07 +0000
Subject: [PATCH 02/74] Adding unit test for filter_cdx command, some
 refactoring

---
 cdx_toolkit/cli.py                           | 130 ++----------------
 cdx_toolkit/filter_cdx/__init__.py           | 131 +++++++++----------
 cdx_toolkit/filter_cdx/args.py               |  34 +----
 cdx_toolkit/utils.py                         |  48 +++++++
 cdx_toolkit/warcer_by_cdx/__init__.py        | 103 +++++++++++++++
 cdx_toolkit/warcer_by_cdx/args.py            |  20 +++
 requirements.txt                             |   1 +
 setup.py                                     |   5 +-
 tests/data/filter_cdx/whitelist_10_surts.txt |  10 ++
 tests/test_cli_filter_cdx.py                 |  49 +++++++
 10 files changed, 312 insertions(+), 219 deletions(-)
 create mode 100644 cdx_toolkit/utils.py
 create mode 100644 cdx_toolkit/warcer_by_cdx/__init__.py
 create mode 100644 cdx_toolkit/warcer_by_cdx/args.py
 create mode 100644 tests/data/filter_cdx/whitelist_10_surts.txt
 create mode 100644 tests/test_cli_filter_cdx.py

diff --git a/cdx_toolkit/cli.py b/cdx_toolkit/cli.py
index 4d0ae13..0ca89db 100644
--- a/cdx_toolkit/cli.py
+++ b/cdx_toolkit/cli.py
@@ -4,15 +4,18 @@
 import sys
 import json
 import os
-from typing import Iterable
-
-import smart_open
 
 import cdx_toolkit
-from cdx_toolkit.commoncrawl import normalize_crawl
+
+from cdx_toolkit.utils import get_version, setup
+
 from cdx_toolkit.filter_cdx import run_filter_cdx
 from cdx_toolkit.filter_cdx.args import add_filter_cdx_args
 
+from cdx_toolkit.warcer_by_cdx import run_warcer_by_cdx
+from cdx_toolkit.warcer_by_cdx.args import add_warcer_by_cdx_args
+
+
 LOGGER = logging.getLogger(__name__)
 
 
@@ -60,14 +63,8 @@ def main(args=None):
     warc.set_defaults(func=warcer)
 
     warc_by_cdx = subparsers.add_parser('warc_by_cdx', help='iterate over capture content based on an CDX index file, creating a warc')
-    warc_by_cdx.add_argument('--prefix', default='TEST', help='prefix for the warc filename')
-    warc_by_cdx.add_argument('--subprefix', type=str, default=None, help='subprefix for the warc filename, default None')
-    warc_by_cdx.add_argument('--size', type=int, default=1000000000, help='target for the warc filesize in bytes')
-    warc_by_cdx.add_argument('--creator', action='store', help='creator of the warc: person, organization, service')
-    warc_by_cdx.add_argument('--operator', action='store', help='a person, if the creator is an organization')
-    warc_by_cdx.add_argument('--warc-download-prefix', action='store', help='prefix for downloading content, automatically set for CC')
-    warc_by_cdx.add_argument('index_path')
-    warc_by_cdx.set_defaults(func=warcer_by_cdx)
+    add_warcer_by_cdx_args(warc_by_cdx)
+    warc_by_cdx.set_defaults(func=run_warcer_by_cdx)
 
     filter_cdx = subparsers.add_parser('filter_cdx', help='Filter CDX files based on SURT prefixes whitelist')
     add_filter_cdx_args(filter_cdx)
@@ -108,48 +105,6 @@ def set_loglevel(cmd):
     LOGGER.info('set loglevel to %s', str(loglevel))
 
 
-def get_version():
-    return cdx_toolkit.__version__
-
-
-def setup(cmd):
-    kwargs = {}
-    kwargs['source'] = 'cc' if cmd.crawl else cmd.cc or cmd.ia or cmd.source or None
-    if kwargs['source'] is None:
-        raise ValueError('must specify --cc, --ia, or a --source')
-    if cmd.wb:
-        kwargs['wb'] = cmd.wb
-    if cmd.cc_mirror:
-        kwargs['cc_mirror'] = cmd.cc_mirror
-    if cmd.crawl:
-        kwargs['crawl'] = normalize_crawl([cmd.crawl])  # currently a string, not a list
-    if getattr(cmd, 'warc_download_prefix', None) is not None:
-        kwargs['warc_download_prefix'] = cmd.warc_download_prefix
-
-    cdx = cdx_toolkit.CDXFetcher(**kwargs)
-
-    kwargs = {}
-    if cmd.limit:
-        kwargs['limit'] = cmd.limit
-    if 'from' in vars(cmd) and vars(cmd)['from']:  # python, uh, from is a reserved word
-        kwargs['from_ts'] = vars(cmd)['from']
-    if cmd.to:
-        kwargs['to'] = cmd.to
-    if cmd.closest:
-        if not cmd.get:  # pragma: no cover
-            LOGGER.info('note: --closest works best with --get')
-        kwargs['closest'] = cmd.closest
-    if cmd.filter:
-        kwargs['filter'] = cmd.filter
-
-    if cmd.cmd == 'warc' and cmd.size:
-        kwargs['size'] = cmd.size
-
-    if cmd.cmd == 'size' and cmd.details:
-        kwargs['details'] = cmd.details
-
-    return cdx, kwargs
-
 
 def winnow_fields(cmd, fields, obj):
     if cmd.all_fields:
@@ -234,73 +189,6 @@ def warcer(cmd, cmdline):
 
 
 
-def warcer_by_cdx(cmd, cmdline):
-    """Like warcer but fetches WARC records based on an CDX index file.
-    
-    Approach:
-    - Iterate over CDX file to extract capture object (file, offset, length)
-    - Fetch WARC record based on capture object
-    - Write to new WARC file with metadata
-    """
-    cdx, kwargs = setup(cmd)
-
-    ispartof = cmd.prefix
-    if cmd.subprefix:
-        ispartof += '-' + cmd.subprefix
-
-    info = {
-        'software': 'pypi_cdx_toolkit/'+get_version(),
-        'isPartOf': ispartof,
-        'description': 'warc extraction generated with: '+cmdline,
-        'format': 'WARC file version 1.0',  # todo: if we directly read a warc, have this match the warc
-        # TODO add information from the index file
-    }
-    if cmd.creator:
-        info['creator'] = cmd.creator
-    if cmd.operator:
-        info['operator'] = cmd.operator
-
-    kwargs_writer = {}
-    if 'size' in kwargs:
-        kwargs_writer['size'] = kwargs['size']
-        del kwargs['size']
-
-    writer = cdx_toolkit.warc.get_writer(cmd.prefix, cmd.subprefix, info, **kwargs_writer)
-
-    def get_caputure_objects_from_index_file(index_path: str, warc_download_prefix=None) -> Iterable[cdx_toolkit.CaptureObject]:
-        """Read CDX index file and generate CaptureObject objects."""
-        with smart_open.open(index_path) as f:
-            for line in enumerate(f):
-                cols = line.split(" ", maxsplit=2)
-
-                if len(cols) == 3:
-                    # TODO can there be a different format?
-                    # surt, timestamp, json_data = cols 
-                    data = json.loads(cols[2])
-                    data["timestamp"] = cols[1]
-                else:
-                    raise ValueError(f"Cannot parse line: {line}")
-                
-                yield cdx_toolkit.CaptureObject(
-                    data=data, wb=None, warc_download_prefix=warc_download_prefix
-                )
-
-    # TODO probably we should support multiple indices as input
-
-    # The index file holds all the information to download specific objects (file, offset, length etc.)
-    for obj in get_caputure_objects_from_index_file(index_path=cmd.index_path, warc_download_prefix=cmd.warc_download_prefix):
-        url = obj['url']
-
-        timestamp = obj['timestamp']
-        try:
-            record = obj.fetch_warc_record()
-        except RuntimeError:  # pragma: no cover
-            LOGGER.warning('skipping capture for RuntimeError 404: %s %s', url, timestamp)
-            continue
-        if obj.is_revisit():
-            LOGGER.warning('revisit record being resolved for url %s %s', url, timestamp)
-        writer.write_record(record)
-
 def sizer(cmd, cmdline):
     cdx, kwargs = setup(cmd)
 
diff --git a/cdx_toolkit/filter_cdx/__init__.py b/cdx_toolkit/filter_cdx/__init__.py
index 1b7437c..92152c7 100644
--- a/cdx_toolkit/filter_cdx/__init__.py
+++ b/cdx_toolkit/filter_cdx/__init__.py
@@ -1,48 +1,44 @@
 
 import logging
-import time
 import os
+import time
 import sys
-import glob
 
-from cdx_toolkit.filter_cdx.args import validate_args
+import fsspec
+
 from cdx_toolkit.filter_cdx.matcher import TupleMatcher, TrieMatcher
 
-try:
-    import smart_open
-    smart_open_installed = True
-except ImportError:
-    smart_open_installed = True
 
 logger = logging.getLogger(__name__)
 
 def run_filter_cdx(args, cmdline: str):
     """Filter CDX index files based on a given SURT whitelist. 
 
-    - A index entry's SURT must start with one of the SURTs from the whiteliste to be considered.
+    - A index entry's SURT must start with one of the SURTs from the whitelist to be considered.
     - All other index entries are discarded.
     - All input/output paths can be local or remote paths (S3, ...) and compressed (*.gz).
     """
+    logger.info("Filtering CDX files based on whitelist")
 
-    validate_args(args)
+    # Start timing
+    start_time = time.time()
     
     # Resolve input and output paths using glob pattern
-    # TODO this should support glob via S3 (e.g., to fetch the indices from s3://commoncrawl/cc-index/collections/* ...)
-    input_paths, output_paths = resolve_paths(args)
+    # This should support glob via S3 (e.g., to fetch the indices from s3://commoncrawl/cc-index/collections/* ...)
+    input_paths, output_paths = resolve_paths(input_base_path=args.input_base_path, input_glob=args.input_glob, output_base_path=args.output_base_path)
     validate_resolved_paths(output_paths, args.overwrite)
 
-    logger.info("Filtering CDX files based on whitelist")
-    logger.info(f"Found {len(input_paths)} files matching pattern: {os.path.join(args.input_base_path, args.input_glob)}")
+    logger.info(f"Found {len(input_paths)} files matching pattern: {args.input_base_path}/{args.input_glob}")
     
-    # Ensure output directories exist
-    # TODO make sure this works with remote paths as well!
-    ensure_output_directories(output_paths)
-    
-    # Start timing
-    start_time = time.time()
+    # Load SURT prefixes from file (each line is a surt)
+    surt_fs, surt_fs_path = fsspec.url_to_fs(args.surts_file)
+    logger.info("Loading whitelist from %s", surt_fs_path)
 
-    # Load SURT prefixes
-    with optional_smart_open(args.surts_file) as input_f:
+    if not surt_fs.exists(surt_fs_path):  # Check that surts file exists
+        logger.error(f"SURT file not found: {surt_fs_path}")
+        sys.exit(1)
+    
+    with surt_fs.open(surt_fs_path, "rt") as input_f:
         include_surt_prefixes = [line.strip() for line in input_f.readlines()]
 
     # Create matcher based on selected approach
@@ -60,6 +56,7 @@ def run_filter_cdx(args, cmdline: str):
     # Process each input/output file pair
     total_lines_n = 0
     total_included_n = 0
+    log_every_n = 100_000
 
     for input_path, output_path in zip(input_paths, output_paths):
         logger.info("Reading index from %s", input_path)
@@ -68,9 +65,20 @@ def run_filter_cdx(args, cmdline: str):
         lines_n = 0
         included_n = 0
 
-        with optional_smart_open(output_path, "w") as output_f:
-            with optional_smart_open(input_path) as input_f:
-                for i, line in enumerate(input_f):
+        # Input/output from local or remote file system
+        input_fs, input_fs_path = fsspec.url_to_fs(input_path)
+        output_fs, output_fs_path = fsspec.url_to_fs(output_path)
+        
+        # Make sure output directory exists
+        output_fs.makedirs(output_fs._parent(output_fs_path), exist_ok=True)
+
+        # Read and write compressed file if needed
+        compression = "gzip" if input_fs_path.endswith(".gz") else None
+
+        with output_fs.open(output_fs_path, "w", compression=compression) as output_f:
+            with input_fs.open(input_fs_path, "rt", compression=compression) as input_f:
+                for i, line in enumerate(input_f, 1):
+                    # Read CDX line
                     surt_length = line.find(
                         " "
                     )  # we do not need to parse the full line
@@ -84,8 +92,13 @@ def run_filter_cdx(args, cmdline: str):
                         output_f.write(line)
                         included_n += 1
 
-                    if (i % 100_000) == 0:
-                        logger.info(f"Lines completed: {i:,}")
+                        if args.limit > 0 and included_n >= args.limit:
+                            logger.info("Limit reached at %i", args.limit)
+                            break
+
+
+                    if (i % log_every_n) == 0:
+                        logger.info(f"Lines completed: {i:,} (matched: {included_n:,})")
 
         logger.info(
             f"File statistics for {input_path}: included_n={included_n}; lines_n={lines_n}; ratio={included_n/lines_n:.4f}"
@@ -105,63 +118,47 @@ def run_filter_cdx(args, cmdline: str):
         f"Script execution time: {execution_time:.3f} seconds"
     )
 
-def optional_smart_open(*args, **kwargs):
-    """Helper function to make `smart_open` an optional dependency."""
-    if smart_open_installed:
-        return smart_open.open(*args, **kwargs)
-    else:
-        return open(*args, **kwargs)
     
-def resolve_paths(args):
+def resolve_paths(input_base_path: str, input_glob: str,  output_base_path: str):
     """Resolve input paths from glob pattern and generate corresponding output paths."""
-    # Construct full glob pattern
-    full_glob_pattern = os.path.join(args.input_base_path, args.input_glob)
-    
+    # Use fsspec to handle local and remote file systems
+    input_fs, input_fs_base_path = fsspec.url_to_fs(input_base_path)
+    input_full_glob = input_fs_base_path + input_glob
+
     # Get input files from glob pattern
-    input_files = glob.glob(full_glob_pattern, recursive=True)
-    if not input_files:
-        logger.error(f"No files found matching glob pattern: {full_glob_pattern}")
+    input_fs_file_paths = sorted(input_fs.glob(input_full_glob))
+    if not input_fs_file_paths:
+        logger.error(f"No files found matching glob pattern: {input_full_glob}")
         sys.exit(1)
     
-    # Sort for consistent ordering
-    input_files.sort()
-    
     # Generate corresponding output paths
-    output_files = []
-    for input_path in input_files:
-        # Get relative path from input_base_path
-        rel_path = os.path.relpath(input_path, args.input_base_path)
+    output_file_paths = []
+    input_file_paths = []
+    for input_path in input_fs_file_paths:
+        # Get relative path from input_base_path without last slash
+        rel_path = input_path[len(input_fs_base_path)+1:]
         
-        # Create corresponding output path
-        output_path = os.path.join(args.output_base_path, rel_path)
-        output_files.append(output_path)
+        # Create corresponding full input and output path
+        output_file_paths.append(os.path.join(output_base_path, rel_path))
+        input_file_paths.append(os.path.join(input_base_path, rel_path))
     
-    return input_files, output_files
-
-
-def ensure_output_directories(output_paths):
-    """Ensure all output directories exist, creating them if necessary."""
-    created_dirs = set()
-    for output_path in output_paths:
-        output_dir = os.path.dirname(output_path)
-        if output_dir and output_dir not in created_dirs:
-            os.makedirs(output_dir, exist_ok=True)
-            created_dirs.add(output_dir)
-    
-    if created_dirs:
-        logger.info(f"Created {len(created_dirs)} output directories")
-
+    return input_file_paths, output_file_paths
 
 
 def validate_resolved_paths(output_paths, overwrite):
-    """Validate resolved output paths."""
+    """Validate resolved output paths and create directories if needed."""
     # Check if output files exist and overwrite flag
     if not overwrite:
+        output_fs, _ = fsspec.url_to_fs(output_paths[0])
         for output_path in output_paths:
-            if os.path.exists(output_path):
+            if output_fs.exists(output_path):
                 logger.error(
                     f"Output file already exists: {output_path}. "
                     "Use --overwrite to overwrite existing files."
                 )
                 sys.exit(1)
 
+            # Make sure directory exists
+            output_fs.makedirs(output_fs._parent(output_path), exist_ok=True)
+        
+
diff --git a/cdx_toolkit/filter_cdx/args.py b/cdx_toolkit/filter_cdx/args.py
index af2a8f8..02e46fe 100644
--- a/cdx_toolkit/filter_cdx/args.py
+++ b/cdx_toolkit/filter_cdx/args.py
@@ -3,6 +3,8 @@
 import logging
 import argparse
 
+import fsspec
+
 
 logger = logging.getLogger(__name__)
 
@@ -11,25 +13,20 @@ def add_filter_cdx_args(parser: argparse.ArgumentParser):
     """Add command line arguments."""
     parser.add_argument(
         "input_base_path",
-        help="Base directory path for input files"
+        help="Base directory path or remote URL for one or multiple input files (e.g., URL to S3 bucket)"
     )
-    
     parser.add_argument(
-        "input_glob",
-        help="Glob pattern relative to input_base_path (e.g., '**/*.cdx.gz' or 'collections/*/indexes/*.gz')"
+        "surts_file",
+        help="Path to file containing SURT prefixes to match (one per line)",
     )
-    
     parser.add_argument(
         "output_base_path",
         help="Base directory path for output files (directory structure will be replicated from input_base_path)"
     )
-
     parser.add_argument(
-        "--surts_file",
-        required=True,
-        help="Path to file containing SURT prefixes to match (one per line)",
+        "--input_glob",
+        help="Glob pattern relative to input_base_path (e.g., '**/*.cdx.gz' or 'collections/*/indexes/*.gz')"
     )
-
     parser.add_argument(
         "--matching_approach",
         choices=["trie", "tuple"],
@@ -45,20 +42,3 @@ def add_filter_cdx_args(parser: argparse.ArgumentParser):
 
     return parser
 
-
-
-def validate_args(args):
-    """Validate command line arguments."""
-    # Check that surts file exists
-    if not os.path.exists(args.surts_file):
-        logger.error(f"SURT file not found: {args.surts_file}")
-        sys.exit(1)
-    
-    # Check that input_base_path exists
-    if not os.path.exists(args.input_base_path):
-        logger.error(f"Input base path not found: {args.input_base_path}")
-        sys.exit(1)
-    
-    if not os.path.isdir(args.input_base_path):
-        logger.error(f"Input base path is not a directory: {args.input_base_path}")
-        sys.exit(1)
diff --git a/cdx_toolkit/utils.py b/cdx_toolkit/utils.py
new file mode 100644
index 0000000..f175d76
--- /dev/null
+++ b/cdx_toolkit/utils.py
@@ -0,0 +1,48 @@
+import cdx_toolkit
+from cdx_toolkit.commoncrawl import normalize_crawl
+
+import logging
+
+LOGGER = logging.getLogger(__name__)
+
+def get_version():
+    return cdx_toolkit.__version__
+
+
+def setup(cmd):
+    kwargs = {}
+    kwargs['source'] = 'cc' if cmd.crawl else cmd.cc or cmd.ia or cmd.source or None
+    if kwargs['source'] is None:
+        raise ValueError('must specify --cc, --ia, or a --source')
+    if cmd.wb:
+        kwargs['wb'] = cmd.wb
+    if cmd.cc_mirror:
+        kwargs['cc_mirror'] = cmd.cc_mirror
+    if cmd.crawl:
+        kwargs['crawl'] = normalize_crawl([cmd.crawl])  # currently a string, not a list
+    if getattr(cmd, 'warc_download_prefix', None) is not None:
+        kwargs['warc_download_prefix'] = cmd.warc_download_prefix
+
+    cdx = cdx_toolkit.CDXFetcher(**kwargs)
+
+    kwargs = {}
+    if cmd.limit:
+        kwargs['limit'] = cmd.limit
+    if 'from' in vars(cmd) and vars(cmd)['from']:  # python, uh, from is a reserved word
+        kwargs['from_ts'] = vars(cmd)['from']
+    if cmd.to:
+        kwargs['to'] = cmd.to
+    if cmd.closest:
+        if not cmd.get:  # pragma: no cover
+            LOGGER.info('note: --closest works best with --get')
+        kwargs['closest'] = cmd.closest
+    if cmd.filter:
+        kwargs['filter'] = cmd.filter
+
+    if cmd.cmd == 'warc' and cmd.size:
+        kwargs['size'] = cmd.size
+
+    if cmd.cmd == 'size' and cmd.details:
+        kwargs['details'] = cmd.details
+
+    return cdx, kwargs
diff --git a/cdx_toolkit/warcer_by_cdx/__init__.py b/cdx_toolkit/warcer_by_cdx/__init__.py
new file mode 100644
index 0000000..f6a109e
--- /dev/null
+++ b/cdx_toolkit/warcer_by_cdx/__init__.py
@@ -0,0 +1,103 @@
+
+import json
+import logging
+import sys
+from typing import Iterable
+
+import fsspec
+
+import cdx_toolkit
+from cdx_toolkit.utils import get_version, setup
+
+
+LOGGER = logging.getLogger(__name__)
+
+
+def run_warcer_by_cdx(cmd, cmdline):
+    """Like warcer but fetches WARC records based on an CDX index file.
+    
+    Approach:
+    - Iterate over CDX file to extract capture object (file, offset, length)
+    - Fetch WARC record based on capture object
+    - Write to new WARC file with metadata
+    """
+    cdx, kwargs = setup(cmd)
+
+    ispartof = cmd.prefix
+    if cmd.subprefix:
+        ispartof += '-' + cmd.subprefix
+
+    info = {
+        'software': 'pypi_cdx_toolkit/'+get_version(),
+        'isPartOf': ispartof,
+        'description': 'warc extraction generated with: '+cmdline,
+        'format': 'WARC file version 1.0',  # todo: if we directly read a warc, have this match the warc
+        # TODO add information from the index file
+    }
+    if cmd.creator:
+        info['creator'] = cmd.creator
+    if cmd.operator:
+        info['operator'] = cmd.operator
+
+    kwargs_writer = {}
+    if 'size' in kwargs:
+        kwargs_writer['size'] = kwargs['size']
+        del kwargs['size']
+
+    writer = cdx_toolkit.warc.get_writer(cmd.prefix, cmd.subprefix, info, **kwargs_writer)
+
+    # TODO probably we should support multiple indices as input
+
+    if cmd.index_glob is None:
+        # Read from a single index
+        index_paths = [cmd.index_path]
+    else:
+        # Fetch multiple indicies via glob
+        index_fs, index_fs_path = fsspec.url_to_fs(cmd.index_path)
+        index_paths = sorted(index_fs.glob(cmd.index_glob))
+
+        LOGGER.info('glob pattern found %i index files in %s', len(index_paths), index_fs_path)
+
+        if not index_paths:
+            LOGGER.error('no index files found')
+            sys.exit(1)
+            
+    # Iterate over index files
+    for index_path in index_paths:
+        LOGGER.info('filtering based on index from %s', index_path)
+
+        # The index file holds all the information to download specific objects (file, offset, length etc.)
+        for obj in get_caputure_objects_from_index_file(index_path=index_path, warc_download_prefix=cmd.warc_download_prefix):
+            url = obj['url']
+
+            timestamp = obj['timestamp']
+            try:
+                record = obj.fetch_warc_record()
+            except RuntimeError:  # pragma: no cover
+                LOGGER.warning('skipping capture for RuntimeError 404: %s %s', url, timestamp)
+                continue
+            if obj.is_revisit():
+                LOGGER.warning('revisit record being resolved for url %s %s', url, timestamp)
+            writer.write_record(record)
+
+        LOGGER.info('filtering completed (index: %s)', index_path)
+
+def get_caputure_objects_from_index_file(index_path: str, warc_download_prefix=None) -> Iterable[cdx_toolkit.CaptureObject]:
+    """Read CDX index file and generate CaptureObject objects."""
+    index_fs, index_fs_path = fsspec.url_to_fs(index_path)
+    
+    with index_fs.open(index_fs_path) as f:
+        for line in enumerate(f):
+            cols = line.split(" ", maxsplit=2)
+
+            if len(cols) == 3:
+                # TODO can there be a different format?
+                # surt, timestamp, json_data = cols 
+                data = json.loads(cols[2])
+                data["timestamp"] = cols[1]
+            else:
+                raise ValueError(f"Cannot parse line: {line}")
+            
+            yield cdx_toolkit.CaptureObject(
+                data=data, wb=None, warc_download_prefix=warc_download_prefix
+            )
diff --git a/cdx_toolkit/warcer_by_cdx/args.py b/cdx_toolkit/warcer_by_cdx/args.py
new file mode 100644
index 0000000..f31ac2f
--- /dev/null
+++ b/cdx_toolkit/warcer_by_cdx/args.py
@@ -0,0 +1,20 @@
+import os
+import sys
+import logging
+import argparse
+
+
+logger = logging.getLogger(__name__)
+
+
+def add_warcer_by_cdx_args(parser: argparse.ArgumentParser):
+    parser.add_argument('--prefix', default='TEST', help='prefix for the warc filename')
+    parser.add_argument('--subprefix', type=str, default=None, help='subprefix for the warc filename, default None')
+    parser.add_argument('--size', type=int, default=1000000000, help='target for the warc filesize in bytes')
+    parser.add_argument('--creator', action='store', help='creator of the warc: person, organization, service')
+    parser.add_argument('--operator', action='store', help='a person, if the creator is an organization')
+    parser.add_argument('--warc-download-prefix', action='store', help='prefix for downloading content, automatically set for CC')
+    parser.add_argument('--index-glob', type=str, default=None, help='a glob pattern for read from multiple indices')
+    parser.add_argument('index_path', help='Path to CDX index file (local or remote, e.g. S3)')
+
+    return parser
\ No newline at end of file
diff --git a/requirements.txt b/requirements.txt
index 2d0357f..af525d7 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -3,6 +3,7 @@
 
 requests==2.25.1
 warcio==1.7.4
+fsspec[s3]
 
 # used by Makefile
 pytest==6.2.4
diff --git a/setup.py b/setup.py
index 3b30256..8d57c1d 100755
--- a/setup.py
+++ b/setup.py
@@ -10,18 +10,15 @@
 ]
 
 # remember: keep requires synchronized with requirements.txt
-requires = ['requests', 'warcio']
+requires = ['requests', 'warcio', 'fsspec[s3]']
 
 test_requirements = ['pytest', 'pytest-cov']
 
 package_requirements = ['twine', 'setuptools', 'setuptools-scm']
 
-warc_by_cdx_requirements = ['smart-open']
-
 extras_require = {
     'test': test_requirements,  # setup no longer tests, so make them an extra
     'package': package_requirements,
-    'warc_by_cdx': warc_by_cdx_requirements,  # extra for the "warc_by_cdx command
 }
 
 scripts = ['scripts/cdx_size', 'scripts/cdx_iter']
diff --git a/tests/data/filter_cdx/whitelist_10_surts.txt b/tests/data/filter_cdx/whitelist_10_surts.txt
new file mode 100644
index 0000000..0754ed2
--- /dev/null
+++ b/tests/data/filter_cdx/whitelist_10_surts.txt
@@ -0,0 +1,10 @@
+com,example)/
+edu,si)/
+com,youtube)/
+gov,archives)/
+gov,census)/
+com,741,onlinedegrees)/online_university_degree_program.html
+com,72pines,star)/2007/06/25/%e6%8f%90%e5%8f%96%e5%85%ac%e7%a7%af%e9%87%91/trackback
+fr,missiondefrance,bibliotheque)/
+fr,mnhn,biodiv)/fr/taxonomy
+fr,mobilierpourchr,wip)/produit/t-837
diff --git a/tests/test_cli_filter_cdx.py b/tests/test_cli_filter_cdx.py
new file mode 100644
index 0000000..92c9fab
--- /dev/null
+++ b/tests/test_cli_filter_cdx.py
@@ -0,0 +1,49 @@
+from pathlib import Path
+
+from cdx_toolkit.cli import main
+from cdx_toolkit.filter_cdx import resolve_paths
+
+fixture_path = Path(__file__).parent / "data/filter_cdx"
+
+def test_filter_cdx(tmpdir, caplog):
+    # check if expected number is reached
+
+    index_path = "s3://commoncrawl/cc-index/collections"
+    index_glob = "/CC-MAIN-2024-30/indexes/cdx-00187.gz"
+    whitelist_path = fixture_path / "whitelist_10_surts.txt"  # matches on first domain and after 100k and 200k lines
+    
+    main(args=f"-v --limit 1140 filter_cdx {index_path} {str(whitelist_path)} {tmpdir} --input_glob {index_glob}".split())
+
+    assert "Limit reached" in caplog.text
+
+
+def test_resolve_cdx_paths_from_cc_s3_to_local(tmpdir):
+    tmpdir = str(tmpdir)
+    base_path = "s3://commoncrawl/cc-index/collections"
+    glob_pattern = "/CC-MAIN-2016-30/indexes/*.gz"
+
+    input_files, output_files = resolve_paths(base_path, glob_pattern, output_base_path=tmpdir)
+
+    assert len(input_files) == len(output_files), "Input and output count must be the same"
+    assert len(input_files) == 300, "Invalid input count"
+    assert input_files[0] == base_path + "/CC-MAIN-2016-30/indexes/cdx-00000.gz", "Invalid input file"
+    assert output_files[0] == tmpdir + "/CC-MAIN-2016-30/indexes/cdx-00000.gz", "Invalid output file"
+    assert input_files[-1] == base_path + '/CC-MAIN-2016-30/indexes/cdx-00299.gz'
+
+
+def test_resolve_cdx_paths_from_cc_s3_to_another_s3():
+    output_base_path = "s3://some-other-bucket/filter-cdx"
+    base_path = "s3://commoncrawl/cc-index/collections"
+    glob_pattern = "/CC-MAIN-2016-30/indexes/cdx-000*.gz"
+
+    input_files, output_files = resolve_paths(base_path, glob_pattern, output_base_path=output_base_path)
+
+    assert len(input_files) == len(output_files), "Input and output count must be the same"
+    assert len(input_files) == 100, "Invalid input count"
+    assert input_files[0] == base_path + "/CC-MAIN-2016-30/indexes/cdx-00000.gz", "Invalid input file"
+    assert output_files[0] == output_base_path + "/CC-MAIN-2016-30/indexes/cdx-00000.gz", "Invalid output file"
+    assert input_files[-1] == base_path + '/CC-MAIN-2016-30/indexes/cdx-00099.gz'
+
+
+if __name__ == "__main__":
+    test_resolve_cdx_paths_from_cc_s3_to_local("./data/tmp")

From 4dcf3a1e6ba13978c9649a07b48fd35ab37e0581 Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Wed, 20 Aug 2025 17:17:25 +0000
Subject: [PATCH 03/74] Adding unit tests for warc_by_cdx and index resource
 record

---
 cdx_toolkit/filter_cdx/__init__.py            |   41 +-
 cdx_toolkit/filter_cdx/args.py                |    9 -
 cdx_toolkit/warcer_by_cdx/__init__.py         |  171 ++-
 cdx_toolkit/warcer_by_cdx/args.py             |   45 +-
 tests/data/warc_by_cdx/cdx-00187              | 1140 +++++++++++++++++
 .../filtered_CC-MAIN-2024-30_cdx-00187.gz     |  Bin 0 -> 63684 bytes
 tests/test_cli_filter_cdx.py                  |   48 +-
 tests/test_cli_warc_by_cdx.py                 |   28 +
 8 files changed, 1374 insertions(+), 108 deletions(-)
 create mode 100644 tests/data/warc_by_cdx/cdx-00187
 create mode 100644 tests/data/warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.gz
 create mode 100644 tests/test_cli_warc_by_cdx.py

diff --git a/cdx_toolkit/filter_cdx/__init__.py b/cdx_toolkit/filter_cdx/__init__.py
index 92152c7..da38e5b 100644
--- a/cdx_toolkit/filter_cdx/__init__.py
+++ b/cdx_toolkit/filter_cdx/__init__.py
@@ -1,4 +1,3 @@
-
 import logging
 import os
 import time
@@ -11,8 +10,9 @@
 
 logger = logging.getLogger(__name__)
 
+
 def run_filter_cdx(args, cmdline: str):
-    """Filter CDX index files based on a given SURT whitelist. 
+    """Filter CDX index files based on a given SURT whitelist.
 
     - A index entry's SURT must start with one of the SURTs from the whitelist to be considered.
     - All other index entries are discarded.
@@ -22,14 +22,20 @@ def run_filter_cdx(args, cmdline: str):
 
     # Start timing
     start_time = time.time()
-    
+
     # Resolve input and output paths using glob pattern
     # This should support glob via S3 (e.g., to fetch the indices from s3://commoncrawl/cc-index/collections/* ...)
-    input_paths, output_paths = resolve_paths(input_base_path=args.input_base_path, input_glob=args.input_glob, output_base_path=args.output_base_path)
+    input_paths, output_paths = resolve_paths(
+        input_base_path=args.input_base_path,
+        input_glob=args.input_glob,
+        output_base_path=args.output_base_path,
+    )
     validate_resolved_paths(output_paths, args.overwrite)
 
-    logger.info(f"Found {len(input_paths)} files matching pattern: {args.input_base_path}/{args.input_glob}")
-    
+    logger.info(
+        f"Found {len(input_paths)} files matching pattern: {args.input_base_path}/{args.input_glob}"
+    )
+
     # Load SURT prefixes from file (each line is a surt)
     surt_fs, surt_fs_path = fsspec.url_to_fs(args.surts_file)
     logger.info("Loading whitelist from %s", surt_fs_path)
@@ -37,7 +43,7 @@ def run_filter_cdx(args, cmdline: str):
     if not surt_fs.exists(surt_fs_path):  # Check that surts file exists
         logger.error(f"SURT file not found: {surt_fs_path}")
         sys.exit(1)
-    
+
     with surt_fs.open(surt_fs_path, "rt") as input_f:
         include_surt_prefixes = [line.strip() for line in input_f.readlines()]
 
@@ -68,7 +74,7 @@ def run_filter_cdx(args, cmdline: str):
         # Input/output from local or remote file system
         input_fs, input_fs_path = fsspec.url_to_fs(input_path)
         output_fs, output_fs_path = fsspec.url_to_fs(output_path)
-        
+
         # Make sure output directory exists
         output_fs.makedirs(output_fs._parent(output_fs_path), exist_ok=True)
 
@@ -96,7 +102,6 @@ def run_filter_cdx(args, cmdline: str):
                             logger.info("Limit reached at %i", args.limit)
                             break
 
-
                     if (i % log_every_n) == 0:
                         logger.info(f"Lines completed: {i:,} (matched: {included_n:,})")
 
@@ -114,12 +119,10 @@ def run_filter_cdx(args, cmdline: str):
     end_time = time.time()
     execution_time = end_time - start_time
 
-    logger.info(
-        f"Script execution time: {execution_time:.3f} seconds"
-    )
+    logger.info(f"Script execution time: {execution_time:.3f} seconds")
+
 
-    
-def resolve_paths(input_base_path: str, input_glob: str,  output_base_path: str):
+def resolve_paths(input_base_path: str, input_glob: str, output_base_path: str):
     """Resolve input paths from glob pattern and generate corresponding output paths."""
     # Use fsspec to handle local and remote file systems
     input_fs, input_fs_base_path = fsspec.url_to_fs(input_base_path)
@@ -130,18 +133,18 @@ def resolve_paths(input_base_path: str, input_glob: str,  output_base_path: str)
     if not input_fs_file_paths:
         logger.error(f"No files found matching glob pattern: {input_full_glob}")
         sys.exit(1)
-    
+
     # Generate corresponding output paths
     output_file_paths = []
     input_file_paths = []
     for input_path in input_fs_file_paths:
         # Get relative path from input_base_path without last slash
-        rel_path = input_path[len(input_fs_base_path)+1:]
-        
+        rel_path = input_path[len(input_fs_base_path) + 1 :]
+
         # Create corresponding full input and output path
         output_file_paths.append(os.path.join(output_base_path, rel_path))
         input_file_paths.append(os.path.join(input_base_path, rel_path))
-    
+
     return input_file_paths, output_file_paths
 
 
@@ -160,5 +163,3 @@ def validate_resolved_paths(output_paths, overwrite):
 
             # Make sure directory exists
             output_fs.makedirs(output_fs._parent(output_path), exist_ok=True)
-        
-
diff --git a/cdx_toolkit/filter_cdx/args.py b/cdx_toolkit/filter_cdx/args.py
index 02e46fe..469eeca 100644
--- a/cdx_toolkit/filter_cdx/args.py
+++ b/cdx_toolkit/filter_cdx/args.py
@@ -1,14 +1,5 @@
-import os
-import sys
-import logging
 import argparse
 
-import fsspec
-
-
-logger = logging.getLogger(__name__)
-
-
 def add_filter_cdx_args(parser: argparse.ArgumentParser):
     """Add command line arguments."""
     parser.add_argument(
diff --git a/cdx_toolkit/warcer_by_cdx/__init__.py b/cdx_toolkit/warcer_by_cdx/__init__.py
index f6a109e..333f853 100644
--- a/cdx_toolkit/warcer_by_cdx/__init__.py
+++ b/cdx_toolkit/warcer_by_cdx/__init__.py
@@ -1,103 +1,162 @@
-
+from io import BytesIO
 import json
 import logging
+from pathlib import Path
 import sys
 from typing import Iterable
 
 import fsspec
 
+
+from warcio import WARCWriter
+from warcio.recordloader import ArcWarcRecord
+
 import cdx_toolkit
 from cdx_toolkit.utils import get_version, setup
 
 
-LOGGER = logging.getLogger(__name__)
+logger = logging.getLogger(__name__)
 
 
-def run_warcer_by_cdx(cmd, cmdline):
+def run_warcer_by_cdx(args, cmdline):
     """Like warcer but fetches WARC records based on an CDX index file.
-    
+
     Approach:
     - Iterate over CDX file to extract capture object (file, offset, length)
     - Fetch WARC record based on capture object
-    - Write to new WARC file with metadata
+    - Write to new WARC file with metadata including resource record with index.
     """
-    cdx, kwargs = setup(cmd)
+    cdx, kwargs = setup(args)
 
-    ispartof = cmd.prefix
-    if cmd.subprefix:
-        ispartof += '-' + cmd.subprefix
+    ispartof = args.prefix
+    if args.subprefix:
+        ispartof += "-" + args.subprefix
 
     info = {
-        'software': 'pypi_cdx_toolkit/'+get_version(),
-        'isPartOf': ispartof,
-        'description': 'warc extraction generated with: '+cmdline,
-        'format': 'WARC file version 1.0',  # todo: if we directly read a warc, have this match the warc
-        # TODO add information from the index file
+        "software": "pypi_cdx_toolkit/" + get_version(),
+        "isPartOf": ispartof,
+        "description": "warc extraction generated with: " + cmdline,
+        "format": "WARC file version 1.0",
     }
-    if cmd.creator:
-        info['creator'] = cmd.creator
-    if cmd.operator:
-        info['operator'] = cmd.operator
+    if args.creator:
+        info["creator"] = args.creator
+    if args.operator:
+        info["operator"] = args.operator
 
     kwargs_writer = {}
-    if 'size' in kwargs:
-        kwargs_writer['size'] = kwargs['size']
-        del kwargs['size']
+    if "size" in kwargs:
+        kwargs_writer["size"] = kwargs["size"]
+        del kwargs["size"]
 
-    writer = cdx_toolkit.warc.get_writer(cmd.prefix, cmd.subprefix, info, **kwargs_writer)
+    writer = cdx_toolkit.warc.get_writer(
+        args.prefix, args.subprefix, info, **kwargs_writer
+    )
 
-    # TODO probably we should support multiple indices as input
-
-    if cmd.index_glob is None:
+    # Prepare index paths
+    if args.index_glob is None:
         # Read from a single index
-        index_paths = [cmd.index_path]
+        index_paths = [args.index_path]
     else:
         # Fetch multiple indicies via glob
-        index_fs, index_fs_path = fsspec.url_to_fs(cmd.index_path)
-        index_paths = sorted(index_fs.glob(cmd.index_glob))
+        index_fs, index_fs_path = fsspec.url_to_fs(args.index_path)
+        index_paths = sorted(index_fs.glob(args.index_glob))
 
-        LOGGER.info('glob pattern found %i index files in %s', len(index_paths), index_fs_path)
+        logger.info(
+            "glob pattern found %i index files in %s", len(index_paths), index_fs_path
+        )
 
         if not index_paths:
-            LOGGER.error('no index files found')
+            logger.error("no index files found")
             sys.exit(1)
-            
+
     # Iterate over index files
+    records_n = 0
     for index_path in index_paths:
-        LOGGER.info('filtering based on index from %s', index_path)
+        logger.info("filtering based on index from %s", index_path)
+
+        # Read index completely (for the WARC resource record)
+        index = get_index_from_path(index_path)
+
+        # Write index as record to WARC
+        # TODO at what position should the resource records be written?
+        writer.write_record(get_index_record(index, index_path))
 
         # The index file holds all the information to download specific objects (file, offset, length etc.)
-        for obj in get_caputure_objects_from_index_file(index_path=index_path, warc_download_prefix=cmd.warc_download_prefix):
-            url = obj['url']
+        for obj in get_caputure_objects_from_index(
+            index=index, warc_download_prefix=cdx.warc_download_prefix
+        ):
+            url = obj["url"]
+            timestamp = obj["timestamp"]
 
-            timestamp = obj['timestamp']
             try:
                 record = obj.fetch_warc_record()
             except RuntimeError:  # pragma: no cover
-                LOGGER.warning('skipping capture for RuntimeError 404: %s %s', url, timestamp)
+                logger.warning(
+                    "skipping capture for RuntimeError 404: %s %s", url, timestamp
+                )
                 continue
             if obj.is_revisit():
-                LOGGER.warning('revisit record being resolved for url %s %s', url, timestamp)
+                logger.warning(
+                    "revisit record being resolved for url %s %s", url, timestamp
+                )
             writer.write_record(record)
+            records_n += 1
+
+            if args.limit > 0 and records_n >= args.limit:
+                logger.info("Limit reached at %i", args.limit)
+                break
+
+        if args.limit > 0 and records_n >= args.limit:
+            # stop index loop
+            break
 
-        LOGGER.info('filtering completed (index: %s)', index_path)
+        logger.info("Filtering completed (index file: %s)", index_path)
 
-def get_caputure_objects_from_index_file(index_path: str, warc_download_prefix=None) -> Iterable[cdx_toolkit.CaptureObject]:
-    """Read CDX index file and generate CaptureObject objects."""
+    logger.info("WARC records extracted: %i", records_n)
+
+
+def get_index_from_path(index_path: str | Path) -> str:
+    """Fetch (and decompress) index content as string from local or remote path."""
     index_fs, index_fs_path = fsspec.url_to_fs(index_path)
-    
-    with index_fs.open(index_fs_path) as f:
-        for line in enumerate(f):
-            cols = line.split(" ", maxsplit=2)
-
-            if len(cols) == 3:
-                # TODO can there be a different format?
-                # surt, timestamp, json_data = cols 
-                data = json.loads(cols[2])
-                data["timestamp"] = cols[1]
-            else:
-                raise ValueError(f"Cannot parse line: {line}")
-            
-            yield cdx_toolkit.CaptureObject(
-                data=data, wb=None, warc_download_prefix=warc_download_prefix
-            )
+
+    compression = "gzip" if index_fs_path.endswith(".gz") else None
+
+    with index_fs.open(index_fs_path, "rt", compression=compression) as f:
+        return f.read()
+
+
+def get_index_record(
+    index: str, index_path: str, encoding: str = "utf-8"
+) -> ArcWarcRecord:
+    """Build WARC resource record for index."""
+    return WARCWriter(None).create_warc_record(
+        uri=index_path,  # TODO this could be a local / internal path
+        record_type="resource",
+        payload=BytesIO(index.encode(encoding)),
+        http_headers=None,
+        warc_content_type="application/cdx",
+        warc_headers_dict=None,  # TODO should we add some other metadata headers?
+    )
+
+
+def get_caputure_objects_from_index(
+    index: str, warc_download_prefix=None, limit: int = 0
+) -> Iterable[cdx_toolkit.CaptureObject]:
+    """Read CDX index and generate CaptureObject objects."""
+    for i, line in enumerate(index.splitlines()):
+        cols = line.split(" ", maxsplit=2)
+
+        if len(cols) == 3:
+            # TODO can there be a different format?
+            # surt, timestamp, json_data = cols
+            data = json.loads(cols[2])
+            data["timestamp"] = cols[1]
+        else:
+            raise ValueError(f"Cannot parse line: {line}")
+
+        yield cdx_toolkit.CaptureObject(
+            data=data, wb=None, warc_download_prefix=warc_download_prefix
+        )
+
+        if limit > 0 and i >= limit:
+            break
diff --git a/cdx_toolkit/warcer_by_cdx/args.py b/cdx_toolkit/warcer_by_cdx/args.py
index f31ac2f..7d40ea6 100644
--- a/cdx_toolkit/warcer_by_cdx/args.py
+++ b/cdx_toolkit/warcer_by_cdx/args.py
@@ -8,13 +8,40 @@
 
 
 def add_warcer_by_cdx_args(parser: argparse.ArgumentParser):
-    parser.add_argument('--prefix', default='TEST', help='prefix for the warc filename')
-    parser.add_argument('--subprefix', type=str, default=None, help='subprefix for the warc filename, default None')
-    parser.add_argument('--size', type=int, default=1000000000, help='target for the warc filesize in bytes')
-    parser.add_argument('--creator', action='store', help='creator of the warc: person, organization, service')
-    parser.add_argument('--operator', action='store', help='a person, if the creator is an organization')
-    parser.add_argument('--warc-download-prefix', action='store', help='prefix for downloading content, automatically set for CC')
-    parser.add_argument('--index-glob', type=str, default=None, help='a glob pattern for read from multiple indices')
-    parser.add_argument('index_path', help='Path to CDX index file (local or remote, e.g. S3)')
+    parser.add_argument("--prefix", default="TEST", help="prefix for the warc filename")
+    parser.add_argument(
+        "--subprefix",
+        type=str,
+        default=None,
+        help="subprefix for the warc filename, default None",
+    )
+    parser.add_argument(
+        "--size",
+        type=int,
+        default=1000000000,
+        help="target for the warc filesize in bytes",
+    )
+    parser.add_argument(
+        "--creator",
+        action="store",
+        help="creator of the warc: person, organization, service",
+    )
+    parser.add_argument(
+        "--operator", action="store", help="a person, if the creator is an organization"
+    )
+    parser.add_argument(
+        "--warc-download-prefix",
+        action="store",
+        help="prefix for downloading content, automatically set for CC",
+    )
+    parser.add_argument(
+        "--index-glob",
+        type=str,
+        default=None,
+        help="a glob pattern for read from multiple indices",
+    )
+    parser.add_argument(
+        "index_path", help="Path to CDX index file (local or remote, e.g. S3)"
+    )
 
-    return parser
\ No newline at end of file
+    return parser
diff --git a/tests/data/warc_by_cdx/cdx-00187 b/tests/data/warc_by_cdx/cdx-00187
new file mode 100644
index 0000000..70ecc69
--- /dev/null
+++ b/tests/data/warc_by_cdx/cdx-00187
@@ -0,0 +1,1140 @@
+fr,missiondefrance,bibliotheque)/index.php?id=319&lvl=bulletin_display 20240716153155 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=319", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "D5K3FUWDRAOMMTJC2CTWV7L2ABFIJ5BP", "length": "9754", "offset": "111440525", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00337.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3195&lvl=author_see 20240718133156 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3195", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5MLMHDQBJHBS5JOG3CQYRL4KT4O3P4LG", "length": "6870", "offset": "3241425", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00254.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=320&lvl=author_see 20240715050657 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=320", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LZKPLQ53PRFNQJPVWIKPNY4LJIKHBCEZ", "length": "10778", "offset": "3365888", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00517.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=320&lvl=indexint_see 20240718213058 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=320", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3A7T4X637S4NEG2LTUHE2HNTCY7KTIFZ", "length": "7228", "offset": "110658803", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00004.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3202&lvl=author_see 20240725190426 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3202", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DFVLVMRCEGVF2UPFHDCM35YYZZNEMP46", "length": "7712", "offset": "3636501", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00033.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3207&lvl=author_see 20240719171239 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3207", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PNERB34T6HSUZ73VNH3625HHWTYPJ4T6", "length": "10232", "offset": "109644433", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00017.warc.gz", "charset": "UTF-8", "languages": "fra,lat"}
+fr,missiondefrance,bibliotheque)/index.php?id=321&lvl=author_see 20240712181238 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=321", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4CZ2F4QQVSQJYGBCMCSV26XTNCI6CGRP", "length": "11074", "offset": "101668117", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00031.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=321&lvl=bulletin_display 20240712182607 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=321", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TANZBWJVSMNAZVTBFCHRUXXWYJ6C6RQC", "length": "7512", "offset": "6207916", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00007.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3211&lvl=author_see 20240715060529 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3211", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PMKUAOHC67VJZNRLU5NKJDUBF2CXEJ5A", "length": "6579", "offset": "116903011", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00042.warc.gz", "charset": "UTF-8", "languages": "fra,ile"}
+fr,missiondefrance,bibliotheque)/index.php?id=3214&lvl=notice_display 20240721141815 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3214", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AL3XQXGL5VJVVZDXL3YUCCLU43QEYDAY", "length": "5171", "offset": "104033233", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00045.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=323&lvl=categ_see 20240721224004 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=323", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XRL4Q5EV5R3CTLPLHJVAB5HMVSIKHRYU", "length": "11126", "offset": "103147750", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00360.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=323&lvl=indexint_see 20240718134355 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=323", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BNAPPBLALPVKY5HX46VKOK7L3JSD2GO5", "length": "10478", "offset": "109213036", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00007.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=325&lvl=coll_see 20240719185127 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=325", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DQXVMOSQBNCAPXF4HYJVMHXQDLAQMMYB", "length": "9934", "offset": "5404195", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00541.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3250&lvl=author_see 20240712184727 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3250", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OPD54ULURX3SFX6SAFDSKJ64QU4C2IZ7", "length": "7972", "offset": "101781185", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00165.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3257&lvl=author_see 20240718140811 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3257", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TZ3OHCPGGHBRZBHQ32KQOANJGSVNTMXW", "length": "10635", "offset": "110151404", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00172.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3257&lvl=author_see 20240719100624 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3257", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VLQDVYWMJPQNC43WAO776XZFV6D6UHYH", "length": "10618", "offset": "3189587", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00193.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3257&lvl=notice_display 20240716153007 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3257", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FKJQY5S3Y5EN6NUJ5SHQ6UUZ7Q5XCDWS", "length": "5201", "offset": "111695995", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00172.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3265&lvl=author_see 20240719085015 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3265", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FHYMN3G5X7TBVS4DHNW7FVN7P7S7DUIS", "length": "8315", "offset": "6668861", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00222.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=327&lvl=indexint_see 20240719080658 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=327", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4GAIJFCWIJSKRCW3WV3HM3VD3DKRWW2W", "length": "10350", "offset": "5818330", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00022.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3270&lvl=author_see 20240721225817 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3270", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GWVEY7Z44QEQEUP2DWNBN5UO2IGKFRCQ", "length": "8774", "offset": "112555391", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00227.warc.gz", "charset": "UTF-8", "languages": "fra,deu"}
+fr,missiondefrance,bibliotheque)/index.php?id=3289&lvl=author_see 20240712164225 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3289", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "V6UWTQQIA6J2CN6HYIWYZ6MZ366T5HUW", "length": "6848", "offset": "98596750", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00267.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3294&lvl=author_see 20240719082544 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3294", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AGDO5DYYWCQHI6GFEVCAUSMYIV4P2KZJ", "length": "7330", "offset": "3988723", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00314.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3298&lvl=author_see 20240724152346 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3298", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DNZBTPTZZ2V23SDPATYKCXHMQVNFAJ34", "length": "8208", "offset": "106718478", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00297.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=33&l_typdoc=a&lvl=categ_see&main=&nbr_lignes=90&page=2 20240719081240 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=33&page=2&nbr_lignes=90&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ECM3RMASSMOFX3ELTTM75KM36QLVFXKB", "length": "11107", "offset": "4641382", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00050.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=33&l_typdoc=a&lvl=categ_see&main=&nbr_lignes=90&page=6 20240719100237 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=33&page=6&nbr_lignes=90&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HSF4MSLRACRVC3Q2JPUPLX33TYPXQUN7", "length": "11227", "offset": "4029291", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00030.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=33&l_typdoc=a&lvl=indexint_see&main=&nbr_lignes=75&page=2 20240719083242 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=33&page=2&nbr_lignes=75&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VX2BZQ5TUZE3EO56GKUYRWUIVIQD2ULH", "length": "10297", "offset": "101301987", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00197.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=33&l_typdoc=a&lvl=indexint_see&main=&nbr_lignes=75&page=5 20240719084107 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=33&page=5&nbr_lignes=75&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2UH4UV7UF4GY6FCXU4SNGWZ5ABWQOOGK", "length": "10175", "offset": "115498821", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00818.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=331&lvl=bulletin_display 20240718213832 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=331", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LVEINXI2U5DQALVD2WWW76T7RCTDULX3", "length": "8323", "offset": "118792214", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00391.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=331&lvl=categ_see 20240712185739 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=331", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "W7VHSBYM2MPQ3OW4MQV6S2XI4MHP6WTR", "length": "10942", "offset": "103787910", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00389.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=331&lvl=publisher_see 20240716144215 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=331", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TZZJGK75ZQVUGOQ6NZMO3AI7YA3UFNYY", "length": "8368", "offset": "4640756", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00018.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3319&lvl=author_see 20240721124130 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3319", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VAFI4Y22EKGYZKPN23GWR7JVXVKJU5IC", "length": "8608", "offset": "108528806", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00111.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=332&lvl=indexint_see 20240712172818 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=332", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HFP23ZMUSJ3CRPOKF7XHVYAOQTCPDZ5X", "length": "9888", "offset": "4383961", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00048.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=332&lvl=notice_display 20240721214207 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=332", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4NOO5NO7PWRGZS54BXGE6OELAKMGOJMQ", "length": "5244", "offset": "117089991", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00111.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=332&lvl=subcoll_see 20240721233314 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=subcoll_see&id=332", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4TKSFK5ZSAH2YO4XGC4B5JPNQW7M6DGS", "length": "6652", "offset": "3512793", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00651.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3328&lvl=author_see 20240721224401 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3328", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QVWSNPZ4JZOSG64UFQQ5NAUJFLVTSVYH", "length": "10766", "offset": "114497217", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00141.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=333&lvl=coll_see 20240721014429 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=333", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "37IQIIUAR5L6T6RQVXCQHFFTGOME6QKL", "length": "10034", "offset": "110695616", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00579.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=333&lvl=publisher_see 20240721141441 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=333", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3IPNBZJBBRVPDSMUYKUKLBI3MFLTCTW6", "length": "7230", "offset": "103322354", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00595.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3336&lvl=notice_display 20240716163001 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3336", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VZJLHLKFOEOCQ5TF5V4CM4MBOTJ6NLZX", "length": "5291", "offset": "115716368", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00170.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3349&lvl=author_see 20240719085604 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3349", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HKYKSUK3O7VLVRP57JFYORVZM3BYH276", "length": "9038", "offset": "5762377", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00225.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=335&lvl=subcoll_see 20240715045851 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=subcoll_see&id=335", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BLNS3DRJ3OOGJNLQRE3VINJ4UYQXUHW3", "length": "6840", "offset": "113001478", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00633.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3357&lvl=author_see 20240724155059 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3357", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KLGPRZFAEVAQXT5HAOJX5JVTG7L5U4QC", "length": "6717", "offset": "115078936", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00233.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=336&lvl=indexint_see 20240715050735 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=336", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AFM7J6VYG25TLBTVXQLJBEO7DU3XUPFS", "length": "10535", "offset": "4406404", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00052.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3364&lvl=author_see 20240716143953 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3364", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "H4P2RN5XO6TOBRHUWPKT5ZCGJV4DELOJ", "length": "6591", "offset": "128783727", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00261.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3372&lvl=notice_display 20240724144930 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3372", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NXVGLK736JFAUHXGKP56ZN6TSUCQSY42", "length": "5261", "offset": "3307445", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00359.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=338&l_typdoc=a&lvl=indexint_see&main=&nbr_lignes=44&page=2 20240712171210 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=338&page=2&nbr_lignes=44&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DQVMSHNRHBSJWDAFEC7NEDO4TB7JIFJN", "length": "10666", "offset": "99134830", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00745.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=338&lvl=indexint_see 20240716154649 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=338", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MWSKS37DNC6TVQP7MMV2HFBYGMIGUXHU", "length": "10123", "offset": "121782940", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00043.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=339&lvl=author_see 20240718150551 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=339", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5WKBW5OOPVEAUQEG6HVVSK4RKVPNO2FW", "length": "8700", "offset": "112867508", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00070.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=339&lvl=categ_see 20240718143421 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=339", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HTFY5I5RPRCDYM3GJ3PK2LUI3JELMW4W", "length": "9374", "offset": "3651513", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00430.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=339&lvl=indexint_see 20240721005217 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=339", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PHWTCZDOIHRTOREXE52KO4HQV5TPQI6L", "length": "10049", "offset": "115428364", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00044.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=34&lvl=categ_see 20240718201326 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=34", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KZHT6K4KCVSERUBGSCQ2G5X7C76D2H2Z", "length": "11179", "offset": "115532168", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00257.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3407&lvl=notice_display 20240719083554 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3407", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3W6PAA4K3AYAEOIU2CLV7HHJEL5JEKHM", "length": "5039", "offset": "4567515", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00208.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=341&l_typdoc=a&lvl=indexint_see&main=&nbr_lignes=31&page=2 20240725194516 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=341&page=2&nbr_lignes=31&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6B2DOKLOGV4OEXOQIWPP6M47ELS2UDT2", "length": "10882", "offset": "3686476", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00886.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=341&lvl=categ_see 20240721135840 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=341", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LXVIRECQI5F2B6KBWBJVQ7NHMIUCUWOW", "length": "9620", "offset": "6007166", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00453.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3419&lvl=author_see 20240716151912 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3419", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ANU4ZEQAY4Z6ZLLP6GQQ6BYCJJEZ5LJW", "length": "6603", "offset": "111688390", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00172.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=342&l_typdoc=a&lvl=categ_see&main=&nbr_lignes=38&page=3 20240725191055 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=342&page=3&nbr_lignes=38&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HW4NEXWCFF6QFETOI6KVSERJVULW2OG6", "length": "10302", "offset": "105817623", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00213.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=342&l_typdoc=a&lvl=indexint_see&main=&nbr_lignes=33&page=3 20240724150356 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=342&page=3&nbr_lignes=33&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "V2VR7UQOSKDIPW2YOR3NAPLA2KGM67UP", "length": "7627", "offset": "104405410", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00181.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3424&lvl=author_see 20240718143448 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3424", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EPAM42EAOUOLOTJXDQRZZK77CNO4QJYC", "length": "8599", "offset": "104514050", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00198.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=343&lvl=indexint_see 20240718195946 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=343", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6UBAC57HXVBMZMFPGPRR5OSWO33FCFET", "length": "10263", "offset": "107175133", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00069.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=344&lvl=coll_see 20240725185302 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=344", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YPRDKFR3W7E2M3O2S6PALYBPJQY2SUJY", "length": "10550", "offset": "102887989", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00611.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3445&lvl=author_see 20240724162904 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3445", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "P7RNC43RMNJKQW6JD6SC5KRVIVNYT6WZ", "length": "7206", "offset": "110805878", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00261.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3451&lvl=author_see 20240718203605 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3451", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5RUWSRSPYOB5BVL76PDHFQQ5XDMNWPAW", "length": "8990", "offset": "4163840", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00309.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3459&lvl=author_see 20240716162809 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3459", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OJSTHTHHYELHXUUDZTQNNYN2VO36NT3H", "length": "9419", "offset": "111121813", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00296.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3459&lvl=author_see 20240724153644 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3459", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HZKCH5K26OJFZ4XU7F22AHY5JVMMOMRT", "length": "9378", "offset": "3913523", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00317.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=346&lvl=publisher_see 20240718150444 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=346", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6NNVCH7PQQ7LDJM5P65FLKHOT7JZ3EFS", "length": "6714", "offset": "115464847", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00629.warc.gz", "charset": "UTF-8", "languages": "fra,lat"}
+fr,missiondefrance,bibliotheque)/index.php?id=3465&lvl=author_see 20240716151219 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3465", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PWGKH3YQPZ53GREEMMHOOCTSMSY6V222", "length": "9580", "offset": "3808067", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00344.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3469&lvl=author_see 20240716161347 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3469", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PCFIBEYIIPIDOBBCTQ37MCMR3LBEG7JE", "length": "6660", "offset": "114064199", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00327.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3469&lvl=author_see 20240721140900 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3469", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FE7LAYNAW4Y2HUDT7YZTQHZV4AVS5KV3", "length": "6616", "offset": "4395083", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00348.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3471&lvl=notice_display 20240721140157 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3471", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "35AQ4YR4NPQ26274TEMQMOEZMXO33LBB", "length": "4979", "offset": "4408008", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00419.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3476&lvl=notice_display 20240716162107 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3476", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "B32OTBA3Q2DAIU3BRFLEDRMW3O55BYPS", "length": "5108", "offset": "125784975", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00355.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3477&lvl=notice_display 20240716144858 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3477", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XICPUFQAGDHIAJEW4XILKAKGZ6FXNPVU", "length": "5116", "offset": "120790101", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00356.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3478&lvl=author_see 20240719082335 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3478", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4INMESTVFLFOSFZAQCOHGAR7FZWXCRDC", "length": "11354", "offset": "3902615", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00378.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=348&lvl=author_see 20240724143540 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=348", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YUA3W7AKFDGRQD5MQ6RJEYQTZ2TN62QJ", "length": "10991", "offset": "3627080", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00587.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=348&lvl=categ_see 20240721005147 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=348", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TWFHO7BHPHOQ4NICWDABKSLVLI64ZFFX", "length": "10590", "offset": "3973419", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00460.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=348&lvl=indexint_see 20240721004659 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=348", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OK4PM4BHKR77Y3YKDLLN7EZMIDMIGGNP", "length": "11080", "offset": "5054144", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00085.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=3484&lvl=author_see 20240715060450 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3484", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GM4PQKM3DT7TD554I5374N2XAWEJ5QVL", "length": "7022", "offset": "4380430", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00405.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3489&lvl=author_see 20240722111346 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3489", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YOC3PF44P2QNTEIVGU263YFZYJ5HMJE3", "length": "9321", "offset": "106063616", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00389.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3491&lvl=author_see 20240721130750 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3491", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NNYBGSFEHZIXW3GFNSPPJEBDCJN4WSHC", "length": "7328", "offset": "106114157", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00412.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3498&lvl=author_see 20240721020253 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3498", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ETPJP4JTGOO456GHPWXGADPH654LL2TE", "length": "7185", "offset": "108548300", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00419.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=35&l_typdoc=a&lvl=indexint_see&main=&nbr_lignes=32&page=2 20240725192325 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=35&page=2&nbr_lignes=32&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OH77GUHKEVJQDH3T2C775N25F2SNM4V2", "length": "10840", "offset": "102289291", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00178.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=35&l_typdoc=a&lvl=indexint_see&main=&nbr_lignes=32&page=3 20240722111709 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=35&page=3&nbr_lignes=32&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2F26KLIGYPIJGRBIZ63JB7QP6AVBO4CC", "length": "7174", "offset": "106682890", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00385.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=35&lvl=author_see 20240721015846 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=35", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2SW6T26LV7UH4PMMIDC7WJGNHDE424IV", "length": "10313", "offset": "7229516", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00266.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=35&lvl=publisher_see 20240718142747 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=35", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "N6VKPG4BE45HJ7ZAZD6BLGRALWWN5MUF", "length": "8622", "offset": "3478668", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00025.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=350&lvl=categ_see 20240712174144 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=350", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XRS6UT2K773O6UQEDCLNNKI536UQZRQN", "length": "11482", "offset": "4941278", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00483.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=350&lvl=coll_see 20240725183643 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=350", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "H6GLBSZCTXV4NMCL5MC7U2VV72WQJEUK", "length": "9912", "offset": "4893977", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00629.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=350&lvl=indexint_see 20240716152208 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=350", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MFRQAPQM4CSMDDVOL2S7U64XRQG7QJEG", "length": "10978", "offset": "125820055", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00097.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=350&lvl=publisher_see 20240718135611 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=350", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AHROEWCW7XKGFEXQPHHULL3GZBLMFBUM", "length": "10925", "offset": "3252567", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00079.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3500&lvl=notice_display 20240719100713 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3500", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HAT4BTIIK5WOXV54E7BD7CZX5XH2MGSR", "length": "4960", "offset": "104059794", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00193.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3503&lvl=notice_display 20240721135609 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3503", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "V65WTUQB7C4GTXZEPOJVYJDLQSP6AYLO", "length": "4918", "offset": "103641308", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00196.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3505&lvl=notice_display 20240721125540 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3505", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EOJEKRJA2M2B4Y53DJJGQ5UAPX6MUFC5", "length": "4998", "offset": "112003401", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00198.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3508&lvl=author_see 20240721010831 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3508", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LFGOUBQ53GV5BDOZ5ARPVGFV6RKZIYVN", "length": "10026", "offset": "3453451", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00222.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=351&lvl=indexint_see 20240715053453 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=351", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3FZNHI3UN47XDTP3WUINB5Z4KOTUNSWQ", "length": "9006", "offset": "5115337", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00109.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3516&l_typdoc=a&lvl=author_see&nbr_lignes=51&page=4 20240725190244 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3516&page=4&nbr_lignes=51&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AIYQTZZC6UUYUL7FRG55INVT4IWY2KBV", "length": "7820", "offset": "6036684", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00381.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3516&lvl=author_see 20240719171535 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3516", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FHDYB6HBFNRWMBX4R6BARLOYOUT263ZC", "length": "9831", "offset": "106664963", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00230.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3518&lvl=author_see 20240719081328 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3518", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HB4A5YLYVEYJ6V6MA4MKHYG6HVA6W6ED", "length": "11339", "offset": "112512378", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00232.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=352&lvl=categ_see 20240718193752 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=352", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RO7LKCQKFCHOBMCV5RS7MIBUSA2I4HLL", "length": "11550", "offset": "120184872", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00452.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=352&lvl=indexint_see 20240718150741 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=352", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "24PFP5ALHYKTOHWFYPIQKTAGR4GO52UN", "length": "10700", "offset": "111689310", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00099.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3521&lvl=notice_display 20240721011841 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3521", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SQVTQBQ67BY2IAMVOIEWYNAFQMZNDVPL", "length": "5047", "offset": "115209813", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00256.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3534&lvl=author_see 20240722115116 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3534", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3VEYUZRYIRWWRF2RMMMRQA2QJ6X3OUTN", "length": "8792", "offset": "108016873", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00290.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=354&lvl=subcoll_see 20240721215420 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=subcoll_see&id=354", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WIJZ4JPPKD7YSR2QAVMGJSMZXNXO37ZF", "length": "6988", "offset": "3025884", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00715.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3546&lvl=author_see 20240724155638 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3546", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FRQCPI67BD3BYLL5XBFJVAJPXZYTIT6E", "length": "6852", "offset": "100665454", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00323.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=355&lvl=indexint_see 20240718143244 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=355", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Q7Y4JP3LFUIALIIC4ZORFFNUU6ACP6P3", "length": "11837", "offset": "5131478", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00113.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=355&lvl=indexint_see 20240718200749 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=355", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DQ7HNNGTZGHUC5BOXQCAF77XDGXVSAIV", "length": "11846", "offset": "114700386", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00102.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3557&lvl=notice_display 20240721133011 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3557", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "47DJJYCT5K2TYA5HLPKCQJ2GWD2AM47B", "length": "5189", "offset": "5832253", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00424.warc.gz", "charset": "UTF-8", "languages": "fra,deu"}
+fr,missiondefrance,bibliotheque)/index.php?id=3559&lvl=notice_display 20240725185110 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3559", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "N5ZL3CRRWIH4H3UAVTIPUH5CHXCCXBSK", "length": "4997", "offset": "107332037", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00357.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=356&lvl=publisher_see 20240721234016 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=356", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KYL2NKK23YK6AVOA2K7EZ4BRB3FFXZWO", "length": "6890", "offset": "4637976", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00085.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3563&lvl=notice_display 20240721141515 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3563", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6Z2SHNCC5D7VYPKNEJQHDAIRCN57TC5Q", "length": "5009", "offset": "6715817", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00451.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3569&lvl=author_see 20240724160749 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3569", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OMLHNHEWUIVWICDLYVQZCHP2OWZFKFP7", "length": "7189", "offset": "3505866", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00409.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ile"}
+fr,missiondefrance,bibliotheque)/index.php?id=357&lvl=categ_see 20240718193446 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=357", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YU6ISPV67OHN4FS23X3GGOQG56KBJAMB", "length": "10816", "offset": "4469056", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00490.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=358&lvl=categ_see 20240718140346 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=358", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "V2NSUMH3MP6RKCP75CUJ74R3DXTIGO3D", "length": "11547", "offset": "110223098", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00458.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=3586&lvl=notice_display 20240719082143 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3586", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "T66REETLOXMD2TQPILVF7O4TGB7Z3BEW", "length": "5036", "offset": "111484535", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00447.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3587&lvl=author_see 20240721231828 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3587", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SGIP2ELHPYAPINBW662KU5CUCJTZCAHB", "length": "6812", "offset": "108319504", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00448.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3589&lvl=author_see 20240721221112 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3589", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DGHTMUJVBHLUPOWNKAUWYFPPEP6A7IOM", "length": "6443", "offset": "4632456", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00471.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=359&l_typdoc=a&lvl=indexint_see&main=&nbr_lignes=73&page=2 20240721223414 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=359&page=2&nbr_lignes=73&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7BLK64K4WWASOABT5JTIAASFFJIMFG7T", "length": "10406", "offset": "5612361", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00871.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=359&lvl=indexint_see 20240718202337 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=359", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RSHTFCCM4ZX2BGKFTT7YCZ4FL4L6JW3C", "length": "10732", "offset": "113289062", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00106.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3596&lvl=notice_display 20240721004941 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3596", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZWFNAXVFFV7IN5VLVHBINTS5SCUBKMG6", "length": "5110", "offset": "101721918", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00478.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3597&lvl=author_see 20240718205913 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3597", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SMY5S3IAO3ME6GMMUBFUNA2YLAM6LFO6", "length": "7285", "offset": "111644616", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00479.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3598&lvl=author_see 20240716153802 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3598", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CYQSNETBLT7LRTUNA3I6ICUITJUJKWJ7", "length": "6473", "offset": "5124833", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00501.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=360&lvl=bulletin_display 20240718211421 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=360", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UBE5KDPOEE7QVVCFVHZ253MPTUXRBPVO", "length": "8821", "offset": "104937437", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00483.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=360&lvl=indexint_see 20240716143904 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=360", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2XVHZ2WYEJKG4IKO5XHZCBHU5YQMTKKX", "length": "10639", "offset": "4792802", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00139.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3611&lvl=notice_display 20240716160423 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3611", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3TBBKTUGGNIDWCPJ4Q75KHYNJ4ANYX5K", "length": "5192", "offset": "3359051", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00355.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=363&lvl=categ_see 20240724161814 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=363", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DHZJG3WDPZZJ7YAT65MMVC6WHBVNGW5Q", "length": "11698", "offset": "5171068", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00517.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3636&lvl=author_see 20240721001422 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3636", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5X74HFLPBCALBWPA6OTHTAZ373O2ZLWA", "length": "8439", "offset": "112628692", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00353.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=3637&lvl=author_see 20240712170828 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3637", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "V7BS2HLTX3BDR3LMJ55RLCF4KQYQLBZC", "length": "6551", "offset": "4096472", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00375.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=3637&lvl=notice_display 20240718203435 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3637", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OWUJXASTJHNXCX2ORGBAX7ZZRDBBCAYY", "length": "5126", "offset": "117005264", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00354.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=364&lvl=bulletin_display 20240716151643 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=364", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "35IXN3BLJ4YNVNV6DYN57KVWOSW6IFRA", "length": "6778", "offset": "2915926", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00134.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=364&lvl=categ_see 20240721232543 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=364", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TPEYTR2NA22BT3KERZSTGJOXPVIOCME7", "length": "11137", "offset": "4899425", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00518.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=365&lvl=notice_display 20240718195355 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=365", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7PTQ6IB33PXHUMKYXMFIGSUHEU75XIG5", "length": "5068", "offset": "3382824", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00346.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=366&lvl=author_see 20240719100648 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=366", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "R2UT7KZL6IRIPNLSCTE37KHQQWLRXSG3", "length": "10507", "offset": "112809809", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00160.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=367&lvl=author_see 20240718212646 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=367", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PDNBRU5AIAWG7S2KOYE4MWVMUFRPUZML", "length": "11010", "offset": "112746073", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00161.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=3680&lvl=notice_display 20240721004017 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3680", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6CHGWTQ77VIBC3VM6KYRC5EEUQJZ3G46", "length": "4993", "offset": "3064377", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00571.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3682&lvl=author_see 20240719100630 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3682", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "64NZYKOHGZ2UKZZ6LJUAT4IEO7HBVAWS", "length": "7503", "offset": "4664034", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00525.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=369&lvl=categ_see 20240718141554 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=369", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3QIZE7FVUXAPFIZTDYJ6WRM7IYTN6MAY", "length": "10824", "offset": "3385965", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00523.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=369&lvl=indexint_see 20240724162326 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=369", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FHMENI6KPOZWWJWRLGUO3EHROLR6QD2V", "length": "11845", "offset": "102840436", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00137.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3691&lvl=author_see 20240721125800 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3691", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3R54H5PXUBHZT6C2G7FKPI5UHDHM2BGT", "length": "7191", "offset": "4450552", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00555.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=37&lvl=bulletin_display 20240719094934 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=37", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "T3UF6XZL3GMXDJ7DOKNZW3RWGYTIDYS4", "length": "5113", "offset": "103786248", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00642.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=370&lvl=categ_see 20240719090509 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=370", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FI6PG2NWHMMLUJEDLMRV73XFH5JSOBQW", "length": "10636", "offset": "112579439", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00512.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3705&lvl=author_see 20240721140120 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3705", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WK3FMK2LL4W4MNPTADYNW6JV73G46HVI", "length": "6593", "offset": "3320019", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00341.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3713&lvl=notice_display 20240725183244 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3713", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7LZYELUUV3SWSS2DV5GZRXUOUASXQA37", "length": "5175", "offset": "116389243", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00349.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3717&lvl=author_see 20240721000443 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3717", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "A4KWHEWWQFXEMX4TO6MXIEAVIY4OZ2O4", "length": "9445", "offset": "112638161", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00353.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=372&lvl=categ_see 20240712185712 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=372", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JL2JBCRQEWKAT4OATUIF2ORKPD6Z7S44", "length": "11582", "offset": "100858271", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00514.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=372&lvl=indexint_see 20240719100559 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=372", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YC5TLIAMUZPDKK7AGGKQEXENJEANTY5E", "length": "10525", "offset": "3948413", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00172.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3730&lvl=author_see 20240719170547 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3730", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4FACZOUQBBEEP553LR2MK7UOZ7A3KGSE", "length": "8067", "offset": "5452087", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00429.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3738&lvl=author_see 20240722104448 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3738", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UTGYCHTXONXPVSVVHPMM3T34V4GRBBLA", "length": "7397", "offset": "102302620", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00416.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=374&lvl=categ_see&main= 20240719175718 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=374&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "H6LIOWKYQIOE6H7TO5STNW4G65UTVVD5", "length": "11075", "offset": "3083611", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00071.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=374&lvl=indexint_see&main= 20240716142846 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=374&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2CH2NEULNOX4EIYCQKMYQFGJJPYANFJU", "length": "10598", "offset": "4556137", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00160.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=374&lvl=indexint_see&main= 20240721001740 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=374&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6XUFA5WXFQH3KG7ES62CG5ETXQ7EGA7G", "length": "10603", "offset": "112441831", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00361.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=374&lvl=publisher_see 20240721214936 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=374", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YSI3QL3UJSBPZKACHN3JXBQEE57QLMM5", "length": "10667", "offset": "104494029", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00720.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=375&lvl=indexint_see 20240719085816 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=375", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DECLAA24T7C7YFMX4SH6N7IOTYUSDZ4N", "length": "11037", "offset": "4489277", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00175.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=377&lvl=categ_see 20240718134953 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=377", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PU3GUKFJZZ234ZZUKQR36PCQWKRN5UQB", "length": "11106", "offset": "3813574", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00552.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=377&lvl=indexint_see 20240725191028 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=377", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6RJWALYEXWNCB774MWG656VV4E3MMHT3", "length": "10834", "offset": "3100272", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00177.warc.gz", "charset": "UTF-8", "languages": "fra,eng,lat"}
+fr,missiondefrance,bibliotheque)/index.php?id=378&l_typdoc=a&lvl=indexint_see&main=&nbr_lignes=39&page=3 20240725185934 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=378&page=3&nbr_lignes=39&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6F4VQBPWW3CQTEFNYR2PBJBLBSSOFYD6", "length": "9702", "offset": "104367076", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00406.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=378&lvl=indexint_see 20240721234118 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=378", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KMIYNWMCX3MKD655WRHC2URUEQHFLBUD", "length": "10540", "offset": "2962080", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00178.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3783&lvl=author_see 20240719082745 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3783", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6UZ4NLA4BD43PLMVWDEE6R3QALZC3IVF", "length": "7927", "offset": "106242709", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00566.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3787&lvl=notice_display 20240719181604 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3787", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BQOPOSTVFX66KVBYKUVXXAU5O2TTPMX4", "length": "5464", "offset": "4286393", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00639.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=38&lvl=categ_see 20240724143909 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=38", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HXSV7ZRVZH6RDF5ZON4LDQO7LY3GQD5T", "length": "11468", "offset": "110814077", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00261.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3801&lvl=author_see 20240718135536 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3801", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JDVHXQBJBUGKTRQK6TL4LZKGJAKLNY5Q", "length": "7542", "offset": "111466347", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00377.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=381&lvl=indexint_see 20240716151528 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=381", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NECNGS2GEMEBN2RCDC5ED5DAK4PDUW2G", "length": "9968", "offset": "3528059", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00202.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=382&lvl=indexint_see 20240724152313 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=382", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JKP43QQMNDQ4D3ZUNDBI2SNDWCF724OP", "length": "12129", "offset": "108389621", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00192.warc.gz", "charset": "UTF-8", "languages": "fra,ile"}
+fr,missiondefrance,bibliotheque)/index.php?id=382&lvl=indexint_see&main= 20240718193006 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=382&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "B3O2MLZDZQQL2LJVK7DDPXZ6ZB5KV4DH", "length": "12134", "offset": "116442035", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00834.warc.gz", "charset": "UTF-8", "languages": "fra,ile"}
+fr,missiondefrance,bibliotheque)/index.php?id=3825&lvl=author_see 20240725183347 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3825", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CGPKURCN2W27ZAMXCYPBPBVBG2QZXXAT", "length": "11030", "offset": "4188396", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00464.warc.gz", "charset": "UTF-8", "languages": "fra,eng,lat"}
+fr,missiondefrance,bibliotheque)/index.php?id=383&lvl=indexint_see 20240724145807 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=383", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "O5WY3RZPCQALG23AIPJRWW6QLBQ32COI", "length": "9768", "offset": "111025716", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00193.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=383&lvl=subcoll_see 20240725195536 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=subcoll_see&id=383", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "K3VY627EOAZPMMKFCUXLDOEIG73F7BCK", "length": "6851", "offset": "118622712", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00786.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3847&lvl=author_see 20240715061331 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3847", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JLWZXOJ3SWFRU4PDOD5ABII5FQIW7JUQ", "length": "7896", "offset": "109567616", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00507.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=385&lvl=publisher_see 20240718150626 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=385", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LQZJVNX3GTI2QS4GN2CESE6SYOWSIXRH", "length": "9015", "offset": "118760371", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00752.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=386&lvl=bulletin_display 20240722104707 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=386", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "V25XTWWII5GZ5KMEYZVHCOUHASUJVYD3", "length": "4945", "offset": "109898310", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00551.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=386&lvl=indexint_see 20240716154530 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=386", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JGV47BMDXJ6Y7LMRLMBSAHI67K2XLINL", "length": "11755", "offset": "110550922", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00196.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3864&lvl=author_see 20240715043955 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3864", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QZNE7SFPHCRPGXSFFB3PVEMHOLLU3VIA", "length": "8133", "offset": "4299732", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00587.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=387&lvl=publisher_see 20240718200153 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=387", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SMQMWJFZBTZUPQUF3B3HAYA7Y3WOYID5", "length": "10568", "offset": "3485202", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00179.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=388&l_typdoc=a&lvl=indexint_see&main=&nbr_lignes=31&page=1 20240718144526 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=388&page=1&nbr_lignes=31&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AV4DKDQ527GZ7TIETJGYW45ECOXB4S7L", "length": "10766", "offset": "3829055", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00894.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=388&lvl=categ_see 20240721221455 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=388", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7ZWP6XIQVKBBBS4YHAXEF3JW23KZDRV7", "length": "11969", "offset": "114950107", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00551.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=3889&lvl=author_see 20240712174648 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3889", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CR4MDVP3V6EN7KFFEJTSSLCFEVUOFM3T", "length": "6990", "offset": "99986181", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00633.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=389&lvl=indexint_see 20240715050200 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=389", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JNZGLAEYJSP3N3BQ5VTI56OSKBFT6DLQ", "length": "10193", "offset": "4146151", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00210.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=389&lvl=notice_display 20240718213730 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=389", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YZMYWYB4KQ3GKI2KXFCL3J5VAFXDHTCM", "length": "5087", "offset": "116173519", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00273.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=390&lvl=author_see 20240715041828 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=390", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "REI3RBX4DB5XZCRZRECSJ4G2MWRSEHRX", "length": "11351", "offset": "3732112", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00734.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=390&lvl=coll_see 20240718205130 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=390", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "E5ZGSWVGACX4NJYUSLYJBYOLQNASVBHB", "length": "6512", "offset": "4985868", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00753.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=392&lvl=categ_see 20240712183844 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=392", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4LEM7RXOYWFCRA5A2H45CDSFELFP2W3A", "length": "10489", "offset": "103047443", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00576.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=392&lvl=categ_see 20240718144548 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=392", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6UHO7G37SBVMAP25MD4TIBGSIKD42CFI", "length": "10451", "offset": "4107890", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00609.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3924&lvl=author_see 20240721221152 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3924", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NWPJHHMUDNR24HXMLXO6GUDFRDHHX77I", "length": "6676", "offset": "3049006", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00524.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3929&lvl=notice_display 20240716145225 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3929", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OS5IW67KA6COHZEFFHRVKTP5BT3LVL4C", "length": "5115", "offset": "110689686", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00508.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=394&lvl=categ_see 20240721004234 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=394", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YDYQH723HKA22VLZVUZZ5CFZN23NMZ7O", "length": "10603", "offset": "119318859", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00578.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=394&lvl=coll_see 20240718132800 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=394", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KUSA6NUAREPMOPVYDX4J32DCYB2U5LPT", "length": "10430", "offset": "4323060", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00757.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3941&lvl=author_see 20240718191950 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3941", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TEPHQ7WL6QXAQIT2BF3IZOHZ672UDGWB", "length": "7065", "offset": "4924766", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00583.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3945&lvl=author_see 20240712163144 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3945", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WDCEVHK5PASE7BFXYUNXADZWUQUQLYQP", "length": "9476", "offset": "113921519", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00566.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=3952&lvl=author_see 20240725182243 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3952", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PCUOS6K3RHLG2R4UBNKHU7BT5MZKV4W7", "length": "7523", "offset": "2885015", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00615.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=397&l_typdoc=a&lvl=author_see&nbr_lignes=47&page=2 20240721233626 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=397&page=2&nbr_lignes=47&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7HW6Q6GOZZMEYEPELUPORJW7Q4IHUJLW", "length": "12634", "offset": "113324759", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00883.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=397&lvl=author_see 20240724152546 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=397", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2BF6OG5DURNESDFEKHALZTIUM7SZ2XLK", "length": "11746", "offset": "109874011", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00254.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=398&lvl=categ_see 20240715050903 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=398", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ERL256BMHTIYVY6PJQFXANUGU7WKISM4", "length": "11084", "offset": "4128266", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00615.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=399&lvl=bulletin_display 20240722111329 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=399", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CLNDFB5BSK5Z37BSMRVT4QTIXQVVQN2H", "length": "6299", "offset": "102171867", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00585.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=399&lvl=categ_see 20240718140219 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=399", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DODC3JH3KGB57EPX7XBPE336A6D3G4D5", "length": "7692", "offset": "102976697", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00583.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=3995&lvl=author_see 20240718205800 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3995", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TUJFC5YGSQMJVMGSLHGLT26DEBRU45EP", "length": "7097", "offset": "5626233", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00742.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4&lvl=categ_see 20240716155311 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=4", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3I6R72ZEFRFQ5GPYQ5K7JJE46MEJJBAV", "length": "10757", "offset": "113580701", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00548.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4&lvl=indexint_see 20240718192824 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=4", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QRJJWLMLQFRSVAPT7DIDWCPY5US7LCFJ", "length": "10370", "offset": "4480850", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00490.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4&lvl=publisher_see 20240712162424 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=4", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MYSWVMUXA46V3HRXVLQD3QSEKXEPDLNU", "length": "11249", "offset": "107766283", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00156.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4&lvl=publisher_see 20240716151334 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=4", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZZWHGBJJJ4Y4BH34WW6ZSEM7FHAMP7GB", "length": "11210", "offset": "2854114", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00229.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4007&lvl=notice_display 20240712182048 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4007", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AA4JHGHUXJFOMOTYYSNNLGDNBMYL3N6Y", "length": "4986", "offset": "3335481", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00055.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4008&lvl=notice_display 20240721222257 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4008", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KFNOE2WRJTXGZPBVX6L47PLCQ3ZZWFFM", "length": "4903", "offset": "105678995", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00887.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=401&lvl=categ_see 20240724144629 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=401", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EY53JS7HVRSU6AZ25FGPJAO4CU6YQCU7", "length": "11034", "offset": "3081328", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00390.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=401&lvl=publisher_see 20240724161328 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=401", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "25GYNXQ2OTA3TOLCMX3YQUJQP5LCOG56", "length": "6767", "offset": "113719408", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00561.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=402&lvl=subcoll_see 20240721222757 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=subcoll_see&id=402", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "M4MSJOXPDHMRRAQZGJAKB7VIIPHTVXC6", "length": "7446", "offset": "114784702", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00598.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4022&lvl=author_see 20240722111311 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4022", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AEWY3YIEA7IRQCRIS5FML2GQXKWFAV2T", "length": "6459", "offset": "3849146", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00064.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=403&lvl=bulletin_display 20240722110014 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=403", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UDSKLGQTRRYZI73TCFQG4QVG42RNKPG4", "length": "7455", "offset": "107111223", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00361.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=403&lvl=categ_see 20240718193646 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=403", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AEYTYVS2MWMDN3VYQWVYJ7MB6C3VIDW2", "length": "10465", "offset": "3353245", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00392.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=404&lvl=bulletin_display 20240722110045 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=404", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EA4J5IUETUTKVJIKQWRWJKDAZM2XCRAL", "length": "8109", "offset": "112563006", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00362.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4049&lvl=author_see 20240725184122 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4049", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PQJ2TYQGZ2367BVLUMM7E6CRXO5Q4MIN", "length": "7248", "offset": "3615714", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00133.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=405&lvl=author_see 20240721003944 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=405", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZFE3DNL6IK2KXTIJLBT7RIVO42J7ANWJ", "length": "8059", "offset": "4291474", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00521.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=406&lvl=indexint_see 20240712173901 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=406", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JOPDHN2P4FCTTM6HMYNFCPDVQCS36R4M", "length": "10979", "offset": "109546284", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00009.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4065&lvl=author_see 20240718212117 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4065", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "STKZRTKRPMSYWAPK4I2ODWQH5SQVTB5M", "length": "8849", "offset": "107343433", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00170.warc.gz", "charset": "UTF-8", "languages": "fra,ltz,lat"}
+fr,missiondefrance,bibliotheque)/index.php?id=4065&lvl=author_see 20240725182544 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4065", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CHJCJKFHFCFEMMJPHZFMAV777LJPZDR7", "length": "8839", "offset": "5502851", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00191.warc.gz", "charset": "UTF-8", "languages": "fra,ltz,lat"}
+fr,missiondefrance,bibliotheque)/index.php?id=4067&lvl=author_see 20240721015708 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4067", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HCDJ4FCI3XEQQIGSYKFAJ6LNAXMCG3FV", "length": "6738", "offset": "4203794", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00193.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4068&lvl=notice_display 20240725191500 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4068", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "423WYNPU2GDPJFZDQKLBRU4DMO3RGEPS", "length": "5019", "offset": "114925039", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00173.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=407&lvl=bulletin_display 20240718140620 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=407", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KIHS3USI6ZV6NEVFHU7U4BNW4UWES4PV", "length": "8153", "offset": "105917796", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00365.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4071&lvl=notice_display 20240725201326 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4071", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GMKG7ORTL46CU57UVZAJXM4EERL2PPU2", "length": "5017", "offset": "113975326", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00197.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4073&lvl=author_see 20240718143258 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4073", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JXWAX3GDC3QZYZGS63VYBCS2DNIHDF2A", "length": "8141", "offset": "117416741", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00199.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=408&lvl=bulletin_display 20240722110315 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=408", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RZV4LG2QQEFNG3N4JLRFY2TIHCC2PCVM", "length": "7101", "offset": "112122325", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00366.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4082&lvl=author_see 20240716144556 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4082", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FU6INYWHNJIPAZYH3HDXI7R4RDC4GXEW", "length": "9569", "offset": "120621075", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00229.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=409&lvl=bulletin_display 20240722110416 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=409", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Y3MADDW2CSJM4N67QLX2SUVL7XWZZD73", "length": "7700", "offset": "106001986", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00367.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=409&lvl=bulletin_display 20240725191220 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=409", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SS533UOVLN6DC6HH2KSGPNOJ55GORGFG", "length": "7687", "offset": "3107290", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00014.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=410&lvl=publisher_see 20240716145629 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=410", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3D34YSTD3Z3SNMLDKMOW6454N4UQ7R24", "length": "10237", "offset": "3350164", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00016.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4100&lvl=author_see 20240724144245 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4100", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TWV4YL2MWOTZM4MISYVPPV3XG6Q2NHD3", "length": "11634", "offset": "108207086", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00040.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4101&lvl=author_see 20240721012626 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4101", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VUEWNSLNXO7GUSD5QWMKLCE45NUXN55O", "length": "10247", "offset": "107456155", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00041.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=4113&lvl=author_see 20240715052748 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4113", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Y7H6PSM7RCIHTP7D3U3JRBP2AGV3D7EV", "length": "9338", "offset": "113492048", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00074.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4113&lvl=notice_display 20240719084030 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4113", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "P75C6PSHAKSNFAOAAFBM2XYRNCGNKZGR", "length": "5024", "offset": "110928237", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00074.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=412&lvl=bulletin_display 20240724155518 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=412", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "IKHGDUGCPPGT57H3ZEWYYYSJAK4TVDEQ", "length": "21798", "offset": "111309438", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00391.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ita"}
+fr,missiondefrance,bibliotheque)/index.php?id=4129&lvl=author_see 20240719090635 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4129", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AG7J4SQJFOM6YCLWK6APVTQEDEEPMRVX", "length": "7100", "offset": "105754336", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00111.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=413&lvl=categ_see&main= 20240721012316 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=413&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5POYDA4IHGOAYS64CCTREMN7MFIZZTKX", "length": "10649", "offset": "114201003", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00136.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4130&lvl=author_see 20240721020356 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4130", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GOX5JATARRSINEHVDVJGHPVQMPLHNEMF", "length": "6633", "offset": "3258959", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00154.warc.gz", "charset": "UTF-8", "languages": "fra,ltz,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4131&lvl=author_see 20240721232837 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4131", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TSEYMHJENCFT3G5ULQARGNFRHG5DPQZX", "length": "7196", "offset": "3084584", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00155.warc.gz", "charset": "UTF-8", "languages": "fra,ltz,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=414&lvl=author_see 20240715042232 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=414", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3RO5XGSGPNJIYZCTX52EXR57DU45MUZ4", "length": "8498", "offset": "110917246", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00064.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=415&l_typdoc=a&lvl=indexint_see&main=&nbr_lignes=36&page=2 20240721011018 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=415&page=2&nbr_lignes=36&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CLRJAUP7EDQPZZX4TOBSBO4IQELU4AVL", "length": "5138", "offset": "113282529", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00170.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=415&lvl=indexint_see 20240721005046 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=415", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XIVOXIIN5MJPZHOTEPE5RBMK5V3ROLSX", "length": "11275", "offset": "4265356", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00050.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4151&lvl=author_see 20240721002643 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4151", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7XVVIMXVBWS3K3TIOT6DDREHVUCEAIFO", "length": "11058", "offset": "113206898", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00196.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=416&lvl=categ_see 20240718203535 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=416", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EOKTL2GKOM3PIP6WR4GKBDXKE7LCRHKA", "length": "12004", "offset": "4531351", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00426.warc.gz", "charset": "UTF-8", "languages": "fra,deu"}
+fr,missiondefrance,bibliotheque)/index.php?id=416&lvl=indexint_see 20240718145543 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=416", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MSC6KVQXQOU5AKNMKTEN7QX5KICZ4RXE", "length": "9831", "offset": "5792512", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00051.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=417&lvl=categ_see 20240721000847 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=417", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KBTM5JSKIMXVWCMNRMSBI7NZ2UNURH4G", "length": "9245", "offset": "105099721", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00394.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4176&lvl=author_see 20240721005905 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4176", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CCIZRGLGKOPOJ3YEGMAQP3RRDKT2VCQ3", "length": "6436", "offset": "120476322", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00263.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=418&lvl=indexint_see 20240715060948 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=418", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6ZNXTGAUYZUXZDHS3H35GJ6RPVYDTQKR", "length": "10069", "offset": "5425601", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00053.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4189&lvl=author_see 20240721015235 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4189", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FFGWO32NEUXJE5TT73HA6SBU63I6NOIE", "length": "9079", "offset": "117800461", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00297.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=419&lvl=categ_see&main= 20240719074559 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=419&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3VZ4WCFRFCO3E43WHKHJSAV7CVBQV5KJ", "length": "9944", "offset": "118377379", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00426.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=419&lvl=coll_see 20240719081108 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=419", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "X4P7JA5S3VVCONXEMTRF7M4QGIV4ZZNJ", "length": "7554", "offset": "116454212", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00584.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4192&lvl=author_see 20240721002025 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4192", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DC3N6WOFAJD4PHKRDGBM3UCHDIJRJ3IG", "length": "11016", "offset": "3590832", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00342.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4194&lvl=notice_display 20240718195516 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4194", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EEKNPXUD7ZDJZO4VKT5EWXAWV7764EFX", "length": "5130", "offset": "116048737", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00323.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=42&lvl=categ_see&main= 20240718213737 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=42&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HKRJZ7MY5DCDIHBUW72CLYTCJTUEKYHP", "length": "10781", "offset": "113915068", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00364.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=420&l_typdoc=a&lvl=categ_see&main=&nbr_lignes=66&page=1 20240725200541 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=420&page=1&nbr_lignes=66&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Y6DEFEXSXA35HFWK66RTM7RCNLCVM7SA", "length": "10270", "offset": "102825030", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00469.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=420&l_typdoc=a&lvl=categ_see&main=&nbr_lignes=66&page=4 20240725200729 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=420&page=4&nbr_lignes=66&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Q3JH2WEUXYHTTQC37OZVALNURVDQTGJW", "length": "10638", "offset": "107193371", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00190.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=420&lvl=categ_see&main= 20240725201536 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=420&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "H5ICQFLECTLFVE5JVTOJ4DTFRHG6GHQA", "length": "10249", "offset": "104893866", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00376.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4201&lvl=notice_display 20240721013655 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4201", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "U5GAMNKUPD56FUPRUFA5KLDSOAEQWA4Z", "length": "5005", "offset": "114650137", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00102.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4208&lvl=author_see 20240721010152 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4208", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SGSIWZMHDUK3PNMIXWUOXFD7F6PEJOYU", "length": "7959", "offset": "106394584", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00109.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=421&lvl=indexint_see 20240718141802 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=421", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RFACXFTMISICRT3AEZRTP2J5LFX5V3FP", "length": "8916", "offset": "110382169", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00066.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=422&lvl=categ_see 20240721232947 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=422", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "H7NX3CDPJ6WYLSKH27XJM5DSXC5H74QP", "length": "11172", "offset": "103514199", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00420.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4221&lvl=author_see 20240721230115 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4221", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BYJULGG5N5AFYFMHG6YVRCOR33Z627R3", "length": "9204", "offset": "111655969", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00164.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=424&lvl=coll_see 20240715061845 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=424", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MWK43CB5JRXC2VYAIXA5QTJWGKW6ZX36", "length": "6718", "offset": "114887043", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00610.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=426&lvl=author_see 20240718132040 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=426", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TBRCH4ZCHFUDUVUJER6AZ7USNNYVHLDJ", "length": "7953", "offset": "106355434", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00097.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=426&lvl=coll_see 20240725194954 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=426", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ESXOAP2KBQPAQ2TMTW3ZWZRZ4YMGFFPM", "length": "9124", "offset": "3040732", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00603.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=426&lvl=indexint_see 20240724160507 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=426", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2YDW7VNN2EHDQLIEXJC343XOL6LJDXAI", "length": "9120", "offset": "5404793", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00082.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4260&lvl=author_see 20240722113832 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4260", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "W3OCSG7DGULUTOB6HWVTE7XIXBH5TIBY", "length": "7045", "offset": "115516692", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00287.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4263&lvl=author_see 20240715044812 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4263", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7TH7PJZOP6YV4S52QRJ2A6YU7446O6TR", "length": "6653", "offset": "4864414", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00311.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4264&lvl=author_see 20240715043351 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4264", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SW3YQGMLUOF2DWQ4DJIOUE553WOCRK6Y", "length": "6651", "offset": "4389433", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00312.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4265&lvl=author_see 20240715041709 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4265", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ARSEAXZIMERT2ACJNWPVB4RYTXGXTZBX", "length": "6649", "offset": "3443205", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00313.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4266&lvl=author_see 20240715061254 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4266", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "36OED2IQRJ62RVE453ZMQTEJNDVRIFX5", "length": "6649", "offset": "5301822", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00314.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4266&lvl=notice_display 20240725194108 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4266", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GHLNDZJKP6AOFI6TVODA2XPKDFF3YEIK", "length": "5063", "offset": "2944203", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00362.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=427&lvl=indexint_see 20240718135108 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=427", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "E6R4QGBYCVEY53WKDW564U2GXFYGBCBI", "length": "10411", "offset": "3558063", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00083.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4270&lvl=notice_display 20240724152805 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4270", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZJ5H6T2LGQ6TPRDEX6XIBBA7OFEVTYVS", "length": "5268", "offset": "3380821", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00387.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4271&lvl=author_see 20240718194433 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4271", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ADPOAY5VGLRYCHVNGBFVKRT74R4HMOO4", "length": "8176", "offset": "118967593", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00319.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4271&lvl=notice_display 20240721231350 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4271", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SVM4JDZS43VRFLQFA72CBXJTF35ZMV4E", "length": "5293", "offset": "3188135", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00388.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=428&lvl=indexint_see 20240712185910 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=428", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UPWAERD3NBJ7VOLDLEARW3QXHTX6X6RD", "length": "10750", "offset": "102415846", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00073.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4294&lvl=notice_display 20240716151410 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4294", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "H2WSJFZP4EK2LKL2GMF3OMU4NTMUT6DO", "length": "5228", "offset": "125623261", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00384.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4295&lvl=author_see 20240721134017 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4295", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2STM75BKWYT7CBNIQ3QNHIS44QWOTF53", "length": "7036", "offset": "3158940", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00406.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=43&lvl=categ_see 20240712175906 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=43", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ING446HAADYFIKAKWYF6MKEXH2FYKTGZ", "length": "10625", "offset": "3089604", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00330.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=43&lvl=categ_see 20240721000945 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=43", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VX33Y7V4UOFYEYLEYJC6XEDKTDK5JHAE", "length": "10631", "offset": "108570574", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00287.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=430&lvl=publisher_see 20240721123328 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=430", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7GOZKB355LKGMW3K73QTBFIYUQXJ6ISD", "length": "7021", "offset": "116667812", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00653.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4306&lvl=author_see 20240715051701 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4306", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5WUQUTY5BXQBBMF2A6VJEKDLVDALSWQS", "length": "8149", "offset": "3795675", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00189.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4317&lvl=author_see 20240721214637 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4317", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "F6YZOOJPKDF3WO4K2XKDB72URMILSCSK", "length": "6501", "offset": "116444997", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00200.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=433&lvl=categ_see 20240721213731 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=433", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TD7X3KGQDM6IHE6VRVEATKEFBHYRCAF2", "length": "10640", "offset": "111891058", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00452.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4332&lvl=author_see 20240716154759 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4332", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FCTBROHYAHEM5FGGLCLIPHNCDDNYZTOR", "length": "9624", "offset": "6113166", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00278.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4332&lvl=notice_display 20240724150506 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4332", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Y6DJPLOVIX64VI3EFQA34JSBE6XR5RKT", "length": "5215", "offset": "4186864", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00326.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=434&lvl=categ_see 20240719083321 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=434", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DDMWEI5LY2HSXLNTZLSO3FEAHCOL3YUM", "length": "9405", "offset": "111432011", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00453.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=435&lvl=indexint_see 20240724144349 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=435", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LOQTOK467FSAGPTY6MFXVYT7G4S4RPWP", "length": "10586", "offset": "114049479", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00101.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4357&lvl=author_see 20240722111738 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4357", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7T6URKW3B2ZOR6GYA63LJJ5REZJJIB3X", "length": "7895", "offset": "110381132", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00324.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=436&lvl=publisher_see 20240721230336 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=436", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ACFWQU7TVWLJFRDCWTLT6DQFMUJUUZOV", "length": "10656", "offset": "112149653", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00659.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4362&lvl=notice_display 20240718200353 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4362", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SQOIBPOV5JOQGNC57ICZ5QG5V5DLSG72", "length": "5206", "offset": "116620355", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00350.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=437&lvl=author_see 20240722111058 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=437", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UFNTYPAIHDFNF4AGXRVTS2DTWUL7KNI5", "length": "7741", "offset": "4911037", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00616.warc.gz", "charset": "UTF-8", "languages": "fra,deu"}
+fr,missiondefrance,bibliotheque)/index.php?id=438&lvl=coll_see 20240721232034 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=438", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YGVUTOM2INQ5KIQ27GTDYYO2MRDPYBHS", "length": "10061", "offset": "4683126", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00636.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4396&lvl=author_see 20240721131850 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4396", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CI5YEQMC6RHHU6V4PVSQVCLARQPHEHUR", "length": "6813", "offset": "4331517", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00468.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4397&lvl=author_see 20240721130823 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4397", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EQDVLR7IUFGRRGUWIJM2I4WF3OTX452F", "length": "6820", "offset": "3866150", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00469.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4398&lvl=author_see 20240721125725 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4398", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XYZFKIXBR26W3HH76GW5VRGUFGRBAZBD", "length": "6818", "offset": "6255220", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00470.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=44&lvl=indexint_see 20240712164421 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=44", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LJ3WREDNSXCQAM54KCZV4YUEXTYFKUQR", "length": "10052", "offset": "99197642", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00285.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ile"}
+fr,missiondefrance,bibliotheque)/index.php?id=44&lvl=notice_display 20240718211555 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=44", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XGXFA6NY4BLSZZ7BA5BAUATOP3NJKHJR", "length": "6107", "offset": "106856202", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00767.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4401&l_typdoc=a&lvl=author_see&nbr_lignes=17&page=2 20240716160725 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4401&page=2&nbr_lignes=17&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DVLL7U4L6HXUDLTXSHAENLBQ6XIRBYWE", "length": "6794", "offset": "118535754", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00350.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4404&lvl=author_see 20240718145721 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4404", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YYARGYOSMCTQBGWFAKWVFYK2TBYRIY2O", "length": "8029", "offset": "104521666", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00227.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=442&lvl=publisher_see 20240721122949 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=442", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XHIN2FTO2ZM4ADT2E3DQAKF2LKO5I6RV", "length": "6821", "offset": "109686369", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00686.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4424&lvl=author_see 20240721215503 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4424", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NPSHWJNIBRL3JTGMCIXCX4DUZACFDYRR", "length": "10346", "offset": "4440590", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00310.warc.gz", "charset": "UTF-8", "languages": "fra,lat,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4433&lvl=author_see 20240716152629 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4433", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ULFHJL6VR2LDZUDGRDVUAGR5YKOERTI3", "length": "9421", "offset": "3411795", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00340.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4437&lvl=author_see 20240718132528 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4437", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RXL6V2QJWYN7HGF3JPADO2URFKCQQ45Y", "length": "7873", "offset": "115858238", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00323.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=444&lvl=author_see 20240721140353 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=444", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "42YJPQIDCRQOMOILMMWLN22HXKIOBP3I", "length": "10362", "offset": "3098068", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00644.warc.gz", "charset": "UTF-8", "languages": "fra,ile"}
+fr,missiondefrance,bibliotheque)/index.php?id=4446&lvl=author_see 20240719084257 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4446", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VC7MUO2JWVLYQMVFQ626ZATYK2NIZEHQ", "length": "9123", "offset": "3917754", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00374.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=446&lvl=categ_see 20240725193819 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=446", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "W3UDNLH7I6UNYGDCP6K7NZJDAD2N5U7F", "length": "9908", "offset": "109940269", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00486.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=447&lvl=indexint_see&main= 20240721014209 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=447&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JZZOZVDUGVF4O32SVTUT3W4UICHCN2VD", "length": "10696", "offset": "113747762", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00332.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4470&lvl=author_see 20240722100835 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4470", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LBZTYNGRGCZL6DWKKYUWOLJ6GSWZ2C73", "length": "6541", "offset": "113283925", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00440.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4483&l_typdoc=a&lvl=author_see&nbr_lignes=26&page=2 20240718213743 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4483&page=2&nbr_lignes=26&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DWEPE5VWCK7RSJU4R54DFCSMZLZ7JYYC", "length": "9819", "offset": "112085249", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00866.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4491&lvl=notice_display 20240715054844 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4491", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GM4WJSVFWWCCGGWHI2MCPUFTE4P47AGS", "length": "5146", "offset": "117255373", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00503.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4496&lvl=notice_display 20240721122509 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4496", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3TQIJUUOVIRH7YXUQ562I3R23STOK4XE", "length": "4912", "offset": "105355406", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00508.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=45&lvl=author_see 20240721010520 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=45", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7RVX7KV5K5TZSLVELLNSZZMFPEBKHCKY", "length": "11367", "offset": "5050717", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00297.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=45&lvl=publisher_see 20240715052541 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=45", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MVL3PWOM5FVHM34CBA657SF5RQK47FPE", "length": "11409", "offset": "112778453", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00893.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=450&lvl=categ_see 20240724150318 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=450", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KW3NMHJT2SNSYUXXHZVZ2COD5OME53QA", "length": "10359", "offset": "4100157", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00544.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4506&lvl=author_see 20240722102036 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4506", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LNCY4DEDP53IPY6NVFG665BVS32CGMFP", "length": "6785", "offset": "108026625", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00290.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4515&lvl=notice_display 20240719083358 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4515", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CIDC4GT6UCDSDMHN4O7AGLXXYI7XUZJO", "length": "5146", "offset": "106985095", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00320.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=452&lvl=indexint_see&main= 20240721223516 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=452&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UA4NM655UKLY6ECZG7SASHVLWUHWJVO6", "length": "11549", "offset": "4571182", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00009.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=453&lvl=publisher_see 20240712185520 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=453", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GRXKERT4WDUNGKKKCPCCCL6TR2BMTKTU", "length": "10588", "offset": "98357235", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00718.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=454&lvl=author_see 20240715061447 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=454", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "C2CENUZNC6KAWIOBQKHJKUGK67YWTC2A", "length": "6659", "offset": "112427277", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00188.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4544&lvl=author_see 20240725191342 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4544", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ANHF7VOEURH2DT57ET4DPRFVXKITHEZS", "length": "9399", "offset": "3895423", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00433.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4548&lvl=author_see 20240725194643 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4548", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TMMFUPNQRXPUXCTHSFBY5G6JGYHDTCJY", "length": "7193", "offset": "116295744", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00416.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4548&lvl=notice_display 20240725183521 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4548", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TF57DEQK3LFEEKHLUQBLI7H2RV66FKK4", "length": "5089", "offset": "3671559", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00485.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=455&lvl=publisher_see 20240712162637 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=455", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BU7ZPAUROHTXHTXYLSCNAPU4CTJKSNIF", "length": "10134", "offset": "3198139", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00145.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4551&lvl=notice_display 20240725200619 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4551", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4J5HSUTM3PT5MJFFGNCDN3KRLDT3XIMT", "length": "5018", "offset": "3415137", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00509.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4554&lvl=notice_display 20240725190928 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4554", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BC5KSJ3ULMVQ4KFIDH32MBRRDX466ARI", "length": "5268", "offset": "4377364", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00512.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4587&lvl=author_see 20240712182513 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4587", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "22RDJ63QWZXW4BX7SPYOMNUDQ5R2WM4S", "length": "6952", "offset": "101185119", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00539.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4594&lvl=notice_display 20240718142306 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4594", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GVXZABHMAJHPU5VN2FK6KET6DMCQ36JD", "length": "5045", "offset": "102615813", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00567.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4595&lvl=notice_display 20240721123644 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4595", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RCQCGYHYXMKHR765DN2UJ22U5HYFTNIH", "length": "5050", "offset": "4750920", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00637.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4596&lvl=author_see 20240715043046 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4596", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JMLVZYBBVWXBOVFSUPD73R3TQ3XLL6TY", "length": "6673", "offset": "111021015", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00569.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4597&lvl=notice_display 20240721130716 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4597", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4YYL4MPQAMAC7EPJXO3PVK3YJGV4Q6ER", "length": "4992", "offset": "112478571", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00570.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=46&lvl=categ_see 20240718212721 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=46", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QJLTXGDTBW7YWW7NRQLITC5GAODZONZZ", "length": "11741", "offset": "112129653", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00290.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=46&lvl=publisher_see 20240716151835 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=46", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UPVS6VMWRW2DAVVDPL5ANUJHFLZFVL4K", "length": "10970", "offset": "118014779", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00894.warc.gz", "charset": "UTF-8", "languages": "fra,ile"}
+fr,missiondefrance,bibliotheque)/index.php?id=46&lvl=publisher_see 20240718132400 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=46", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YN7XQU5VFDY67EBP3NE74VY3NXQG67FX", "length": "10925", "offset": "2813055", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00057.warc.gz", "charset": "UTF-8", "languages": "fra,ile"}
+fr,missiondefrance,bibliotheque)/index.php?id=4613&lvl=notice_display 20240719095950 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4613", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YJ3RAHBBFW4Z66EEHE73GDLAGID2E443", "length": "5019", "offset": "110705289", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00379.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4616&lvl=notice_display 20240721011534 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4616", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FJ532SCL2OJ4WLJVFTW7R2PQP5HDRWPS", "length": "4958", "offset": "110739080", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00382.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=462&lvl=publisher_see 20240721133426 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=462", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "R4QADWEC6TEDBQDP3UHLYWFKRZRPPNER", "length": "6562", "offset": "115706769", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00748.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=463&lvl=categ_see 20240719094354 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=463", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "624YCVBHXO7NPEHGTZCDP44NMFVSFTXE", "length": "10502", "offset": "3616941", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00578.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4637&lvl=notice_display 20240716155104 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4637", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KOWCFUZ5GFQAYRL2LD722DTY4ILQAWC5", "length": "4992", "offset": "4150417", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00514.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=465&lvl=categ_see 20240718142456 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=465", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NIQUWR3WTVEESIFN3QLWJRSTZ7VVNMG4", "length": "11135", "offset": "3299786", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00580.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=465&lvl=categ_see 20240721222111 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=465", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5UYGQR4HLDLIXDPVSVIKSBCOSY6RTUFU", "length": "11150", "offset": "110102085", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00547.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=465&lvl=indexint_see 20240718143432 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=465", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VPL7YIIYW75MSCLYWOA2O7VKAWXMNJLK", "length": "9094", "offset": "112097473", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00194.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4650&lvl=author_see 20240715054633 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4650", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XIZRG4EHZHQFMNL63264FUNVP4UD2PPS", "length": "7177", "offset": "112919060", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00500.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4652&lvl=author_see 20240715054927 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4652", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "M7FDRTDGWKL4XNVQ7LULG432K2LE5GFX", "length": "6532", "offset": "117710644", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00502.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4663&lvl=author_see 20240716145428 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4663", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "B5JYBQJYHPWSKH7LMPY42XTMYBHEXNWS", "length": "6605", "offset": "113852114", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00534.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4665&lvl=author_see 20240721215954 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4665", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3ACXUVKZFGB3A76I4AVJHVSKMD24XJ5R", "length": "7477", "offset": "109457203", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00536.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=467&lvl=categ_see 20240722114021 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=467", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AE6BWHD5WIWIYH5NNQVZNBQK6JPLFDJ7", "length": "9182", "offset": "112076855", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00549.warc.gz", "charset": "UTF-8", "languages": "fra,deu"}
+fr,missiondefrance,bibliotheque)/index.php?id=468&lvl=categ_see 20240722120455 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=468", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VEU4KZ5QMMDQOXHR5GBGKWAMXP6DWQXP", "length": "8771", "offset": "116500634", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00550.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=469&lvl=categ_see 20240721130857 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=469", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HWTHRCJORVGJJQZR6BIFLQGTHUZR2EPY", "length": "11007", "offset": "6605945", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00584.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=47&lvl=author_see 20240718204602 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=47", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VR7PYMFBEGBWSICPJTFIBLFKXBBK3ZGY", "length": "11170", "offset": "110484190", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00266.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=470&lvl=categ_see 20240721215708 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=470", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WPTCU2STZ4VZ4YCACQQE3IMJQ4XEOXRQ", "length": "10688", "offset": "111296051", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00573.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4700&lvl=author_see 20240712175242 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4700", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZYBTSCHPR2WYI5UADNSNZDPVGZJVQYKS", "length": "8167", "offset": "107009667", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00406.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=472&l_typdoc=a&lvl=categ_see&main=&nbr_lignes=22&page=2 20240721123245 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=472&page=2&nbr_lignes=22&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DZY337BYTHNLT7DYVNINBORU4SENBPJN", "length": "9805", "offset": "108692265", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00013.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=473&lvl=author_see 20240719181103 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=473", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "P3TPZMDXZHGPZNCMEYIB73PMCS7BU6BY", "length": "10141", "offset": "3696337", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00736.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=473&lvl=publisher_see 20240718203258 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=473", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Z4L3FYY5WRDH6M4RKGJNB2MEK2K74JLX", "length": "10503", "offset": "116421052", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00780.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=474&lvl=indexint_see&main= 20240721221308 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=474&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SHD6QFBH5K5DB57NP4B3JOJIFSDIX4US", "length": "10421", "offset": "3331599", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00397.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=475&lvl=indexint_see&main= 20240716160459 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=475&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QABEWJQSBCE46HAAOGJFURPGSGVXSFJR", "length": "11279", "offset": "4057758", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00578.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4757&lvl=author_see 20240715051553 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4757", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6MFFQJATGJYPVUHPCL6KFNY6WIYYZK4V", "length": "7385", "offset": "111685130", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00568.warc.gz", "charset": "UTF-8", "languages": "fra,deu,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=476&lvl=indexint_see&main= 20240719174543 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=476&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KEAX6PVCPLPCXIEUSY4VGQMTM267EYUN", "length": "10865", "offset": "6217865", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00759.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=478&lvl=categ_see 20240721001646 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=478", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "X53P456LB7CZXNSAMYUCEXSQPJB6SOSH", "length": "10457", "offset": "4788129", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00614.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=478&lvl=notice_display 20240719095042 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=478", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SVFOZWIJZUG6C6LKDHL4ZCLMV6BIZWD7", "length": "5038", "offset": "3181949", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00441.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4786&lvl=author_see 20240718205630 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4786", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XBG2SUJ5KAKXYZMJEPTYZRR36BYZPWD6", "length": "7306", "offset": "103492728", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00660.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=479&lvl=bulletin_display 20240722115843 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=479", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BD4BBLGAAHEIG4TIWTEKBNE2OLE6ORPI", "length": "7127", "offset": "3125345", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00231.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=479&lvl=categ_see 20240718131103 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=479", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "63GYSFWFV7MSK36DTOFDMF5JH5UJUR7G", "length": "11129", "offset": "5534152", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00615.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=479&lvl=coll_see 20240716160339 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=479", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "N5WO3JGHA54DQECETQI56B6GEVVUKBAG", "length": "11205", "offset": "116111467", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00770.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=48&l_typdoc=a&lvl=author_see&nbr_lignes=85&page=5 20240721002719 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=48&page=5&nbr_lignes=85&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "22XKXI5NWHQ3FH2ZDVL6J5JPGTTUNY2Z", "length": "10697", "offset": "5136492", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00204.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=48&lvl=author_see 20240716161702 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=48", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LBEYZX2TW6TLYNX7C6SB4K5OIQYEWDF6", "length": "10069", "offset": "122862730", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00267.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=48&lvl=indexint_see 20240712172020 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=48", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5R3N5SJQV2FOV2FZ45YJVTRJ6MKBRYLA", "length": "10864", "offset": "5475317", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00310.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=48&lvl=indexint_see 20240721220530 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=48", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TTNU4GC6KYIQVRHBQLES4BGFT6AGWUEW", "length": "10869", "offset": "112277997", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00289.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=480&lvl=bulletin_display 20240722114847 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=480", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "K6LZWQDQQPUAVXN4GYIOVGBZM7AJHZED", "length": "6943", "offset": "5237620", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00253.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4809&lvl=notice_display 20240712172910 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4809", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "INT5CPH4AVASNMVK55BNFVYWEHM47Q6Q", "length": "4975", "offset": "103428511", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00476.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=481&lvl=publisher_see 20240724152029 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=481", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZPRH6RU6V2ACRYSEV3EPUKKY7ZCET2RT", "length": "8367", "offset": "4321397", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00234.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=482&lvl=publisher_see 20240718133555 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=482", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "J72HM2CFBVCXIZAVPCGAPHP3OAZW2OBY", "length": "10733", "offset": "108924862", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00810.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4822&lvl=author_see 20240716153413 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4822", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZQ2JRKANG7Q6H67WGXDRXX5FMV7VA3XV", "length": "10208", "offset": "109417392", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00531.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=484&lvl=author_see 20240712180317 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=484", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UMJ74KEXLVN27AXTCGL2OAN2X7RFK6VX", "length": "9539", "offset": "3547608", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00768.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=484&lvl=categ_see 20240712185645 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=484", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VIAQIXBLGP575ZIPTZSEI34FXOBELY6Z", "length": "11408", "offset": "106182215", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00608.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4849&lvl=author_see 20240718145504 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4849", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EUPG72JT53QTHTNQAOHECOA2AYVSKJEY", "length": "7183", "offset": "112130157", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00600.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=487&lvl=indexint_see 20240712180513 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=487", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PAOPG52WDXPBJ6Q2KE3BMYYW5UKRWNQY", "length": "10992", "offset": "2930430", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00269.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4886&lvl=author_see 20240718150945 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4886", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QUMMQUOGQ3SFIXZ6GNFTUSQKWSKRNDKN", "length": "7883", "offset": "3948921", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00742.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=49&lvl=author_see 20240724142510 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=49", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KFWVWP2UXFKLMROPQNXJ3TDFWGYCQUXA", "length": "11197", "offset": "107762694", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00268.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=49&lvl=publisher_see 20240712181856 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=49", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ITNVZ3NRZ6TGYE6M27RRJM6T5XRUKW7K", "length": "11389", "offset": "103369292", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00897.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=49&lvl=publisher_see 20240718204325 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=49", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "44CRTIMLNE3WSSR23QHRCEU7FVNM6RLB", "length": "11345", "offset": "4483037", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00060.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=490&lvl=author_see 20240721225303 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=490", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GCOQ6APENARFQI52QODHSWSZKV4YJ3SL", "length": "11167", "offset": "3548455", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00795.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=4907&lvl=notice_display 20240721134029 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4907", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "X4XO3GH5SQLIK7PSUT2YK7PZ7L6LD5QT", "length": "4967", "offset": "3857127", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00604.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=492&l_typdoc=a&lvl=coll_see&nbr_lignes=17&page=2 20240724151426 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=492&page=2&nbr_lignes=17&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JAJUCF6EH2TPYFN2J3GOMD2ZTLYQ62LI", "length": "7435", "offset": "112649908", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00623.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4923&lvl=notice_display 20240722105259 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4923", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XHMKKLE5Z4F2WOL3TWLDTCNSH5WOLNPR", "length": "4963", "offset": "99306201", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00593.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4935&lvl=notice_display 20240722111418 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4935", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LHCQJRTVUKEA2E5B4L22JM42OXH2X7VG", "length": "4920", "offset": "4603608", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00695.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4944&lvl=notice_display 20240722110744 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4944", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZXR6ZYFKHBHV4S2SYOR3PNOOR427H2PW", "length": "4932", "offset": "4239625", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00725.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=495&lvl=categ_see 20240716145308 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=495", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6NBJSH4KKEWBENTR3OO6YBTQ5UTIUBPW", "length": "10995", "offset": "111991573", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00640.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=4977&lvl=author_see 20240722113907 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4977", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GZRY6NJG7VCMTACF23TBSNKBIMF7YWJ6", "length": "9735", "offset": "109220945", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00752.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=498&lvl=bulletin_display 20240716144318 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=498", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XJ2QRCGI3MIPS4PYV67XRJV2ZHVBIT4B", "length": "8879", "offset": "5895298", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00292.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=498&lvl=categ_see 20240719095117 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=498", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "L5HNZF5SC5N33IORSF3DCLBVKWHMPKZ5", "length": "10435", "offset": "108750990", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00643.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=498&lvl=indexint_see 20240715061930 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=498", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5C3JNL23NNBLVR6OK43XQ3W4VFWS2ZZW", "length": "11064", "offset": "3026240", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00301.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=499&lvl=author_see 20240721225251 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=499", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "R5ZARFVTM2GYYQVQC7OXPIG2AR4OLR7I", "length": "6659", "offset": "4565854", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00804.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=499&lvl=coll_see 20240715061754 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=499", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SK3SMQRGSPNWZEUM7KA2IIK2YDESAKC4", "length": "6714", "offset": "120325520", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00832.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=4998&lvl=author_see 20240716143302 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4998", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7XY2W24Q6NSFSOH6EZFB7DGUKGQNDR6Z", "length": "6793", "offset": "117784267", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00815.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5&lvl=categ_see 20240716151141 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=5", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "V55MJ6A7OXFSRNXNKDCOCY6BIDNMQHH7", "length": "11171", "offset": "123432233", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00549.warc.gz", "charset": "UTF-8", "languages": "fra,deu"}
+fr,missiondefrance,bibliotheque)/index.php?id=5&lvl=categ_see&main= 20240712185414 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=5&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZMRGJ2ZSQCDM5AQP2ZP3ZPMLFZTFEMJN", "length": "11178", "offset": "106265194", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00787.warc.gz", "charset": "UTF-8", "languages": "fra,deu"}
+fr,missiondefrance,bibliotheque)/index.php?id=5&lvl=coll_see 20240716145144 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=5", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3JVJZPVPBDERXK6BBI2J6YDRPPAEUIJ4", "length": "10648", "offset": "4037199", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00568.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=50&lvl=categ_see 20240712180418 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=50", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CZL2XFZTVMMQPVDSB26C3PZX4U3S42WH", "length": "10651", "offset": "5852308", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00358.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=50&lvl=categ_see 20240718211919 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=50", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3TIHSBDSPRZRKTZLNWZ3Q5YZ7N64OBY4", "length": "10661", "offset": "107357616", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00315.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5006&lvl=author_see 20240724162550 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5006", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UGDW5T346OABJ4ZBDC7HKN7KBVCTOZJC", "length": "6624", "offset": "107217293", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00076.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=5011&lvl=notice_display 20240721131636 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5011", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VPPAL2EWE6VNTNAKISHXUBK7V5IRDPSR", "length": "5001", "offset": "108410504", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00102.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5016&lvl=notice_display 20240721135753 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5016", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6JIZNHHQYIP7MHPLQ2ZRE2XEDDEMO3M2", "length": "4996", "offset": "103275280", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00107.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=5018&lvl=notice_display 20240721125912 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5018", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VOXLJA7FFOVY2OFXD5CQBMSTUPYPBTD4", "length": "5261", "offset": "105901939", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00109.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=502&l_typdoc=a&lvl=indexint_see&main=&nbr_lignes=17&page=2 20240721011721 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=502&page=2&nbr_lignes=17&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5J6Q4TCQY675HN4S5654OF6GY6P5HM3B", "length": "7311", "offset": "107513370", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00622.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=5022&lvl=notice_display 20240718201853 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5022", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2IULTTOH5VBC5YZ4MP5US5HEI64V23TJ", "length": "4919", "offset": "4367002", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00203.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=504&lvl=indexint_see 20240721231436 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=504", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CP5BZVTOIFLHLV5VZPKQFPBLX74N7ZFV", "length": "8761", "offset": "103770150", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00068.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5042&lvl=notice_display 20240722105220 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5042", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZUFFZCRUD22YG35Z4WFDLO3Q4H6ZNCAM", "length": "5030", "offset": "112494741", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00196.warc.gz", "charset": "UTF-8", "languages": "fra,ile"}
+fr,missiondefrance,bibliotheque)/index.php?id=505&lvl=author_see 20240712181144 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=505", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "B7CS2GCTAZZ7TL5KRVRERT7E663R5LKR", "length": "10019", "offset": "103580848", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00095.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=505&lvl=coll_see 20240715055810 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=505", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "N4BHRQO3IBNUSLQ4BJ4KJ5X5LP64CJVK", "length": "10266", "offset": "3165524", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00601.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=505&lvl=coll_see 20240721010735 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=505", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AHKGPZQMZNDEWQXP7UVJGLDMK5IMARSF", "length": "10274", "offset": "116975271", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00610.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5054&lvl=notice_display 20240722101749 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5054", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BAYRY2FHCE4UWBDO7POC4XGHCL65VBDO", "length": "4989", "offset": "4250945", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00298.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=507&lvl=coll_see 20240716152348 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=507", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "STSBLWHNR3A7M4D4PMYJ4AVQBODY4G5C", "length": "9342", "offset": "118348780", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00612.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=507&lvl=publisher_see 20240724162823 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=507", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "66M4SBHZZ6B4F3QQOYHFNLJYVLQOTZYD", "length": "11920", "offset": "118096390", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00628.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=508&lvl=indexint_see 20240721015528 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=508", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WMKEDZ2JEQQCNG7KKA6RAXVBHVPBLCNI", "length": "11240", "offset": "108847858", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00072.warc.gz", "charset": "UTF-8", "languages": "fra,lat"}
+fr,missiondefrance,bibliotheque)/index.php?id=508&lvl=indexint_see 20240725183926 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=508", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WVLUNIUSAHNMBE2C5VDXVKQHZKORO64V", "length": "11230", "offset": "3415321", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00083.warc.gz", "charset": "UTF-8", "languages": "fra,lat"}
+fr,missiondefrance,bibliotheque)/index.php?id=5082&lvl=notice_display 20240725182844 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5082", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "P4357GT5TCFJTGWWPDNBG7CGG56XSAPB", "length": "5040", "offset": "104472525", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00320.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=5086&lvl=author_see 20240725181539 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5086", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LGOPEJH6SXEAQ4AFUQ6DHD24LKPSEAIK", "length": "6602", "offset": "3392814", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00345.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=51&l_typdoc=a&lvl=author_see&nbr_lignes=63&page=2 20240724143951 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=51&page=2&nbr_lignes=63&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Y47DY4Q47GGIUBESY7QVJWYB3NYYPRFJ", "length": "10864", "offset": "109728217", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00542.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=51&lvl=categ_see 20240715044155 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=51", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QY3ZJDLKXI5VMF7ROG6DRYZS26PKDCIG", "length": "12713", "offset": "3095804", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00359.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=51&lvl=categ_see 20240721014133 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=51", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CGCTG5MY6UV4RGL3TSN4YEREVH5VHEEI", "length": "12719", "offset": "116211483", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00316.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=51&lvl=coll_see 20240718213557 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=51", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "URPGROH3LYWHYFXT2FAFHNYWOXPM2YAL", "length": "10106", "offset": "5950915", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00697.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=51&lvl=subcoll_see 20240721014505 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=subcoll_see&id=51", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LVZYPIYCX4ELKNSWL4C46HUHTKKKT2HU", "length": "8079", "offset": "114271960", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00728.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=5109&lvl=author_see 20240722115730 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5109", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "J75XZYBIUTSTJIDB5HTBWWUXQDFCA5PD", "length": "6427", "offset": "3703058", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00161.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=512&lvl=author_see 20240718133857 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=512", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3PHXI77MOY6RO6CUN24TT7GJKR757NPG", "length": "6576", "offset": "123894680", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00123.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=513&lvl=author_see 20240718193915 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=513", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TEMOXFSQRL6FV6HX6UGF5QVS4HXZMPNC", "length": "10850", "offset": "111497444", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00124.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=513&lvl=categ_see 20240712182659 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=513", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YBZXPBGPX2JPRVKYDZ5YBZIGIKFC2QD3", "length": "11354", "offset": "101718726", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00451.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=5143&lvl=author_see 20240722103101 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5143", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MHQZA5UGSBZFNDXCXWK2XJGYJ45Q2HUC", "length": "7447", "offset": "106944307", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00258.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=515&l_typdoc=a&lvl=publisher_see&nbr_lignes=22&page=2 20240718200908 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=515&page=2&nbr_lignes=22&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZUCVYBN2Y3DWR34D2EDNRJSLCNXRVIKJ", "length": "8751", "offset": "119617632", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00357.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=516&lvl=categ_see 20240715050123 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=516", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QSLO4G5IPKOBKT3H2SZKNDALVXLNAUUU", "length": "9744", "offset": "2709942", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00487.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=516&lvl=categ_see 20240721223306 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=516", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BXFLT4PZHRHQA2RS6MLBAXPCG2RVXJGH", "length": "9751", "offset": "106652797", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00454.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=516&lvl=coll_see 20240724145508 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=516", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "35NDPBCK3P7GSZEI3RFLK2DK77A6YOSU", "length": "6850", "offset": "5291347", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00633.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=516&lvl=publisher_see 20240718143357 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=516", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2LWVYFM4NRGWPRPEPZUZ7UOYXT2TBEZL", "length": "11307", "offset": "3569393", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00083.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=5169&lvl=notice_display 20240722120826 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5169", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "A2JNXH5LG5IBIBLI2UGZEPXZYWLSJKWT", "length": "4992", "offset": "3840011", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00395.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=517&lvl=categ_see 20240722112108 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=517", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EQLZW4JIZ3BXJX2VD2G4GT2AKHGYI52G", "length": "11768", "offset": "108705581", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00455.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=5176&lvl=notice_display 20240722110810 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5176", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NG7OHT3NSW6QPCQXUGHRTNF7TXW5ZEFJ", "length": "4944", "offset": "4709567", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00423.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=518&lvl=indexint_see 20240718201551 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=518", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LYGEOPZT3FB3OWQZLTXSX5I7RHBNXMWW", "length": "7153", "offset": "112119686", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00103.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=52&lvl=categ_see 20240721015000 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=52", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DWCDAMCES4Q5EXRA72364OAXUMFIJUQX", "length": "10268", "offset": "6394200", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00360.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=52&lvl=coll_see 20240722111035 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=52", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UJRNWXHSI6UGFVXP7HJMGUTDBJJ56CBJ", "length": "10209", "offset": "105854640", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00413.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=520&lvl=categ_see 20240721213926 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=520", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GZNM6CLWCRU7KLSITQDG4M33TZDN3URQ", "length": "11409", "offset": "105769618", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00479.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=521&lvl=categ_see&main= 20240721124325 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=521&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5R4FGNUYTAUQQUHRSQ3PXR3KHRSOCE3K", "length": "10890", "offset": "5775650", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00863.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=5214&lvl=author_see 20240721225314 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5214", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "F6VPABWY5M3DDO4HVJI46HYHYPJROHIR", "length": "6775", "offset": "2931061", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00248.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=522&lvl=categ_see 20240721223932 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=522", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HXKTBXCNWOT2LCZEJMC3OIRQXEH4VQJ5", "length": "11477", "offset": "106612139", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00481.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=522&lvl=indexint_see 20240716150523 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=522", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "V6OWNTDN74U4F7YCL4HED2QSOPDVPXOZ", "length": "10245", "offset": "118148601", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00128.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=522&lvl=indexint_see 20240724162513 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=522", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "COOLJFMHRNRBZAGSDDCLBL5VXSKLGJ5H", "length": "10202", "offset": "4116636", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00139.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5237&lvl=author_see 20240719091103 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5237", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FINGB7JM3IZDLHCXN2VD5EULFZ4M76RB", "length": "8921", "offset": "108658303", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00292.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=5238&lvl=notice_display 20240722104052 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5238", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5WKZFNUS42N23QGSFJJTSSS4FAGIZJPO", "length": "4979", "offset": "3003893", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00362.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=524&lvl=indexint_see 20240715055642 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=524", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AUMMGHHTCWWCC2T44HCAFW3H45SZ545Q", "length": "7220", "offset": "111029095", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00130.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=5251&lvl=notice_display 20240716144128 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5251", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UTKENZS5JGM7W4A4VXA2T4PDYBVKQUX6", "length": "5219", "offset": "3943745", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00417.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=526&lvl=author_see 20240718213712 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=526", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XLPP4XZL4I52GJKEBU4RLPR3GIKBI5IZ", "length": "6678", "offset": "107166828", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00158.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=526&lvl=coll_see 20240721134410 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=526", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TU5QZ647WN2G3ANEJOP43IUVC44RCSJ2", "length": "7511", "offset": "104070025", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00673.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=5278&lvl=author_see 20240718204946 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5278", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HA5I4DZXZAIQ3QREWMINAGOZHEOVQN2K", "length": "11034", "offset": "113469743", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00417.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=528&lvl=publisher_see 20240724160632 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=528", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "S44FNHSIGQISSQDYDWKDFDLPGNXCSLCT", "length": "8964", "offset": "6275933", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00116.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5283&lvl=notice_display 20240721133448 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5283", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HGUDCBBWLXRFW6UHZVTXSYBJ6XSTT7BM", "length": "4994", "offset": "102123870", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00443.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=529&lvl=indexint_see 20240712175335 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=529", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Z7H4P3R5OHMWKDLC6ICVTJ2RAXXFX5B3", "length": "9693", "offset": "7295653", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00146.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=5297&lvl=author_see 20240715060759 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5297", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OZNOOJD357XBTQQZOCRRWIMF3APTTMY7", "length": "6922", "offset": "122390100", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00478.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=53&lvl=categ_see 20240721225438 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=53", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TVIB6FODXOQSZ2R7PIC6UUXF2QYIUTIA", "length": "11490", "offset": "110279183", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00318.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=53&lvl=categ_see 20240724151026 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=53", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EOQSR2KDDQXQJTNWJBJ5KN3PJ6PX7VSO", "length": "11480", "offset": "5314577", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00361.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=53&lvl=categ_see&main= 20240721224500 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=53&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "B3IGR323RPZWNXOX7BG4NMNBRW2UH5BE", "length": "11507", "offset": "103844697", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00584.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=53&lvl=subcoll_see 20240712180010 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=subcoll_see&id=53", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5K4VMWQYNIEZUKA3RZSF7AV3PGOCDWL3", "length": "6704", "offset": "105828510", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00730.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=5302&lvl=author_see 20240715052717 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5302", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MP4EOWZNHZ4PXROMF2Y4XK7HBWXEH7A5", "length": "10829", "offset": "111730327", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00255.warc.gz", "charset": "UTF-8", "languages": "fra,eng,deu"}
+fr,missiondefrance,bibliotheque)/index.php?id=531&lvl=author_see 20240719190025 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=531", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TU7TXG5UQNJTQP3O35TYJST7FZBFX7SV", "length": "6687", "offset": "110095550", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00184.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=531&lvl=publisher_see 20240721134056 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=531", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CBCSOYC2R6FJHY4YUMN7ZBXMTWBZHAWY", "length": "6624", "offset": "112248205", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00715.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=5326&lvl=notice_display 20240721224527 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5326", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2MLSEWNCOYCU2KU4SWB4VR66MF53SG44", "length": "4965", "offset": "5021281", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00390.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=533&lvl=categ_see 20240721011736 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=533", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LB5O72QY75KG6CX2YFQIRE63CXSFH6WI", "length": "11652", "offset": "108229386", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00513.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=533&lvl=publisher_see 20240715061028 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=533", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FOVAZED2VV562BN54C6AUKNCIK6FDGZS", "length": "9301", "offset": "114011156", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00717.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=5335&lvl=notice_display 20240721125128 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5335", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GULNSKXKFS6JX4MKZNJSTWLV5OGCH7MP", "length": "4991", "offset": "111638627", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00351.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5338&lvl=author_see 20240722104415 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5338", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CSDEYCWVUYB23G7LUDKMXIKAIRE7HZRP", "length": "7430", "offset": "107911046", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00354.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=534&lvl=publisher_see 20240718213808 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=534", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OQE5HPZWU3OPSKQPUPBRMPCGAPYEZK5C", "length": "7528", "offset": "110555806", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00718.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=534&lvl=publisher_see 20240724144116 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=534", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MSZ72RY5MXGNSIA2XMJK2Y2JYU6ZTHSE", "length": "7513", "offset": "3902939", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00143.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5349&lvl=author_see 20240721012829 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5349", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PDHIUM3KIQN4T4FXF5554VCQLRGG6JQC", "length": "7421", "offset": "110170410", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00386.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=535&lvl=categ_see 20240712162942 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=535", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZHWQPJV57ZJQW2B5X7H7IZGP5VYDCZUR", "length": "10896", "offset": "98375314", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00515.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=535&lvl=coll_see 20240712172633 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=535", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WQS7ILRAJEPPZFS4NLUKHBZ72IH5RQJF", "length": "7046", "offset": "3288943", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00694.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=536&lvl=categ_see 20240718200550 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=536", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CDNHWRWNCWOSWHD3QF2EDPFNLXPBGE3B", "length": "11674", "offset": "112538987", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00516.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5371&lvl=author_see 20240725184458 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5371", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UQZG6DA6A36WXMZKXLOU4RXQ6U3WT72S", "length": "9303", "offset": "109611628", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00471.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=538&lvl=coll_see 20240712165723 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=538", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2XEK63M73PHDZ3X2OKY5OU7QGV4PD2EF", "length": "10781", "offset": "3885099", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00697.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5380&lvl=author_see 20240721224842 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5380", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RV63CXTH3SEHVSI7AJQ2KXSLYQCLZIOZ", "length": "8821", "offset": "4728558", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00522.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=5380&lvl=author_see 20240725194200 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5380", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6TB2ASGLII2S2BB3GRCSM34SNPXZHME4", "length": "8825", "offset": "110876702", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00501.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=5386&lvl=notice_display 20240719172925 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5386", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3DMQQTGLYMXFE2OVQPS2ZSVTVYRO7XAC", "length": "5099", "offset": "3736918", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00576.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5392&lvl=author_see 20240721132844 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5392", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TZPJ2IVBLSAMA36TRBQZXG3UVD6S32GG", "length": "7115", "offset": "106763114", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00534.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5399&lvl=author_see 20240721124053 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5399", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EIMUT32IIZSXPCJD3BB6V4ZGBXB3EHIT", "length": "8924", "offset": "101926228", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00541.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=54&lvl=author_see 20240712184448 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=54", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QX65I2VJJAPNZHKLCBBNJR77NAA3ROF5", "length": "6995", "offset": "96226783", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00294.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=54&lvl=coll_see 20240721135424 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=54", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "L6WQBINDYZWUGJB5O3AAL5IXSD3RBREY", "length": "10272", "offset": "106550717", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00415.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=54&lvl=indexint_see 20240712162531 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=54", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KZC43F3SHOOFZUFKYFXUAXLSUJN3C6NS", "length": "11475", "offset": "105652051", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00316.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=54&lvl=publisher_see 20240712185234 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=54", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "67ZXMQDYL6EKX7VXAMF5P76FLDZOPO25", "length": "10961", "offset": "2893911", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00086.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=540&lvl=categ_see 20240724162145 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=540", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6CHTLE5FRE6MF7QCAJGHCVAETUNYGT3Z", "length": "10663", "offset": "108729886", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00541.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=5402&lvl=author_see 20240721140437 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5402", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FX5NZBHJO6FV62QUHHIDJ6B65CLRTXO6", "length": "6608", "offset": "111567839", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00316.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5409&lvl=notice_display 20240721134403 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5409", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4RE3BIKI7FTDEUUIQM53DCD6JIAYSTXV", "length": "4953", "offset": "4751248", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00392.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=542&lvl=categ_see 20240719084503 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=542", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "53IOJ2K4OYH24MY2UZQTOFHSUYFNRKBZ", "length": "8511", "offset": "112955894", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00543.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5420&lvl=author_see 20240715052336 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5420", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "A3RR7FNQOLUOWQ7VKE7KPG4BY5MLIGS6", "length": "7733", "offset": "114620117", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00376.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=543&lvl=categ_see 20240721222618 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=543", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DSCXJNJVB26DU3TIHUJLNIOHQOCP5O4W", "length": "11036", "offset": "4445616", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00577.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5436&lvl=author_see 20240718143748 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5436", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2N64EOX6X4MLF3YLN4IA3SP37GCZEK2D", "length": "6764", "offset": "4084464", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00434.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5437&lvl=notice_display 20240718204813 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5437", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZJHPDUIXKEKLWPUFNKLF4YIUIF57XAVO", "length": "5004", "offset": "3646633", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00483.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5440&lvl=author_see 20240718142547 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5440", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WB4DSN3NUCY5ZWUU2CQRTOXUIPJUWBZG", "length": "7952", "offset": "5142949", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00459.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5444&lvl=notice_display 20240721123854 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5444", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZSH4LUTCNQ57SEFBFORQ7JJ6S6LNBIL6", "length": "5077", "offset": "7059141", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00511.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=5460&lvl=author_see 20240715043223 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5460", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "P733B25S5PJPJI73DGRCMNVQIEFRW7H3", "length": "7387", "offset": "112927223", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00500.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=547&lvl=publisher_see 20240715041153 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=547", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MX5A22JXFDWR45MJVMJEZB4G4R75IFQZ", "length": "10467", "offset": "5802100", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00177.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=548&lvl=categ_see 20240718143231 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=548", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6UMPP5DUAZ7OUFUTM47LEPUH3DIYBFBD", "length": "8523", "offset": "109584666", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00549.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=548&lvl=coll_see 20240724161133 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=548", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MSYV7B5K7MX5VMAZN4O4NYHGTIRRD7DP", "length": "8096", "offset": "110041700", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00737.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=548&lvl=indexint_see 20240715055603 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=548", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2CAHFD2AM2G266KE3K45ZBJILCT57HWL", "length": "7772", "offset": "4143863", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00207.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=549&lvl=categ_see 20240712185003 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=549", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VMTEV6VYUVMF6ZNCXUAC2HOU6VGOGWWQ", "length": "7456", "offset": "106446610", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00550.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=549&lvl=coll_see 20240724160237 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=549", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YLWPKHYPESZMPOSI3QFNVCU3DDOMNEA4", "length": "7585", "offset": "121831271", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00738.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5490&lvl=author_see 20240715055524 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5490", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "D5HSHKEMPJR2DKFPXPUBQKN67Y2TAXIV", "length": "7606", "offset": "113566454", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00593.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=55&lvl=indexint_see 20240721224553 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=55", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "W3E7DDLX3FSB4R7XXM2MPKA2KWVN2F7A", "length": "11169", "offset": "103898599", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00317.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=550&lvl=author_see 20240721222146 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=550", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HE3SURGF6DJ4VQFQE333HDF2BBCDGVTL", "length": "10713", "offset": "114295200", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00245.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5509&lvl=author_see 20240725192319 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5509", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OTJ5TSOB4MOMX2PUHQPMNHD7ECO2QBYX", "length": "9431", "offset": "110768117", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00384.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=5518&lvl=notice_display 20240721140520 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5518", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MXBEUROV5BKHARMBMAZHO34EGG25D25G", "length": "4951", "offset": "113084687", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00414.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5518&lvl=notice_display 20240721222723 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5518", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MXBEUROV5BKHARMBMAZHO34EGG25D25G", "length": "4936", "offset": "4666421", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00483.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=552&lvl=author_see 20240715061408 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=552", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JLJQN6WNQ3GN2B6K5H7QBPI6ZFFXTGLI", "length": "7507", "offset": "3744383", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00734.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=554&lvl=categ_see 20240722114106 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=554", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SIZ7NK4WF627LK3CH34T6Q6XAT2IC3MI", "length": "6824", "offset": "110373991", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00576.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5540&l_typdoc=a&lvl=author_see&nbr_lignes=16&page=1 20240718141700 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5540&page=1&nbr_lignes=16&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OFCBDUWPYQCX7HXUBJADDYVXWT5KW76X", "length": "10063", "offset": "3546211", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00572.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=556&lvl=categ_see&main= 20240721013340 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=556&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JQDSYAV67RFTLDX6QG2IPJTKBXUY3WLI", "length": "10647", "offset": "4026870", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00881.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=557&lvl=publisher_see 20240724161553 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=557", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6RQONWEC2NYEACJHCOTH2ZF6URX3JSAG", "length": "10123", "offset": "107985396", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00783.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5576&lvl=author_see 20240721132745 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5576", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EY5JZTKJQRRE23D66C4L55QYTAJU5Y5F", "length": "7110", "offset": "3808741", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00619.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=558&lvl=author_see 20240721130932 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=558", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CXBRZ43P4CIP4INUGLIKSQJBIO3O7YQZ", "length": "6935", "offset": "118110255", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00253.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=56&lvl=coll_see 20240716163417 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=56", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4OBO2JJRY5DXLZAXVTRZFSBY23MGDJNL", "length": "8428", "offset": "109713923", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00417.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=56&lvl=coll_see 20240718134432 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=56", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "IUL7AT3JYGFXKEUNQ6YE4KF36YUITDH7", "length": "8395", "offset": "5438670", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00702.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=560&lvl=author_see 20240721131039 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=560", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "V6CDX47EWUVAITYPNJZ36GH6QEOH4ZUE", "length": "6544", "offset": "3136971", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00763.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5630&lvl=author_see 20240721125834 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5630", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AU7R5AE6YUWJCP7TO5OEBI3ZWAH25Q73", "length": "7848", "offset": "4903010", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00550.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5639&lvl=author_see 20240721125615 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5639", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QIXEOEE3PW6MXDBCTZLFE66OGQYJX6PV", "length": "6502", "offset": "3785357", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00559.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=564&lvl=coll_see 20240719174900 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=564", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6377HKFQ3LHR4JNTHHPMXA6TS5SGJI4P", "length": "10732", "offset": "113443365", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00795.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=565&lvl=publisher_see 20240721223825 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=565", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PYZ3YM264EZQKVHLD5ZZL76PCOPCKM4D", "length": "8586", "offset": "6708131", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00237.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=5652&lvl=author_see 20240721131922 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5652", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "J6Y5LV5ZASGHAG3W7LHCESLYCFRKA5K5", "length": "7678", "offset": "5921204", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00614.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=5656&lvl=author_see 20240721123202 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5656", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TYNEJBJRIFZPFWDE4TJBIMGJZUB5MJCS", "length": "6762", "offset": "4846503", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00618.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=566&lvl=categ_see 20240719082046 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=566", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "J5RT5EJQBETV77T6OANYYQSM4BNZTFJW", "length": "9485", "offset": "101461631", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00609.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=566&lvl=categ_see 20240721005702 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=566", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2KABMN7PLW5GLHKTFQDFYHBZKRFLM6FX", "length": "9470", "offset": "3665020", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00642.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=5694&lvl=author_see 20240721003912 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5694", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VACDFWJA6AV74HZC7PU7IPTVTCZVCIQ6", "length": "7317", "offset": "117049466", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00719.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=571&lvl=categ_see 20240719175757 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=571", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "56OYMOWQVETE5H6BQ54PRFRBTCELOKPY", "length": "11231", "offset": "3203606", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00668.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=571&lvl=categ_see 20240721233942 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=571", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4JDTXKGD5OFB2ZQFCQDXAUIHINRZIE4V", "length": "11250", "offset": "109572022", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00635.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5716&lvl=notice_display 20240712175646 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5716", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NCQAWRFD4RJZOSRQLQ7HVYDAWRNPIW5L", "length": "5050", "offset": "3202641", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00603.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5742&lvl=author_see 20240712170248 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5742", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NCQREKCGGYCRNN4UDY7VIWTHMFBRKIGT", "length": "8286", "offset": "2690151", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00644.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=576&lvl=author_see 20240721012619 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=576", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "IZBJSGCAVVEMEEAX5VGJCWWY5CYWMSLS", "length": "10330", "offset": "3707587", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00800.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5766&lvl=author_see 20240715044322 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5766", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7R2CRDCJJL3LIICYWHZXTHFNPAQOBMKU", "length": "7266", "offset": "4275288", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00710.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5769&lvl=author_see 20240725185657 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5769", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BZXJCKSPZXVVQGKKAF7A7JXZK4JFEIGS", "length": "7690", "offset": "109057002", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00692.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=577&lvl=author_see 20240718213249 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=577", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EJC3LVTBAKK7UHXKQU77LQXL6SIFWUFC", "length": "10478", "offset": "5426776", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00801.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=577&lvl=categ_see 20240724150156 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=577", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VKECCZ75SVRYB2V5WW57OKLPI4MTKLRF", "length": "7821", "offset": "110267829", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00641.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=5783&lvl=notice_display 20240722112426 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5783", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3ELBJYLJBO3HYOTL3QAZP5ONZTSHQQOA", "length": "5028", "offset": "3942336", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00817.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=579&lvl=categ_see 20240718212757 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=579", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KLKPFGUIIZWFKOHVBFA5H4XMSL6URLRD", "length": "11421", "offset": "2925838", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00676.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5794&lvl=author_see 20240721002532 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5794", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EAZP45EDDJCRTMCWQYGXHGEEWQTMNDMS", "length": "9323", "offset": "4526835", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00801.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=5799&lvl=notice_display 20240712184632 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5799", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "72VEJWNYISO3OC3JDFYIQMRWALWLSI2G", "length": "4981", "offset": "108428117", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00785.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=58&lvl=indexint_see 20240724143454 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=58", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FFWEOPJVN5CMFSU2KZ52X4JWBAMSD5PS", "length": "10950", "offset": "116636408", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00320.warc.gz", "charset": "UTF-8", "languages": "fra,deu"}
+fr,missiondefrance,bibliotheque)/index.php?id=5802&l_typdoc=a&lvl=author_see&nbr_lignes=50&page=4 20240718205958 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5802&page=4&nbr_lignes=50&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5ZBKKQOVAFDNVCDWAWU2GKGOWBMZSTRV", "length": "9351", "offset": "5131982", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00336.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ile"}
+fr,missiondefrance,bibliotheque)/index.php?id=5802&lvl=author_see 20240721230326 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5802", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DS2OJBUXCD6HAH4TLJ4A5TWXPYYIBHF7", "length": "11657", "offset": "106913113", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00560.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ile"}
+fr,missiondefrance,bibliotheque)/index.php?id=5807&lvl=author_see 20240712170345 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5807", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XXSUBXBKV4FUCZEDE5DMHIJIW7I5NY7S", "length": "10086", "offset": "103634993", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00565.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=581&l_typdoc=a&lvl=author_see&nbr_lignes=20&page=2 20240719094201 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=581&page=2&nbr_lignes=20&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5GRQWG3BN4AW7REZBXLR5EIPRK26IYVK", "length": "8119", "offset": "104518713", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00885.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=581&l_typdoc=a&lvl=author_see&nbr_lignes=20&page=2 20240721125502 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=581&page=2&nbr_lignes=20&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LDJGKQLFTWSGPCTSPTFXQ3SCVO4A6ISR", "length": "8092", "offset": "3146769", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00536.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=5810&lvl=author_see 20240719091016 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5810", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QPZZIV2MIUYPQCMBQXNDIJKI5XV2OP3L", "length": "6743", "offset": "117529527", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00589.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=5841&lvl=author_see 20240718143815 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5841", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GLUP24S4CP4YK2COM3QVBV3I23YCCY5E", "length": "6957", "offset": "116142202", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00683.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5857&lvl=author_see 20240718145306 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5857", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WOG2DOAGBDYWAUT77QQBO6FBYJJH6UKN", "length": "6533", "offset": "4427791", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00741.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5858&lvl=author_see 20240718143559 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5858", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7KI4JX4NKACH7NMLW46KQ6DK6CUGLJCG", "length": "6532", "offset": "3957725", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00742.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5864&lvl=author_see 20240718140019 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5864", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PKWY5OWQ6RRYI7O4EOO2WK6CXIUN7KZ7", "length": "6684", "offset": "4280666", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00769.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5864&lvl=notice_display 20240721005535 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5864", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CS4AGVCEWC7LR76KWJ2IVIA5FY2RSHKM", "length": "5011", "offset": "4400042", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00817.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5866&lvl=author_see 20240724144158 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5866", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4XROISUZC6ASRJOTPVXQGPO37WLL2PWD", "length": "7118", "offset": "3081955", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00771.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=587&lvl=publisher_see 20240712165441 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=587", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5YRD4NX6VCDVPIQSDAOB4IBNASDEIXPM", "length": "7273", "offset": "105951183", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00876.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5886&lvl=author_see 20240718142240 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5886", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YGNQADWVH3SNVE2M2TIMLB2PJIJQOVPR", "length": "6509", "offset": "3123935", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00833.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5895&lvl=author_see 20240715061641 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5895", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UB5U2ALWFJIVDORCZSSAPUHF5GPOLBOD", "length": "6508", "offset": "3706743", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00863.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=59&lvl=publisher_see 20240718195308 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=59", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "L2OTKUTJMPMEXZ466JNMHI6HLUDS5YE5", "length": "11626", "offset": "117780098", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00028.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=590&lvl=categ_see&main= 20240719082251 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=590&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "R7DSRDRRS72HL44Y66OXGH67DFAE5XIJ", "length": "10298", "offset": "112834723", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00418.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=5901&lvl=notice_display&seule=1 20240718201248 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5901&seule=1", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PWSAF3TWDFLQNCJAAMVZEJ4BEZ6TH5TC", "length": "5617", "offset": "114783976", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00802.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5904&lvl=author_see 20240715061955 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5904", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NJRQ4ZZDMNLJ4OMFCEHGVMBJDILN2UCI", "length": "6712", "offset": "5365277", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00644.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=5908&lvl=author_see 20240715052129 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5908", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HQV7QVNJKXSJDZRJGNNWXVQQA3PYUP5U", "length": "6567", "offset": "4619898", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00648.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5921&lvl=notice_display 20240724153702 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5921", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "W7WVANFAPJV7UM54424JMJ7AOLNVMU6P", "length": "4991", "offset": "105801604", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00682.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5929&lvl=notice_display 20240721140315 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5929", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FTQLXRPR6Q5XO6Z3BXR7PY4L7OJDTK7I", "length": "5019", "offset": "5410878", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00759.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=594&lvl=author_see 20240718210920 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=594", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XVGOTGCMQTQNOUFDISTDWN7WCH2JFOAG", "length": "10391", "offset": "111088405", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00373.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=595&lvl=categ_see 20240724155841 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=595", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "E47UQAEAMPVELXYNRGWFPZA5XHKBEKDF", "length": "11860", "offset": "105959780", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00701.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5955&lvl=author_see 20240715061948 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5955", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QKCWJN3TD4M42D4HHQJG2GS47KQ76HU4", "length": "6581", "offset": "4563210", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00800.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=5979&lvl=author_see 20240725194758 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5979", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FZPMC2SSX6MJVD3NLV3P4GJND7GDB5R7", "length": "6998", "offset": "97354147", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00845.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=598&lvl=categ_see 20240721005315 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=598", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4MKR2Q557RFWE4S3WG5LZ6N2FXN7WVUF", "length": "7639", "offset": "115416969", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00704.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=599&lvl=categ_see 20240712180900 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=599", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EU5CPQMIC3BZJJJ6XYWPMEAFZF4L5IGL", "length": "10879", "offset": "104303430", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00705.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5997&lvl=author_see 20240718142902 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5997", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XKVLOPZEIBCFXMXGLLGM7VRLIQ4BKHJN", "length": "6505", "offset": "5801882", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00026.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=5998&lvl=author_see 20240715052056 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5998", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6UKCJJZZ7AK6CZF2HD5A2LQENU4BNKAE", "length": "6504", "offset": "4408898", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00027.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6&lvl=categ_see 20240719190252 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=6", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7K6TMKOSG4ABWD7A2WNQDX3EEMKWUCF4", "length": "10984", "offset": "4962335", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00835.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=6&lvl=coll_see 20240718141522 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=6", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZMW46Y7TVCE7NDJPD4XYKVJ3FDVOIO74", "length": "9882", "offset": "3372248", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00569.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6&lvl=indexint_see 20240716152704 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=6", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4NE3O7JMJX5FLHJEHJN6FKWXKP3J65BU", "length": "10473", "offset": "4007356", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00492.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=60&lvl=categ_see 20240716152255 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=60", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MRXLFRONGPNFYDXHYW7CDTFE265JWTVH", "length": "11041", "offset": "120494594", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00346.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=60&lvl=categ_see 20240721005828 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=60", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TMFLF6BEU5NDS7TWEDAAKXS4GPAL3TVY", "length": "10985", "offset": "2961718", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00389.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=60&lvl=categ_see&main= 20240712171307 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=60&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LLBD3SKDEHGILTBEFALDQUWAUYBSB6SM", "length": "11037", "offset": "102521711", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00824.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=60&lvl=indexint_see 20240715053808 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=60", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NO5UJJXICVBKFZCYNALQYSQS6EQBVI3O", "length": "10794", "offset": "4261296", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00364.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=600&lvl=author_see 20240715050005 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=600", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "APDGMJZEW5OL23BIXGHKQYVSDNC7PMCO", "length": "10747", "offset": "5061280", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00638.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=600&lvl=categ_see 20240721014055 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=600", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "D2FI7SXYQ6KEKBHE5WOG77YIYYFW4R3W", "length": "11687", "offset": "101709208", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00478.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=6008&lvl=author_see 20240725201215 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6008", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OMTT3KJDQDM7NIXZOHEYSGYFTJC6BXWS", "length": "7222", "offset": "114159557", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00169.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=601&lvl=coll_see 20240724160550 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=601", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MKVG3LNFZSLBTUVP2YFXGZTQHPTL47FN", "length": "11467", "offset": "4765630", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00658.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6017&lvl=author_see 20240725184535 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6017", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XCDF5IQENOCE32RER4MKJVGNIXFZJZ7F", "length": "7594", "offset": "104853085", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00199.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=603&lvl=notice_display 20240721141213 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=603", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LAGF2OLO477275RU2ZP46Y35JSDBFNMB", "length": "5027", "offset": "3327559", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00341.warc.gz", "charset": "UTF-8", "languages": "fra,ile"}
+fr,missiondefrance,bibliotheque)/index.php?id=6054&lvl=author_see 20240721130104 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6054", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SBFP3IV4OAMFJXB56RNQFAW3RGQR4GOD", "length": "7087", "offset": "114218642", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00320.warc.gz", "charset": "UTF-8", "languages": "fra,ile"}
+fr,missiondefrance,bibliotheque)/index.php?id=6057&lvl=author_see 20240724162111 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6057", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FYOIYCTO5RFEXRFGJMJ7UZTXCFWLLD5B", "length": "8708", "offset": "4276944", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00344.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=6059&lvl=notice_display 20240721011549 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6059", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MPAHGI6CZSWKJOVXZPU6VWWA6TPVECAS", "length": "4974", "offset": "3868716", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00394.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6060&lvl=author_see 20240719100534 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6060", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7H63IDTEAISA24JH4UW73LAMIRWHJS5Z", "length": "6774", "offset": "4104079", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00368.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=6061&lvl=notice_display 20240712163339 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6061", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RTV7GRVY4BQVBNBFANRRB7WNRQY7QHGL", "length": "4996", "offset": "2708376", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00417.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6062&lvl=notice_display 20240721004520 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6062", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BH3RYM4XBAO7BU4RL3Q2JQIVHVNTBQQY", "length": "4989", "offset": "4622632", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00418.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=6065&lvl=author_see 20240725185532 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6065", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5IEL7QZWPOTQ6P23ACXELVQPB7EMQP5V", "length": "7189", "offset": "2776816", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00373.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6066&lvl=author_see 20240715044650 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6066", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XC62ZNTKWER6KGIJ377AW25EWGQGKKZQ", "length": "7087", "offset": "4325073", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00374.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6067&lvl=author_see 20240715043306 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6067", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4S47LSTDSOFL2CKGWOQRRUJXIEMNFXMB", "length": "6771", "offset": "5136070", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00375.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6069&lvl=notice_display 20240718210447 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6069", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZFGLEJZKQT2BVPUSP3WTQVPMNLHB4PTH", "length": "4906", "offset": "4959370", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00425.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=607&lvl=categ_see 20240716153904 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=607", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "APK3LDZNM5UMRGCGRT7OSWZNDYXT7O3J", "length": "10968", "offset": "3144085", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00518.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=607&lvl=categ_see 20240718200708 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=607", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LFNA7VQCCFQSZNRVWR6TICNPRR2CXHJI", "length": "10976", "offset": "116109818", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00485.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=608&lvl=categ_see 20240715051517 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=608", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "L5Q4PWKSWF5O2UBL2RAGKN4VJHMZMKNR", "length": "10723", "offset": "4192569", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00519.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=6098&lvl=author_see 20240715053818 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6098", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TOTGFIURT2KADMY37QNLKYU3M4PTMK6W", "length": "6545", "offset": "3380806", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00469.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=61&lvl=author_see 20240721215830 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=61", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UV4YGACSCHDT5RYBE2Z2ZAZA5ZJ7XIAC", "length": "9915", "offset": "115780996", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00322.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=61&lvl=indexint_see 20240716153935 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=61", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OQQUBHT325KRDVRFAKRX3FIAXIFE52NC", "length": "10547", "offset": "4781265", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00365.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=61&lvl=indexint_see 20240721223024 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=61", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GUYGKU3WK2C4OWBG5SLPHLCUQCITGJPG", "length": "10570", "offset": "113698731", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00344.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=61&lvl=subcoll_see 20240719100719 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=subcoll_see&id=61", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KI2IP5C5KY2NWI2MHCRLVIDFGAHHTONN", "length": "7339", "offset": "121766225", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00759.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=610&l_typdoc=a&lvl=author_see&nbr_lignes=17&page=2 20240721125240 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=610&page=2&nbr_lignes=17&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OXWUKUKUQPINFFRZNSLXXDVHQ5H4PGWP", "length": "7035", "offset": "8188181", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00355.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=610&lvl=coll_see 20240718131404 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=610", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "G7OJQWHM4IOPVLXU7ROSGVF32U2NIGKP", "length": "11753", "offset": "4517045", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00688.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=6105&lvl=author_see 20240718204729 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6105", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7N427TDZD3YLZAFZOEMIBKGNULRBOEKI", "length": "6634", "offset": "108264018", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00227.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=611&lvl=author_see 20240724152710 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=611", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TKXFUIG6LBSIVWJ7ECXYJ2QLFHVJCARD", "length": "8158", "offset": "4933645", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00670.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6115&lvl=notice_display 20240725183436 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6115", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BUBQSCK5FDBVRV7DS7AEQTCNWATECBXI", "length": "4978", "offset": "5256482", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00327.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=612&lvl=author_see 20240722102121 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=612", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "G3BNB4ZU4G5IGV6HDI6TE46ELFTPKI2V", "length": "10399", "offset": "109853221", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00184.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=613&lvl=categ_see&main= 20240721141740 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=613&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "I4H2GHRHE6PDY244EG2WK5WPMAN63TWC", "length": "9024", "offset": "102257206", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00506.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6134&lvl=author_see 20240724160421 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6134", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GYZHAIIDKQLA32HTS6UKTWP5ZYTABUBF", "length": "8314", "offset": "102721625", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00319.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=6134&lvl=notice_display 20240721132300 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6134", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JKPLGHWKQAE7GU3ZJDIBGUK74YF6UFZN", "length": "5001", "offset": "108239707", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00319.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6137&lvl=author_see 20240722104310 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6137", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FYNIHACE3JCIJIP5MUQWLDDS5EDVH26A", "length": "7891", "offset": "103935638", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00322.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=614&lvl=author_see 20240718133935 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=614", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5ZUEW3GDWE2UTCQI7ADSXIGZKTJQN5IU", "length": "10840", "offset": "3752736", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00673.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6150&lvl=author_see 20240718142658 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6150", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NXZ55GTENDC4E6TRC7Y27UG5J47UZEKT", "length": "8721", "offset": "3546619", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00398.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=6154&lvl=notice_display 20240721141851 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6154", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NSVECZ6FQER7HEPKOCB2RCB4GYRDXE56", "length": "4916", "offset": "107530314", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00381.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=616&lvl=author_see 20240716155434 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=616", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "J2Y7XC2BN6KDWRXGGQEMFN7XICYBKU4E", "length": "10010", "offset": "116214134", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00188.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6172&lvl=author_see 20240715045244 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6172", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WYBFNHLM5O6PYROPEX763PXQ6BZGYFAD", "length": "6865", "offset": "112871439", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00441.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=619&lvl=coll_see 20240724160827 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=619", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SU5BS33KK2PS4L3WQBOUXZ4DUSNEKYSY", "length": "7730", "offset": "119843304", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00706.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=62&lvl=indexint_see 20240716152555 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=62", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UODEBXBEZDMHI3EMYUOEEXHJE4B3XVE2", "length": "11501", "offset": "4742825", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00366.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=621&lvl=categ_see 20240721015349 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=621", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "F2FYJN44TXF45MGFV4LSSXIVEK3P66HM", "length": "10864", "offset": "111588899", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00541.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6212&lvl=notice_display 20240725185616 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6212", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5SPJ7RKLS5WIA2SKU6W34CLHS4PAMWKK", "length": "5231", "offset": "4901254", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00385.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=6216&lvl=notice_display 20240712164529 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6216", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RMQYOLUGHAE4ET4X2IQCTTL3BVDHBO2A", "length": "5321", "offset": "2968992", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00389.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=6219&lvl=notice_display 20240719094550 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6219", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DC2LAFR55QE2MFOCEODZM37NNQKXORTR", "length": "5285", "offset": "5305077", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00392.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=6221&lvl=notice_display 20240725194327 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6221", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BYLXMZVFD2RYNM56MHALDWE5J2VU36ZK", "length": "5509", "offset": "111449043", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00346.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=623&lvl=categ_see 20240722095224 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=623", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TEGYH4DEPN7UJISQZ3AK6QL7HIWLENCX", "length": "7511", "offset": "5807652", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00576.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6233&lvl=author_see 20240719095152 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6233", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2J4NKTHRNKAIHY3MJQDIEK3C4WEDS6GF", "length": "6812", "offset": "3700510", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00400.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=6235&lvl=author_see 20240719091124 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6235", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DGNBXRM7V5B72GAX5SR37M3BNNUWVZEE", "length": "6813", "offset": "5129878", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00402.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=624&lvl=notice_display 20240719090340 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=624", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3GTUROIO2JUZAXVNTC4YOLYAKF2GPSRB", "length": "4976", "offset": "4876915", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00404.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=626&lvl=categ_see 20240718212234 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=626", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7KGVJU2DTXBUEUQM5YEQ46BPQLMHEKOB", "length": "7206", "offset": "3276464", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00579.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=626&lvl=notice_display 20240719093803 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=626", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DNICTMUZOCV5WTHQNAGSBSEQVLWUYU2S", "length": "5032", "offset": "2902723", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00406.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6281&lvl=author_see 20240715060912 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6281", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EMRYVINHUNKET2JLREL53PGDC7ZIXNAD", "length": "8424", "offset": "111549563", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00532.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=629&lvl=author_see 20240721010951 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=629", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "IPXPWAYFZ4ZPH5IXCJUJ6PEUZHJJH4FX", "length": "10858", "offset": "105253112", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00222.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=63&lvl=author_see 20240719183551 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=63", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QSGP56GAQCGI62XFMBRNBWVV55OFDTBV", "length": "10592", "offset": "107050879", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00324.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=63&lvl=categ_see 20240716151028 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=63", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ODYI46YVDLF3WSFH6Y3AHNDCQZ7YPLI4", "length": "10788", "offset": "119373318", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00349.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=63&lvl=categ_see 20240716151104 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=63", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LBG6EDT6RDBATV4UWLCP7LIOII6CP4JI", "length": "10748", "offset": "3704160", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00392.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=630&lvl=author_see 20240721220624 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=630", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UOBU77ZSIRQ3GPK23E6TFHQC4KHUUBT3", "length": "10092", "offset": "3359942", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00731.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=630&lvl=author_see 20240722115004 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=630", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HBZG5FJ6NX5O4AJBRLUGRHOUNRQ2BLRX", "length": "10094", "offset": "112756324", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00244.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=6311&lvl=notice_display 20240719091144 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6311", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "B2JK22DWBFSAKHRMMZ5C3L5AGI2A7NVV", "length": "5025", "offset": "106507934", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00376.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=632&l_typdoc=a&lvl=author_see&nbr_lignes=99&page=7 20240718200944 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=632&page=7&nbr_lignes=99&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "IOSELULJ5AYIPOICSH7PY4KWWQNYZCIY", "length": "8826", "offset": "114194002", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00361.warc.gz", "charset": "UTF-8", "languages": "fra,lat,ile"}
+fr,missiondefrance,bibliotheque)/index.php?id=632&lvl=author_see 20240721224903 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=632", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MRWFZYTB4ITUWXW4QQECIH2TF6YY76C7", "length": "10339", "offset": "107594002", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00246.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=6328&lvl=notice_display 20240724151351 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6328", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UDYCLIZYKXFXELR2JKFS5B2QS6OWAYFH", "length": "5130", "offset": "3408514", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00483.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6333&lvl=notice_display 20240716153550 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6333", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SD3FUS47RPJFMIX5XDW3IM27SHTV3PZL", "length": "5021", "offset": "3641956", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00509.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=635&lvl=notice_display 20240721020428 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=635", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KBE4XMXWYT546ZX2Y2UNTIVMOUJO6TZF", "length": "5064", "offset": "117810572", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00297.warc.gz", "charset": "UTF-8", "languages": "fra,deu"}
+fr,missiondefrance,bibliotheque)/index.php?id=637&lvl=notice_display 20240712172728 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=637", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HTDBDGNYGYDZ3IFQUXQ6K3R2KNG5HMR5", "length": "4962", "offset": "99448193", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00299.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=637&lvl=publisher_see 20240715060116 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=637", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PARGZRKI3B4SQVCDA4MKUDUPSJBME7ML", "length": "11218", "offset": "112236195", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00782.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=638&lvl=coll_see 20240722100922 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=638", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "IOMHCPIUFK5KM6RMUKUMI3PDXYIAKHJ5", "length": "6798", "offset": "105516623", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00767.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=6387&lvl=author_see 20240718202010 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6387", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TXFOHXAHUBR4L63SBZ7PRZ4J37EF6KFW", "length": "8682", "offset": "3716677", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00620.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=64&lvl=categ_see 20240716162532 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=64", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "252DC6CKOP5KGC2IMHTEKJZHR7I7LZIL", "length": "10425", "offset": "6223218", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00393.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=64&lvl=categ_see 20240721220723 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=64", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7ZGENKQ4L7WPPJ2KGU5WOSRDXW7R5FT2", "length": "10442", "offset": "109653792", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00350.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=641&lvl=categ_see 20240719180032 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=641", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "46G7SSDHF7SGUL4XRW5QS2RUSLZSUE5G", "length": "10425", "offset": "5541226", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00636.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=642&lvl=author_see 20240721232201 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=642", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5PWXOEDDGQHSKH6LZEPIEDR723ILKM5M", "length": "11533", "offset": "112064778", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00277.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=642&lvl=categ_see 20240718150704 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=642", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DD2MRDM4KMQX2TQBT2PUHJA3G2HXLPNY", "length": "10984", "offset": "118782835", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00604.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6427&lvl=author_see 20240721001553 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6427", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZFHZARKWX6QEOOUC65JXDTRAUUTE675B", "length": "9549", "offset": "122573511", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00474.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=643&lvl=author_see 20240712183313 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=643", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NY3E67VYV7LWEQG2GEB3XCGZRVXGLUPH", "length": "11154", "offset": "4031015", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00765.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=6433&lvl=author_see 20240718143107 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6433", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "H7H35NRB5GIIB6VKMB55K7FHY77GV6ZK", "length": "6682", "offset": "5150482", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00522.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6443&lvl=author_see 20240719095301 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6443", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Y2RYVTQ3YBKO2JAOGU34IYLB4UGGOSCZ", "length": "6569", "offset": "115297166", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00532.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6444&lvl=author_see 20240719083952 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6444", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "K2JIHFC4TCPJJCHA6DV3HHDD4YIN3PK7", "length": "7443", "offset": "108212048", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00533.warc.gz", "charset": "UTF-8", "languages": "fra,deu,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=645&lvl=categ_see 20240725182415 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=645", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "N63XMOUN75ZYJYUAIJJM3PQTSKL4QMOY", "length": "6624", "offset": "2290240", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00640.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=646&lvl=categ_see 20240725181440 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=646", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KB2CSBDBSLOQZUFGZPNVTPBSFMJY5LW7", "length": "10087", "offset": "3100114", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00641.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=647&lvl=categ_see 20240725175733 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=647", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2DKV2TNWFK4EA6N6HQPE3MI5DKDWEOQA", "length": "11262", "offset": "3153832", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00642.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=649&lvl=bulletin_display 20240718203635 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=649", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "25KLTKALPP62NRHLYW75FETQJ3QM2T3I", "length": "6988", "offset": "4007850", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00260.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=6494&lvl=author_see 20240721135530 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6494", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RMTYSZWN6TPPFSKUBPBNHYBPC2BLIA63", "length": "7173", "offset": "107961441", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00688.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=65&lvl=indexint_see 20240721002457 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=65", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CRK4LYONOMXUNB2V2VLBT5423E5ZT6UU", "length": "10893", "offset": "4503698", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00369.warc.gz", "charset": "UTF-8", "languages": "fra,deu"}
+fr,missiondefrance,bibliotheque)/index.php?id=65&lvl=subcoll_see 20240721132437 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=subcoll_see&id=65", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FMDLIPZRCLRELRJYZE2NDHEW73EZTYB3", "length": "8697", "offset": "104789300", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00763.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=650&lvl=author_see 20240721003837 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=650", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PJA2E6TXMD6SICUBUDFAQ3E67CJ7FWFV", "length": "7314", "offset": "117342965", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00306.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=6517&lvl=notice_display 20240712171741 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6517", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6IA4NFHZSQH4HX2O6DYQIICTKZFJGEES", "length": "5017", "offset": "103600651", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00504.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6522&lvl=author_see 20240715054946 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6522", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LO3JA5GLLX6DABWWAOEGS7CKQSNUVYET", "length": "6895", "offset": "116276084", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00530.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=6522&lvl=notice_display 20240718134657 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6522", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WSFPHQCWRZKRH4YEYM5ZBQVHL2KHNSRP", "length": "4962", "offset": "111521355", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00530.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=653&lvl=bulletin_display 20240716150123 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=653", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5BSQGGT4RHHE6QAARE2ZFBUUKWYO6RWG", "length": "7454", "offset": "3331826", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00285.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6536&lvl=notice_display 20240721134221 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6536", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6QC4G654QBME4CVQOXR6CQU4ZVBUZRBT", "length": "5014", "offset": "2918941", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00634.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=654&lvl=bulletin_display 20240715050818 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=654", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZQV2C43BSPQTGM47JZGV2J7ZYQTRWIUV", "length": "6192", "offset": "3979338", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00286.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=656&lvl=author_see 20240724153147 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=656", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GJKJPD6KHNJPHY4FHQ3WJ65C4DBMPNBD", "length": "11380", "offset": "112236896", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00312.warc.gz", "charset": "UTF-8", "languages": "fra,ile"}
+fr,missiondefrance,bibliotheque)/index.php?id=6563&lvl=author_see 20240721004159 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6563", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PFKP35FQ5VJCVYVBVH55GJJ4PQFYCWPK", "length": "6536", "offset": "3746272", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00676.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=6564&lvl=author_see 20240718195020 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6564", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JLUMNZC6GUY23DR3YO3VBFBBMPKIVEWM", "length": "6597", "offset": "5598244", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00677.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=6565&lvl=author_see 20240716144422 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6565", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VCXUTRKKCQHPKVUQSIALV4NZZLP2CXVA", "length": "6551", "offset": "6244772", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00678.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6568&lvl=author_see 20240712182418 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6568", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CDOGXGYNC6LNASBJPIFUPNSGANRB6S7T", "length": "6873", "offset": "3225612", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00681.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=6581&lvl=author_see 20240721132616 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6581", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2PSCIDBCHARQR4TNP4ITEFRPDUL6MIO5", "length": "6961", "offset": "112240285", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00715.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=659&lvl=publisher_see 20240715052646 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=659", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JGGFG3FQNQ6A2TT5RENORYUANLDTH2G6", "length": "10472", "offset": "115727987", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00846.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=66&lvl=publisher_see 20240718212156 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=66", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Z4LREXPG5IVNU5XESABFOOIII4VYUSJJ", "length": "7109", "offset": "5058240", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00119.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=660&lvl=coll_see 20240712172446 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=660", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BNAW4FFSFCUV2BOOXHCLWCRTWKZPXGHV", "length": "10982", "offset": "112165569", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00852.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=6603&lvl=notice_display 20240722111251 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6603", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5AX3GZACZETEIM3C6DIOPCBSAIY4M7ZZ", "length": "5152", "offset": "4574507", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00599.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=6605&lvl=notice_display 20240718213634 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6605", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2YYDJMGPPJMIPO2SBORCSNL4VPV6XK7G", "length": "4985", "offset": "4827088", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00601.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=661&lvl=categ_see 20240715052613 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=661", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SJFH6HVTAABLVTAFVXUBRKCIEQCG3YFW", "length": "8446", "offset": "4741273", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00698.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=661&lvl=coll_see 20240721015921 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=661", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OOW64MRH7O7DOJ6NDWZVUEWXNYKAYGFC", "length": "10360", "offset": "4218820", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00844.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=6614&lvl=notice_display 20240722112503 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6614", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7537BEC6SOABUEMXD4E6XFLQ7C7BD2V5", "length": "5264", "offset": "111696998", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00562.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=6616&lvl=notice_display 20240721221823 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6616", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TBDFVPTGOP7IX7CAKGH4FAF2MZYLKLOR", "length": "5100", "offset": "4940309", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00633.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=6629&lvl=author_see 20240721132056 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6629", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5QGS5AHWGGXAK4WWIW6QINKANXOANT4B", "length": "6538", "offset": "107889055", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00598.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=663&lvl=categ_see 20240718132626 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=663", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JOOWCN4ZCSV5K4TK5LSUXPPNQEVT2H7N", "length": "11055", "offset": "108194652", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00667.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=663&lvl=coll_see 20240712165106 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=663", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LNNXRAAE62UVYCAWODME2QBMI256REB4", "length": "10116", "offset": "101773129", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00855.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=663&lvl=publisher_see 20240715055858 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=663", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DFONSCNR4STCVBQ7ZRRKLZQCSUJ7IP65", "length": "7732", "offset": "4503520", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00296.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=6630&lvl=author_see 20240721140822 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6630", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KF3V73OSXFRBYA6LQKDODRPUDPPKBWEU", "length": "6543", "offset": "118213412", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00620.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6637&lvl=author_see 20240718140057 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6637", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5U53JCWB57BXHPI2SK6R5ZTFV5TUREPZ", "length": "6896", "offset": "112683575", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00627.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=664&lvl=coll_see 20240715055100 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=664", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6Q2HD4A3HEBUFRTDNN7Z6CKRPPNXGRCQ", "length": "10946", "offset": "8406254", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00847.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=665&lvl=categ_see 20240716153305 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=665", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "P2WBPCKSBS4GD4R3QZFVCTECYCOYT2HR", "length": "8108", "offset": "126680471", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00669.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=666&lvl=bulletin_display 20240722105549 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=666", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ACKJTL4OQNQCF5MHHEOEAJYZUO7BZPTR", "length": "6968", "offset": "107640621", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00672.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6672&lvl=notice_display 20240725181906 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6672", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EFVYS5V7VNYF4ISFH4EOID54BYC2DKLP", "length": "5166", "offset": "3462554", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00815.warc.gz", "charset": "UTF-8", "languages": "fra,ile"}
+fr,missiondefrance,bibliotheque)/index.php?id=668&lvl=bulletin_display 20240721133814 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=668", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TJ7AZGMV2VAXEFDICEBBRJJXA3DU2KCM", "length": "6692", "offset": "4881275", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00321.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=668&lvl=coll_see 20240721233242 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=668", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AZIN2GLM7UIJWX7GVBZ6BK2AH3QPHKOQ", "length": "10052", "offset": "109875784", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00860.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=6681&lvl=author_see 20240725195722 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6681", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZHEP5S6VRGL4BBYRVQ2OGS7VBVJHAPG6", "length": "6633", "offset": "110549201", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00776.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=669&lvl=author_see 20240724151531 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=669", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QR2G6HC5OIJCZ55PQ2DQIPATW7XZDEFG", "length": "7747", "offset": "117071042", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00346.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=669&lvl=categ_see 20240722105803 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=669", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7VKG2KET2KIE4FCCKIGFGBPWGAJS7UYU", "length": "6631", "offset": "112730001", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00673.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6693&lvl=notice_display 20240721122125 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6693", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "U3ZMALUQW7QLGWARZNXCT5DVTVFFCYQK", "length": "5001", "offset": "104055956", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00809.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=6696&lvl=notice_display 20240716161125 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6696", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "772NSG3AZH7HKIA7NYUKDNMKUF5RIFLD", "length": "5181", "offset": "125472935", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00812.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=67&l_typdoc=a&lvl=categ_see&main=&nbr_lignes=36&page=2 20240719085344 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=67&page=2&nbr_lignes=36&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "P2VXVAKZRQ22FWAXA5TT67YNKEMTGZFF", "length": "11417", "offset": "111852391", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00596.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=67&lvl=coll_see 20240716152436 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=67", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3QYFFCGEDZ575PQCAJAKNLDKZHKSWZHY", "length": "9462", "offset": "118664315", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00449.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=67&lvl=indexint_see 20240721223654 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=67", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DVQVQEUT4HRHJSWQ45K33EHIE3JUB5AS", "length": "11288", "offset": "109665281", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00350.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=6753&lvl=author_see 20240725185802 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6753", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HGPABLBUAVRC5LSIBN3LV5V47ND62PEZ", "length": "6990", "offset": "101002167", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00746.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=677&lvl=coll_see 20240721010858 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=677", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "W2ROMSB6VRRQLFBF3IYMJBATGRC46PP2", "length": "10765", "offset": "113917326", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00890.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=679&lvl=author_see 20240712181953 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=679", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DJP56AMBQYWV5CYV7FCEFQVF2EBQ37A7", "length": "7456", "offset": "99084946", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00377.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6790&lvl=author_see 20240718195103 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6790", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ICSSQI5RUJDK3BGNALYU27WZMIXFHRDO", "length": "7737", "offset": "4026366", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00888.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6792&lvl=author_see 20240712185618 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6792", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WN2SESA7MMGIC4UEHIFP7MX3PRP5HCEY", "length": "7216", "offset": "5201597", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00890.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=68&lvl=categ_see 20240716163358 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=68", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CSMUORXB32RDVDBXGVZRPYCJRGO6XFDF", "length": "11491", "offset": "120429963", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00354.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=6808&lvl=author_see 20240722103554 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6808", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QWHCZWKSNC4F4OGHSGCIJ7B3G5GFSVOK", "length": "7372", "offset": "3454755", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00678.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=681&l_typdoc=a&lvl=author_see&nbr_lignes=23&page=2 20240721124632 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=681&page=2&nbr_lignes=23&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "V4ILPLPP23YZ7MK3PCRQOC5RBASHM3XA", "length": "9680", "offset": "4469375", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00342.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=6813&lvl=author_see 20240724142245 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6813", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DPKYFZPUUUC2WAEGEWWLA3BSB7PXMVW6", "length": "7333", "offset": "105965246", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00683.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=682&lvl=categ_see 20240718144018 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=682", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OZOWLAS5MAJL7YQQNPMYRPHNLNAVU43Y", "length": "9647", "offset": "107156532", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00728.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=682&lvl=coll_see 20240721010051 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=682", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DIC7P2YB4KSDPQNN57J4BCBRVWWNWJQT", "length": "10207", "offset": "111336360", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00016.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6828&lvl=author_see 20240712174326 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6828", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OHMC22XSLW6BLLNPUHZ7PGUNU5E5CLCS", "length": "6897", "offset": "109956863", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00719.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6829&lvl=author_see 20240719192652 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6829", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "253IC74NOKMDQLD6BACZJOLYCTOXCROZ", "length": "7207", "offset": "113172242", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00720.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=688&lvl=author_see 20240718192520 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=688", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PP7LHRVHCXPLX6MED7YSCTRXPUT7HB3O", "length": "8952", "offset": "114560583", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00407.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=688&lvl=author_see 20240724155308 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=688", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2A6JK52VTAJAPQGKZJKD2VCB5TH2UZCN", "length": "8942", "offset": "3656865", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00894.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6889&lvl=author_see 20240721004308 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6889", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7HU5X5UG6DOG3ZCPRAQLTQ35MU74VSQ2", "length": "6882", "offset": "107802910", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00006.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=6895&lvl=author_see 20240718133437 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6895", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VTQGMEHRMLI767LHLAXAGYUKXN6VVOXZ", "length": "6539", "offset": "108737252", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00033.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=6912&lvl=notice_display 20240722110213 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6912", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RADVIZKLCJHA5NKHNPLKQAPX5SAFC5JQ", "length": "5098", "offset": "104320251", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00743.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=692&lvl=categ_see&main= 20240722103406 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=692&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JDRNN6T4GG4XQDPSRECTZ524TCLT5IG3", "length": "7470", "offset": "109112943", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00117.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=6922&lvl=author_see 20240721221931 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6922", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GBCGEX75MZNOXD5RU37XLLAIO7QE5CZE", "length": "9161", "offset": "3560611", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00795.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=694&lvl=notice_display 20240721142004 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=694", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4YXIJFETEWVOWFLRRCA627ENXSMHDCQF", "length": "4911", "offset": "3949880", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00621.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=695&lvl=publisher_see 20240718135142 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=695", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UNDMERSQQBI2TC34NEC2AIPXPEFZVVS6", "length": "7831", "offset": "110392074", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00066.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=696&lvl=categ_see 20240719081627 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=696", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KPHU3K4I3F7YLPFCX3V5DR62M374PB4T", "length": "8811", "offset": "4975957", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00796.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=697&lvl=categ_see 20240718132444 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=697", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CKUW73CSGEC5P2JVEGWHBREMVIB7PLAT", "length": "8123", "offset": "5174067", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00797.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=697&lvl=coll_see 20240715043836 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=697", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WNJ3LHEFJGVTS6477L225EDQNNFFDHAU", "length": "10837", "offset": "3384671", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00043.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=698&lvl=publisher_see 20240722111402 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=698", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FM5KB3OV5JASNLUXTIEN4EQBSKVYEKXS", "length": "6574", "offset": "96776029", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00069.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=699&lvl=bulletin_display 20240718133820 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=699", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MKKI47WV4OZMAT7BE4NMS4OLCYTQITT5", "length": "6162", "offset": "111437473", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00768.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=699&lvl=notice_display 20240719181138 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=699", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MAVWS5JT3U42LZNHUEVDQ6F36FSOIA2Q", "length": "4976", "offset": "115905668", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00487.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=7&l_typdoc=a&lvl=categ_see&main=&nbr_lignes=42&page=3 20240719100707 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=7&page=3&nbr_lignes=42&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HH7YOJSHBENKVSQPW735SQFT5Y6V742Y", "length": "11374", "offset": "110187827", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00498.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=7&lvl=notice_display&seule=1 20240725191524 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7&seule=1", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EWLZJBX5ZJ2BNAMOEFAL4P2T4RWMGTEV", "length": "5502", "offset": "104740060", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00890.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=70&l_typdoc=a&lvl=coll_see&nbr_lignes=19&page=2 20240722100217 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=70&page=2&nbr_lignes=19&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UC7HEES3X7DSFSP2OBX4VWEE5CSMZPHJ", "length": "7653", "offset": "106531502", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00577.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=70&lvl=categ_see 20240724142357 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=70", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PHIU7BIM2DX7SYS65JX7PZBZ4LRZMDU4", "length": "13096", "offset": "118342763", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00377.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=7001&lvl=author_see 20240718135353 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7001", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HS5QCHRXAS6HJUMQAJCGPUO4F7XBWNJF", "length": "8740", "offset": "107433793", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00253.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=7015&lvl=notice_display 20240721001841 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7015", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "25544SOQX7KNWZOGEYTIKLY6GBWFWVQT", "length": "4975", "offset": "110470292", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00288.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=7019&lvl=author_see 20240712173100 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7019", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YVI3HF5EWUOM35V5TVMSQZYBWSP23KMG", "length": "10244", "offset": "4927239", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00313.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=7029&lvl=author_see 20240716154623 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7029", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "W5JBATUZMGPQXJCOBOYTX3RMNIMV2EXL", "length": "6544", "offset": "3818601", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00344.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=706&lvl=categ_see 20240721013010 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=706", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AETWSRDW6GUYCQTEJIFDXDUQKG4ZABMW", "length": "6873", "offset": "119166982", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00545.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=706&lvl=coll_see 20240715044610 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=706", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5YUBPHWE4NGOVVN42L45WAB5VFFXNBDQ", "length": "9824", "offset": "3514331", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00724.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ile"}
+fr,missiondefrance,bibliotheque)/index.php?id=707&lvl=categ_see 20240721223344 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=707", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YYPMWY3HGFYCIU7FZVKWTLE5T47MM4F3", "length": "11528", "offset": "5819722", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00579.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=7077&lvl=author_see 20240722111230 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7077", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XMFHHZLEOKRK56C7NI6Z6GXR4QDBUUOM", "length": "6729", "offset": "106376358", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00476.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=7078&lvl=author_see 20240722101003 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7078", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2DQ5UKRGEKCC7BA4QDEMQG4DWDPGDMDP", "length": "6726", "offset": "110363714", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00477.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=708&lvl=notice_display 20240721001338 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=708", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CS5UGU32WBWGMDZ5IGXX7OBTX3P2WIUY", "length": "4937", "offset": "105446866", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00268.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=7096&lvl=author_see 20240712183509 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7096", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XMVIPUFCSFWMYGBKNIWWDSGNWGV55QX4", "length": "11023", "offset": "105269171", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00537.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=71&l_typdoc=a&lvl=indexint_see&main=&nbr_lignes=41&page=1 20240721124514 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=71&page=1&nbr_lignes=41&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HLBCDSXXPOR5PE5ELHQRNCH42NOZSKHT", "length": "11566", "offset": "100451897", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00341.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=71&l_typdoc=a&lvl=indexint_see&main=&nbr_lignes=41&page=2 20240721124835 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=71&page=2&nbr_lignes=41&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FI27N25QTOKUF5PBP4DCTWIOZOR4SU6H", "length": "11292", "offset": "105851728", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00548.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=711&lvl=bulletin_display 20240718135427 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=711", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HVHYE7KWJ4ZYVMW4JSHTOS3BYFJKIDX5", "length": "7259", "offset": "114566329", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00573.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=711&lvl=bulletin_display 20240721141928 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=711", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QDEHZ24X7YPSCD22J2HPR2WK7JYL2JVI", "length": "7239", "offset": "3916401", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00220.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=712&lvl=categ_see 20240722114310 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=712", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TNST2S4KKXBFVXD4HEPJMXN4755HKPLV", "length": "7475", "offset": "106449825", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00572.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ita"}
+fr,missiondefrance,bibliotheque)/index.php?id=7129&lvl=notice_display 20240718202253 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7129", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "75INNDG5HVAXZCVXZWFCB3HIZRDXEVUN", "length": "4965", "offset": "117723689", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00384.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=714&lvl=author_see 20240721232912 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=714", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YVEQNEMEXQ64K6FXLUJBPMCPBC5BZNAS", "length": "10195", "offset": "107137141", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00247.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=715&lvl=coll_see 20240715060645 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=715", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EUG6MHDASA7LA6Q7SWQF5YU6ASTF6SCD", "length": "6660", "offset": "103394762", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00763.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=7152&lvl=author_see 20240721131253 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7152", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "U2TPTPBH5TR34YX57ARTMCWQVW6LRA7Z", "length": "7482", "offset": "119618225", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00470.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ile"}
+fr,missiondefrance,bibliotheque)/index.php?id=7160&lvl=notice_display 20240719100452 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7160", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PFAGEWXJZJMMK4MVRCKODEWQHNPYUFTE", "length": "5026", "offset": "112822103", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00499.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=7161&lvl=notice_display 20240721215913 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7161", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "O4FOZX3USNRHLAONKXO2HRLAHIRBSQGX", "length": "4938", "offset": "117093262", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00500.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=717&lvl=author_see 20240722110947 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=717", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2PQWVC2HEY4LTIFHPL7VITUSECKECC7G", "length": "7033", "offset": "106713717", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00250.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=717&lvl=coll_see 20240724155557 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=717", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GYWUOZ6XDCXR6ANPKWIKDAV7PYX6EXSS", "length": "8796", "offset": "3504202", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00756.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=7178&lvl=notice_display 20240721220158 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7178", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TNME7TA2JKCL67HX2MEZ72X4BQLXR7IS", "length": "4922", "offset": "109421640", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00538.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=7181&lvl=notice_display 20240716153730 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7181", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YHTNF2BH5ATFXGUSYNI4MWLLCPABFWRQ", "length": "4952", "offset": "118711677", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00562.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=7182&lvl=notice_display 20240719095411 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7182", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "77AJVZJTMTJTRDXIHOLLMXQUTX3Y7Z4O", "length": "4882", "offset": "4034145", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00632.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=7183&lvl=notice_display 20240719075211 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7183", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NNKEOLQIGBTMHVOU6MOLVDIP74JVRI4S", "length": "5288", "offset": "4495984", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00633.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=719&lvl=author_see 20240724150038 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=719", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BSMCLRTPZD4DOO6NIZH6FSAZ344ZK6RS", "length": "9022", "offset": "106768451", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00252.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=72&lvl=indexint_see 20240724155028 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=72", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2U5BROBNNQIOEKDVF2PO637NJQMXD2HB", "length": "10128", "offset": "5489429", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00397.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=7220&lvl=notice_display 20240725191938 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7220", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BVDPZ234YL2KMFO7QHUCKRTTCSUXSCYQ", "length": "5128", "offset": "2553987", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00505.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=7221&lvl=notice_display 20240725195335 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7221", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "IUDOMWJ7JBON3OD3EY7RJXXI3AVMRCVI", "length": "5108", "offset": "3671541", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00506.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=7283&lvl=notice_display 20240719190335 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7283", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YBMCMUJA243QUSCXGINTVDU447HQGSU4", "length": "4956", "offset": "3730797", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00694.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=7284&lvl=author_see 20240719084642 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7284", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HALNAVM2OFXS3CUHXPCKHHZNPMBMXHXM", "length": "7185", "offset": "103875384", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00626.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=73&lvl=author_see 20240718141418 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=73", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "U55NJBQLCV7WUGP7SFK5G7YM7RDKMPNF", "length": "10738", "offset": "116369138", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00355.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=73&lvl=coll_see 20240712183939 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=73", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YUGIYZWTGHXIWTXMOXXPBUL2BZ573X32", "length": "10947", "offset": "103416567", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00476.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=73&lvl=publisher_see 20240712165201 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=73", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BY5UB4HHCXJ5CFIO7COAG4P2YMPZSD5S", "length": "11659", "offset": "3846524", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00147.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=7303&lvl=author_see 20240721234102 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7303", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CFNQX5LULCQBKTEJKW5KK3GF5AMXPNQF", "length": "7379", "offset": "116605722", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00438.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=734&lvl=author_see 20240724150237 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=734", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PO3DDTWXWDJPSHDMJIQMV26V5CXNORA3", "length": "6691", "offset": "110259335", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00309.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=7342&lvl=author_see 20240716143521 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7342", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5SLD2U5OONJGSVSV3HJMIFHDBSTHTEPS", "length": "6811", "offset": "125433420", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00561.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=736&lvl=categ_see 20240721010548 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=736", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MLUF5VMCMESNCJ4DZRLGQSPP5EP6ZPJ7", "length": "6828", "offset": "119907507", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00638.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=7376&lvl=notice_display 20240721141135 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7376", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "J244ME2RQ3HXLAVCD4NPPJ5JJTJNUHUQ", "length": "5147", "offset": "109701770", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00658.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=7389&lvl=notice_display 20240722115153 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7389", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "G4WBOQEBJHU6RWJQDGONQHJEJSXUAESO", "length": "5176", "offset": "104682590", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00692.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=7392&lvl=author_see 20240716161204 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7392", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OAVGBHA2E7UOICHYP3BFZEHKMEGVVNGG", "length": "7421", "offset": "3724401", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00737.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=74&lvl=indexint_see 20240716161620 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=74", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GNMDSVPGDXEHAJROLU4TRT62VLHPIHNS", "length": "10439", "offset": "113996310", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00378.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=74&lvl=indexint_see 20240718202646 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=74", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GTGVYPVCJCHXXSBWKNTGHK6AZDTO7QR3", "length": "10398", "offset": "3570334", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00399.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=74&lvl=publisher_see 20240716155514 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=74", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "IDXTE7A2ZIEKQT725NX2NDW4P2KBI5GW", "length": "11025", "offset": "5329789", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00148.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=74&lvl=publisher_see 20240718200829 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=74", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BXHBVSM5EJRZH5Y7ZJBHAYIKSY4HW2DB", "length": "11027", "offset": "102926260", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00085.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=7417&lvl=author_see 20240718133117 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7417", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PLILXGT36EHMXJ5KSVY26I5FC7QA3WXL", "length": "6559", "offset": "114517963", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00534.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=742&lvl=categ_see 20240716145830 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=742", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "65HCKKKMLKRAA4OTBNP6Y5ZH4UVKDC3C", "length": "11594", "offset": "3518355", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00698.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=742&lvl=categ_see 20240721133038 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=742", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KUFZXPOGWQO7RWER5STUBK3V2VZSOK2D", "length": "11598", "offset": "99966506", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00665.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=7458&lvl=notice_display 20240719081156 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7458", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MV5QS54WDBNINOGFG7O5NZ7GGKV3TH7P", "length": "4972", "offset": "111983218", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00659.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=746&lvl=coll_see 20240718205847 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=746", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ACS4AS62SXZI6PHCUDNT5ML6HME2BW47", "length": "7052", "offset": "4770742", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00848.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=747&lvl=author_see 20240712165255 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=747", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "J52CAHGQPVWSPOWDN3HQIN5ZDMMOSNNS", "length": "10776", "offset": "107424482", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00343.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=749&lvl=coll_see 20240724151749 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=749", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FDRIZD626F6MPTLVDYPVFRRY3EERAHOV", "length": "6583", "offset": "109515131", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00860.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=75&lvl=indexint_see 20240712171554 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=75", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JIWV5GYXWDUHN2TAQSFBOVHVISXYZVSV", "length": "10638", "offset": "105243304", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00379.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=75&lvl=publisher_see 20240712163046 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=75", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZSWK2A6Y6GQJU4XANBY7JOHLY2SWLZEE", "length": "10534", "offset": "100492536", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00086.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=7503&lvl=notice_display 20240719100204 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7503", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Z33YUE4D4NI2I7CQH2XE2W2R3VCL754G", "length": "5253", "offset": "100367278", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00560.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=7510&lvl=author_see 20240721140004 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7510", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "67QZUE6GWMP4GDNKLAOZG5BPLWG2TVTZ", "length": "9401", "offset": "103754535", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00588.warc.gz", "charset": "UTF-8", "languages": "fra,ile"}
+fr,missiondefrance,bibliotheque)/index.php?id=7516&lvl=author_see 20240712183751 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7516", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "R4EXJAHGPB2C2IXWRKEYP3DJUVWOZKU5", "length": "6841", "offset": "104996738", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00594.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=754&lvl=author_see 20240716160548 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=754", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EFZC3TRHT4TQKOJ6NVT6ZPGEUXIULUZC", "length": "10383", "offset": "113263747", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00371.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=7550&lvl=notice_display 20240721002224 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7550", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "O2VHDYOYR6S34ELYXU6GPCXMMEFXS2VY", "length": "5007", "offset": "114811429", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00712.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=7562&lvl=author_see 20240715041534 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7562", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MKHRS6GLGIY2UU3ZSZYDZBMP45FH3S5V", "length": "6489", "offset": "4066783", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00766.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=7563&lvl=notice_display 20240719100526 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7563", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Y4F75V4GZKUZVCFZD4BXRHTCQCNVRHIZ", "length": "5039", "offset": "5301476", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00815.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=7577&lvl=author_see 20240718205753 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7577", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UI3VOG5HOH4GXSPWBTNKINGSODKBRAZP", "length": "7844", "offset": "120042372", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00781.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=76&l_typdoc=a&lvl=publisher_see&nbr_lignes=20&page=2 20240721015116 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=76&page=2&nbr_lignes=20&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "B4EA3BRGKLI2JDCCP2ZYPFESX3SEXM2M", "length": "8633", "offset": "3558169", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00756.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=76&lvl=categ_see 20240721020326 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=76", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "C2GBMR4MAFQV4AB7SZRFPN522QYXB2FV", "length": "11469", "offset": "3679991", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00426.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=76&lvl=coll_see 20240721012632 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=76", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5XHBW5OJA6BI4XFMSLFCBUDIU6LTZTEZ", "length": "11119", "offset": "112074561", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00479.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=76&lvl=subcoll_see 20240712181422 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=subcoll_see&id=76", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NNHLCJOKMHFHTG3OGJOPLXV7FBR764MS", "length": "6884", "offset": "99360703", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00795.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=761&lvl=categ_see 20240719085309 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=761", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ONGUGZXO4TLBOFGUN6WOQP4F5PXK4XGU", "length": "10041", "offset": "4049741", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00759.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=7619&lvl=author_see 20240721224925 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7619", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OLDIIDGIP4ORJNI5EGECDMFT4PBAANX4", "length": "9790", "offset": "112950437", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00658.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=7619&lvl=author_see 20240724142956 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7619", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RLR6RI4LWLJEEITZ4STY2TBRPGIEKKU4", "length": "9785", "offset": "4428257", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00679.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=7631&lvl=author_see 20240722104236 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7631", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VBIVRA72XVH5XEPM4I7XVTHJHNJAWLEQ", "length": "6681", "offset": "112519627", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00712.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=764&lvl=coll_see 20240716163447 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=764", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "V45KG5CSTUUM76IK6TX3ECBY63TXCXGF", "length": "11742", "offset": "122683641", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00017.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=7652&lvl=notice_display 20240721134821 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7652", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "G7KL7GANZUZB5NCUWHK7ODDDUACQ6SIP", "length": "5117", "offset": "116058073", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00775.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=7658&lvl=author_see 20240721123033 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7658", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QRXPA6DYK4UO3CGFGI5F2LMQLWY4MDNN", "length": "6575", "offset": "6785537", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00802.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=766&lvl=bulletin_display 20240715052920 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=766", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SJ6TRSWHNO5TFWHGRBEN665SEMBT6IMM", "length": "6733", "offset": "111455426", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00733.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=7679&lvl=author_see 20240718201747 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7679", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TYVZB7WKALIWFPY4CEZNUDLKNHCM2CAZ", "length": "8872", "offset": "3862834", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00865.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=769&lvl=author_see 20240719091936 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=769", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WWALEVPPI4CTTSEULMQ7TCF7TA36JUQ5", "length": "8868", "offset": "6005615", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00894.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=77&lvl=categ_see 20240721224819 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=77", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "34XAKTSDZWO2EI2J2H5W27FSS2SAPZ44", "length": "11716", "offset": "4335418", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00427.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=77&lvl=indexint_see 20240718132923 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=77", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FPDSPFVZXZVORWW5YQHQT6PT4WIXWCDX", "length": "10433", "offset": "4271895", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00402.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=7708&lvl=author_see 20240724150931 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7708", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6URMY6MRAPTMJRU3KTAOM4GBXQOPQ5SV", "length": "9933", "offset": "109879896", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00687.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=7708&lvl=notice_display 20240718201402 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7708", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "M67ALCRDS4XBBJXCA26LCMGGA5HE6EEI", "length": "4898", "offset": "108271847", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00687.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=7726&lvl=notice_display 20240721012002 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7726", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "L2KM4QJ6ICYDEZTXXABIJEHGAZVYD5XE", "length": "4931", "offset": "6513013", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00816.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=775&lvl=coll_see 20240712181051 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=775", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6KB3P64ERKJR44R63HSNYE43WFXZD2PM", "length": "7199", "offset": "3002160", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00040.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=776&lvl=author_see 20240718213213 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=776", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "L4TK7PIUHZOSTYL7C373QBZQF7JTPMMM", "length": "11579", "offset": "4220337", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00022.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=776&lvl=coll_see 20240718134733 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=776", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NSZRHLDWTZDMWVAGLJ45ZYRGYKDMZBU6", "length": "10805", "offset": "4825014", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00041.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=776&lvl=publisher_see 20240721010615 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=776", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SELSDI6H3VRNDC3SVWE6XZBNBYRIQ7IN", "length": "6567", "offset": "2954910", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00391.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=7788&lvl=notice_display 20240719092757 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7788", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NIKB6SQB3NQ4ER6PSREHDHFXDMSW7GZ5", "length": "5090", "offset": "5163582", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00104.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=7792&lvl=author_see 20240725185451 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7792", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZZ2MDH5BHQMTO5HSAUE77ABQQ2ZMZTXB", "length": "8343", "offset": "107892802", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00060.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=7820&lvl=author_see 20240715045512 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7820", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2SJJLG442RITPAMNLSHFBQCAHFBLK7BA", "length": "7538", "offset": "111468418", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00802.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=783&lvl=bulletin_display 20240718132841 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=783", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "67C3QWJTKOVGYLVSLQ3YXIQJULYJVDDG", "length": "6100", "offset": "107212204", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00792.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=7833&lvl=notice_display 20240721020035 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7833", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZOQ5Z6334WKJIQY3GV33PG4TU7RQD3QM", "length": "5326", "offset": "4311925", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00005.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=785&lvl=bulletin_display 20240718133004 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=785", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GRU6TNS7HJABR6YEGH7IZQTCZA6YVTTG", "length": "6658", "offset": "109123635", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00794.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=79&lvl=publisher_see 20240722103328 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=79", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YBSMB4MY3CQRXUVKAUGSDMXQF4RYAMSS", "length": "10801", "offset": "106392397", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00090.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=790&l_typdoc=a&lvl=coll_see&nbr_lignes=18&page=2 20240722105729 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=790&page=2&nbr_lignes=18&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6WTINDOBVAGOJHQ6WOWYPW56H3Y4S66L", "length": "7781", "offset": "4794797", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00090.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=791&lvl=bulletin_display 20240718135831 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=791", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HZEM3REFVS4JI57RO53YGWSDZYZDVN4O", "length": "6378", "offset": "111511780", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00821.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=792&lvl=coll_see 20240718213534 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=792", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZOJFE4MYF7ABA6MV73CWVZRYDMNCF5TT", "length": "7731", "offset": "114482270", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00108.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=7923&lvl=author_see 20240724143623 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7923", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LUHMUPB5NE6BKDMXW2QQIQM4UGW7LXZK", "length": "7674", "offset": "106975746", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00866.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=7929&lvl=notice_display 20240715044526 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7929", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CKPY7M2RXEWTC7HCZECSPR4TL3LYWN5K", "length": "5108", "offset": "118440406", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00872.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=794&lvl=bulletin_display 20240715050046 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=794", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JSCYTSPWN5Y4BYUWXLAW4DKS3NNRVKPA", "length": "6558", "offset": "106699362", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00824.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=794&lvl=categ_see 20240715054907 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=794", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SU6RLX4YGXJNIKYMQQL5SCHUD62OJOC4", "length": "6986", "offset": "126624560", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00822.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=7941&lvl=author_see 20240716162027 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7941", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CWMPITZ4HAGGZ2GWSB6RWQ6HK5ALANQC", "length": "6718", "offset": "112678118", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00026.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=795&lvl=coll_see 20240715045816 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=795", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XQ5DVTSBXBGCOJETQVI6R7R2OJJ2LMFU", "length": "9247", "offset": "2889231", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00102.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=7977&lvl=author_see 20240718141732 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7977", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XOGTHS62OJ77YD3CDNJE24XMJKYNOD72", "length": "6976", "offset": "111462607", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00125.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=7984&lvl=author_see 20240718150034 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7984", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MQCDDNXEO6IK4M4ORZTCOEUV4F2MEVBR", "length": "6538", "offset": "116683020", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00153.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=8&lvl=bulletin_display 20240719093657 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=8", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CARLBTUYV6P3OXJS4I5XST7LN7VMVSVN", "length": "5319", "offset": "5589575", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00365.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=8&lvl=coll_see 20240724150729 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=8", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GGNL7BLPOAYYUFWB2KLLVMN5OI5BHMVS", "length": "10608", "offset": "3514633", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00571.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=8&lvl=publisher_see 20240718212311 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=8", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XUQHGAVEWY4LGFSQQY7PYVRED52LX6FC", "length": "12126", "offset": "3672326", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00233.warc.gz", "charset": "UTF-8", "languages": "fra,deu"}
+fr,missiondefrance,bibliotheque)/index.php?id=80&lvl=coll_see 20240718145632 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=80", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ICKALXR4V7BXH3WMH7B7QREILRKHPYLT", "length": "7449", "offset": "108873408", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00504.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=8012&lvl=author_see 20240724153845 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8012", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WOF5O6MBIOSI6ECHPH2FS6T5NX5UU56B", "length": "6788", "offset": "107296147", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00376.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=8032&lvl=author_see 20240718140134 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8032", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "G7VLG5735YNRITGTKHSJ4IVB3TVQB5JN", "length": "7632", "offset": "117658818", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00438.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=8046&lvl=author_see 20240722104952 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8046", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GYGW3LN5CSJUGZYGAPG2MDMJ4WZOPBPY", "length": "6493", "offset": "113472070", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00473.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=805&lvl=bulletin_display 20240722103906 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=805", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LZ7S37DNKC3NTEGYYCKFFB27YTR2W2UR", "length": "7228", "offset": "103234013", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00607.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=8056&lvl=author_see 20240722103442 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8056", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Q6B2FCYYOX7JDF23H7T3NO56IXIGRISZ", "length": "7757", "offset": "102397436", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00504.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=807&lvl=coll_see 20240718213826 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=807", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "N2AOORTH35RWLCFX52SYWQYAFI2UULKE", "length": "10448", "offset": "105907457", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00795.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=8073&lvl=notice_display 20240725193808 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8073", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SECPH5LPY63I5PCQGXNLQ2QQ2PLKOQWL", "length": "5016", "offset": "5534966", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00632.warc.gz", "charset": "UTF-8", "languages": "fra,ile"}
+fr,missiondefrance,bibliotheque)/index.php?id=8083&lvl=notice_display 20240719094240 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8083", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GWOEJ3VYXZO4N3WNMGPLQJPBHTCKYPYN", "length": "4961", "offset": "4268462", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00663.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=8089&lvl=notice_display 20240719100611 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8089", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6DBEAZI2SISAYNRV4PSXAPPY35YXAIUP", "length": "5055", "offset": "4122466", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00669.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=81&lvl=categ_see 20240718204521 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=81", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WJ6MPZ2ZUGFK5EEACG3OUKIRC4R3D3BH", "length": "11716", "offset": "114145645", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00409.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=8139&lvl=author_see 20240718202107 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8139", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "V424YUVR7U3RXPY4HMBMQWRRBQKVOI6S", "length": "6707", "offset": "6028824", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00527.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=8157&lvl=author_see 20240716163304 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8157", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ARFVGLYHP33KUJTVGMVIIB2K3EZ7ZCJK", "length": "6891", "offset": "114763011", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00566.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=816&lvl=author_see 20240718204301 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=816", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6F7MLN5VLWJG6RGPTWS56DX4ZEFQPBZD", "length": "11246", "offset": "111796778", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00310.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=8184&lvl=notice_display 20240725182105 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8184", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "P7ESMSA2JNLAPOVMO44YM4MFQZFRFA6F", "length": "5056", "offset": "112021156", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00656.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=8199&lvl=notice_display 20240725192611 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8199", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SZPSGZCAOKLLZGOXUCMIV2ABECZAXOZB", "length": "4830", "offset": "109065658", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00692.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=82&lvl=publisher_see 20240718135215 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=82", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JRCQQEIB5CZSG6GF4OSETFF75FRH2MFK", "length": "9421", "offset": "114278197", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00114.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=8200&lvl=notice_display 20240725192004 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8200", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "25AWPKPIS37MGQ3DXZ6D4KKZWVR6MWOJ", "length": "4828", "offset": "107742862", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00465.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=8202&lvl=notice_display 20240725181722 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8202", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PEVGJHQHZKWVAATWBS44K66GF2WGSOVW", "length": "4841", "offset": "104805125", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00467.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=8208&lvl=author_see 20240721003728 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8208", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "U3N4CK6KSZOOZJTSRRDF54XVAEMPEMDR", "length": "6468", "offset": "110163329", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00473.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=822&lvl=notice_display 20240725200315 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=822", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2SHKCQC3HZYZVZNEW4H3IR6SFAQ5BEXG", "length": "4932", "offset": "102770939", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00385.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=8221&lvl=author_see 20240724141818 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8221", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FDFXORFVOGPB4CPPCE5JV3CXN7F2DXRL", "length": "6576", "offset": "4437374", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00549.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=8231&lvl=author_see 20240716150913 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8231", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VFQKZ46CEW5N64TLUYURUNHZ4Q7VVECJ", "length": "6833", "offset": "3249198", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00580.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=824&lvl=author_see 20240721000612 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=824", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YEWQI3NLK5KM2SAD666N5BOBW5YYAZ5Z", "length": "11557", "offset": "109802217", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00339.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ile"}
+fr,missiondefrance,bibliotheque)/index.php?id=826&lvl=coll_see 20240721125650 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=826", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZWQIUHENGW3THRAPAAD5N3DNIN7BHBZ7", "length": "6595", "offset": "112195933", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00856.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=8267&lvl=notice_display 20240716154139 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8267", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VS6IV4RE4ZNYI52EI4PPE4PQ3XRUXVFB", "length": "5115", "offset": "115281848", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00658.warc.gz", "charset": "UTF-8", "languages": "fra,lat,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=827&lvl=author_see 20240716155356 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=827", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FGD2PXIRKWS3L2OY6JAFSUMYLFI35FRO", "length": "11201", "offset": "122518211", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00342.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=827&lvl=notice_display 20240719095844 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=827", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YBNK6PR5JZJXJMZN4AFN2HONWYWTKXOB", "length": "5012", "offset": "105373984", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00390.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=828&lvl=coll_see 20240721124436 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=828", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7QL2CUC4CIOYLU7OGFUZ2IGSAVJUPYSN", "length": "7221", "offset": "114468550", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00858.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=829&lvl=bulletin_display 20240721231714 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=829", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PFZ6T5XEQXRXP6GDZEAZ6I76F2G627N2", "length": "7469", "offset": "114642608", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00673.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=831&lvl=coll_see 20240721220449 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=831", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YXKH5OWKXSAJXSTKTUAFMW26563F7PZV", "length": "7373", "offset": "103381907", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00882.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=832&lvl=notice_display 20240721020113 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=832", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "I25Z6R2F6AJVFKJ54GTO74WYP7FI52CE", "length": "5015", "offset": "115129062", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00416.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=8327&lvl=notice_display 20240725184348 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8327", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "F2FFFFR5E7EE3NXMZAPWA62X72OV7MC4", "length": "5260", "offset": "5485782", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00664.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=833&lvl=bulletin_display 20240718131731 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=833", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UNOAAPHS6ZJH5D6EBCE5GPRTF5DM5EIJ", "length": "7359", "offset": "108717423", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00698.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=8341&lvl=notice_display 20240725184236 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8341", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6L4QNZKBZNBZN6KDSEOEB3OWZRDDRZFT", "length": "4881", "offset": "4146496", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00720.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=8348&lvl=author_see 20240712161634 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8348", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PVJ2EGGRTLUZ2NAJ42HL3XR6HNAIG2BE", "length": "6509", "offset": "107417032", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00658.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=835&lvl=coll_see 20240724153653 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=835", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SCAXNE3HKQTYYXNDSMPRRIV7JCXCTH4W", "length": "7202", "offset": "2796043", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00877.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=8355&lvl=notice_display 20240725183105 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8355", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WAYCP62BAON2QTIJ5DZPDL33UCNMON45", "length": "4936", "offset": "5283394", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00755.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=839&lvl=author_see 20240715053828 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=839", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DMPHJNHVWGIRI4CNCHIGHGCNTDFEYYYM", "length": "9264", "offset": "112727625", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00375.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=8393&lvl=notice_display 20240725184312 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8393", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "COS5MPEILDNRUAAV3QPDBOXSEOJIXFT6", "length": "4954", "offset": "111600115", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00808.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=8398&lvl=notice_display 20240725191814 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8398", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4RX7SAR7JMSGVU3ZPCXL35BMU7SRYIAR", "length": "5159", "offset": "114667343", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00813.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=84&l_typdoc=a&lvl=publisher_see&nbr_lignes=57&page=4 20240719191201 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=84&page=4&nbr_lignes=57&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WKOCT6FCI26IWMHLIT6O6M4S4I6OU2N5", "length": "11764", "offset": "110716675", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00600.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=8408&lvl=notice_display 20240725200429 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8408", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CN3EKDPZSKI5CTU3UVR5JFGFKPMFYSG3", "length": "5217", "offset": "105664843", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00595.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=8419&lvl=notice_display 20240721130029 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8419", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "36XQGZTJ3VTZET2CHREM3SXCVJAJFCPQ", "length": "4975", "offset": "112964769", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00627.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=842&lvl=bulletin_display 20240724145654 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=842", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JP3EN6DJLRLRLDXU3TGFR2Q7YXWFKSRX", "length": "7996", "offset": "110693700", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00728.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=8421&lvl=notice_display 20240721131145 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8421", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3SAETIL7NV4GMDWHP4NVOL5FWKNG7EJ3", "length": "4988", "offset": "104539394", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00650.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=843&lvl=bulletin_display 20240724145730 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=843", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MKTE3V2OGBYYMTSDJHNXYIOXFTF2A2DB", "length": "6756", "offset": "103587241", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00729.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=843&lvl=notice_display 20240719083116 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=843", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7VLECSXO2WKOU2Y5T2H2PKFFWD6ABBLL", "length": "4967", "offset": "115112430", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00448.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=8434&lvl=notice_display 20240721131006 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8434", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OJ2T5VVKGZRPSHBJG67NJWHNUOIBIEI7", "length": "5040", "offset": "108712565", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00684.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=8435&lvl=notice_display 20240721133841 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8435", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Z6RZPH4P4WX3TCTUGIHECRNU7SCEONRM", "length": "5188", "offset": "113293606", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00685.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=846&lvl=author_see 20240718195824 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=846", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GEZBDP37KDTUMOTAUGGJMFJXL54N3YUK", "length": "10729", "offset": "109782432", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00403.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=8467&lvl=author_see 20240724152209 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8467", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HSOUSLME3FDTECXF6HKVJH54YYXU7MK4", "length": "6459", "offset": "99378552", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00780.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=847&lvl=bulletin_display 20240721222036 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=847", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VLTP3W64N5TQHLLSOMPUD2GA6OJOJ3RD", "length": "8491", "offset": "115991949", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00733.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=847&lvl=notice_display 20240724142754 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=847", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7TKFU4EGOW45L4XSATD2JIIBXRQK446L", "length": "4969", "offset": "106948201", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00452.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=850&lvl=notice_display 20240719094040 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=850", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZTCW5DF7A23Y3ZOA63CAGDP4TJ55O4FH", "length": "5148", "offset": "109781492", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00476.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=852&lvl=coll_see 20240722105112 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=852", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RSZ7SE3RQDPVSGDCJYGEL5CWUF2XZGBC", "length": "6786", "offset": "104771728", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00045.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=8537&lvl=author_see 20240715050317 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8537", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6PAIDTFXLG7JRMSYZRQQFPUXYS6JHXPW", "length": "6490", "offset": "4127776", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00769.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=854&lvl=coll_see 20240724145005 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=854", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TGM5I6FMRIY5QOKNOLM6XLPHSBA5YKPK", "length": "8913", "offset": "105952666", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00047.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=856&lvl=bulletin_display 20240715052025 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=856", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "N2HLIOC7MLRCKYZ723GVYH2YNHE5BRZQ", "length": "6980", "offset": "103386793", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00763.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=8568&lvl=notice_display 20240725182802 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8568", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TGG7VRNIMYRTUBRA5K424H4NKN3VPQ45", "length": "5167", "offset": "106878944", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00842.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=8569&lvl=notice_display 20240724153857 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8569", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "S3QZH3C7PR75LRTSRSK4ASGKVLQVXLS7", "length": "5171", "offset": "3972145", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00012.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=8572&lvl=notice_display 20240718211717 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8572", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7GBSETNRKZL3KX2PQB5XWYTVDAND76IB", "length": "5340", "offset": "105766897", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00867.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=8576&lvl=author_see 20240724143747 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8576", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "W6N5XAB6VW4RH2GSG72KCGXABVMU57RH", "length": "10522", "offset": "112852730", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00871.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=8577&lvl=notice_display 20240719081458 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8577", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DW3GAEEF4NVCSPTWEYLJ67SCW62RSG4T", "length": "5277", "offset": "105166781", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00872.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=86&lvl=publisher_see 20240725192526 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=86", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PAG5VFYL6IEVCFLKHF3PUURFLEXRBRD6", "length": "11303", "offset": "4523921", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00181.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=860&lvl=bulletin_display 20240721014630 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=860", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4ZZK2E76RPJGWHDIMJ34WW36CSIMNXCM", "length": "7663", "offset": "108567365", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00788.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=8608&lvl=author_see 20240719183102 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8608", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CXXSYOCCXOTWYXUGECOJTYD7DZZCUB3N", "length": "9909", "offset": "3485532", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00738.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=8613&lvl=author_see 20240712174827 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8613", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2UOW46NO56KY5YOXWMXVVWZJMUQBIXGX", "length": "6631", "offset": "104060289", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00743.warc.gz", "charset": "UTF-8", "languages": "fra,ltz,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=8613&lvl=notice_display 20240724162630 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8613", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QW35CA3GOIFXDTVW6PSYYKF3Z6M22FK2", "length": "4986", "offset": "118177865", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00743.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=8614&lvl=notice_display 20240724144720 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8614", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LAAU235OANP5OTWQWHYJA5HWZOQFQBT7", "length": "4985", "offset": "106995569", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00744.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=862&lvl=coll_see 20240721233732 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=862", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KB3TKGZO66DTRW4SLUUBXDEYPOX4MW3T", "length": "6781", "offset": "114770277", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00076.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=8622&lvl=author_see 20240721141056 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8622", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MO4JGN7MYO2AIS3DM752OC4VXLUC52HX", "length": "6590", "offset": "112712726", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00773.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=8623&lvl=author_see 20240721130610 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8623", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6TG3CWDTMMPAIG4YFHJCVOQJN4YTG4DI", "length": "6588", "offset": "109451055", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00774.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=8623&lvl=author_see 20240721132813 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8623", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RHDEQOCMOQ6IUJGOI2ZVUQ2EAD3Z7F5Q", "length": "6576", "offset": "5135807", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00795.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=8624&lvl=author_see 20240719100132 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8624", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NVCSZCCOUTAZ2DMKQNKQLKSZXIVPPIU2", "length": "6592", "offset": "103741507", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00775.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=8631&lvl=notice_display 20240719095917 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8631", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YKVHZ6JP2WODPPIDU3SXTQBJCNQ4MSOD", "length": "5298", "offset": "117323221", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00803.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=8668&lvl=author_see 20240715060835 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8668", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "C3CRILMMMGFVLIAFGG2PAD25NTJPQDVR", "length": "9825", "offset": "3409825", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00024.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=868&lvl=categ_see&main= 20240715061605 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=868&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TQAH5Q6DECWMJWIJSHK62PYX6BAMJB5J", "length": "6809", "offset": "109013639", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00868.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=87&l_typdoc=a&lvl=indexint_see&main=&nbr_lignes=39&page=1 20240725184652 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=87&page=1&nbr_lignes=39&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "M2LEDGILU4GT3JZHML4S3DYWMVVM5HC3", "length": "11212", "offset": "118867907", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00577.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=87&lvl=author_see 20240716162337 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=87", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZSFRYZXGNMOA37WNV4SEZZYFVU6LFNGH", "length": "11808", "offset": "4782728", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00423.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=87&lvl=categ_see 20240724145316 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=87", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4CV5CDA72E64NBMPVQEKGNO2JTFMH72F", "length": "11534", "offset": "116406893", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00415.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=876&lvl=bulletin_display 20240721132508 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=876", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CTNGIT6UJZVID5GOS2UR3NGXW6SRWDB5", "length": "7488", "offset": "3826319", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00472.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=878&lvl=bulletin_display 20240722101050 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=878", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BEP5L5HWZLDEEC3YDTJAJ75JB3DFV64Z", "length": "8773", "offset": "105295063", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00827.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=88&lvl=indexint_see 20240712170152 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=88", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3QDEBSXWK3PTKPO54MRLXOSLAPFYHOQF", "length": "10631", "offset": "4405300", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00434.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=88&lvl=publisher_see 20240719091658 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=88", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AQYOWFJMKAJYLZXX7QLX3XTQN2QKLYUW", "length": "6812", "offset": "3427370", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00183.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=881&lvl=bulletin_display 20240722104559 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=881", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PRUBKHLC7JQHFOOBCPGYWT47BU3SL4YC", "length": "8174", "offset": "116319661", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00851.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=882&lvl=bulletin_display 20240718135645 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=882", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NYSYMIZOCQHFEAR4IVVR7BA4AXO3S2VE", "length": "10646", "offset": "106795814", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00852.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=8855&lvl=notice_display 20240721122803 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8855", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NHJB4CFIDGDZU3PL2FGSRPFJUB2FEKJK", "length": "4771", "offset": "2745650", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00160.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=8858&lvl=author_see 20240718141628 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8858", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QXCLW74BD4GD3TWSEE7RGJQ4TVBUE6KR", "length": "7658", "offset": "5453711", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00115.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=888&lvl=author_see 20240721233348 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=888", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TKOVOXU3XWRPSNMFZL3GK4AMDDLTF5B7", "length": "7084", "offset": "112041693", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00529.warc.gz", "charset": "UTF-8", "languages": "fra,ile,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=89&lvl=author_see 20240724155937 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=89", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2WOBDT26LOWPAT2UHA2Q66QFE4B6YHZC", "length": "12674", "offset": "3886637", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00425.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=89&lvl=indexint_see 20240716144938 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=89", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "O4UGLSPDE3XUISKLUSXEMBHLGQOFBYBI", "length": "11523", "offset": "3901026", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00435.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=89&lvl=publisher_see 20240719093911 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=89", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ODTPXPJXNHETSQQVDG65BXGWKAYWK56D", "length": "10782", "offset": "109842688", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00121.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=890&lvl=author_see 20240712162032 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=890", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LTIB7RVDLW2CT42ZKPKDRMUMJOCFKRGQ", "length": "7460", "offset": "108045512", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00552.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=8906&lvl=notice_display 20240724152418 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8906", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2V3FUX4CPZWPIJK2BEC2RQGI42OO4WLP", "length": "4946", "offset": "3636075", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00067.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=8919&lvl=author_see 20240721131820 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8919", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Q3LZBJYMYW6TBR3SEYJTYQCPUG6IBTGU", "length": "7367", "offset": "5966461", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00053.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=8932&lvl=author_see 20240724155758 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8932", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DG43KIBQZ75OAZ2UZUSLOJV7U4YENOXE", "length": "8300", "offset": "7386883", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00108.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=894&lvl=author_see 20240716154038 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=894", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EYDCPRJNJFAOHC7J43QRDWDVU45QADJF", "length": "8439", "offset": "119856846", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00556.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=8964&lvl=notice_display 20240719093958 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8964", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZA3IW2CHZXEDZSLSIGGYM6446SS7IWSL", "length": "5211", "offset": "3228505", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00251.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=8965&lvl=author_see 20240716154238 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8965", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TDMLGMGMXABN2EDG2RN653X3VUY5OJZE", "length": "9680", "offset": "120756310", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00183.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=8968&lvl=author_see 20240718133042 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8968", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TVRTWUOSKEGYRRT2GM5UJOYKJXTFHRS5", "length": "6728", "offset": "114120911", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00186.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=8969&lvl=author_see 20240718142611 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8969", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JXVUXJO3TQX2PLQ3VWHYB453KK5OS32Z", "length": "6727", "offset": "113603189", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00187.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=8978&lvl=author_see 20240725180355 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8978", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AJYRIYGNU7NU64ZQYDPF723GC7422FVS", "length": "6754", "offset": "105004567", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00217.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=8998&lvl=author_see 20240721231750 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8998", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HMEJ4VOS6CBM5QH5PBOWBLSWABVWEZLO", "length": "6651", "offset": "101444240", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00279.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9&lvl=categ_see 20240718210609 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=9", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CVT4IDIIOO7HQAOGOVJEM6OSWRC7GM6P", "length": "11083", "offset": "110665144", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00553.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=9&lvl=categ_see 20240721222541 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=9", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DMGNQMWWA6H2M72XCJPQDETMDNLCPLIM", "length": "11074", "offset": "3188975", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00838.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=9&lvl=indexint_see 20240721215626 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=9", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XE7C663KMINIHU6WAVQXBO6C7NAP2UMN", "length": "10533", "offset": "5502891", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00495.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9&lvl=publisher_see 20240721014014 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=9", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "REVTOCCJE23BQYAUN6OGVOLD2YEEUGRA", "length": "10919", "offset": "5019253", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00234.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=90&lvl=indexint_see 20240712180115 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=90", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "22DXJVMDCF2KHYKYIATGBXTJ6G5C6RC2", "length": "11807", "offset": "107827990", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00436.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=90&lvl=publisher_see 20240712173953 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=90", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "APDBKHXSA3GOGF565XN4RHQLUMB3HIVG", "length": "9574", "offset": "4435100", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00206.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=9007&lvl=notice_display 20240725201502 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9007", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "S5FMFXV54HHW4UULMPXGOTX74NZ3VLPW", "length": "4971", "offset": "112864677", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00441.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9015&lvl=author_see 20240718194339 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9015", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6D6WSQZPTVR2CAJNXBYAISXAJBY7WWPK", "length": "8343", "offset": "121134184", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00470.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=902&lvl=publisher_see 20240724152102 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=902", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "K3MKQBQGR7NGJCIEINB6EOPEQLO4G34A", "length": "7020", "offset": "100968961", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00867.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9021&lvl=author_see 20240719192355 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9021", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "U5UUNW3RIH4X4C5I2EFQSTNSSH67HDPP", "length": "8009", "offset": "117601543", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00497.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=9026&lvl=author_see 20240721003034 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9026", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UDQUSK2DZJLO6IJZ4X7TSYOT4NQXLZYE", "length": "7070", "offset": "3943103", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00523.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9029&lvl=author_see 20240724161402 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9029", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OI3PA4MEFQAQM5FAZWZLBVDNS5J2V7OX", "length": "6660", "offset": "3796086", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00526.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=903&lvl=bulletin_display 20240722110144 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=903", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EEYPJ4YOSB6SYG5WKLEQFIWSORSPIJDG", "length": "8251", "offset": "103859477", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00666.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9045&lvl=author_see 20240716160804 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9045", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7XW7ZLYFK2I4CBPURT6TSMJHBEBULFSF", "length": "6904", "offset": "125373956", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00563.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=9063&lvl=author_see 20240715051737 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9063", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "B6R6RY3RGXG66MN5JZUHOPSCOJCDD7EU", "length": "7088", "offset": "115704854", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00623.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=907&lvl=coll_see 20240712184214 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=907", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HO3SJI2NFNFGSS6QIJA64KHTNQT4EUCX", "length": "8034", "offset": "103289308", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00856.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=907&lvl=indexint_see 20240715052947 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=907", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6I2FXJUQVRE4YUE65PRBV5WCUXOGRFJP", "length": "11378", "offset": "4508507", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00326.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9076&lvl=author_see 20240724150116 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9076", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UUMV4XG6TEYV6SGGU4BXMNIYVGWNNJQ5", "length": "11556", "offset": "6107244", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00678.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=910&lvl=bulletin_display 20240722113432 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=910", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TRWJ54VR6EOB3ETQU6JWKVNKJP72XLA3", "length": "7402", "offset": "111452935", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00694.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9108&lvl=notice_display 20240721124955 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9108", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7VKXOVI3PVKWUHVNICGKDC7WNMUWG7SM", "length": "4863", "offset": "4535754", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00572.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9119&lvl=notice_display 20240719090409 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9119", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YNZLPLYRKCEDGYPVE7QKG6MZSJNGHV5O", "length": "5113", "offset": "4231683", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00604.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=912&lvl=bulletin_display 20240718143347 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=912", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5NFLJYM5DO2OC7ENTNFKIG6DAWSM6NBH", "length": "7348", "offset": "115241052", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00696.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9124&lvl=author_see 20240721013046 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9124", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PG44B2362Z6PKLHCRREWXSYAWXI6UOD5", "length": "6855", "offset": "110589055", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00561.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=914&lvl=publisher_see 20240718143311 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=914", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UENULGW4T7KDFL5JF6XCPBMHTSMQBXDS", "length": "7366", "offset": "2830712", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00325.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=9149&lvl=notice_display 20240725200241 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9149", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7Y7ICPCKRL5IN4YKFMF3NTAXGLRBTPJD", "length": "5150", "offset": "3822909", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00697.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=9174&lvl=notice_display 20240725194559 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9174", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AQKTHVUKRUB774RXRAEKZJEF3H5KY3JU", "length": "5225", "offset": "103323137", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00716.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9177&lvl=notice_display 20240725195255 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9177", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EK4PM47LMKRBW4766A5WPLRAJ5X5W5EP", "length": "5066", "offset": "5506327", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00788.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=918&lvl=categ_see 20240718200631 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=918", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5YSBYNPJAAWTBA4MIZYKMWQAVVQY4CIS", "length": "6886", "offset": "111280990", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00700.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=918&lvl=notice_display 20240725194438 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=918", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RLM3GCOI3TCCLAMIG46T55WQVUKR3EV2", "length": "5094", "offset": "5147938", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00560.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9181&lvl=author_see 20240716153120 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9181", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JN4FF4WYIRQCUVHZ3G5KHX2OFQCNA3HM", "length": "6822", "offset": "119014029", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00744.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=9193&lvl=notice_display 20240721140652 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9193", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OVMQBZHQNZGVUHXFEJIFUZGG36DYOFGL", "length": "4905", "offset": "105292085", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00777.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9196&lvl=author_see 20240715053836 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9196", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "L5FEDWLYAR3OVFF3DB5OJZ42KK6CQXGO", "length": "7340", "offset": "5254976", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00801.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=9197&lvl=author_see 20240718202503 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9197", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LZKLLP5TCI4YUSWYCYGWJPEKNX4N6LNP", "length": "6727", "offset": "120051239", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00781.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=92&lvl=publisher_see 20240722114731 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=92", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "546QDKEDWEB3G7PEJ7I2BSZ2ILTQCCGG", "length": "11130", "offset": "100932724", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00145.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=9202&lvl=author_see 20240715043559 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9202", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GTSUXABR6II5MFAUXOF6OZDPXUMDDUB6", "length": "7857", "offset": "112805928", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00558.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=9224&lvl=notice_display 20240719094706 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9224", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LPJAIDWOGOBHBBFTYLJDDUZDMKODMGP4", "length": "5004", "offset": "115362256", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00622.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9228&lvl=author_see 20240719100636 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9228", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "N3DFCPINSUC5F6CHLRG6KCL7IBASDX6L", "length": "6624", "offset": "103883558", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00626.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9238&lvl=author_see 20240725181241 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9238", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4DMWRILCJXG4ELDSGMQ6RO4MPYRYDOHH", "length": "6727", "offset": "3928616", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00678.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9252&lvl=author_see 20240712180217 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9252", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QRX54MX32UZKRG2OCGV7WWH5I5YXLNDR", "length": "6887", "offset": "99247799", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00713.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=927&lvl=author_see 20240718142429 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=927", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DIO567PCYAZUD463FS6GIP4X7PEA66MT", "length": "7752", "offset": "117411529", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00403.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=93&lvl=indexint_see 20240718194005 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=93", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2XP36JQELZLUOZDVZCL4MNJPF5A5UB3P", "length": "11189", "offset": "116462821", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00439.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=931&lvl=author_see 20240718141348 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=931", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "IY7JSYNQ266YR7WXDXNLYAKO4OHTNYHH", "length": "9201", "offset": "121694989", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00428.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9313&lvl=author_see 20240715055035 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9313", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "A4TXOTPEJ5I7NMKJ24DJIHOK5AMXE5RR", "length": "7482", "offset": "112971103", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00651.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=932&lvl=publisher_see 20240718145104 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=932", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SUS7UJMNNWHSM7O6QTLZULSHZDNL6SJB", "length": "6990", "offset": "108175697", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00060.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=933&lvl=bulletin_display 20240722103634 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=933", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HKDAYWCHBS5MPJLH64L5OXXUNBG4BDLA", "length": "7629", "offset": "110666123", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00759.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9343&lvl=author_see 20240725195943 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9343", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MJQSV5MDVNFAANAZUK3OZYPVLWWA45IX", "length": "6781", "offset": "4105349", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00765.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=9344&lvl=author_see 20240718143125 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9344", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WPBQBJRKGBZYUDDY6BFAHYWWRWZGFSJ3", "length": "6783", "offset": "5247092", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00766.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=9372&lvl=author_see 20240718204147 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9372", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EP37DUMV4FGZIGZYMKLQ4GTAVCH3INPB", "length": "10255", "offset": "112012848", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00836.warc.gz", "charset": "UTF-8", "languages": "fra,eng,deu"}
+fr,missiondefrance,bibliotheque)/index.php?id=9372&lvl=author_see 20240721224756 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9372", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TISTSNT2ML3C7AYCC7OYVV6HQU7NZW37", "length": "10233", "offset": "3214090", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00857.warc.gz", "charset": "UTF-8", "languages": "fra,eng,deu"}
+fr,missiondefrance,bibliotheque)/index.php?id=9381&lvl=notice_display 20240719082420 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9381", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RBN6LPLCXKEY2NNQRNL4OMHHC6ARH3GG", "length": "5028", "offset": "5137481", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00035.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=94&lvl=author_see 20240718205206 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=94", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LIXFRS527GGPLHDJ7OVMF6NDVIPARRCJ", "length": "10309", "offset": "107371760", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00418.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=94&lvl=categ_see 20240718193328 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=94", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PYLVH2QDPDXL5J2OYIO7LSA4GPCCDDLN", "length": "9900", "offset": "115394762", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00443.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=94&lvl=coll_see 20240715044033 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=94", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JD3MA7KYP2AASAE7B4WG6ERJPIWKVVDU", "length": "10514", "offset": "4628676", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00824.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=94&lvl=coll_see 20240716150244 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=94", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "342BN7PFXF5L7SWMBXMVVMBBXCEOO32E", "length": "10552", "offset": "118397198", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00539.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9407&lvl=author_see 20240721123935 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9407", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OP4NQJDNLZW6N46PUQVY74ZYHJBBIYFZ", "length": "3965", "offset": "113288678", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00685.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=941&lvl=coll_see 20240722110115 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=941", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MSJOFUEVRDH5SQZVGQIMHLT5PCF6KVIJ", "length": "7670", "offset": "3302621", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00065.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9414&lvl=notice_display 20240719095811 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9414", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "K6QJXVVXPCPTGBM7TPRAWJTFAI6O2NKP", "length": "4876", "offset": "5478050", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00782.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9424&lvl=notice_display 20240712185845 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9424", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NMSDLAYB3PTXGNFAJMAXUE5ZQYQXG2SA", "length": "5088", "offset": "105120339", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00744.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9432&lvl=author_see 20240724145123 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9432", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CUUW5UXEMLGWNRCMLTV3Z7QT72NEY76Y", "length": "9416", "offset": "105409274", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00773.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9433&lvl=author_see 20240715055008 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9433", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OKN4KXDZOXW2BWLWO5H6MX4T6OSXOHLC", "length": "6936", "offset": "113232135", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00774.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9434&lvl=author_see 20240715044850 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9434", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7AY7ZN7CPEZDIUSIUGEUACJIDWEHUQ66", "length": "6930", "offset": "107165624", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00775.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9434&lvl=notice_display 20240721003125 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9434", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZZUAO6DOSGD2HDEGYB3XJ5OST2KZMQRH", "length": "5049", "offset": "115117772", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00775.warc.gz", "charset": "UTF-8", "languages": "fra,ltz,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=9435&lvl=notice_display 20240718195907 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9435", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "IN2KHELDOZZYU72TZMYU3PF2N4DQPO4L", "length": "4982", "offset": "3264561", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00845.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9436&lvl=notice_display 20240712182234 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9436", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6CORJ7BWNYMVP5QOO6M6GI6VYDQSYWB7", "length": "4947", "offset": "104633457", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00777.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9462&lvl=author_see 20240715061141 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9462", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZP66564AE2R6FYRT4LKQXCDTMBERC3IJ", "length": "6749", "offset": "111100970", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00866.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=95&lvl=indexint_see 20240721140043 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=95", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "X7VXR54SEEXZDIDC76HT5LK4JCYZRXAI", "length": "9196", "offset": "4212330", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00462.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=951&lvl=bulletin_display 20240721013935 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=951", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AMFQ4KGEIR3ZJLXQBPQRR7NOZONOF7OK", "length": "7965", "offset": "112414977", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00819.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9515&lvl=author_see 20240718134120 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9515", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VQ5QPXASSQEWUOUGZEHIONADPMBBZHXK", "length": "7986", "offset": "113245425", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00775.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=952&lvl=categ_see 20240724151822 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=952", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "L3MJ67TOTFK3M4ZAMVHPFPXIJKEOFGMJ", "length": "10478", "offset": "4273580", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00851.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=9533&lvl=notice_display 20240719091721 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9533", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NEW2TYAYQMXEXKDWNR52YMNEVZ76UOII", "length": "4910", "offset": "3473264", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00004.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9538&lvl=notice_display 20240721130139 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9538", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VS37FOU4SOHPB3EWPVKVQ6E3GUV2FDGS", "length": "5048", "offset": "108251030", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00840.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9539&lvl=author_see 20240721122255 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9539", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "J2PXONL4B7VJWEOPZ4KLWDPDD2AP53WL", "length": "6655", "offset": "111031174", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00841.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=9543&lvl=author_see 20240715053757 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9543", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GHSPGNPGBG5KLURMHU5CXKFJ5U3B47L5", "length": "7868", "offset": "3551959", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00887.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9543&lvl=author_see 20240716162300 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9543", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PULUOWMWRPG2D3SG4QJR2D7ZBF5DCQGH", "length": "7918", "offset": "118476572", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00866.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9558&lvl=author_see 20240724145844 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9558", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VCMU5Y6TZ3RU4RRT6J552I5Q2QEI47N5", "length": "6814", "offset": "110738686", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00002.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=956&lvl=coll_see 20240721005013 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=956", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2GX4MWNYWRZNL27QDXB7BNYMVJGQPBMU", "length": "9348", "offset": "2800065", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00101.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9568&lvl=notice_display 20240719100553 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9568", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BB6PLTZFBRZ7UVIDHE7Q4NAX5K3ZTSQW", "length": "5040", "offset": "2990347", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00102.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=957&lvl=bulletin_display 20240722110834 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=957", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2AH3MNAPVGSJEJYKAZHSIP3K4TXOTL4S", "length": "8330", "offset": "4335202", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00472.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9578&lvl=notice_display 20240722100537 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9578", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DDS2ABXIK4MOY4RSSB2Y6EJBX3JZ42FN", "length": "5141", "offset": "3747026", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00133.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=958&lvl=bulletin_display 20240722114405 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=958", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TBABQXKVXRRWMRETDHB6Z7T53HGCC4HE", "length": "7805", "offset": "105930258", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00826.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9581&lvl=notice_display 20240721134950 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9581", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PLCIHNPQRDGSHBJQQIYMQZADHVAJM47C", "length": "5146", "offset": "6393417", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00157.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=9585&lvl=author_see 20240712172306 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9585", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6JCCFD4DKC4U2MHUR3DHMKRPEJH2LRHM", "length": "6790", "offset": "4631783", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00113.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9590&lvl=author_see 20240715055402 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9590", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "R5SXK6AHXA3ODPOLDA5O6LUKZ7X54J6B", "length": "6916", "offset": "104645778", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00118.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=96&lvl=indexint_see 20240712180612 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=96", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FDFTHAHJXMCUU3XKM7PVLMIGERZFD2AC", "length": "9977", "offset": "97769136", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00442.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=963&lvl=notice_display 20240724142607 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=963", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QQAZDWSOCY2DG74YNAJYC26XVCSX5GT5", "length": "4981", "offset": "3495808", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00710.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9637&lvl=author_see 20240722103716 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9637", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XK2ZATVIYARKWHBPZTPK6XIPOLWVCIKH", "length": "6785", "offset": "109593598", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00000.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=965&lvl=author_see 20240721135149 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=965", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OBI5LGJCHJCMYVVOVIPNTQPBAZHORMAG", "length": "6618", "offset": "118094555", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00525.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9651&lvl=author_see 20240719100605 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9651", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "W5SHYT5IPMKBRY6QI6YZPP3P66TDHWBC", "length": "7401", "offset": "108164672", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00056.warc.gz", "charset": "UTF-8", "languages": "fra,ile"}
+fr,missiondefrance,bibliotheque)/index.php?id=9653&lvl=author_see 20240724162805 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9653", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GBZ5U2BJ7UGUTIM6N5CWDUXYV6HPESXS", "length": "7942", "offset": "111338151", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00058.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=968&lvl=bulletin_display 20240720235925 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=968", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ESFTAYLXOPH7SY6RXTM2HTR7IUOIQGFH", "length": "8517", "offset": "114989075", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00857.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=968&lvl=categ_see 20240722100047 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=968", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "J42PRRP2WK2DUAEQY3JFN4OGS5AS3RUI", "length": "7689", "offset": "111995923", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00855.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=969&lvl=coll_see 20240715042509 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=969", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LIIEZBINXG766JI6KP5IIMYUYNENCDHD", "length": "8566", "offset": "3042231", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00135.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=9695&lvl=notice_display 20240722105837 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9695", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XQEXIG55W4NAKURMFIXAWYWBWDUJPOZK", "length": "5005", "offset": "5245492", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00253.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=97&lvl=categ_see 20240712184125 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=97", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PLM4UQNBD3VTOWINUENLHUDDZM2GXIOG", "length": "12927", "offset": "101528294", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00446.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
+fr,missiondefrance,bibliotheque)/index.php?id=970&lvl=bulletin_display 20240722101911 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=970", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HZXHWJ6AA3J3JRC4U3XUMO4ECY7YWRRP", "length": "9132", "offset": "4537830", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00527.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=9708&lvl=notice_display 20240718213430 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9708", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZE5XL2GZIXJXSV5GUFNF7RV4IMKJ6IWM", "length": "4873", "offset": "108112532", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00869.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=9718&lvl=author_see 20240721130431 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9718", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EM7BFDAY67OJKHEVDXUBK3YRTFRVK7IZ", "length": "6819", "offset": "3949237", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00021.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9762&lvl=author_see 20240721224644 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9762", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SE3H55PMYNBCKAIANVYSPE3VWJPGMTGT", "length": "6659", "offset": "112778820", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00149.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=977&lvl=bulletin_display 20240718200030 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=977", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LDDOJQPYN5KRDCVFFXD7FRAFINQZX5NE", "length": "9015", "offset": "108880600", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00887.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=978&lvl=author_see 20240722111800 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=978", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RY6BDSKDXO6I3W6VJHQHZKVI7UA3AZAS", "length": "7446", "offset": "109680960", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00559.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=978&lvl=categ_see 20240718213648 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=978", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "43W7JQU5U3YEGBFOPV5WCYTTLGWACNKC", "length": "10655", "offset": "119211447", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00886.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=979&lvl=bulletin_display 20240724145619 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=979", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GLJL6XXV7IL4GB6TQLEYXDYNBYX5EUL4", "length": "9809", "offset": "110439143", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00889.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=979&lvl=categ_see 20240718195154 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=979", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4W4RWYQDIDCCMHFJRPY2VY64BJQXIBVW", "length": "10709", "offset": "108890614", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00887.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=9792&lvl=author_see 20240718134239 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9792", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "N7FRREQKDVGG7LIBP5J4RC6X22KDEZNQ", "length": "6536", "offset": "111705895", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00242.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=9794&lvl=notice_display 20240719093545 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9794", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2GWCLRA4KIEEM5UJOKC3BGGMTCO5JKOC", "length": "5173", "offset": "109966372", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00244.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=98&lvl=categ_see 20240712183221 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=98", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6I6R4UCSQF6WQDYEKW3JBUCTRTTONJUV", "length": "11383", "offset": "109957826", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00447.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=98&lvl=indexint_see 20240715053109 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=98", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5XDQWNLCIUEVQDA4AAVKFR3AZDS6DEFA", "length": "9837", "offset": "108910101", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00444.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=98&lvl=publisher_see 20240712175151 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=98", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YOSJQ35BRWQ6GO6GWKB23OUQXFNAI6EL", "length": "10292", "offset": "2926328", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00214.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=982&lvl=bulletin_display 20240718141243 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=982", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5WYV2AU7F3JEVRRL3GVML44AEN6XDKNI", "length": "9541", "offset": "109699565", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00013.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9823&lvl=notice_display 20240721141018 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9823", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3JNBVEOBRR2IRYF7NZYF6O3VEFQDRKE5", "length": "4944", "offset": "4087916", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00156.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9848&lvl=notice_display 20240719095701 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9848", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PRV7WILTPOE2SJC77D5UOX2LQKBMNIH4", "length": "5200", "offset": "103826450", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00154.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=9854&lvl=author_see 20240719100540 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9854", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TBL6RBGWNQJGP6HDHFOZBFGNIDBCZHR7", "length": "6659", "offset": "113870598", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00181.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=9860&lvl=notice_display 20240716150204 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9860", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QQRGXKB3VLGKSB3FWXSG34VQ73W4JXJM", "length": "5174", "offset": "111471177", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00208.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=9864&lvl=author_see 20240715055943 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9864", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OZTK5CFONUFD52O4PUZ6Z7UBVKBWIO6H", "length": "6899", "offset": "115256346", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00212.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9867&lvl=author_see 20240725185337 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9867", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PJOVH2UH4WZONNVCL6AD6CWZ6JVLQTIH", "length": "7230", "offset": "113797707", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00215.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=987&lvl=publisher_see 20240718142052 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=987", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Y2UHXNGFP4E3M4KGMMAU63TLBGVQOFKH", "length": "6576", "offset": "3340641", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00545.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9876&lvl=author_see 20240725195130 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9876", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JJUWXPBM6XMJAKKSONABPPWKJLJS3H4L", "length": "7870", "offset": "98937641", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00245.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=9880&lvl=author_see 20240718210647 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9880", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CSTC6UQIKC6X6MQKCMDBUHF2RXDTTI72", "length": "6637", "offset": "4355941", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00291.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=990&lvl=publisher_see 20240718142837 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=990", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ICWBULWCQRATH7VR6OCGGDJCXQFUONID", "length": "6473", "offset": "3383048", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00569.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9912&lvl=author_see 20240725201028 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9912", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3T54SYNF5EGMBBOYVUDIPSD3FRPQZ63L", "length": "7485", "offset": "2972838", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00137.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=992&lvl=author_see 20240718144113 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=992", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "R55C6LKIIGG4LUQTCJ53CJDSTQBX5AIX", "length": "6971", "offset": "112401391", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00615.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9932&lvl=notice_display 20240721003222 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9932", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JDK7R6TTCMKRCBJXUIZNTAPBA2N3RXIW", "length": "5171", "offset": "117976823", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00178.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=994&lvl=publisher_see 20240715055443 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=994", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DOCLYYTKLO3VGFJ3CM2QR2LGLW5V4QPM", "length": "11546", "offset": "4933350", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00573.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9948&lvl=author_see 20240715045205 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9948", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KCZ5BMCQY2TNGER4DDINDYLRDLWUAKEI", "length": "6961", "offset": "112770151", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00215.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?id=9951&lvl=author_see 20240722111642 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9951", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XNLTD5QGJHVPZP64RYK27DNI2M4R6QGR", "length": "6816", "offset": "109375717", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00239.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9952&lvl=notice_display 20240721011222 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9952", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GHDZ2F6PTR7E3HXHNFLE62POEO6HAN3Y", "length": "5149", "offset": "119444828", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00240.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9952&lvl=notice_display 20240721135021 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9952", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GHDZ2F6PTR7E3HXHNFLE62POEO6HAN3Y", "length": "5132", "offset": "5918750", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00309.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=996&lvl=author_see 20240721125950 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=996", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZOUXENJBI7M67SGACWZGPJTEZDM7SNAQ", "length": "7231", "offset": "109547550", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00619.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9962&lvl=author_see 20240718130816 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9962", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SVQ3IVLH7TR5MNP62VSUPOBGO5H3ATMB", "length": "10488", "offset": "110500556", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00271.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9986&lvl=notice_display 20240721125044 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9986", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WZR7LFJXY6XNTLVUM62Y7VIEO2URDD7B", "length": "4942", "offset": "106585653", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00337.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?id=9987&lvl=notice_display 20240721131717 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9987", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CWXJDKB3TT6SOOG3MLDZ5WNITNAXPSVY", "length": "4829", "offset": "106385331", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00338.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,missiondefrance,bibliotheque)/index.php?location=1&lvl=section_see 20240724145239 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=section_see&location=1", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "T2R7E4YPVQOYMRGQHN3NRFOWS2COTB37", "length": "3839", "offset": "6282192", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00847.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?location=2&lvl=section_see 20240724151311 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=section_see&location=2", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5UFNW7UXNFMIBLL7TKVC4ZJ7VJCBYHVP", "length": "3774", "offset": "3827684", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00848.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?lvl=index 20240712170635 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=index", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "X5JASAJHR32WAUW57C5WPMPQXSBAVRNL", "length": "9309", "offset": "3717231", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00677.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?lvl=index 20240721013634 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=index", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VMWOHIOXEUEMD5K3TRWDJVMTSEM6WX2Y", "length": "9318", "offset": "105264950", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00222.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?lvl=index&search_in_perio=31&search_type_asked=extended_search 20240718131846 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=index&search_type_asked=extended_search&search_in_perio=31", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VTEJEDUHBLT3RPAPLS7RTQ56JE7BX5WK", "length": "6995", "offset": "113337507", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00386.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?lvl=infopages&pagesid=7 20240721233024 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=infopages&pagesid=7", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LMUUDM5JSIU3TDI6NQUNJAWKMD6BQQ2J", "length": "3556", "offset": "5671966", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00020.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?lvl=more_results&mode=keyword&tags=ok&user_query=exp%c3%a9rience 20240721132718 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=more_results&mode=keyword&user_query=Exp%C3%A9rience&tags=ok", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GUES2HEN5MX47ZKWD5LLN676MSLERUAX", "length": "8189", "offset": "109696531", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00201.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?lvl=more_results&mode=keyword&tags=ok&user_query=syrie+jusqu'%c3%a0+333+av.+j.-c. 20240716150405 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=more_results&mode=keyword&user_query=Syrie+jusqu%27%C3%A0+333+av.+J.-C.&tags=ok", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UQJR2X2QPHX32TEEORY2JWQENRTKJNCQ", "length": "6485", "offset": "3310893", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00268.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?mode_aff=aff_simple_search&search_type_asked=extended_search 20240721215228 {"url": "https://bibliotheque.missiondefrance.fr/index.php?search_type_asked=extended_search&mode_aff=aff_simple_search", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "IQ4RZ7MIMOP2PKKUAKZH2Z7DVL5Y2PBF", "length": "5687", "offset": "111907687", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00679.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/index.php?search_type_asked=simple_search 20240724145043 {"url": "http://bibliotheque.missiondefrance.fr/index.php?search_type_asked=simple_search", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KJWZ35G3RRH33NZXMNCQXAM5W4VSXVJA", "length": "10101", "offset": "2733680", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00824.warc.gz", "charset": "UTF-8", "languages": "fra"}
+fr,missiondefrance,bibliotheque)/robots.txt 20240712161634 {"url": "https://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "765", "offset": "571443", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/robotstxt/CC-MAIN-20240712161324-20240712191324-00185.warc.gz"}
+fr,missiondefrance,bibliotheque)/robots.txt 20240712161907 {"url": "http://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "722", "offset": "48901", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/robotstxt/CC-MAIN-20240712161324-20240712191324-00890.warc.gz"}
+fr,missiondefrance,bibliotheque)/robots.txt 20240715041153 {"url": "http://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "722", "offset": "39529", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/robotstxt/CC-MAIN-20240715040934-20240715070934-00890.warc.gz"}
+fr,missiondefrance,bibliotheque)/robots.txt 20240715042232 {"url": "https://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "767", "offset": "712678", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/robotstxt/CC-MAIN-20240715040934-20240715070934-00185.warc.gz"}
+fr,missiondefrance,bibliotheque)/robots.txt 20240716142519 {"url": "https://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "765", "offset": "556987", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/robotstxt/CC-MAIN-20240716142214-20240716172214-00185.warc.gz"}
+fr,missiondefrance,bibliotheque)/robots.txt 20240716142846 {"url": "http://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "721", "offset": "36790", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/robotstxt/CC-MAIN-20240716142214-20240716172214-00890.warc.gz"}
+fr,missiondefrance,bibliotheque)/robots.txt 20240718130815 {"url": "https://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "758", "offset": "620127", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/robotstxt/CC-MAIN-20240718130417-20240718160417-00185.warc.gz"}
+fr,missiondefrance,bibliotheque)/robots.txt 20240718131103 {"url": "http://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "722", "offset": "35421", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/robotstxt/CC-MAIN-20240718130417-20240718160417-00890.warc.gz"}
+fr,missiondefrance,bibliotheque)/robots.txt 20240718191949 {"url": "http://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "724", "offset": "52522", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/robotstxt/CC-MAIN-20240718191743-20240718221743-00890.warc.gz"}
+fr,missiondefrance,bibliotheque)/robots.txt 20240718192520 {"url": "https://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "757", "offset": "491992", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/robotstxt/CC-MAIN-20240718191743-20240718221743-00185.warc.gz"}
+fr,missiondefrance,bibliotheque)/robots.txt 20240719074558 {"url": "https://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "756", "offset": "486032", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/robotstxt/CC-MAIN-20240719074314-20240719104314-00185.warc.gz"}
+fr,missiondefrance,bibliotheque)/robots.txt 20240719075211 {"url": "http://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "724", "offset": "48990", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/robotstxt/CC-MAIN-20240719074314-20240719104314-00890.warc.gz"}
+fr,missiondefrance,bibliotheque)/robots.txt 20240719170546 {"url": "http://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "723", "offset": "60002", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/robotstxt/CC-MAIN-20240719170235-20240719200235-00890.warc.gz"}
+fr,missiondefrance,bibliotheque)/robots.txt 20240719171238 {"url": "https://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "752", "offset": "490181", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/robotstxt/CC-MAIN-20240719170235-20240719200235-00185.warc.gz"}
+fr,missiondefrance,bibliotheque)/robots.txt 20240720235924 {"url": "https://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "757", "offset": "762089", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/robotstxt/CC-MAIN-20240720235600-20240721025600-00185.warc.gz"}
+fr,missiondefrance,bibliotheque)/robots.txt 20240721001506 {"url": "http://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "723", "offset": "33797", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/robotstxt/CC-MAIN-20240720235600-20240721025600-00890.warc.gz"}
+fr,missiondefrance,bibliotheque)/robots.txt 20240721121807 {"url": "http://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "723", "offset": "51177", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/robotstxt/CC-MAIN-20240721121510-20240721151510-00890.warc.gz"}
+fr,missiondefrance,bibliotheque)/robots.txt 20240721122125 {"url": "https://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "756", "offset": "555138", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/robotstxt/CC-MAIN-20240721121510-20240721151510-00185.warc.gz"}
+fr,missiondefrance,bibliotheque)/robots.txt 20240721213217 {"url": "http://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "724", "offset": "49742", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/robotstxt/CC-MAIN-20240721213034-20240722003034-00890.warc.gz"}
+fr,missiondefrance,bibliotheque)/robots.txt 20240721213731 {"url": "https://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "757", "offset": "561307", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/robotstxt/CC-MAIN-20240721213034-20240722003034-00185.warc.gz"}
+fr,missiondefrance,bibliotheque)/robots.txt 20240722095224 {"url": "http://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "724", "offset": "38634", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/robotstxt/CC-MAIN-20240722095039-20240722125039-00890.warc.gz"}
+fr,missiondefrance,bibliotheque)/robots.txt 20240722100047 {"url": "https://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "758", "offset": "611179", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/robotstxt/CC-MAIN-20240722095039-20240722125039-00185.warc.gz"}
+fr,missiondefrance,bibliotheque)/robots.txt 20240724141215 {"url": "http://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "723", "offset": "37142", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/robotstxt/CC-MAIN-20240724140819-20240724170819-00890.warc.gz"}
+fr,missiondefrance,bibliotheque)/robots.txt 20240724141602 {"url": "https://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "756", "offset": "564386", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/robotstxt/CC-MAIN-20240724140819-20240724170819-00185.warc.gz"}
+fr,missiondefrance,bibliotheque)/robots.txt 20240725175732 {"url": "http://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "721", "offset": "36834", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/robotstxt/CC-MAIN-20240725175545-20240725205545-00890.warc.gz"}
+fr,missiondefrance,bibliotheque)/robots.txt 20240725180355 {"url": "https://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "755", "offset": "627917", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/robotstxt/CC-MAIN-20240725175545-20240725205545-00185.warc.gz"}
+fr,missiondefrance,bibliotheque)/select.php?auto_submit=no&caller=form_values&date_anterieure=yes&date_caller=&param1=bull_date_start&param2=date_deb_btn&what=calendrier 20240724151114 {"url": "https://bibliotheque.missiondefrance.fr/select.php?what=calendrier&caller=form_values&date_caller=&param1=bull_date_start&param2=date_deb_btn&auto_submit=NO&date_anterieure=YES", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GWACPCVL6E6S2IZ2NCJMQVXA3X4E2ZMZ", "length": "3324", "offset": "111935641", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00413.warc.gz", "charset": "UTF-8", "languages": "eng"}
+fr,mnhn,biodiv)/fr/taxonomy/term/1017 20240719210808 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/1017", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "6PWC6QZLKGZ4C7GBJ6PG7XFIUFOF473I", "length": "8730", "offset": "108450574", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00876.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,mnhn,biodiv)/fr/taxonomy/term/1023 20240719204155 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/1023", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "XDSO3L2DMI35PPGCKTQKEDMB2F3V4MRP", "length": "8797", "offset": "116676062", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00003.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,mnhn,biodiv)/fr/taxonomy/term/1025 20240719221032 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/1025", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "4UP33YIXFFRZDQDS6DYKHQVJSG6KZJ62", "length": "8801", "offset": "112460055", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00005.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,mnhn,biodiv)/fr/taxonomy/term/103 20240719212230 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/103", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "4UZFS4HFOEFXLD6IL4DBOK2AWBOS7CHP", "length": "8938", "offset": "110435689", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00053.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,mnhn,biodiv)/fr/taxonomy/term/120 20240723092605 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/120", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "WBM6SZL2DX3RWI2K44QLSJODESS6A6FB", "length": "8862", "offset": "107100378", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518029.81/warc/CC-MAIN-20240723072353-20240723102353-00112.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,mnhn,biodiv)/fr/taxonomy/term/136 20240719204102 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/136", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "7NP5WWF7BVPJ5NUPDJZLR54HDPE6ULDL", "length": "9139", "offset": "114748215", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00149.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,mnhn,biodiv)/fr/taxonomy/term/142 20240719215813 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/142", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "4CKVR6ZATYKTYEPBJVET5YVBQ5H6EV67", "length": "8904", "offset": "109719400", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00176.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,mnhn,biodiv)/fr/taxonomy/term/182 20240723092214 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/182", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "PEXQMEW2WCIQWYYIRAUHLVKHVJGR7H2O", "length": "8907", "offset": "105425196", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518029.81/warc/CC-MAIN-20240723072353-20240723102353-00300.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,mnhn,biodiv)/fr/taxonomy/term/190 20240719224448 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/190", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "NNCUPPD54EHOGDBX6XSW2IRJARNB3HOU", "length": "8957", "offset": "111963925", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00329.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,mnhn,biodiv)/fr/taxonomy/term/247 20240723180128 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/247", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "5JJ5265Y6BKJ3EFHNNDO5PIT6JW75XGO", "length": "8850", "offset": "116773154", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518059.67/warc/CC-MAIN-20240723163815-20240723193815-00242.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,mnhn,biodiv)/fr/taxonomy/term/25/feed 20240719221158 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/25/feed", "mime": "application/rss+xml", "mime-detected": "application/rss+xml", "status": "200", "digest": "5BJF37C3M7RMB4H5PB6TGUX5UU23UZYY", "length": "1089", "offset": "113330648", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00347.warc.gz"}
+fr,mnhn,biodiv)/fr/taxonomy/term/258/feed 20240719210308 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/258/feed", "mime": "application/rss+xml", "mime-detected": "application/rss+xml", "status": "200", "digest": "BHQ645JWFI5MY3TU5MGHUTF6PJGK4KLR", "length": "1049", "offset": "119385775", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00059.warc.gz"}
+fr,mnhn,biodiv)/fr/taxonomy/term/29 20240719220806 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/29", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "6F74DIIJDPXADX3NPLLJGGCJWN33B2JU", "length": "8663", "offset": "111332665", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00298.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,mnhn,biodiv)/fr/taxonomy/term/295 20240719224813 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/295", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "SISPFF2OZDZSBZYJ4DJJLW4HQQ7PALGT", "length": "8937", "offset": "113487891", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00395.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,mnhn,biodiv)/fr/taxonomy/term/372 20240719222307 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/372", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "J5FSMMHHGHBE4Z72OXIEXSZQUP2MJ7PG", "length": "8538", "offset": "112935403", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00391.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,mnhn,biodiv)/fr/taxonomy/term/377 20240719210017 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/377", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "VXDJ35C7SIUWENPXTG5LRHN24E6LUT5B", "length": "8749", "offset": "113454441", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00396.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,mnhn,biodiv)/fr/taxonomy/term/382 20240723093403 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/382", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "TWUAWHFPAW2FMGHZ4T3V4OAODEIHGJT2", "length": "8658", "offset": "108141805", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518029.81/warc/CC-MAIN-20240723072353-20240723102353-00422.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,mnhn,biodiv)/fr/taxonomy/term/430 20240712114115 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/430", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "6FBQEWWZPSQ6YI2LAROTUIK7PTOKKUI4", "length": "8560", "offset": "90166484", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514387.30/warc/CC-MAIN-20240712094214-20240712124214-00326.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,mnhn,biodiv)/fr/taxonomy/term/448 20240723180031 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/448", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "COULGLSXTX7IJFCAGQKP5S4Z7AL5A3OM", "length": "8544", "offset": "116564582", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518059.67/warc/CC-MAIN-20240723163815-20240723193815-00365.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,mnhn,biodiv)/fr/taxonomy/term/492 20240723172943 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/492", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "WFUYM6SMJL3JQZZODYIC5EJ7HERPYEFS", "length": "9014", "offset": "110092666", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518059.67/warc/CC-MAIN-20240723163815-20240723193815-00514.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,mnhn,biodiv)/fr/taxonomy/term/547 20240723171240 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/547", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "FAH4AWWSLQLZDAPBXC32SXM5LQVZ6RNP", "length": "8531", "offset": "111634062", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518059.67/warc/CC-MAIN-20240723163815-20240723193815-00425.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,mnhn,biodiv)/fr/taxonomy/term/548 20240712101216 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/548", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "RTE4QU5YDNZCLYOLZKA3FMUDZONQTITS", "length": "8573", "offset": "88514768", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514387.30/warc/CC-MAIN-20240712094214-20240712124214-00426.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,mnhn,biodiv)/fr/taxonomy/term/557/feed 20240719201257 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/557/feed", "mime": "application/rss+xml", "mime-detected": "application/rss+xml", "status": "200", "digest": "RIEJIECICB7XS2J5MDTMFXDJTDPJFMF4", "length": "1055", "offset": "109941332", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00717.warc.gz"}
+fr,mnhn,biodiv)/fr/taxonomy/term/566 20240719213116 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/566", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "OPGIVQ5Q5ZSQDCLAJJBOOZTUKF6ZQTDN", "length": "8590", "offset": "110959283", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00486.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,mnhn,biodiv)/fr/taxonomy/term/664 20240719204905 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/664", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "PLSFUPZXHOKGOPFOZMUVC6TG5QFIMWUH", "length": "8749", "offset": "113989689", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00545.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,mnhn,biodiv)/fr/taxonomy/term/69 20240719223102 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/69", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "QYEGFD4NRZVR6ILHHRCJ64JEVZRRO7J7", "length": "8778", "offset": "119181746", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00422.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,mnhn,biodiv)/fr/taxonomy/term/731/feed 20240719221243 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/731/feed", "mime": "application/rss+xml", "mime-detected": "application/rss+xml", "status": "200", "digest": "US523WAQAOABYKOO6UONEFQUV2KDEP3S", "length": "3416", "offset": "117494461", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00271.warc.gz"}
+fr,mnhn,biodiv)/fr/taxonomy/term/742 20240723184133 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/742", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "HY5URRLP2KH7RZCSJIAUDTOGJVWGFMPT", "length": "8751", "offset": "102351348", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518059.67/warc/CC-MAIN-20240723163815-20240723193815-00542.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,mnhn,biodiv)/fr/taxonomy/term/753 20240723183300 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/753", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "HKU7SXS5E7RYOSCJEDHNPPMAB33PCJEJ", "length": "8756", "offset": "114241930", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518059.67/warc/CC-MAIN-20240723163815-20240723193815-00574.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,mnhn,biodiv)/fr/taxonomy/term/759 20240719204536 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/759", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "5YWVB7NFAVL4JC4VHICQIDYGSLAYAFIX", "length": "8764", "offset": "109343145", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00580.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
+fr,mnhn,biodiv)/fr/taxonomy/term/768 20240719211110 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/768", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "RPBB6KTJUDYWEY767YQZN3IGX7JG4BBI", "length": "8763", "offset": "104917490", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00610.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
diff --git a/tests/data/warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.gz b/tests/data/warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.gz
new file mode 100644
index 0000000000000000000000000000000000000000..47941edb9c3bb5f953bedd593380e8ef00bc3503
GIT binary patch
literal 63684
zcmV)PK()UgiwFqz+@)v&|6^o$Eif=KI5z;?y=#vpx0NmUeSSs59}En}mV@NpWbgvU
zAl~nH1mp3gA=_nJfGm5g(%imxF#mlRsgza4$dkHtP6SW)xPi7$sg#kKE4aBIYp?a^
zfBxog-+cf5H-G=`PappL&#%Ax<A>k;;hR5v`_11!{`JHE^}~n%{deE!fAAk){o}9y
z_&>k-)9)FPzy9|B{`U8O_~F}cKYaY=yMO=FH{bu`+pqt}zfp&RBM2wR2;#r}Kfn6n
zpWpuKzx~^<{`&FbKfeEOzx&;%U-K*DfnWXkpPxMCtuO!UA0Pdz-~8LJ{`Sq^KI~uk
z<A?wF_`AP;{M)xb{o!x_^x@-&KYsl1r~RLP{f~cq`^_J}{-~ewyZ_k#*8lMzKmN_{
zKYso3hwt~lLLF!SgFk)qmk-~6-2WiNg2mGu_Fhv}V;<08oRui4=f_!&e!KteZ$EtZ
zmydtl|F#qe`=9*%&wu{@!^^)<2mx@A;{L~f{zm`RuYdej|M<_Z|NFPU{nOVUzy4hi
z{I>G4`nUV9>$lAL-S;2<^0yD)ef<7+L{LX?h6Du4ubBAVfB*WQfBfvPzx;NAQUX7J
z6fYkghcWTh{x5v>m;bpx{EvVA`k$}g)HKGwbzi>oufO}t4`1t_b^lZSd;it{`@jA9
zOQFXX?7#lu<6r;&&wu~^!-t<xcL~#|^UqQLV$gs7y038KwRmGyR%zJzdFl_CHwg>6
zwJ)I<p<ykQ$>(@;S2&;J%_wL*9z@$^<SWA7L|gw>9U$W8kNoAM<4}a_(WcG~u+c$>
zqc|6A>RgL;xfN~MA#3}%?($a6S<%)jlzCR9eh_V+V@(_(Tmx*z(RJO&z~=gBQ~D;@
z=zt>`{QOb8d~_Tn!W!5wfB4OJA3r<WRKJGkJ{r+K{nAztXPy{g;Y<urM+q&*DUE1a
zkHIR6F^dhvbs%-kXzuKYJM6*ptszH#<9tgZfc@*Ej^+DDNB_sl`KE6laEe4aK>67R
zoL+o;$Es9SA4G|Y>D0z)7*q_`b=&HwYJnSg3qp+p&h-g*$OCA*`g%tCmFvERw*IXO
zM8JQ2q|VDnXTQ9^6z$*WpW`0H#f^}z-$O!~eDsVTAQ#s{-qum?GZ=X~Oq*b;P8p||
zrt`SAx&C7_s8eQOP8`VrfIWD|^{?-%x36&hPxMpqUmx|4uz%E`e|c2@&9`5FyaRM{
z19Ph54`uGzn3HQEhhU>Ibe$Tyd`<kI3I;{_GS)%HgQPcdbRENmnWQ^}bC(eD803J?
zSMc^tPIX?cQ^TJ>%9oG(K_?c%I(fG~)2LJKJes_{S)N@D{pi)3Kj&(wYHw4c9|vha
zEz7*-Jm7s77y%y50M9jclJF<s?g&c(o{*b4JJ*Hj=>eWx40&4>lh>pH7b@TCzMQZw
z@^JEF8Z1$co>8HpkY*0YrNbOT?5FKIgZg67^*4AA=<ovicYpu*%^yD)=UpQNI?g}b
zkNNzIzk(0fg71}V>6WBKl`FM{OUc$L2+9dq7p<YUeh$7)uZS7xL8n&q!OL9;hkPa9
zOyKn|ml7n-&mZyS;|@Mri1h3Qcl}%a@Rv{1cS7}lIq)dt|N6Q=qRp-ad+AH)FjCmF
zU@Y4*&6Ve4TB$)7=>0mG_d226M4J&10-XoZmi#M9-bQ;bg#UHass0gOKI;GCj-~j{
zZdd7q0eigfdaTkf#@(;Iw)IP|Y*n#hx&T*2Q;3q~Lr9Yb%@iKYzKl-cUvS~}+i-W>
z>vv%OW6$-EfB*K|&nq@pCpeGhaX)?4AECau-5Pd_s+ytm>%eQ57}7OYRl0Ox>2+1L
z`bK+QU!$KRji7(;60MhN2*lFyM(1{|2Es)9@$?NZZoxHeh%l8?zpx=*_~6CiP~;rC
z2?CmJ!pPXAIF#o^=u*u^`#C$|XbW_4bEpE2{^?H#{o<y~xG|lvw@H%v{pP0~qea(v
zb)F2W9;;<GBf5s@(0J8pls@eCBf9>#pN+aCj>9RO+<d(nbX9htTIVWnyE*_idyNo$
z*<!^*KBa4V0G*iQ72-;CA8g7<$N387+tJ+-z<!>b>fiFqM-91Tb|HVWPJ5Y~JC3-b
zPP-cWxX8N|2ex8V^Lom0NIO1Fo9J)}!g(<2H0qGU*qlq0@(E+}JI?zZ!1G&UbLqI~
zn8o?SXPsZ1$HnPd)hxk9jJ_HmOzT<1surynL^x#z-Z~5$@tt$-x}4ZQ>XhCU-GB4#
z$NzZ;>f&atreWVlix0wnEY&VP=a6_=9tU%l4@Do$Y*s9-m<m}~^z%#)7du0PFM%#`
z8FTCd?@$}ZT-?as_lAuA(NE9b#l_isGOK768$cIz(bUp#uKgOPhGt0-_d#czb8(oo
z5Q>OQ68jw)O2540{-+N=+yS~PZ<cIaUpja;=<dZFIK`)V?7Gb3ISp!_uGze9yxJJ&
zBc{`Aa-zV<<D`p{KiY-6t74<vMmI*n?Yo>JoSnDJt9$H8*kHJ>bI_$3PvS@g-ZWHe
zrl6(8mKzoNYxMpkZI`YqD6=2Z_5ZhlwtFL_13}7wpMAQedvOb{-u$s0w~Z>whOqU<
zwFs89>Qo(j`Hu~^PeM9%4$W3B_EywmG&omR-(L}UGo-^y(?kCJQM`QA$6H!B-t5=k
z{`<%O@sB_K{g1!@`t#w+umAS-H{bpK*Wdl&pa1^tH-Gu=!}q_J&aeNWANG6tNdzGJ
ze>~cf{cP;QUY}t+_{VSN=kN8}w<ZcI)>qyzR873Fs2s;iU{NvNl`38e|1g{Rk@xfS
zYXckzbLkTjKXm?czBK&Pb`NFZikF5z^`%LN7^<P{y`WbC>uBCiZMiTuuI<uIwJ={A
zO3jx>A9*UDP$udm@(C}^XXV`Cy%Bf}HahL0r_cM|3OM@VcHbSfP=D)ioVJKX4f3Rz
z)_$Hcm31MV%0o9%-wlVs0dt6aPCrrnr+s_yleY)R<K4zvZx258?V(c&lM+)5$;#tk
znP8}sc|*^iyQWDB^X(zxFn~bNc`bcH>~V=}ryI@QrwQ()e;r^hS>s|Clg3IFW%ZKL
z3B%4SRY>P~7JL+aFou)9g3SKpkLAm!@Vi3NS9+6O;y;rX7^1Jxo4lcY$c*A~61b6z
zTnzRsR66);MXR=B%?!Gf;R9VVsM40tV{aaI35OXo6B=*wgpLJsr8Ttw@q_*=-~aW)
zXFUt9zi;~R{Nb}NZ3T2)z~)IIaO>2RG##(Es$pIxR*y|_y{_g7=kB2%aRhSv^CsuZ
z!}~pm%Ug|TU7za2=;W@&<$Jlxi!)d$jf!O5ingXKnR}6|MHTsknL+$^`LS!^B6VGd
z+b4qRV%XAsPH&Ez^yNZzUUBxgiCw(UmBuY)TQv<i3;MPxVzH!Z^_p%B+Hk|gpo_ik
zW`1(Wbpj(F9W&lV_XpQ1<~NAnI^xhv2nAOI4|UUE-H3MXlWjoomn7m%RC+~~G<nsT
zd;&PkorL2``HZ>K9moA{*uVeb4+beze_u>T<40!@pL}6Ec#p*p7q|^xO4kOKBmf`t
zw(e$8@h~y?1e~L}xVaNyC9{t<M=NN%x5vr=&e{AxMlYU0bZQ>zc7uFthJ?cucOBN=
zl*gqS2X&;132rj|by$}A#}`jH-(UlA_7>xt5@*lWA1}{7JK7hs`<ckPEStO@OFr_x
zQ%lgLaXcnX74fbpO{^UT$0dA;{K2g~fdF5@+iTf7$(uVrr)~~?`RF((q@`<|-K@}F
z*0%s2KI3ncXjdbjwY9(HzTc}h9I9z8rlRySR>kEQjI+6oPtCzH*;ltTG+;kxM~OBL
zIe(W8%9-<cXn!kt`*Bg`!eVX9%d{-wCTfBX#~2j^6;ysR=DaSq#mwI1feniK=YK8P
zZL>iw?Qt=X?=V8Sb25uWKknjEtyqg;Dp(^_srnX09<NQWwu<>{N`-OQrNfL;4F#u6
zh-WZDzkJK%E;cB`8#(*FK#VRveAEv~`^6++zpMuq_Bm^sB(KY^kC@8p9HzBfrgUZp
zo|qZm$sXVyWs=;rnayqKt*~259y@&q^*wWT>V7rTzbKQo-(oLPUbl>xdQHAyuEs=^
zIDx6azy%S9*zO2dKDeuSAAQIg==^3QZWm4y3{P*wU3{Z^aV2uD)`a3%`lDL9GWVlK
zgcDn)HXh6*9?gX=U8VAe*SYS}U_fdM^jox0ooq0P?Cg`yFXn}&(9*ufrQu`a_vtjZ
z#fV#w<O;&5Y;se0<B-KsSGY`2VLywb+(wNq-s`>YHJfCQG6CPp-o?eexO!1ZSqR4S
z*qhQNDO%)P&BtL1x?%lscKT`d&WWj#s8cOK`|+KjjajPuWxN{zgSAC>oi*Z|&%1Ho
zpl#`=+a=zFovMbk?o)rr=g^CzK-5v#!03xSi}U)h1ZsBnq$CVn_JmQq088uM%)OZ&
zaDu==Uhr~U3wt#W#lS>Z2YggrE2>J-H1^k|%93eGrvu;WK)BJz!le?NCk*7lR$3@;
zZu#r95Kr&oUtICyT=+9KO{*er>Y{|FN(}|{g=*`D#<RH_<{ZjD>h5bo?h{m7taW+h
z+dL~*r-VSsxs>m#J3M2&VupR&2jN<=Bxh|w%PC`dR8}(>cuQvP0y4gLSDAgZ!3vpM
z-U{mave!ijxqxYVG2m@FkHHo;S=x_HA1x8mqJgwiIJRBJkCPjaM-nY{UkeqxlN$%X
z&IyMb2b?-Ot>EVpDK9SgiY*;^0Y#vOsGs~~2s*m2_y>ZAG^N{N$LA=uh{$w)<=SV>
zQnWz12j@Ncj(r^i5zepp;A#zJHuKi=pkUtWMNKx*pj0AFbzH|hD$>fR_#9^74yf;O
zf=}q(I~KT<K)$TvW90LSZ`V=>B>e22ACNZ+KK*dJ1t0fm*c4@xC}^Uk>9V<Pc?BXW
z2Rel#H7^O*J!r1G90a$ox$e5$&dc+rKqq17p1dduS1(m8D(j=5%P^)s*U7)1t4`Eu
zl}*7kH)aCJsgdyOn_1UgPhj8zG8;(CoBdxM0SG<0yo0ML*Iqrr7IoeV8{f*Z<w@6Z
ze+}|H+OW(`83^vMqo$MVGU@#PRMQFQ7cBk$)SY9WTnfZ_T&&fI0QB`K#-lB-{mxKF
z%N)cp@8W1|GG6Q%Wv-@jrcH9NWMIx=A7|If;SXs_+<7Tb!tCio9p9i|$Sj!g5&_Z4
z81mCA%eUVnW_tygs$NW8GZbOg&U9^hR(oyf(ITn1m<*o>{k|MFfOji4cyO)ju2F<8
zRBQwwxGfvX0M7RH(9gSAWTN#dppn;1P1%h35_bKz6+#4c16{tFOFk&&0q|Wk^ik!Z
zyHrD^jY{M_?Qe+^E{Fsdb42;%djX1cQGT^mahtS#kIgVQjKzVzJPvFA+{`lc53h?)
z_6&<IZiyWX@Fp8v$0pQw=c#OPxcG>#Z66kK&t?(PiZyiLtyivon|CW6rhGjRN$@}l
zrmidGj~Zxpa|3Q`kq-cGlEyfdkNY~9fgLVp3bvx(C4u{@&Wmp5dB}$Vi(X}_UPnG3
zeE6Khx`*THobV}{Q#Pn1`r5j6lhfT=;$(SP{kV%qgZ(rQ{m`zBkG?7eZ^Lxo@ma#E
zo?Fix4N7Soa{Zb!_t9DKUE&Llw1M{RP64N`b2cYbKks6V|9lwJF-_N~OqXd2x3R11
zwWg|JydIgc&Lv+v7oT+sUaaWY6PRL>TZ-woK;Mfv#?Mxbyd3j%D}odY%9}jiV3|Zr
zsh6&ptEy_MemqQrO|f@L7(S>Pc^^xRSaM<mep_{8XM6y_`8!>3F%g*8wF*+vcAY50
zyuy}aTo!3FihN^{Nd)GCz;PtZ!3ANzMAMm*9lK4qDfYg1f+>+FAN8xn-rG4TQnq&O
zhAio$sH)PY3C5usR<0;DMm!Q-Qy|ve#m=8V17=`BAQt#Lw>e>Ow&u5f-o<bSapp&B
zmbF>f_<k^UOjJSDv(k?ekw<3VpC5Q#JJ+8``2@hJwb*`JUk4oNIA<U6i!qNQQF?3b
z&9KsR3P-W(94_4ycxu2xnX6o{%h;a^tw?m-C%7y!TS6-!$om$X4nc7N_d{G<sxkCB
zSbM13j&dqsjH<3`qODpQrcb;f><iN5{D4lgoCi6a_YHN4jZ#hg!iqK}m+0%f5+W|#
z-DI>GeUEiC^s<TheOyLiU(KvR^w-uj>>&p|EsDa`Z^IJ|dl;e(;NN#@0&vm21o(@&
zUP~6VQ`~t;m}Xuc&9G!;;T6fo<E3uZWCCwSda^rcJH#Q+0Nw^+N4W2}J1};3D^6Uz
znE_c{MZ>7#GH!-=^SYo(6R#KXHZMUR1}3TVRc_<cLVfRnK7riFgsrRnw!;JHU&q<G
z+{J*elgDP^6>*sKU5Hi3`#f5^aie3+X_p_=P|dwfrqck&eZtTjU11gQBPmaR4+PE?
z;=da1agNhQ_-UIq9n@Jchn`;yr7ANHTO2Qkftoznw}_v(WOga~z%8t0fcxHB#=cR0
zIxY8Nz?%Zv3jDO_g;?2Igk@O^ov&wMl_g2tngQK0+cCIvV&EA&8LlOz6>x76W6<Fa
z;OP<l;-Ps`LE9A-({=e6B0`2tKus5Kj&kgjv4|raN)Ixq`x2CW@da>fr0Tc)*L2#b
z^O@5fn&4{xwY3RY8w0eotH&r)$wWC@<893`t@4POqZLXH4owbc4-4kGz`qi2_Sh+P
z<h}*+uaCMK+&@~9GY3g-Hs6>d@N98wkQeu0>U#B)A&$~5TV|HT_0YC?<cC3C!#t#c
z>A*&hmR!3?Ac|*nVJyk3z)c@EeZlA}hMf-j#rJqLws{Nrm^2L_PttZ?5-)61j!>3#
zG}`QfxOh}F--QyKCuDBK67dbckRMHtn^%-QZoqlS@$jw9D{7e@-K0V!Q(8nS@4}Rg
zG!O!7iZLDP3e<7)3XW7d>OSbNbtjdM2n%%CJKrAmY5E`>dDYv)p8EFCnDU~`lC{n9
zr1!Ipv)mV5%RS{c5SVukIXL?|oV)t<ah{Q6pp}>B#%)8;1%7S?aq$434l^GqFO`^5
zT|DYiF%WZ})M*$2g-jh5a)?2)*1vs;&k$gyoZEu>22Tg5c(@~Ur0HA?c+FMOCg4Ya
zX)ZQz3%Oq=y;sh2jnx#JZYgHLxVNP_e}*s%wQ;naTjp0{Z;YJU{=<t6+LwOd(?|;;
zSi`3-3WKt)iwv3mu=Sm(x1~`rdjnFZ@Q+Hc-XpiA-w%6GA2%l$2lgn^pDs>Z4Rp$r
z(jT^9Tolw*P+}E`i7F-N+~v_^I2uYxOq^ZG<U{((_ijy4X$|Kal4?4YaL>=;E(W}c
z`_5~-3WA{uL)DaY5EF-`?-HRAPY!b&aU9XR`m5p-M)Zyi1JqZ{Z`|8Dp&;b^d;4P0
zy|izlIhe&#ByqHKZJJJH$&$@4tJt5a1L)M~3g~KA=T71ol4`bk0*>>Z2oKpsCfEhc
z40NuJ@ZJdim}Ldd&7u$@;fEsF7F<$VB|~pAu@1b;z1=Q_gl8BYTe-{Gy9~U&gpij2
zfAJ2i;y8~}=ZgT6aoM7_$<>;NWjE+*d@UOjcyeg}>SRWr%O{ZVh_q3kIruK{6b~eg
zlYqatOpBU4D*D``74>077Up@<;pDXo*F{=@Ch*cdC}{2sScg0VcpD8o=XTGZIQo`4
zxeMc5-10Buq?!B<S)$Mnn+?6bRY|OPUu@Z`4&ulT<z`)uKP_)s?!!<Ef;z8Dus3WI
z_MiQ1uEy1Suq@u{G-Fc@VhP8V%~MwUxIxj3Q$5U`X^La+J)=Hwj0yXLdtze`76~^y
z^q-u_PnzTSs&ogR%ysntIC*7q|8{<SjPYz+EqO27X?k10r)ix^5%&pVR;v-Rd8LJK
zv}uKV)K_DiyI{Y>XRak-gqJtwZE`NruP?)shrq8r?+f>C(s1>8>c@3ISN;M$_r1Ps
z)@B+hXIo$z9J3?UgL7R9Jh(Zne|ulOUGM3CvR?}S`beFZkNf|3Y+?QmA)7Gjo{ss&
zSwQN8hikd2XwA9el?PRkuDg7?$7dde2SzqKtjp`8NZF%J+q(o;nT<Sv-V#lhOdvg1
zG7m3yQ|TK~7C~3ULE89Lps*iAmHE@)(G1ek6wxL}!5iuj7u+9RU+k)30NO+QZBZ+o
zkv#5vdQAH+#+*VMx9FAWT8vFP$7`E)#poqHBn{H(kmtW)jX=078F_+`nImmve)QdC
zN{8q-{tD+)q!%arL#M{h@3`<+nt7FKvS?mwFYc<X4pm#4O4@LA$D@vXR0-w25)UmY
zp&*0XeBFKF?CcBuYTbOMZ}MsD*Q}rCKBj$DRek5tF6Rr=iCk?Op~!>Wsq5(TE|`5P
z4V4ylFc5ASpYA5>2=q}pzUh047vnu=`38C07NJ;&o_3z9l6<JPrCu5)HiKQkrE5yx
z=(Fa!VBfl4mq?b5IPiB|Pj#Jn_7T5Y_9pJTpv`nx51GG~B`$uPD=%-CZ5^|bo0=Fd
z9*(#!)O4{7PtZG}mh7z%-$~?vJ>IW5=5ZJI=R2|LbI!_m%Dghm0@#{9j_YaSUeNNE
znYp{mgxSAikNX?nB}Yqa4CLMcobG;l7f@&MYWqTw)^##&Nje4SH%k|Iu@Fm`ENbu$
zOi7)l9+WCU><uw)zgp9&oDIyy`$JgfJWRWID{;Tt)*3{Z=W8%xLC4j@v}|?Jp3`Iw
zsaJvUO<4rj=*ghVD8(lT-~jz{qpLrC_~9Pp<vYmlTEv80GKIZb$*{()WI^B0Sqdqe
zJT+$Rlwy!BL9qBkahSp$Wab59)L~EH)-fBdS9n{;P^X&v_?e&2v${B+E7p?MMM2qG
za8ETJEkv||-}@|%mu+s$eC{An%bAdZ+fU)|*`dBKo8#}ZZD5Z;7X*5Kwcz|lhqMj?
z424?TqK@(|4ZW-nY7}FDo!Oyrj6lzI5#^F+Y+53*an^6E)be9S_i){IwXR)Lm1&(u
z^OUJM3&L_$-4>)RZRRa5;#M4%EDf}G4v_nxWz}6(8#s5-DSxBC$vaRNw+Alp@UD|F
zZxL6^-|%c`6&FofLp)Hnuq0`^1bN}-UgaOQA`eoAz@>vv$lpQQny9)rO^KZo<Pr?L
z-K$N4>S3x<R<*n@f>vNK<pO#ZE@PH7>@ZEmW6Ry4lsWPVRXU(+M-WBFu=kBiDS=Bk
z)9%H2+{k$!MPu14RY=FK%}N!E2FAn}8}p<2;9Pnr*EMp0><RK_0K(RB7q?iHl<D|$
zdNbC&IK&T0*3zg<+tq8c+MhY6#iY-DkdIs7rM{WGljFRF5sA(dI`Cjit`={K;*giU
zc6xFmceN%?n51Jh<;qXXscq)E@TPf<+cs*sC$h#^jNt(6P_R+JClqWTY;oh{m&qLn
zW{73z7lY}1^z<gZd_ycl*!B_>epzrRV4l69@%$0<G4s43j`OUF6LIhvg98<p>uAY|
z{TIl!`2yW;=TpYS`R)9RqeefZV;lq(Yzy_1A|6Mv1{=gBlsunVa3JC^^QzbhhSK5m
z8SQ*qd<@CoCF3~ziue`Dp}aUb+~&CU78S=zWHqW%rG8eA0}jFD7nSKlySJ~+JV7H!
zUe~QGD=b;j$C2W;>ljLMwxkxys}sX&#erpB!>WiURW<qXRC{zSy^5D{!%dsHgQONA
zI&*kbIPbpV-`e`@EgiLeQJ%TZ*@@xRGHSuv4Rtj7<tWO2)Nr$mXTg+>`IHxPF3iMG
zFmpstb?yEH=P`6F^mF--yV8I7;oEONeEjA+v+{TMMm~KwxSL=8*FQe`THq%?!Xj*&
zC=#7gL9Eh^BCFbQT6(`##t6rCk1ClUnLd2t35VUaM9Jar$zlLIIEg-<(Or!?U3Q%3
zHOh+wvZBEy-2y+IaP6wGC=PPh++3c}ftI=swSV3TvlQVuA@6&ZI6&F?lRN#`i)pr_
z?-%2gBy|?fL7PJ-ut?WB2d`ciEX;Jyq}eik897M)OBj~ii9CB-*B<mY<C1fQt*)Na
zhUu0kY!2IP%f;%A9IHwNd`^8;C$l-H)rp(A9IrEPef*!`7>u?ICOP9b*W;c2Wjr~5
z=j`Hw4Hp4vT(*ATmHym%ycyHc+n8Vt-OAZBu5@@~F^*H0OKQJhW611`ayYwHw9)+y
zG`snaV}5bXri4Gxv>X@ahdnE+9I-Eh7>aJ~O5fao<%mWa2aeQ9J+-f2#{}9%{O$XE
zHwcHv7oXp{(65HRnWud5hA~g;C0J<FC%(6cZR<l{M}T!TFLZhs-U%ITDTgQcgrfy#
zQ4a4GZ@Zc7<06J{*KSvDOkuXv%rA3TYgH>At~H86&CM|LEbcwiMc9<KqmrPc{258S
zJ=~A>M7x&x<EoXPr*Rh}J+{$0_O$jW^+#4j{WgqA-Yl)knxKk=nZ^-wg#uhDfujAn
zi_ZQmK#lK(b|O*N4i}Va7jIFBcI<fOGuAHYR2Az|#aS{;X*3C3vII?51~(Vvn9gJ9
zGr~Gpnz``XIwp?8;cQ9<zc_L4=`@OBD|yyuZCwt*7%@?#T{oBgG9>I^LgpMuSk!f-
z>&Pc)7jjFqJAQlGqEnmGZHoBC*;^adem|j?d2=ELS~P0})vT&1?%Qdr4#F1BVZ27D
z0PZ}v_I%%Ll@m+3yX*YIY}FwbxJGmL;x;S~(qtYxAynoEOjW#C`v9Y8>hg^xzz;h!
z%v^!inX3@?>vXimrr<7pFT}HxJ?OZ5v8D-!dRvPoO*T3e+s4a$@<zy_Mx?&-X2URA
zyo#oNO2FbfyV!nwM{2A4DsR%N3F67!*NcfWtjo4Y#A;f+HqN#&TysA6mB`ky=9RY|
zSo9PQDI7|U_Bqu^Eo?sXn^dX2*RIPnemYg^YQ*ETit3CPZL`gDKKErZH7rW|rtEna
z(l<7r4}N6S1%2qAuq>mCMq5Yxw(}rG*Eu_=Uu`_ddW00)W%AQ)<N-}YT(lWZX_!{j
zPeyY+%Cw5!8>fiW{xTe*1)mu4Zu?C-5+s95xDywr?jxIGzHB8+swK=t*cA0Pvwlw2
zF$>oL4#YTi5F8gSr|<*;LJk&04#W+EAPu=LUFEq8QsUxNJ<fQW(0Wd*s+{sDEUR7#
zw!|ssL*sYzkukxKa+5;74%;l}Zo~@OH@)8Ug+u7cL0w#}DnA!2t_oU~Fhf<hqZh9A
z%ySL8F3eJunG>}`ZN})X?`}V+Gq6;f3Bul&vN(zroib4q<YLl<D7Q5#r%AD49tIjJ
zOtyZRn#miM&SSz1?BYOx<;;~7*b}5IK-vOd+-6NU0B5tF1-bY(_n?^5Xr8-xiK+$0
zhF41#c`93>*=S?j<`NExJE0mi!pVOL*2Eov(_40bE(&t8oUpjK4U?BN_k+HR=E57H
z@y02OY10>N$Tu+n9M+xPqY|B~|4<P7j0yd(Sws6R%In^ELzHJzUay9H4R9<oubQ?t
zEDGTzNzp}1ROgXbk1Ixp;mW}iOo9u9Jz=yWESbX#=G^uLaPVORS2Luui*t5}y<lsm
z&iA9JMPy}9t3pi8COlRog8{kga8q|s-@uM5teXOW4X;PR+?)Er`u;wBc&eXw@g~EV
ztU)?1O}(^gP%3S!ij52uB)#vK1{+4OqW~FY4(0R-R@^`=4a|kXiTQDT_>)tvuX6X)
z7Q24p%QLRFbuF`IF4it<BA$w|!C|atNH|WTQXw9usAkH}9QP;cz15@c*czn0B7a<F
z|74SeKJLhVyw<JYPlJ@!(NxyW0#UXGT~V!FoaA}CdUc#nhs)ihxdS36k1jFYMTNVM
zH*wz_{g+;X7sk7I+y(GSZvkJX*u!~=yHwxrA{sai5{$;B6H(%cgV!%Nr>nY#10b*V
zK$dGbPOQHNH?$~qAY%_t-i~6F;$n{EI%KRX*_01{yA@uL)+}HAE{afeWmVw;eSSy)
z03<k6K0#8RS}+h0w}qzVUd@v8ga6e!(@{`*9)(c^VvVZ>hLqPLYsPgN!VT)fwSS<+
zf-9*I&#38aOx|t^5;Bl@E(2Oz&6As0G8J*YZIr>bO-0u;-Ui)V^fl@d@4$dIm1o#)
zW-j0fR0_0JzKff53fy14hnJd;=lf#Nd7sZ-xkk%e2fh$c%{rs!N<qY`Djg4mSeKdn
znce;Mp|z$v`|$c2xbHgu`r{qIyI-bR#a^|f*r&4NCk)|_?}z*PAmizFMXPuWs`J}<
zW<fVbalQ7m^>e@UhoOnr&|q0g;T(Fsz_@T8(y6}lH3G+iF}QGV#*JN=oRIV5#>K6m
zqRQ5Ku7ZVCMaU87J`L#9Pf?e~r9Xv-au6JIGm2Bkb?hgCL|9Tb6fV2%2TBE;?E$Nw
zckwBobi!A9;D^B4vQl#xMZ9O7S8f5zlwl_&blP|DfTcjiGj=DCTRG+L?Z3(&6PEKi
z^x|q6Q@?B4W*Akxa9${XEhe=r-h>Su$5xjF#;_i^ks<(fIg|FCe>t<z<aci=S?sDc
zCo{0F_WNB1CAMB|DeuD=x2A?N>>5$7Ea^ftr6&oP>u_XODc3)}u+OZe+=57z>yTTU
zQM&R$cJ^kJe%{4H`cS1yr!%!FDaO7l_*g=@6-n+DWxbl(B?5sSRjD~=AnezCOjvM~
zamhQfR7mjrde6NW@j43XWS~h@MSe~DAPg`HG4u*(!)c~Q16Rt!#;g9B9hCOF_|%4J
zm`mSTmq5xMSDHKmel-uLXn}QIRfipfY@6!P&*)Hxa}etvs%ed&uJdMj6d`wYvQD0`
zE+N0XuXC5L$Q!tSKDyftMsz}P0s1zkHa=@;Rc_(dbtNrxRfsTbmyK^e77D`j@D7+w
zo)@`M>OAT`aL)#;`{hCw_r3$S*wy>n%g(0exb))AeUP-p)CV=4so1<~3D(wcedQ;#
z+jROq9y|A@br^A7CZExg;b5<`_gbXC9r6KP=X^2otLyXz=auza8|cbBq0GzLyq{;@
zm43%)&}3#e?wH2!LsLPXu^=Zc368$P{)W{z5_v`{Z+d-S4SK=U%BhGNZ)>Znh=XY<
z!zRiS!D8VD#liU5RGB3%r&N$9bn=C3iJRrZEoBRIIAM&OUB7|2nq)n1OOvx<j{8Yx
z@J)!GpJf<#*(~zOtlwN|ZcI56xp-Jdoa=j?zRj`5-5~B?ZCL$LynNhMr7f+(x_Fa`
zp|cJRJiUO4;a+^Xm)(}DdSS_!(QbgGra?4Bd{~=#$d=y7=%hmqs}!!_x`rn93wMDw
z3OWAXO6&{&Ry=;Qzqt~7wUd~lxQz3xPkFLoQAO*f(x91AZ<unmhRjqnIj+A;S8Cv%
zK*B||M8$lC|3=>ike$!JyBhX9Q6T&(TynmOvg*sqAG|c<qM%Ee)dv+LfrlfnfB%l8
z&rlSXwl4TrMZ&i(cwq8ji8}Lszgm>A+v-RRahnExn=C^d`>a(_l{RHLF_oD*!-Sby
zHdM-2t02p_yKAF6E8e-;_toHs30QAj?3X*kbk&^4n?G(-+f6a^S?aBxSlQgH*@0&7
z;GsbauFkBVVFM*>OxwPcheLj($B<7nj&zA~It|l(rQs0c;dW^_o`SFlJES7n#F#~6
zo~$!q6f}zugD4L!V*J41qtd}Ah#|QW?7Td0%hl>@3i0Gw?Zv}dvCS=CvQ8Dg?+>u1
z-V((upD8Q0uvZ7YTFDO@^q|u;;)o|G)}kd<L-&@s=&nHz=gXJ6SG$V_JyfA;nc`6`
zia3t)aTv-Vj?~n|6*HQ;TuP&-E2VUIiw*lb)tp(_pm%ROL!yHYeOUME82B#+Jg>K;
z^rAH%T2?c^Lp5f|o1yUIk%y(}F0waJ%`QIdqiXvppsum40e;JIfb1L47wDs0jrzJ(
z>%96<bSx<{S}bu;vK*BcFJU?cm8nbZ9#o2T@uh*2_R~NrESz)c+%EIT>DD6h;wAb%
z%2@9&5c;@mLBI7;FyxTXYVL<9?M<sN!pz>ie#>{UBKv1t*l-zm1>2a@yjXvdht+96
zo6%eibc9<n%qsDM1?qgAhH}mQwJE#W8<c<WgGbX39;A!zgHBO*9cqD=#&Ytu1P*f_
zm%92qMVA*-Z=j4S(J#$9$3gF*M^nHc9O9^qTRJoEVCC%|s5iP?5&-N85;(#FVfq%@
zFGV_>tCDav*nCPGkuWj%s`6TjRS09|Cqq_*K!Z3tfPL_X(xsRy9s9L6cccxd;g*;g
z-IeuDcJr0=;?8V6w|SaYQ&{&D(xobwh9^@P_hFhYLYUfxT$r5}XWwJsPpG}AjVqhV
zcbz=}DZRo8Owx-J^Jc(o=A!U;(4<=w$7!#Mu|<Dmr79sf2+|&hFx-{g<<GEjwqO$^
zZ#hEkl1uFD`}=CSgK+IqL0MXOl&W%5)3#v{Z#89gwTb3`LF_^@;<^vgrSG(lu(aj&
z6XIreuJee;WyU|x&M$_$m<Es6lh;RW)wF627swe6gVm=KmhE`B!4HH<Mw!E%XHY7H
zEwFDdz(^wTWCddVxQq40qc-itT=H)5x@@F=%(6`fb}r}?CbLnH35TOukWqLYqS!6S
z(6!NJ0le8g=ZrjFjve5>T5viHB9#`{dP5}qcv+`<@xpDMx~VJIt~CW{#X(?PXBgz+
zw%T3w7`H^BkVtRS;3<9B)zQQpFRshlU}^?lus$sl+Qa16MLG$8#A+)P%)(r8qsARh
z_5J-ypR>z~<;0R5kQC-j{S%Bn8E1p|amGzQkuG2-uqVwo;-|+L&$cy07wOD9o;2H5
zMQhYX<<vHPK8p^rbjnN9hJf<pvJBH_R^Ssvu3VSdduQGZ68oAQ!ujvS#o~s3%$o$m
zsjs6UjH4p;%5BW1N(>ua%Hlw-gCmjJ72uF3EXh#>OPIe+pLm(9O6OdyD|s<{BI-+B
zDfv}8W~*9xn|JZz)l)KwxyXj<pib_%rltX*F6B?)&EIh?+yS-x1^Tp(aa3MHpO#lM
zD9SpFee{O{Hzxd{>eUF{m@S=BT}=(<Jg4%|lh-*oak+Q`ecH7L{aZbG{ga<8XmK^z
zVG{-{-=#`@6j8f~#cv~>w0JyZ37Bk3!R0}hib`GI$tUO=*s1U&-n9C4&bNuvkGr^@
zpYk}sH5s}pS5-2UX;O}qhmqe;fKhAK^QJ&K>U5T}C;0pd3vOX=w`TW+2xNquday6<
z)Uk~Bf^JdV#~mi^+F>E`JOW-tdG34az;nd|KZfm_y$*Ro8y@U5X5l6iPQQe^Y5mDe
zxT`lI`aGY@s_f!^P+mKVFbn6PU2z&j8N|5>`Kw#qXF9ZwuH@|>ZIF(oqy6S01SPxZ
z8l1l3cro79I_wthiw9h>v|m)&g{&K*Vu{+YtWCLjLgA3734L=@_X*qyg8Z3??{rVb
z;Oy0xivi!ZIZgaL&tU~WWiZct8=^|YsaLfkIj9d)VhT#S2!y~Bl!+{O$$(A~-kGS=
zJzsm6FmoKJ?~lEBWyOO$P10$}<ECoHbsg%uOv2i)){@nHHMdz^lSjdrzEPjRXLl?Z
z`|4l6`;Px3q53~4&gW6=&%Joo8rMxk=RO~oWNUr3@DfB@1|8FJAdV{&_QPb|K`z|a
zdct;(RagL?+?16BPUV@sHn>`3Fj|r2gGg0BOx)Wj#z~ud4FnTkyI>MWAtE?92kmSE
z`>j<b9Xq-DE8K6og}_S$a?elTuEw2WvervSo6%!qQwG(-)^5tX7R#VX&=3XZf**@C
zK_oa&03JE91U$VZL$n8X@py1IWQf4Ic-&e+HRR3GhH2IJUbpR1qP|dB)~2Ic0t0jb
zhe3+Y!CVjzE->H6jFhe|(CJNIK>gC2y_g5PZu{dd&f%hYWos6BBI~=L&jyUEk|y0!
z%(17axs(Vf&8=gQ1i1Z%y2HT|;_R2^DY|NeE9NQST&z1bg+oy$-Prf*mI*cnahE`+
z5}<uuv<a98{vb=Dvua(<QDz^0W-ZFITQe2O_``;PMmEQ;KJ4qbs)1H>71m6x-K^GJ
zR6Y-w%EFl*Sdu1ZP8V#tf_j3ID3ca?><;|$Nq^k=;q8-tafc?-r8;I)G)`lo@~r6Q
ze$I=~+bX&Qy;quIG|oYAfFfrPFFo9M(yc%*Z!_mWhq#lkb+~wV+IBe|*Dl#8<HA?v
zR8=D4LBBNEL6sTSZ#sQ8m1sCY@lZqVUS}u^QUl=JQVS+~qyab??28AdTO6^lE_qha
zVi~i%^heQWssWk{uby+$$J<Qdfa(nHLF>2s_8h3KJN&k!oW5X~bjaC~a^PGoDc9&S
zt)?x+!8lett=2jY+E8`Dz<3Xpd6i2ckMg0wsS8hNzkd1B;=Q=vrby`Thlq2jj_|r;
zaG}E3SZw`R^lde)v)2}o(I%X`6o*cYJ{qXI?i+(O2KxWlGbF~Gdvt^D5(d8w{0k8t
zPml0d;~u1WkQZ?p2XRzYd7Ex=<tZUVnYUZm3ln!{;Ew1}_aPyfd#`gzY@#l1-s?J@
zaon>}zj(fu24Sw_d&ZWi>#}56i`dI~S$j(rBrH~D6PB5-?bKmHKH*}wr39}bcyGqG
z+q$CTTrp$g7th#$vU#oBi6&v2$6MGH<xYbOtA_PS)DEVI5P3r&?xlcwhPSJY3|_of
zs=p9kId!fn)h|BvMV1b18Zy2qUPmfUCozFv&oIr=0If1hbv%w&<x3O&3BFz&EuDKo
z-aGeHmywU}HobN3#l>^Cq$(28^kWG;m{3e=^YW#FXy18gbvQVj`{UeA3e-RRGp>3Y
zvvt94E-?e6=$@U?i;G*b`7(P8OTvJ4+qxwKXKM9>frfRKhA};;M8m=QLjd6do?r$*
zq^&Z}{l&g4BNz2$FTUsdO+lH^u8ZP2VKwAsAFp)G(jcI1pp1e}5a$5@K5S+bpV61K
zz?5{{8{^iU(g%qA?DKxLrC&VptX}7|&a>9r)|92;l8GMrFo0x<j15(Z2jyR?6PukC
z|6hVDd6)7pIKQ~TrXvu)=Dc4m4$3Mo3}+e)c?C5WUAfR<Ql(htZ3~5A03w9r9BjDv
z!0SF`4rAkfe;@k2qNDWD&8DXyKMcs&)TpxNVZhUr7DLk3O^%o}eG(_;I-4mA%k-hA
z4@u13nb$ewdeJc;&U>7Az{h!$M-CmiSTU4^4Ax-`*~W&tD#M~`W)287Or7Ydxu@(<
zCJxhfhwvw`;`LK)K<?bsApoF{5892Zoj4ccJ<bZ&l2&swZWUD7u&TCIY)N=W>(n%N
zBIGDOp|cN1IPMd?8y&F3mL<1r*!LbSJzbFm$kj|)HAQnhl=aexWEw*3=Bg-z2(X@(
z8u1`BM?oBBGCIDI2c0|a>eK2p%1%Z{2)ilzjZ~cN<*+~R;yg~Iyd5gh2U$9{B4iWG
zd%vY#qF5**qe&+jJJ_@`ko($?eGv-%x>*SBuYkY3@+2J>oGZlruLr&r7--~EuNdms
zYdkOZE4r+G9VB(JCB508qX&T@XW!su52_MK$N387o4`vAF#Gvdm%G>@xfA$1V?2E~
zi3c6)^fh%!{YEY>-?Ji3!YK*bHW^W*Y>Vb~U5DH&U{qmbSb9(*<k6p*ITF}YHe&9g
z+x+I6kM{%sdds~>I?~ZU!`Tu4YV}|*5jhOqzUs)=pqvZtwQB65FpAo$SIePOcc|P^
z-_eY5`v+gYa~2}L!IS>cKJC-wjy>M9`J67TANlf-Yk|kMSwj!9G-<qb;1C33A62!e
z;%wW-VmT-Y!*Lc%ot;_ugh4#BQOGgpW=c;ThWuRG1z{K0aY?ga?u}mG4_O_hDpYxr
zwyLYzGOeR3Hs#?><Ia5yC7+=iP3};W+sQWfUGnT^Ax9Z?nK&EutL21;Xsyybs)KlB
z2~K6_^+_G~X@X(fZHM?S52gSv;Dc<+yH?-GmoKwFfciTgz55*M>|6b6F`~Y~CD|LX
zdA4rBxFC&|9z{3-R?}v*=v+8vbB@&L!4tFut?j=N{6gDSZc5GS1jKnf-#<{S^*44D
zo7GRZ>)RTXeeO-Ih{CSjwgtw<AN&TgE-EMRRB5_OywM5J^&rw`+!w-vx)H%!-1~jo
zLciW;`}qR7n2ft*s#&tE#wu^Ov>Br|!rre6R63lL!@=^63R8KWa%9M#(C<TAU0%H1
z<#i}Gg~%VjC-CCzKrBjS)uQ})U<DhqX5?Ym>*R0>A}@=ZgANA1am;u7821@$TpL9I
zzp*B}R{&<U|7hKJ@or7j6k|z~qN!M$wS4X&Dg1CLB2fl?TA1E%`rkJNhLQbb^k`YH
zj()k*z@I++a5vm<OB4d)!&U>wsD3f%)e!JPbxYSw=oNKUj8QGR1&b`$pkE@Rqwg|<
ziG@N^eALJD9vYs5mbU1Kxakk2YaelPZ|7>3wLeyv55*qT=b)<lYVb2rZ*;1sJ_Uo0
zAzzo?KWpbXQtBVxemrN=#sEj~+c!8$=k)%qxcGbrLALctsiS(^<ZO+S%IjLz_hB(o
z6?DuLI$``kyaSCHrS<`*+`>i$ao@3D=Z<_>q3{^dFXq<rtzO2&o7QbwwlE!7$}q`!
zzuSY2UD2D3TgT*DBJ2n}!G7IAD}c*)w&m#g6Pl}y*W);u8%FDBTJi|TQLxnGgFkVW
z@w&;(8{9c;L=)la6pB9~q|-0oow$>TA>WzOyiAY~<;gd>v@xY&YJ)k5`#5M=1Z+-=
zG#@-A0_ArK3qu4!N;u5rT_yw*(*Ahvo}~T01Wvwb_b45AH%WOI^-rbh$i-)UfmY-m
z4os<_sh6l4`&d-aC7FV4t8>#C3=eScOicP{zJ3qf=-O)BO8QO{#-Vufgyw3O?l53A
zpPSgrLuk{Y4->y)Q;>#P-sdb!4m}uRj%ak=>ar&!aO}$+BJPD8-l1K&L?V(a_9DsE
z{;p9})a^2bVhi)F0ac6`&5JiHAvi?wa_F)<hx6`$D;}j?-6dT{EhKaFy=&d2gb8+X
zflh7Q>iU%Do2XU{gD^||X%;jn*D=V)DJs^qJ(z{K<hT#J*Dvl9aJMy}qmDVCGv0$w
z=VSbJI!8WPmUa+Mwvf@^(vMFu9&L9txAHKGqh(k;hG{$(ocH5S*{#b!RbucC)NFC!
zZ0(~thdp8I2DtoB{Pw`7Z;znznzsj@`u21zPwA|S$u%9vE?}bBlvmbMuflFj^7+8~
zI!t!=w2v|I6xkie-rIAV^|uQ#AmgXM9X4(r%z`d1qhKs!6=AN%CWmm``9M5LyJPG)
zN^OBFHGWS}Vqk*XLjOG(4zkk^5idwL>D5a;6DD3&7gHM|kEgbuVh@Wl92zg`W)C)#
z<?rBu^2t&E_~HrEUWeKO-@V;G+&hRT_YdjSS`0%nWb;;~;Z(4;uCisGnk5cJ%-bk$
zR>QVRNIaZ)&gA19!23YAU}Hqddoy3+I`njk7rpqL_pui&@mOU;7W5<YqOBiWnqwI+
zs90>&7p^1+#{-Ay>Wa%JjD5MSAWv_MeJP{z?6L3Fb_c1b7Z!wV&gZopij;~auP_{z
z08;^-Sx^#<k$K2>z=(W;LA;KDwh(`Z+U*c>_GE}&ea!tepUNb`8ohXpE1klvst=l;
zv5iyFGjrJQ9J<9sCo+;h0d!)mivVv92hicfeS8=Hv*7@}+JAB`fCWD0{Sr{MdfDP(
zH|BFv%zRte!MunZxO(8a!U6UShj<H=T*_~1s4@NSJ7*v7i<upx-v=pdK^jltq^3OT
zxwnaFsOwdwWtboGHg?S0cE%b!;S#r@nfD5}X;Otmg2YFakUu}zR}(XbrSV!?_+9ID
zbgagiZS&S|uvSSNw}x7pB=lfLw+s4F`xQBNm^GZ=V%md#<8+WYo56E6-gFITq3W7O
zY1oxnwB!K;wlpO#^KkL91Ky5F;Bi1m_5?W<*H#hEo!fR~%sqV}OF!>g$Y<6BLn6Xt
zDyOmWc{-~x5=*xDDUO+Mc*^Qa`p|jVN1R+z`vPh7%gsga1^u>~3V=&aHmlK(yLh=`
zOhub-O{>##7?5^-PCdR(yTf3^$KG7HH7{^*Il!at(f4F)%*J9p<?rlVGX1TejrPUa
z`7pD!OR92eVj9jJgn8CX5h9zLpf60<XpOcp(go(qhaD{LLz~(_8*ihn?-zMC+7~a&
zdHoQ1%a&D9KT<Eq>$z1v^y|1J%eeWAiMBaLVF0=&!DpatC1v9`(dPPMfwR%RIALSF
zi9(v`0M2QzB0#oP-5BL{sQN5k@R!g==IjiLXP^!C(7x$b0pwwilDDR1SEHV!WgTvL
z(Q>beGd`*&^ytzSVH~qH$_jH@#*O=%O4zMRo-io2VJ%3-J7W|5zB;EbR?v%gry|}%
zm-uU-c6<1_2xsIl(PW9&#1H)JU?WP1NyJ3=^)0a6Z*gq|b>X~o%z+?v9lYR}i;GLM
zEyt9Pv`jiawtW~ae93&@6HOec-B#8(=9HVBlFZe0F?oXUnQNoVCdkdMs*Z2$?3H(V
zwH1jMwvD%<O3Ho>QdK8@tcrdV&_h}^jj4_Dy1@6@Mup@8<rBQ-7_mj3d)J3%mpo(W
zTyfMd#(q#0<l!~|Q+-@^u_tKYFZmcV+$sf;dDNvTfkoW?ZnHlwW3FrAsJrjjiR$;2
zIOh`~F6O>W?d(N;$Z9_qswu-V^7@%|OFHT(&-?H|w8kS<R^M#yqe@73*@+5EZgceA
z?FvqIV!#!mw)E=lij>Yn9&ar~1uct`CRNOuYJz&Krjdt@dEBWvFr~;TqYrLQ-X&Gf
zTpNX(ylEIs7&zo)tvmg=i{~oCSPArtc^yUI*ICE9I?V=vZf?dHO&1c!+=XZQq)Tuf
z4DSy4O7geEyFT5zF#7o;zI@zO>Mcmwu(y?LbaH{x;ioFuT-;dC>I8tNo)@lhR(Klk
zm{&!#q%>ZOG1(3jc8Uj4L&=>dSVS}CJPYU-Jrj8X<;5n_YGG^@3Z^DrqqU6IJm5<d
z7Gqdoo_f)7S%Dn9Cr~)}3>$cAqda4`4QBRm!x(*d0s81LbG1^fNSdwi8Dd!^)yxXP
zy3vobb?TO!XG3VlaeCN}<D3ik!7b>!A~{D(NgH!+x7hXf?wmY6(~rAYj(VQDX<X4?
zI^VBi>T#7vMOdoPD~Guo4u+BDKt)L8;t2y4;#w-o8M$c#u5(8I_#&(c`PEugF<-Z)
z$@hjjn;R(TQiQ&sQ(tA}5DZ3teP28|iX8w*DeTwd`hQu7?YA!Sm%ZncS6kV|H~AQf
zg%wE`Ry<21u6h-DV-dxEy7qw=)1%z{Vbxuqw4VehEi=@S+CclZB`EGS<jDb@UF`@O
zjDFvwtCvO<#z|5JW!9#35Qg=-jg7&6k=!ITa$SQG&Y$21DqMSL-yEhm_;5}3M$6@L
z)K?znZP}=7;h-`W#hu3>AN+_fJ@&<Dwp@s*AxvEEKIjd2-!R3NS`mY{>+oH}h0(L4
z`o$f#Fs$Y%!*ZqRu$1+<l|#eg$V-E!Wb0%ym*Kcjy4#yOggil>%7z#n!*{sLpy83H
zx769iO}4V>#-;!+;=xPWaphIKsC5(x4A8gpLAwOq!vGB&kno@+*<FX6IK&3#;x>1g
z2zIt9pnl%fJXSvS#ms!VH9b#OkFzq*v5&Sq&wOTDh`18p*e2bD!k=L7Of9t08Gok-
zLv;@MxKzX&J(!E@aW9DHZW5!K%RKJGU>?hnhh1Dv`7~{fI^^qkIOaN?lCPv@yZQQF
z##=z0zNbmHe>cc3n40P5UOXi4n#^w-g?ZB@b$}uZHULaOv%l;TR2Y^+BB+_dIsDjt
z+tu;$2?PnWQI@|K-t~2Na-DW@aG&COTw5<o!?=#YOO{@Z0}aP{Dn(Ie2DMcPFlp;@
z5AVW$Xy?R|CjfKb+%w#D0(7`JbI*`n%!XJKHH}S0v%13~>!?V^a9tZ(^<lgE>2Oqz
zHo@jDBa}ZOqBC37ndG-e;>3NJ^<<uId9^%zhHKPS0q@gv;tE<dbSfylzH8Gcoy;91
zmzX<9j1eT_2_tcCqYER&ZL}Siva`{?n!((Ks_aEJ#Yx{M)12k{u)`d)W?TTNY4PZq
zi>14+7r|!`Ah?Z;P2N;?(zl8@TR51>i^KV{ZgG(<eoy(#(p2zdMx|lb;QQX@hljIm
z(3?0#r1TkR3rmVG@D8Do13cbsJ9J+z?zfdWoBJrNhb8E|3ZV!#1?v<o;~E!Jcl3Th
zL+3|IA_WI(pZY>wyw9fl+Yk2wf2%axm#MGN@4FcMC0SyR*DLttux-Nk(Dx>9Y+6?5
zMVgy;IdQ~65X41Yno;|Oncx<<FtE!uey;iYNl5-gbCrnCtvvNB%bi2~f4DKXe?Lbj
z&wYw-N$OQ61ErXt<mobn<+u!~7uBWT@g?j1b&gEIAbB*8K(^bvKY{;hqml;)Ztk{#
zP6){9FT}+WVqLvHS(~8>#?DXX*ehlguLT|bwa->+5T0F!9>rae?&K-^D{PcnQki(w
zl)uH8qw?{Y%&}Vw7x(OzG^=SmHgv1N3r8BUu=9$TmPLaZ@6{pkKhPv4cXg31pTL-N
zxh>$~Hh&7yIl0)oTn?^ohjh;C%<oH<k4Y6|ORzvVZC((EYk$ZE85oUP&;bdh^Mq}t
zFIR*6&9`5Fyc2fDZu4p=rzi7jE+<k=Wt`?ES3NDmZ3>e<RFjwVxE4*+kC`d@2<A~|
zK!}j|gex6vT<N#E^DiQRNY5U=Uf!SY7mYRT@_DUAn#3$`y|AHE9~VK_0h+>5u3!h@
zC>LGIT>Dr09S$*f9`T!joxpJl_b}ua$914<-ga3S^j%XmSy@$cSyP%WMb`K&JID~c
z4g^2lZjtVz)-d;7<?!XAuJ@JqaEtsd9TzByvk||zORoY^O%2UwRjys7;*L|kd85wU
z>uihC?jQ(g?j`H8`{6R}9ugH3mSlY4Z6EesU52^jWTTd=;hxzP)@3R(KGkay1}!f{
zz2%`7(i$fbo2HJ=!GT3eaOgwX`n~==u7yoSI7-WWZoonuon$!YbLaGfEqJix+tzF<
zoDvm7!|0&KX=F1@S&#-bRfnZ?E)NU~eeQ(d&#?Ss)CT^y)jxNwo6{S0S4+&4{x+_4
z(kH=I@^CJSb()(p=gBZ{G!UjqH^R~Gjk-)yv`@1DD_OhC{?|IUlpCGf7Y{%<TZCr+
zevX~nU5MCL=XQ?T2-O@Eq95`JdW0|zhH5J}k*{lD+z>7~cs^6d#aHttyRCkg+qfa*
zI|4QP@&vd5S4?>1#R@e^1#>>Ac%FkGN#-=8RnSiH7(oldOH45;0*9+X-`2>)6Ldt;
zh8Q@=_p}E0{w+S97rY7l)e@6qm*vycsH{)Lx=bB%nz5d;VQ1Sf#;iuahX(@}+|~Xa
zZolk9#{yLc-!bLV>FK!z-^D8wqF0M36c#vcL#d*&tcPu@;x_V&G$>Znt%q@AlDlt*
z3GxINHfqDz0dEdy_Q+08aCJQnXf8&)QYCBWrovdI6@$R{IEo?0zAHdz+)c!Fh&^2B
zLg#Pzgt+cX3vnHtx9j_T6Os}4RCOA>INL8~R#$00(xD#KX<5=u=`6nqv8f_tM~_Wr
zI_`n4atI3h`%ws%+BtYjy<)HMsPp*3j2Y0cmai!5V1+OWTVz?g@><0S=jf|}(IBZz
z$2~4wJm}Ool=Ej)cvM=b@N};5PQw1O`-<)bc^eYEnqVCUkc@l^!Xd2E8XBFZm&>wd
zVwtwQ`Nf3Y;nLMPD?XulOKkv8f2o&8b+SSD*<#W9xfWV^lLvLh5vQVDc@%7k7`!1>
z<vgWxt{QIM>uAc>01BduXZtgF$FU?^gY0%Xx66tilJ`^6xr>MJNxu|PKf)YNby5^X
z&;~(J^0B9WH5TJ^T!J=Q_|j!4=z~(Sckyrqu~DtTJN^#<XG;~~#Ut5(22nk2b-)X6
z&Kkcf(!7|Gf{S$?1L_^TU5?p1P@yyUXUJ2zmd^RjDLn4)9-QpngjbK@y*iDBYNDx6
zX*i;YMhM$JR!fnMX|x%gILV|bNajie`ULj}V9XZc?rp?@pWc<%&%0Qos;c6tt-F3{
zrzIHEA@)~Hc%H0jI0m`NwITArwc%8v0C)oEgxiSf?z=`W`c9+de9@xoagR}iQCF}s
zj-nzhr_L`kk<wmq9v20eMlY^;)VYqh_>^fpS~}|ZUJ}RYL4ELy9PZ-E&7Z{9dQ;z|
z<E{t4mP1f`?F7M?7ek%JW)4S~X}e0KOPI8u!s&O#!ePhvJRtNts53cv!C}XXCv1>o
zI!t55+7YWfj*~hFYgY7SII<<HOocMX+?r%SkUS)KaOYu1N7_Ig-uLoyBz3Pq{o-uS
z53m?=HkFm?p!ol&d$(TOaqC?0-{h$gNP~l<^pFQp_q(VorI&-`#OOYNkrTA-hwfkB
z)UNHMidu7(Yfh0u!wFp5_O7{heUs$4e3z_D3IeSd$3!7x(OCXo$PW_E347pSr!LYN
zY4D0Qtvhu6v)x|F1(sRU0Ao@yBDX_rC={QDy>GiEk#vNuMWc9UA-!x<PwkuUKXAEI
z;%YGSZR|(j>*mE{Hb%0xV?Xj$9g!&7s49kqt{r4GtJ9e!Z7d0^67z<?WG#EZeEQQ0
z!!2c=y3onekbcjh&=(zAxZ`cde~ht=b*r|kwk}4_Xwtz_0W7rGv$-n^6L&M~2f2P?
zpYTJ_)w2uK**AI19^Srkv(1>P+Gag=A=XWae$A$3NH`hEEQx9wHeUjlugVyG(Dg<C
zfM+~)VRu4*n%lfO=HygoS-IaWKkm5i4Yq@f+9>AfP^q2_YfbhlUs1AjG^tV{T&J--
zpxl3eD&@-g<ZHRaNtXqFx5=>Ob1ti9R(UdujqlsWyHPgf9Me4NlcVnrGwsLcSN632
zQ-AD4`4$=0$!`6%{pgSIwj22J*WnDao!hrgY;Cu3gCttlWN2vAEme^<N47Rto3oja
zU(x~s&qw~D$?#h`*C2GHg8K&dQ|yYKcl%7vGVFWDmDDABmh6nDVjx}0aotI$WX^b|
zF0h-yUT{{{A3Kk}lfX>5BhY>FEs-YFWwwp5M&?^ysqYmTqe6&m!-KIjEmBVMq>1t}
zffSKk=5m)Et1ho71mP1ZNC)K{^S@=jd%DOVXa#u7hd!$)fhlgFuW)OsHJdj+!XO7)
zB;z(rW;sWLEAS-r0`CDeT;O0h$G$bJAq2sKy|`_Y=@Dg=Y-!BqG!Zfx$Wk=>meu1i
z4nt?w@Qkuc4X;aS#-A{(;pm7_!N{wmkPr#QTRG9p^6kz5_jnbB>UlS$MLr*KG9Y$s
zwocisE<ujeGffTjJrv>tIU$rggPVUJ!>qr47RGYSwu4FCZ*jI9G|yzTj}0`5u9TB`
z$Fh;p7SrEr*G~xmekgW%tB}{f%@OkSMYpbhGNkuL^D@gr*shezHj-^#({w7cj>u-K
z#%VtIx^``jX1DGWGn*H}kOvPq(9ys}uTEcO`u&IxxOp&R8Ed-ixg4=*lBQINZrRte
zo<!VFI~(UETP|4BOPB7Qa*u$z=RZ^A&d~nKfLNbxf&^~2u&|B!Iy8JQ%YEat)kXWh
z^%3-Zt)oq~UDX(qnX^>6D$_%b{DI|~AEFD$z1O+C`mw!xmCkId*;ILqIi|%?$gJ%e
zMu1_qbnAdi0)yF}ai8-G;GwRrnD>Mt-PN?6!Z)CYz;6fLa(mYDEE(q{-|7Zcw@ThD
zO|Gx28k$rWa>{Ja$fZ5w{LFC0CqQ@6le5>Rl1TA(n?Yu~KNGatg{<~s*rvMRO*`xe
zYHoK?q^jFY!VJ3xIg)^$etQp;>BLo;&geG=vLVIWLAU&tlPFfpS|3?1NW@u*(OMPj
zRJRGBs;Du9IW4CyK4hm&w)a598+8>3#Q4_*`wwr)+c&9}Tk$AmVk;85m0P(NwCm)0
zbVAmw8k#Jrxal((TsP+$vw%LJQr6F?o479)yaF6N{5&?o0Nk>&VNDmT4=UR>k-aKL
znv1;NqE-zo*`zXL=>g}L)w!-OJx1^Wz+EH&u<%7Ye#Sq2Y$Ix59oogZ*ydu4tA1Sb
zs*=aZM42@*pNr)fAssHRGM<?aa=z*z(g#>EfrG~Er7yHT*35&O-)_qn`8x7pZ!?kR
zVw=i%sOGE`O;#%*YI5Wkto<uL!ovXl58dD2<HWcyh~wU?Ior873huqdZQDm~!yGR#
z%?GXr?r{`LnUb=tB&xJmqr4b~2A37-Nr3XG|3IO}i3_y7m-+=x0dGIuo@K<3UCdKl
z3?poNNtY<;rtV0FH9x9V?zPd51wOk}=K4nr8RPEt3+TBx-eCHL{`ZOeVf*nL-%j|g
zY3L7%JK)Ww9EYzgLw~xExHAqtc0#z==b~$7p6qK^cA_5_oYGDVRc9K9dRHGJ76Pyb
zssPV-q+92&W;eRwIm3+aH7ekiCpQC`hoeo@QRKtX#cjHmf|H?*CoUEy_KS?wq{k8#
zGV)=9GwQegpT8c*>;LBD&-~Xf^&jB;rLI2TXyO0-*Z=ozyuT(&f=A$U=cy}!#y0E+
zHYD43x{XP}S{&=V>IAfD4K>HAQCC96)vN%){}~YJI1MmxG?(Z2`{q+;r+2scl>S@?
z=2KIVFqw&h)-(~6cLNGi^;MZoNvUwT#Ccz%fX;B|Fnk~Y%7u+6r{9DBBlQt!csuyi
z1^6-&=~l@}#3`~Oiu%0DmT}0Zd{t9shJl{;p{DbgF3mX&9+=m=B2;n8UvK4nO7C99
za%#EjXKj|rDw^|ZAJ(N9;)c~(x3jI>_oGH5<&Tq#$)vvX1FFyD6N<Oso$>9Pz_Z^u
z`RBVtk=%arnTwNOr;%dA8V}77t1?}t9oJm8a|?{8`_h@$e!!@i`|b09QTGKObwHEn
zFUI$$r7pvJxpdriz&j-aQq~9_AF7+8c3<LDO>(FNoBFA^Jn)p8ism5jA#_iSXFfWE
z`n3|q``C2u3%;yv(5E%)kFBhZC1){f>ZEA!h?{n0qCB>Qn>rX``qP|sH$I?(LG)c<
z&R);)DI?z9Z+c)^{h~w;(^Anos?~n9RXWW3F^)uc?#Hkt%zV?mi+?aV2}TgOZ{rwq
z)yDm@rTe$P{rS&-`s@Gt4^#Ve&X9tSUvu;C{tNt;cXlE{A(}jjinPpeF1I<YMVCU~
zq^uu@(j?abHxD~df=`%+6Bma)e8r0=H_Yjbx7;$)jO6>2ZQ07(sU|F$`z&cQS`~Du
zmXYU|jh&gzuKN}AKc3dSL7Qbhb$ZPI=l}lmpMT4!V;&)&M?C)g+d4tJqgzj^yoe|!
zGL6$&mXryWr|Y`ZBD$arS3Vun-vML~$X>WBkBZ<Q%X|yyFN+oWt5P1ge{*hk@bg2A
zPj<Dp0Z_FnX}1-UWCa|_+OUdNLq5+-x5IJGgft_8e8Mn%AQ2Kg2c>@Sl5NY*Zu91%
zFR+~kneK;zd1G_4cZ$bs5?Ir|lzX}*nHd_OZ(vjE4iGTlpU!dKxg6k+8<f3$IlNHL
z!1*WmIPvQ;ys->A9Z5&0O0JOg`u`84d$rDE#oAhodlOx!HimG9YP^X5z(Sw+o~r}?
z1>EO~#-pG2b*}NA=Wf9~X7ygmbu5Hz(g{VL%`D2dCEc!gUo!)M^DyM@*E0|}7}N#c
z?=^K8Ah*%f1-A3QSaWPLk#bm~Rdtx}WxwX)Xn9l>N1B-CqiAeqDG<&+^&xz#siVXN
z?%_9MyYq4neH#WgfoHkqFT0t>LxIs6O<lXzl!`7}_bn}2<dR8K=g#SMk^`sd>;s%F
z?nq4$_^-W8&hFNO@OICtz_OwEF^mNp7q&takNcFaBpsHz-ua>XJ{S!{@!%5XiA3MS
z;R9)ZKwMPr@U2T3q11vqU0_)rS#c;@h%>Rqsyw1~i1TPD2GU2z2K|+D#R<94>_WhR
zJuuD*oRo6_FFUq#j&=9yU4NeCLoT5j>!{21O<pj*<tiDKqFKB0H6m&?5eF~0YUO-R
zKJ3un6i7Ol)du+5L0-2I{N`zmWef48tvJ@HYSs>Tq~<tpppQCGe9UUL8tl4|5;GA-
zcWcZG9!Pg%fitWxbNMsQkKN6ywhi@KMzU0*$p^~mQ4aGlr6s{k^&)L{c3h*GFDIM*
zSc*N6<;OfHXos&>u0B%g-7R|#&~l-kE<?_tnkkWUF?TZRi!|;di1u}=tMn4{6_Bf+
zF!?y3`Mq6?=i>3^-^|_u?-B=c!z{)!ac+qEA*Zk<Y7iBZP^Uz+`@Yeo9=A?j>a~jp
z8HD6C$#;LkfjLS830@N`e0u8qZ+^gS^D5-hwsPrnNv5n+2g|!`UM5*@Q$2P`ZLs8c
zU><T3qAt;W_eY$g1OJj2H~QHt0`>1E(OACE>ug)M0Tz|jO*{63>{LbOB-`>mmWzrm
ztM%}zmg7vHG<={3cTul}-zG4hMce%?xb0!v+^q-c#)HlIp0XDBI94s2sT!Ah<EBBp
zPt43l-y?*D@M%Bx&Yd2Fj&^9_x4I`JKyM$mS%w`k9_O-cx|D3wGy;*u7^e%*)~;n^
zBQCI;*-ohMWbae4+dE`A&lOoN^j?}20VQ{<8$-*xlsxVwi-xp|#!QwJWS<n%HXZef
zdqt+^a<`k)Ro#gPNFOkm<RNt<Zw$TP$@#(0r|MtqQ$o*j(XLSSBroVBo3iG^w9K&U
ze?NG`nuN;P+^1ZSKO=sCKM?2TIWi;*uPXSzliYsAV)D5me?J3EZ!nGj4WTalO8u@s
z*%g1PimD~fSX#h5>{$mD$@?~eV{UfIpfQQGNG^OkU>JrUj_lql0U0>hx`yygYzX|&
z0n^aJ)>VJ5<y)d?>$*wlff;OlL*}hX=D3>*s(;lDmoPA9^m(D~>=}6e0|r;2Bfo=?
z&~LH#ee^A4`i8`^ePL6?vKr@gsnZBjDzE{lT7+H|p!k}b(1V%x$UO4tkp3;?S?GvS
z9U^{@yvJ=MeTHaxW`C%W9eY+6qF8Z)Y41lebbUV}@B)U-MBcQgMIa%A2V@f*93;1g
zFX9AFYg%%*_m%BXSJsJYDzL88O{CpClD=oVm?d52auLIJ9o=3<&td4(PYuW4S-diI
zFs%>y3zhqMzKO2V?;hrH%XNQ#j63V9oUd^^M{x#Z7E@P?vd#FuRR%pe<d;&;3(o`i
zger<taCET;-;pQJZzPhB-}EoZlc8<Ra|LpY^OCgXFyXMTjH|I);V4#7&S*?{g21%3
zpg~9>e8AQMLKk!U;AJEf^?iQx)oxn{L5uFl=oHhAkg^}Aj3jX*)_N=2p+4wE-hMsl
z!5P{8sfpz~VrPcL8QNbhVyVacklZeUunjqlN!2w#x=u9f$od+Il4Qd*+a@@U?cz~u
zsvw95O#cILZ(u?^2PCR6{AP9w)W3OlYk62d(jywPb#5Wwce%=#_i89}h(_$2k(Xws
z05u(oD5C*I_oLgu*#Pfr#p`*v`R8#0za7w7279W>)XFiRhHg93rR8-5Wm&_Xq*GMK
zM(!8mzL^X3!-$W<14la`uBx{1wT=-9xn0K?+P==Y+F=8ftedi_FIakHf+zV>=dw#i
zlRL+FNUkw40m2h1=fJn$iNEZ_={a({wOF&A`bBA5u}ELw*)(>ltCP5ocP7fDYh_XJ
ztKYa8BmigH8IT9Ma97C@^eZ3YUsGez$9pk%;Wl=(V_v~A$vA0gBnLPKatv*g9dnkp
zrlIhO{FNRHjQSsvYu+P62izs{7vBmzf9_9RN`Cc-+l~XO*6JA6K_uy@Y9>Sp72A_>
z7@~A3E4+9RU|?EG65S((4;*pk#!`}cFNyEo=R1_&9&XFTiuh<i=|jA>tsK^562M|I
z910gQA#4|KIYxbR&_aPcA#otoK4tC|&;j`R=Lqk;#w{aF=CYVXG7aM~*7MQm`kY9*
zAG~AOi~V}6nSY^263Us++_R>Liz?0Y*h@Mr(>=+}blCIrEUTCDWTP`d)<>ekLnJXT
z>W<f9jpzQTVzcoEya4_~hfUm*Av{M)Wa|0;_pB+O5q3Wz;{06O0lh=iK)R)D?dC43
z%c)R{sQF6EF&U=O^pEr|r#-;aE*{+zr+f#|of-i4J@Ax&?hO4U@Rm<KtIDG*3b~g9
zZ;PRkaEvLaG)dC7CoPyu@$l*-37kUUJpnv-b?Sp}!3P@pU<G{JL4Un!s)%P<zwXdy
zDxt9y?KCgLK8QIn9(fAaH=c%`ACmA1@Iwcu{z8?!x`Tg9n)LO>%|FlkG&e5i5B4Q-
z(rs)It(e3)mOJCL=y0NpVxO^mX9F!-B1{)r|5_qapAhanU^NZk=<fLGY4EjiO#u3g
zQ*t|*>ik&C)`R8J%yVDRRm8e2z;>X^M2oa!xB{6g^WE^xH4S0h^B#zi0gpJiIPe>1
zGUDUsMdI~Ju*{x|2P%$r?#rwxnw74{P|Iu(jpEqxBU{Z-*y~$C&WoOU?l*HDbJ6=F
z{2o^tJR3y<+BPv+vh0Y*B>~uTLJ!=sr0I#of*oBPwHIsoOK2!yh#VgvOZ(v;?+f)0
z_y+j&wU3E^8RvdJ3$Q%X6+E6GkLTz(_}tKXT*q{rdCC|WX;Y6EuTlT1lca%e2_G2r
zdGFDr-%?Ti9rx=hp3=bg?i}LVhP*>jjIt-C=$5IGC@QQgs%SGXjH|W2SQRm5n#wau
z0o^a+nFEf^3!u;X{v31O$+@tObX3&&aLD%PlJrb-=gV5<P14r1Y@>0?E=Y5{xQvIo
z<>&qr2{E1vtiRVkc)F4dEtKrkas?-%ecT}{;uM!nBt0Mc7*$@x4bxS8(wil_DSk(w
z&k&>`bWy+Y7yDQW1cQ4|xMeQ<G*6=0if$wkZ!y84-7Ab%Df(o`oEnpSeT#y5zytk9
z=D`C_;mikTP`~gKWe@<l-P*!B=!~^EiQ+hzz>G-Q??u)%)xI{epN~B;DHj)En?~IW
z8TpVG{ic}J)h7NM$8g=7QV8zv%Pr4vx3*4`1FBTYxXXE6M{JDLDvDJ%=W$nFLPOBI
ztZoA2!H1!qZ$0Pw7k}LC;9viGEAHo4HUxGvC*D5nYqNCaGDSt#iWFkHCTgu^an$|T
zGc(om%&s?JKXZY|M^;tA$yI`X4!#Ec{7O)y|Mg4oe*DrqnX|4y|863qafjgZ&it!F
z&bE>8fQ0gVrgNNCbG~gu(uthMc}|&{qCuDwnd^y1JQ1Pp!6)Fky6IohGwA6}NA3**
zIzP^`>?!Yuv?|!7(nw;IEs`Zg0@&2UltyK3vNJp|Q@cY5e0%_LbU?=O|FKXgMlPl%
zNJ8r0Jf8EvSkCE>cD0t<k?T5NBG2=35$UvZxmMdQNVo69m{q?U8smE**F~`ZfV(_J
zaN>VN{jaHd^b91W^j1!$W$KRH$x$WE83eYr86W$cCF6cfz=k@BOEWbNxNn+P>b^Vh
z9+=z_>c*z@1=wfFk3J#y@-i)>9p~|!({^Xeieui8dFpUa$8;^|TBK=tMf;Kv#D1jY
z5clOi@tIS+jZu!i(Fmpd&Z)d*u$OVj$G#xVz7>0>X2_zf==QBwLkoLk`q+8Cne$6S
z>V=<rjK7ug`-WTP2lx12{`PNQjOLMgACKmL^>=oGc(We+Q0}q9w5hvkYcNJuEX7>c
z^$f*gY}q}2Io)_3dG-LMhPxW#_+I$hyM*$O_3dUgXFCF_;#3{GD3^Jft1=O^n8mg&
zN+wwx(ZNjq!b_Yp_lQRyaHR5?gUy={FCE6oY1Vjm?QXeuCqto1&f9)xW6$EH1Dt1`
zSM|s#?*^k<W0bRtBr*t*eL9<e$79@gU^z&A@)GWl=%?&%xGftE&S`t9U**`aY-NRF
zOP*1=PFSd;9lH3^i_yze-p7z5qWd@82Xuz_SK>He^k&VJZM1iBs6pg|f@&DodQT3j
z|D!T5>nsMDkc-hYy>#BbMt}o*AkB~Zj-GEMFQ4x-Hum;u3|dCLE#wi=C7;BRb%~1A
zR)ebYy+SH=$rhU~vUmv+U?C#$_!HTkfjhF4Pt7UaZ?~ksnwA0lc2IW`rM>WT7sBgW
z)~8<#>j0b$>y9N}chSL4l5HfIK$>)8H8pXk#<i>~lU8dAYJFYo`}zy;0F#<fNBWze
z+N&>yb@VJs?j6?IPMDdR9&=g_bua3f6fhlimqg8~nl4(F#q=pe<Anh3g&~6bVI2m~
zqJ6qq5#q6%D+0@K3zao94o5K-GJ<hpZ6hKz#5s(sej^GK?#uD^7^A?S$n!>uZUHw2
zIQSzcF1U4EXBllmyJQe?O$MG%M_Q6GYidYp&Lg(>lX1A&rP!ySt1*0F?ZOCgiuH?N
zUnJz?`Ro@@yk*p(+15R4u^aPk7>9H?mV+<-u4b4;dR)>*epY(FP8(smw<Yd7`gf=p
z@0Wip{FYV=Uhpvu=L<H5{#eU=YN$F@&_+M%q7+RDOMaw-I`*xZs(QO5j+iNdBtXye
zA5g~-M~3p$=U>0*Kh(W9TZ>cQGS4!V&9Pxs9z>{0!J0sh`3zBA<a<fMT(|1lJh=ML
z{?LcGM_fOst`KLx6Cv=qJm#yj&MjZ{UC#SrCf&3#ImA*ec`?pi#%HzBBh4<VSF?IY
zT}@N=K%<XNX1A}Mhfkq1rS}WrZ9611d!F{gF_TP?ev?Ntt4Yz4kA>(|yKQFbFa09*
zS9j>a11?Cu3!yW-WL8jJUfkN5TVBj0Tbx8~oK7fds>X-|Vc17%X|u9gq`C^=jC-9C
z-Ise0EM5uooB?h0XlD$NceDP@GR{jicAF}u@?6ENYT!lH=F6Ojs-i3w7j_(Y7j5h5
zFU>x*6Myd(_gx%m@74UpzY^s?t=7PH66DdfEN-@VTzK6~<t&pNTSDd|>Burlvs%M1
z(B>>;e(=BmhC8Cif&YyO?OCMX5c+Ds?z?cIr6Xo}x9oGYNVyc_B*~ygQtQ9!<CI)9
z%|U3+V>qXbK45JXFyab&{4V&_$9uUn;9J(XW^5fIvF)@aNz!AnRwc4xFZQ7t`=T68
zZ*gvfgFr}pkNNHoJD>xNE5Pf~dPv~rtKITLUZ{E&D(<#^h9*AJs*Oosj#8xsuCk(+
ztDRr>uI$I7_Q2I1_|DM&svTqJ?(B1w>!lsDjrq#@t(%jM<ANFA;|7Z~0Xg+UvJR?0
zF2x&Oa@_*mO|cJ?JKvHv`w%>d`7gG#KDk@yXdCjl@0%)Xi?JKU5#>{Irad)uRa4#M
z6)mpyx*6N(`-~CheyO5w76*Wn7eRh!y4Ts9-OQ%ZpJ(|6FS}guswL%-G)1gBSQDBq
zO?F_**=R<&g>ZGEWmMxu+{b&p5$5)0)kcEv9ZFE&?)Q&Z^~YK+*thz~x@AJ>fXIBx
zs%oC539~3Kk7~F$l$h*yq954c!$sPAs}$zIwgT{*U^hw`!u{{L<#Ih*+BPqWIo`H7
zh8eMlqiiDu(&?Z`jrRNm;KGj8r_Kwhdp?Y=>>M3-`i<xKkI+sZ0t<)Ty0~es)9#pP
zmA8Du2v-&9Z@`f3Vy)$(m}x$23fV}Agnwv9^j0CKUw8+HoxS40>z;!9aQCxrd2yzi
zVL){>c&<pRIu#3!%`lR@tVKynGxLjG^MEu0EP&vFJ<1y#*|!K1@HG$0_lZ8@-n}z+
z%W%&Nl?Ow<b&!*&ORIiBQZ8$ZIL1?DxXN>Sb%xe|@{^wIe)PsTaRfIHULJ7|Lu7X!
zac;SKD<WEAa;PIJC6QygwPhFO{ZXX-Dm$nzF|FicEJ%=r9Etlw?&eMpzV#jR7=hc#
zZ(tep2{G%6smx_LO)}Y&txmF}8S+lWQxnf-yJmV#Fwjphc_1^!|KnoxcMvDv$A;*u
zJ+NRw1c7DEOOY>0EX3BRG27Tu9P6y6T~tg>^UOtiA-!FMPNxxiz#rJHAi7whhA(?H
zedSO>=<Rbj%QVM>7dViS_C>3YcoVZSUgrwNNU2OwVQAYzW~R1s2q~k)y|7KUca9ph
z@YN`edd%aWiy6%aJ+wTE>yNJQtAtRl#4P2}$K$w_ZAPMDp4;8XZ)G8vKBDJZ$@9Gj
z(wUJvG9w@_H)<5g&D2)gTIIDAEb9~1%jtlT4`s}jMP(rOa+%BMvQP^z(-;qU=znT0
z^Ugwz_zspUFR;e*VfmQ4?iA`&Lp(yABvQ$0?zT!)wC>1Iu|e^5>Mu|SCNqNgNcjUw
z72?8kf_%$|0npEock|J9!G{r~%tr!b9FDD1z2YLruI<FQ!BS9>ny6FnvN0zCo-LaD
z15N{Uh5OY^=toqq_xTLQG!wFX%4v;jyUD#P(_^V4G9FXLqm>MKA17NwOfrmzSEeHb
z`f__9gxl40op|uFXgf0w?)H}<p5=XcJ7C&xM^_v;sIhM|*iqHI5SvO19?=Ww4K5Z^
zzW%3AfV;2S;5~iHd-3bUf3-OG!}CYE8+hOL$d%73r;F^WSq`Kpbl$6J=Gh@K#i!Mr
zum}87ym=v|AF>@W^!Y!3twPlQ%}HVZuV3mv!TC#luR6Kf{nxX%bMEL-cE7oVZOmg4
zPyHUl$g--~abMbwA40YBCXOQ7_TP<cK5Ll(ya&eY+;=2JBk*l<?^(<Nzkhv7Y_C|L
zZKibVVvYX-^@7tTa2*+IGfJi$(VW0Bg9%5^30&|1)0Kn{<SK-`6ej7{?Pd`Jv0TSB
zg7#c@;hfevixupdEXS0QSWQ{MwoAkVqj2Fw0fgj371~?kB<e!4@)PYZT?ObF8U+@d
zgKVRo^=ovb39Kt+AUcXMi<Y{J%bI0LeoSVH&n1#wx6rzlqs)CB$9+d$F@(_HN#^#!
z#(qVAu4UcQ(sWa;>TF__!nQs-UCV9FO8Y!6cspG7D;Mzn)3G18`<I<i7ZVy1yf%?L
zE!^*}-fdGK<0(n^cw3iU0Lgi?Bz3FGI?@+CFOG3AP2?^qs~$h;zQ`URKe{psBKVDY
zj4n3<8wPR2G6k}iDJ_O$TSz}lwH%f~jO`HT(XgjSZHBe+p9}rp^liFp3%myu=G@89
z9ls+@;K}a4oit$^^L9Eoj5}>r-c4l$s;z3+q1qRA%*B*m=uu{3L+I&pE_{GA;bM1A
z@Rh%}e~M_}?mephJj;1aNl`8>sY}`6jG4;xfyFhJ&6ww`k{5%}i=^SSh4s*X!doD4
zv^@V=$bI1h%pk;@rHQtyx1-qPP_2|7mE1s3#S2~@`9Rk_iH~Kx3Xct!?=T?zT(P+y
zyi?ynTod^^He0_dzzDh1@y|BWo1A#rj8T;i!;wwcHA`IxeY=+h9c5*NDf6H8*{^PL
z2!aqFV8yV|#nAPIaqH>kOX=M!RLcXmIO&RQ+`4${r>#hc%pgsMtZPoo@05tk6y}<n
z4U`07z};7B)CJj*aQ}7Wp8k>scfZ@*wn9Z7IZGlI5w@xJs8!Q1I4a2&vdtW>6Bu&I
zQDbM^Qs6#y54j^Z_n&?E^(tqS!@XCz<qjNFS~JpeG8D-{6!i5@`-RJV#UX(-Gaqdp
z_@<F#K)o=0;x2bUUf13AYo`zl5bkvfA%SIQpm9A1=yO4)v{<K-N0o$HP0cRj<|s`o
zfgmu8a^w(D`hYDE1#oq=y_fg-5394g?{nLbvspki<xN?_1VWH}jHj01)D7w=+7vI4
zU(6%CfHUra`}>@F&hGPX)}?280pZ79P+twyZRh8bq?K~co4r+83jHdF365!<*M01{
ziefV}IW*O#oUrgi7qEB85tO^A+(LMDx9cb7hLmjcq=%MCQ1dZVP_CkxqE=UL^C;w@
za<Z%mn+W8&Y1`@3i#3o&%>S?fe`|e0iHpW8d^uwC^}kVaJK&Z_Y-!mpGl8-^CN;!W
zLWE!|9=TA0q(ym=p}{qHDFg-(JODU4*q6O<c{_=%c!LDZfZOu;Tq;IOSgR@;x}&I@
zSct9~Iq#x~jD1E;T}o)2?ob2Gc<{i~1wu!wGJGW^rwDkfl-x4b4cnwByJSDMC9eeS
zNfb4-R8vAmF{b;){)u0>FO1TYk??@h(8VkjzY!X;)57s~Qy9yL*GG&bBU91$*|B8x
zo~b2L&9qb<iCH&Yef=(vH)Ut#?7KhT#KoNLn=QD$&M6SQeIaTYa>ftU%4Ba?S}VS)
zsLklWS=J;+KlE_ntcT2K#vwSvK_39z3tRy1y%L@=(B0&{V|29LgvZ6)q%<2-)@EGB
zQI!|*8m05n?fFbD7LJUOYkmfVLGXa1-y5aco6ooRx*<ak$=#|Hw5>|X6zvXCRQ(x)
z3vwxnGO3tgG;YRO^~_|ddl#0APtTGqe1Om9<WBd(?~Ni5J#zop1#M@W<Cqdr)+Nv8
zBwdzLwv;4s!m2Xbr&+BgkI~G}(2u)rNFV6Rh$}Bg{MwV*54}J?NaW_r-SRP~r0grG
zvEK{8c8BGVbDtH{vS-~`3v;M`^?mXoq%;W8y?G~fL2W|tzEK+za<}Ib+Rj(d4fn{i
zPWH{xZ<4Qd%IhIVvD3CG^U1i^IVYEV9At26GTf8Y$seDrzGw7>uRS7w`N6He0k*TQ
zlPOkJSFHkAvXHqfma6H>zL0%9&>pv|$Cp8PL0x7upFOZP;|`XjNM71D`lnlEaPN{7
zZF63rW0>}eDQugJ>`jMdM5cl8JU-GI5>r8Lx_jw58j+#<WJ`20MaQ4s+h6a>P8Ywx
zw^6j&w%|UhVn~)!)oI;q!;*D%li^-2Wk$J**52HenZ5ypq3+tAaPbRVyy57*KI1@<
z-+abxH{_eZWa>z_#5+B<Wr0|ZbFY?isFqC}=B_L>#f2Ix2r+!%jMLBs+W5V~j06-d
zoN=@~ayzC1n`MqWN%@p!BI`%VtBOsm=|tI>?#rGTp29sE`shEfF7sW@VA$(g9SOkQ
zJ5v35mSqUK`W8SZI#feda+2g@+;*!h(`?*$Vc5ZNa&?G+5OhgJ+}G;*jd27z|4vDa
z`fEt;AFf+|&RazzfJ$Y_HX?1SwXM=aV2&fFWhO5ZS7Zk8H1OaN7eC)g%^tiUsq2az
zK3|_1{h4JFD_h!Opve*)ykD|qZjm?XuoNUIcae$29KgVpvP=VAy)pOCImOT&*v4WU
zeRi7h-n$qNY>No@l?z&PeZJQ=Iy&sJ+lzcI$1&lFp%@N4Q)6@*{+z1~&;1^S6L;tO
zWn7APdlZ&!#37D~EP<$n92l!pQX@S?RW|WVd9gL-u#I1mu#g1of#+NQUI%!GuM~uV
zE+6h5q+8ybtnHkxY~7c&&Dhb!YKdYf`h~4|pKqHPjDwV2STCrr@h7bNDD~WdeZ9v$
z_<TG1+k4zH)O)iHb+HfWbhJZ1l|*LU8ZT#lY1^d{nqu(4q`T-ZIPrn|Pu$~y3#h-@
znNSLMlaqhi8e5#9(_$*>v>mDuk~$mIun1XqjPEc<sx)?@oOzdrn^4A(;sbqH=qQ(%
zzKpT_;n+s+k1n+>6ecN8l17ni61wqHs)cr_BdE8vgN$FywS5*|y?4WahT#+D+K%j;
z=r<BG@NZAVp_UJNk&<Z{^Nb}Gt}>G;A*4t$5F$?Ub#5+-LjSrQg^+^hJ&{N4fV)b)
z@U_BB_uk>{fLngc`?;d?)C+9;R)Oxj<<NFT!qd11DRyNjhLK#IJ~#_LTZg}?Fe8B@
zYPzm9zMZI_*`=NZ&o=7YZpf8Lm$6@|sEcT9h3?6Vo?x2iKog+(h3j+ypLhYX;1Q;}
zgLUce0I#q3&lThUf581hiD0^#1OJH>dI#%L`r2Qeoqff<+fr(o;8r!2?AX>xl6N3j
zO$#o?P_iS-)SNe^*{qof3WOt);DHeg|Ko&+_t;K<mmZmHr}Jj_y_=nPZ3`2o^59*K
zTgHGlHHiy?Gm}h3Gn6rD4Y*lwHQ4qDCqLae-MTV55f1;5Cj5`T{y+cu@BjOM{>#4_
z2mPP^<KO=8|MBPl^?&}ypZ@YMKKrNt)SvV({;#$x=j{3B)31M=Up~h8?En55E!Tfp
zERtm#b{Q*Ps6|v!lI*M6W?FBYDYN4DOmPFD$ly~U%UjzQ?uhS9*|*_3-kFK$-O7p7
zpXeZ5r;^FEM=RrFHaCf4GKX@g=31y_C!6^)oby?3a^--19EkXi$6pXQ5Fk_jZT6{u
z!${}4S*Mma>ui*Lx1}+3dm6=65%+TeN5+;>k!p%^6LbH%ZslP>N%(-4i90F&IQzy}
zf+M~8{^yqYu<1^#W3DSXjwz6Yu^1al<vvH%LU)>7d?h^7BFYQ+6RaubJ6NvM;5FE~
z481$Ep4ztLR$@Gm3>cRKmffPu`+Aa<D0|ZL-Q>-%kX-D7f-@13K9H^g)WPBYGOk`<
z<&2<z?+VWHsm5OPP*vkj6V)7%TIcb|Cb0u)^Q7vGIc<O!3vMsuJ_$c1#&O-&5&mV_
zraR?x0RG><<UfAtD7XA;po3GC_;F&nOPtH4;n7U0J<n8~E}dk1igiZVzLaxP7<sk<
zF?~bML|67<h4xl)&OLB|viJJ-)@^Kf?^A7??7FfzQOMJ6S)+2^hpsvZ%L^vczQAKK
zEY=xCQ^VjB7V-yPYW+JMU`<|w4K(=JLBa%^*p?wKe56sT5As&U1D|`^r=lds78O7x
zH>u458aFtG9`XDK!swllWf=L!?Ta#>-i@~9Et@P=+NUWQHrA>{#PiW)DPw&u_e!zB
zj5?$qm_u0Ib5Z^T+77C4_NDjJ56M(`Lu~PH-fP>wFog4>&LnAy5vy)4ilJ2zn<qNu
zRf)r8fllDEQqwgGVbr;ABM%+r8#4M$uq6NqKDO(;&Q+LYvdpj_WN(3CddPY$nuH!l
z!`Tq`LtM9bVX+6sMva|A4)VZ84gNT>`MoU*qu)4o>aXF=Zp_U3UXAUvS?Li?c@gDg
z<4qB#Q?tj}SVy#`CMS*?4>%1qC>}mBSV33k{Pidei2lpF5x3lo&3l(tq8iKW7_u!%
zajrz!=GCzX+E(#&k(Qfe_5k(EPM$#A0qK>om##4SYku<<m05<mqT@`{N{Vz|IiFb{
zb^9)-7Dac=S+$w0s0+i{^YI)j`R-j|m=`)a-t1Litw;IChubaQP)DNe_|R-LZ;E=(
zWRmTLIO;KLT9#c{aNL}dv$JM@U=zmB(Grw}_%h<mBcXrysGNnCEA=&slWeOZ7OfnM
zBj&@x%VA#U_*mmonm$0pzi5lOhas{D5{kKt)yU6ioa=qAe`fu!TaUNxSRBgwz3n%-
zrgKUQCM3mS%tkTCY17w(Y00ar6Ei3UJi<N=tbC&<V=Q<KX<eQYa(j@SZK$zIW>x12
z?K1&~%wn0SXeo=b8;>%@^#V2Zu6pA0?1B4UO#em~Xnz-%0s3?^WcPDgxo`Oi?_wEk
zW0v4p9sM-QM)G3a6aAlcL%Gq$v<ES9KN}K;4;b<?&%yYdBfRv}*LTm|HecMfZKFne
zOzSw$_jv3&T#}uy<u(^>CdRtV&GZB?=PkfO&ws*io1p{V`fCo0=L7R^UX0nMu#|_W
zraX?;HEq*0QgqF$c-wXw?^`=HroFmH%%pL`Jx)IrDZIr~^E?+|v)8Uar|r+(Xj_Jx
zj}VVZTvZKe%2H!o9BMAIZir+r+Ilexb6}=80nW(r-~qzA?*#4F0<?fKdbiIuXO>rE
z;!sswPs5?sRpxaaWjx}QI%=%4w9F@Sjv8L;wR7I^M8p{j9grM2f92f==aX{xU2d6w
znpQDs)>%Y#&6h&ea^bv@s$o-^ZA%tkoSiOXa|FgYbMMp`xXQEp3HTS;2~?LXHxE*6
z<Gt2t93Pxc>$nS8>9$ec*UeC3JJ-!<(ocggg5=NOBM9BojhU<H1RjuYRE9tD&A>)S
z7Fc#(CTSz8y{SY`ioKs3BBNuVeRs@LA!Q$#9hpf|Jckd2F!w^Fz<0D0<>9NeaUX7<
zu~~k{>!u#Ed@0Lg%j&*ZMHbNll`hcPGB#s!2|+TC`We$1kih-T&Rpou_;>Sjpyci<
z-S+rA)n^%Lnj}>`&TYKOJy%7ZrkkAGE@>}G<ED;8*IO(g^ogF#)wLdm-wxXJ&Gfmz
z;H!Jxc5)?$HLbR8FQ=aLF{zSlFJ(J!QL{Bu2^aOanL6%!Cn5dg1ci5|FFbHCVSVZ1
zch(vNDc<e`WLZ{{Wn0=0)!Nax&87wFgMz|p6Hz-Qbhr#)!pltEXN)lP0{2xMfj{oU
z`|p4H+Z(8#0a*Wtu$cZ-{Nk@{_i0FPp1__z&MzNhe6}lLF+D_G%YKcrq+8=;i?#*w
zI`22p9@9Lo<^y4Ri_nu57J&P5K$o2FJP`kf{vqG|*1Rx~BKpgFw}Dh(J2owups&QD
z;)E4Zfpb$~MCVNn`(BD7<7OGiD8KkX>f74)$pe8a%yWr6|7IgYJ`YK}AaA+VS87^>
z67`DN5+7-j(xffQs@!-<yPaQN2`{)ffD%S93?E22rp!fM;QwO}1pIs;;J+z!x)b*N
zyT1_r&yO)a+t~w=k8;b2=rG#&m>xnkBTdU;tbvvLS{o}o-@n)kqOJ+}hZn_L9J?TJ
zM3sN{EAvApL+@tTKK+epk}9udlg-<d5Ai$=bEYJj;<d+!mD70f4>wgbKC++t496;(
z_ezR)zAvwwXZ0Q8d;aa^gl}0UCx_!GS7^&+A7tDLsk)@B>XNDz`hhei=Nd15l$@T1
zl>C8s#vpVvMGVmYCc-W7Z?7cKGKVW~mH}|Wc)-1exNnJE#Y##bdmQi7RKkXr67m=I
zxd-lb&&-8KNkI8)z$x+A&DXwdQ<|;MA?c%BB>NUEGv`u@o@HXMs)8+bXR0I3NKQo1
z_5K4ER2+R5Xb0aMZ%V_v(Y8EI;&q9Y!mf_uf_H7RA*&@zY8EefQ^olOZSxh^=bZz6
z0&NHD{(#|Yv_0=`?p9!15IfY{PWw%=aokJZW7_wyX{=Sbbi6*e8KWMUd7Kb<kA(Z^
zLeU-CFAQc+{WYQYuYRqg9#0tMYn*N|Z${4Qt%7nbBbx0nPDS0Ct6wu!8}(P+LwI02
z<iedMc*WQ|$JprKJ_@$Y*h4k;<+L0zi>9&a=V4VcA9}*Krh#EgE*@j%qW_%Le`q@O
zo}(Oh@qT|3&<FnM<Ko}%BN$jN+2}qd*eSNg$vTvBN}^t1DY|G%(ozkrNz&vO8$lXU
z{Y7|S))%-~_Xoi@vDyH5vyE&JSU%!=-pMH0)`CpknnDY6*){@(s;p$c4&%kZBs51a
zKtl3B(H0OF4OvLPu?%PC0sk27(6XDwBIp89vt?DeCjA&6(-aL$kx_lCH=<82Xa^U<
z{ohA1ZYkJ-3oEMd^?iQ6W5jfbzvDi)OzCK#pX+6=+M!L=fs9pMTa>J5mSm!PN-tYG
zxFkGr9(Z2(0Da2?2O7zriC$lOK>zSK0D5!qs{Tj^CeR~KrZE}Ei9^vK?u_*+FBng<
zD5a{b%&i@S!6jokAjsi?H4Of7UyJv~>Y?X<(Wd>=U;gyBKmXbw9z6e|q`QUEb$<TO
z53}5@Z&Q?!c}ucJc5xL&?RumYiu7P}L1%-WPuW!zk31mZGyHsTaSh-%554YT?tSP(
z&vKvMRinh?NZPKcuy3<CE%LP$RZ=z`EU}puq04B4q(c}5&fP!sZ^$U$J^I1xEJyGm
zyc==L)7L_-T&`VJtEozkvC6w{Q>&B_8TMtMi&@&4$?B-T=0O-dfw+rj9{g|Sap+TW
zakjbVf(OeN`^L95>au94R=%_p5wL129`#MPwhJ3f&Te?&?9#wHo2mzNIDw0c9m3y<
zcq6`rL2L+?3;S%AjT(oMNve8w5TQms?AY+WO6HoEmqBc3%I$nF;K2i?!Y+(QLwv2R
z^uo_G{mjeV@@uZvyr1*9m9y;nB}>X_PPUG3aRF7<U&B4f<&^sx?EpRc0PB{!=-lZ`
zY30dkxVe9`JfumHFEUD_c39I!?cJDf*>FTu6}3p~Br|*VfO%icU_;%uKQMUrd>3ec
zH<b(T_B;t~2Qte#-l~qw3AP9c7KN;G$S35r<g8fGEZt1q4N^wnL(A~@rgDGW2ID;@
zRLH+c=S5C~yDxOxqRQ+T+8Cxuv9?+h(lsj?Ft56V=ZT=Bxjhff;Y`She!=m9aNYnN
zQDnp5wGActocm_n>6W`QZ0ivurF_h`6eqIfv^iJ@nbObrx|nkLpT70Ke!w-{Ec}$?
z`j#o7=c*%rA({q1@b0jS|1IE_4|uxJc#v%w6LC~k#niqHZ5m}qh7B$AOW=CIuPpde
zy+XVP#FU-`(L@-2!*zu4Zi>79ILkG9y*B-Dq@{>6)vCN{@|Le-Q%V$dQC+x>o|)*Q
z+wdTGfZ6H+bAk4E(>9N?yV16MpR=WotLiv-RI~WVph##0jZC`*MOR0cOdk&~JgDH2
zX`2W3c~Gwm!+m|K>8<|JwjIlAHn(*@<rs-A;Sp?|OcY7ew%(RF!;3!pLUIfl5aK@a
zBOq>yv{!L#y6=WN<Jc_Ye6$;~ozH8W@-C@{1l3-z70HsdFMDp_9R9qfe?^NR8~}p{
zqLLkOS=lSsgEJ}@banV4&Zg;sZBApClAc#>rD)a^RjQw6merf82U0OAma9>jDM~mK
z>?wO7V9|jq9rM1vyHBWr-rIE9&fRNA)nsGe<wKY4i7NJu$H|<fz-YD2YhljOJT#}K
za2mn?obI~Cnjm`$>mLnv0Ku*Av}LI0Hfu5_bko%(6Q8#<iK1Ffm=94y=5@b5)YSB-
z(*NxJz<qa3g3vk8zvVcA{(}>b-+Z)PP@I}ZBxI_Sw8+b57HJkWiCng5*~KK-)Lsra
zxmZ%@dQ|`MAFzuK0A1n!)zhuJt}_7q?x)-GG4Fc1RFx{@Rn*xL?_Jc$eUcMPrC3YS
zUqbl8i|B~?@L|OLTWuF%F5vcF_t?7gyO+bnJljF4Lz1`Ek#4kafQVA%MJ@MrO1hX2
zZF~hAjnjQDgCKZdEy76PWG(V{z`uCGee`ax)-2<lKvwce?UL1LEsB(Gea`t_?t8Z3
zNVW@AIk?>Bx*gU%@B^<nayNuk{b|9gMc7GFz1tGt{5-p;_w78Bx=Liy@~%`zU!?n#
z@7Y|%OsLIt2?w~us-k~xXdl>w`7WC8p9E!N!~*EEGqCy25sPP;sn*tOPMR(|rbf)m
zI>4T({Fr4i%nkCayZFdn7>b<zJ-*v9QH=&Jfab6L|M8+0{`_S7wihCClF?G8T_2|e
z#&pECuGU;1^6aP%ZmvA3S*z)OJUBHs^nsHdx;WY7dt&10W_LR=k$INA!J8=0pl^EQ
z95@{pI0j@pq1BX#tZT)^8=RY?RQ=oN16EGt4OjSg`~mg7jj!{PJ>SE-4?4BXPMkzG
zkaER7YO_iS%EnG+(MHBxj+mRGLVc-TwI$#O>{C~Ow?KcxMD|V4`AcU2rhg#+=HAS<
zvro47<sQ#H9kW!8S$=ZPmt$6Owlz&cjbk2gQ%H)yS%?pi&dD44lJ|Nu`YrL?I~hHp
zh5OyMqO={NA}?8dOj}*`t2%~-t=kr{d05jpnoPj~H=cF<CI>$=107FVLl+|$_R^>C
z2X75;KIgV4ZoFWmOy&T1K!?9HDyImrDsb62X`;3qx1yTpVd}_Cv{Aoj9uM71NC|V*
zku(3>Gyp~jv2o6s<#uhHSDugSjzX@Y6Is-aqu^UN%AL!?B(Px^nn8^E#wDNXMc<jM
zqXVZO{f{5M_jl55hi3zI%P!xdAmiSm5>d~^f@4D@RI*%)wVQ>M`y~P*G*yHEj6C4)
z<VrHGA)w#n^xd8Ja(<j;!=Ey3xIDI@pCucBM6pVnRStrutsLlTdOVqk1LrLG=skb4
zNp~SE(*O9s%iv_xyBlq0dnm);=;nG$M^@)$ML3T(py`&M5sioZy<QCoP>(-g07JNw
z>W#lfo80ZcdVZW`uG56PndW5bvj*Zi-+DQYOQp)R?J{K!V|4X)jp|?;fhW+WF3|oi
z$LUmxB61sVxaAJ*$nqwwj#|zj)?t|jvdwZG+O8=C4s&6?;hveZ8`6+`iuyZJQ3MyL
z^Op=a5`Ii(G*+hE_KLhFO>%TCUD`2^^Ks_=v>jctEB#mG;_(x*;9{JQpH0}`<hN00
z<r;sL#CYmlf}2<5mho<~F5;_<<4jIRH?G^r<}&VvafDbERe8aiv#Wu+7Y6<VZeHjp
zT7!9C>jqB}jIWEydk?tf?RY~a4qH8K8SP;a4UAD<ceqwXd$e^oUN|t9G)6zv9a8B2
z1*d-K2=4EcMMQtqZ?4&FD~slS&a-kEXQ-p3-3ganQ|}9D_0!$fY%`TbNX-RW;04|T
z6gPB1hwxv9s`)e^H~V_n9<ePe?s*hXagoe)+(ilp9MKWcqvEQJ3{$o+^yx(u%mXj{
zkk9y5q8b5kbG-fU)F-F&?A;Vr%b534E~1!q8(ojdI%ZKlDw36vDzlVA7n?Ua#S052
z@PR#0vJnSSYOmqeUqvALukMamwT*Ya?0LPAt%ex;P2_ZHhN6iV8JBZj4HxSk$}bVC
zgoObo{sV^`(G}u<`P;vlD#CMN#?4raKMwe>{?0D&u1hEf8q<1*ZY!ZJ;;~uFB+H|s
znETFPxp8tadeHSUWAJGV$~!BwH=McNywkmZEd0*rUxeS?ZLxm-G}rLElZ@vm{H|Bq
zQtN-oq3p73Ji4h-Dp?Cj3mo!oFh{b)r~-6}tN+h`fILH~yYI`FGGqO{{d{8co6EuS
zIz8uoCAXr*vLDt)Eqv^!e9Z_f(3N>Tm>gJ6&3;Z}<sp3{|ICr5K|g^nz56`m5Z+zm
zdzKe$yhGq~awKGLjwn0&v@J!QcS|#hKCMkFUPdlF*Z>%MPt0uKkDEojdBXjd>^KVC
zzx&3wTm#It%9b)`jhM=Ht9Tl#y#m=}#ahMDn3w^$)Fj7+gfM&{HivP~LBZ$KZ>SUJ
zPmYA$zjpC`%jaAyLQZi_vqY@p%9Dvlshs0(i{>;Is=N^64Ad!5h94OKy}L+vVF}~I
zixYlwICO<^_pNT3Cv(PI3p^IgX_>FANJ=)R$kHa82i*d!S4Y;1y;m4e0`Oto79jg)
z{^e7y`?!$m&;74o>e~7IrKevKbabneZ*=EBBn}+!wRJl`(t+^2!~*hSEK)WkJ0PYx
zY&G46HtHCeH*;{O|GXF7IZ%xudmypeb6_mt6MW5f_wfGHPAp3t^8F~HvP^2(L<EX?
zVoN=513mUR()YfhWzzNa6>tp#g9qMp;%X7|chFx6nh223O&q^^*lmMf)kBjPTP>rM
z=L<Qiq!js5bKEnwWJhO8nmqqnz>|=B{DBtTcd?Tp{Po+8#J_zjL#&Hiy0VDklvHt9
zl>==Txiv{L(KJ~LV39GA39gw6=VC(FWA5MfH}*1b0RB43nB1_EG2ym+yy>x|8_AO`
zg=LOq$)jXaWq#CiB|BPP48a2Q%uqbtqml=bjF}4ttWUjfd|KJfnYQQ0S@w`o2c`L(
zc1esWo5z^%z?Ym>$d@CnXH&Tb#^ELu8S_K;Xp_(pWy+`cJIdtX^GLj}9&+14)oxnT
z_+Xh#M_!~u-NypPSYW=7iAsO5^!s&(?wjl>k5l6PEbbgX<bm(tsK4U6YiKBvyM@WV
zWv+V#J6AD?j@8LFsyvrzn{`~3@h<8GQ}bf?{LAW<f&R9W2mJs1z=7q2{<PP0cdGl^
zy8-8xr!w0vvaV=a+OuIF`yo{tfk8<oj(pD|Gu}2}^cs1|eIyU?<?s#rf%k6r@TH+l
z0H3=6{$`tIndm+(R7`}_H4GCrWRs#_)Pcz|b!oj%hFFbrayj2&aLPLHiJTk<V;K0>
zxtG%0xl@*p_tGb+P$E5&wkS#3?n|Ghs;E*FM6D^9+f!<G;>ZyKc!WE}+??*8F^69{
z!cl_Zy~9@9*@hWpd(|P%Dnr`l*^14iTeCH-$-r3AUOF>|m)J8J1VQ*fY6?XM1snMA
z{VI*>BJ2KD8ra^h&}pdnST_^h$_S=<VH?4?DJC4EcB^Y+;s(S#=b`5V#Rpbtu0#&-
zvsQoUI-r00&<66BYxc2~d*3X15v7>UsGyYbJU2wFNg;YLMsJju-8qCzA9rx?I`D>%
z^Sj7@r&<iX5I^??{1SP~#at3Y6J;Z%GKDtl<FrqXmhi5Vwd%)tG|#;0;H^7zT}|@`
zoJK-NRCxF{!}tusBcB)WUqNsCofmtf+GEWU827HFtSzD@*-~1;x)64l*FE(v;b{8I
zh8m9tE_`%V*paUbyK@r&aIb6?EPDjbX}%Yjq(jG-s+{COqMFHu7v<KZU93!JNZ-Fi
zWpPHq{dR?N7hM}6uPmhW&*jsb4Mz0G*+m;F?CQA~yE-b1owSuqN?pOnxTVR&^2{8{
z_-42cKh=bu`->glNH=}+Y}40>`##{^h+AgDC3z>**z%PM4tb>LG!ott(RItV9%*_(
zoS3!~5Pq6X{wCtCo^t%YhSTqgjT+AKeud=oGWKN;)pA5??dBMDF~3K32Kg|J;=+J5
zjVA)meu^Aj<L-zN2key_!6|RM`4zVwj+d|10?Dkzk}k5Pdn%EMK{joX*1a&D+fADh
zU92)>=$_S1dFT}Fm#3Tro&|?z+qfrP8PDx<^zll!xsY9yPhv{t+HA|dz+}>)2$(JU
zNrod&oN^b{Tj0OWrq{1I+`LnRz;bhzw&T8*U9og^Iz!crX+z17Cow-t)tNiB0O5-n
zEQXXl;2B1VtLOYxI=%1tXU%>$=9Wh><)DTw+Oq?Xp`fLTtEFN?x*SDS6_}~Z+}#wg
z_#OpHeE$I-NN_=bd)c7*0in0UZMi>_Q$A3ZM>5V!1}baC*okdjDebdl78fZ44dFtI
z@#x<J%$>&E5*HzA<fUJj{?^@WAY~cqKG{oT`<gTv*`};uJBf-eiRHofp(!tU#ykiv
z8*{=5`BaPeULt1bMu7Sa-u})0aJI8JM9$J=W@93vdBtUG;(<41UzRK$@M;&vF}RFg
zPF~0ZV81a_e-CW$rJ;~+Sni&@5YIM2LM)sgQ#neK4>gdK%~>I1tczt4Gr2I{!b^}f
z4a1LvINq=t;lzI!@RMxm-5$PT8}ULMIn658DcWOHiLqJovFMj>lpvZ>T@k;O=fHJw
z4(NWG4z8j&i0^;jh@bl-3yU*iTWBtzssWNsWK&cZW7{4yCJl}95+dHM>m_W-<U4vy
zcT3@?1lPB=rY=?~1pYCjnK1mt0*3$E9W=b1|EhnSUp~h8Y*$V*Wk03O(o{6s%b_ph
zso=wo^|r}wKjPBhO9lb3Yt~|j`rx{s*%9`}`|z)SeJ`wu!0Vzwf7!|HUkl5LJ>!-g
z`z)}WmrZRbWg3?S%o*Ev&SHMis$V>*PHU)-aeu2W09X5U0>L-r3e?3vq5l2DTK%z>
zOTuK2oATIem8rBD^@EX3RDhgVe~x$zGjRQ<G{tSFKeYb<LmC4I;x<CQ31R%<FlmKM
zMQrcfr-Wq7gnS&TtSuE)$wtZ+_*Bd*8II;s7?>hArf+)69`FVC9PMTZ{WiY`Jp6pN
z^A+-zSMRk*QMGE@XNv4lu*1^L<=Xa3)wB7?OyIAKX&#&=lut}<!#{2|_3wZB+Z)jH
zZ>h5!xE<&%tJaG-5lP<d`JNo4%;cgZtH}s;m(!vhskwb;M(?j1f7DkmanGFv7je5k
zQUA}s>Ho=J{;xk>R&&0|l>g(P|K{)Q1oI&p^JA<_B5;yxoJ82xOR@}8CEAp?jj4zM
z|1!`8(6x0)-EZf3;A+Mfe5rVYAM-D`Rq;jw+Z|k6#6!7cHLY7VwoARVB^eU6mr-3*
z)C}|quZubAGxp*3{jF&aXWSLs{I!83cz2r#lECsApH<cuDk>H+V#CNJ4nB+rR)nV+
zt1}}IAYj3TKdBM_lo<a`&(6Ssn;^d0)-d=yi|@DF8q4fCppe8YuKR)3c?@M+%xPU6
z#mGzE9Hn`epJ_?I1)Axr93ENCh2)*0{k`LjF9eSI=HWo@UB_BRoF94G)e;-N4MPQW
zzR<0o#zbv=q}dD?#PPCu4;dvqd|)s`sOJ##uT`xl-{K?z+<VF`&+L)qe43IX<5Rvg
zsK$-T3C3k=j%i70{=3JVQq*5|=A3N7h=Ykez8<|2{q4J(T7$NQtiz`IG)Zz<Om)GU
zBOS^#8TCa~Hg!wei(;LSOMR|;bp9b3{=LyF=g#oH5~6=J3V8E%ZW-+)fp$z<tXrvI
zmSTosDXNI%P^f0;_DeilaGAaYx+@CE6aMZVx<H%1BuaWdrR4VG&22|*7DqJJn_@EU
z`z2<yQpr3<%QB~o)BlgUZ(EiW$FlsJc^Vr7X-k5KegFaDjzC-lZ#_0;V{O*cFH`;h
zBO*^$MTp}bmhMR2Q<ayvSO$L1VoUq7_F5JPJ|=K+`#^-@uLU>HhS@$0b>R_H(&VWa
zhxp!73><gW`yCrp*L`K}mX897JjI%eV_LOn7g^e;`In&CPYW&qK7}~^ci7lp_ilPI
zQ+v3)7=@=4D7zbR$B>t-#H626BC0B-YtyBKG^{9h#>9GAO{SOPo1Fcx2>CzHi4Pt$
zz_V3Ve1E#;I>L7}?dv?^J#7Y5CxcipRC}AkBE+EhVVf_~%O*NO@!4<jPpEle+2Iwy
z;UVA=jtROQaK|NhgX*d*ILutuH7^sIt+*_+4ECzWvaz@k?CS;mRomI5=n#DZaQw==
z?6q+zknh_rB#cgS#Jv@`;~8mBvF?VYXXM!HeMzdi?ywwZ)wD2n!)~AH_C^yrH`pNX
zFE&BJ(?UAXhiIRM;rF6VT~EXjS80~2b{LPP5Qps7S*EJ!>YcRPh5Zyn%=Sn(wMht{
zfZLNKB(O(tGgF=5d*OCmk)f<v(cEuE19?JwT8=WuT}84c+wx&dE)!9E430yBBaA))
zx2J7I_+wk~fBxsc|NGzm{%`+bGaw=qVEVR*yZxvC0e<XygwnKgleAJ&)K6u*Z;TZA
zJl1&Z(2Q-Xwb)*7f^#ZOf)5z2QC}x}{K%Ol3^5_MJ7_};t_9=fT^(CbXDJKSEU8TU
za!(~kX<H@KT6tk1yCiTdHt`A{@Xw?^G@i+0L*<iQOW55Su#S^AJ~hzpLqBwS=~J|#
zwM}ON2<POO>2h^zh%XMB!D*=Mzu{({>WAM(9yluh@ZbT=?simmjCj#yZ6%M1pV9+U
zy&pO1vohZp&X0LdvCV&onH}N4%v%ry{v+J{mmVTKc-&JrnGC!6M0f4aA?pO?bk<!)
zRmGQd$%<q=`>woZ#a67gfp&Ohuwp<lB_D|Jz|*n<34cRjHED$lhYs^xx8Tz%fxajY
zHI`6nG|+4xtBTLfQPd*OFWNHUCDyTl!hBBuEq3B#fJV?`#|C0@EqZsbBgZ4tcEEK)
zMB8ebCF!;$LoO8K&8Yfi-SgR&ii^qBqJz;Of={T+c*@!T1pWJHk3wudz6;$~=iqOu
zkmbm?>1d`B_I&Tik&bKGqNeQCB!9<PKPPPHEL%P>Ucnx?jRZd})K9Oh5MdXEI&nN_
zA*mXLm|-f*oQ_E{<>)BVWofp3pwlMow!1w@#is@d`oMk?`s)Jkui#FfJ87OD?*6Sb
zf*rSF>BvD)0%O|cz}Iom6XoLq$C@t3l+Ksi-EO?cVHAI)QpY~-c6b`?<kVOSBPY@B
zxJPr0E8>7tCC6EG!0JP+sAk7L&eK*cR!UF9iz-RXV*I9?=1W&Riabyr34Q35OiXoi
zd;R7($VJ`MGNa}OuVuMIQI2@4DdCW%o$S-hZouOx_--XBis>i3lK*-O{w0M0@<>AN
zEZPn3@x3$|;#z4+7LCND7|B}mbzjr9Bt+CT$g$Y@CT*I`*G=>DjtZDO{sT*=l=&*z
z>0{H}m;@-e8*$gB*zMBw2d84$5zZ#O4|q+B)WmpGt@+m3h}&H`LgEO)2h@M*U#B&{
zia2>_rwITE-Ho{8KJ3c%GEYsz$5J-yGO8+RSLlzUm5A##u@NVsy`BWX-i+~=a(2pm
z%vosknCfb-nCNb_9dDZQY!F)PJ*RD-sI-<<vB+MDq@Pl%*rhRJ&($z8M{M{3BPJSo
zQj#N&l%9XgS!j5BFV3~nGm?r|S<1^~8Yh^03DukzlgyTucGX}n7soWbCT<XX88dkv
zw1hs&^7xs806`QSC<qY8l!;o1Lf~TTN1C8{CR5%I)4n8qo6RK>^s<h|E=@SX5Q`(`
zzdVb4i9^xHz@PNbki2WMc*Wgum3BZo<ys0-t^GoDu9CDEhN`My-4|8YHf_ST+%oTb
z^d1ND#q=!<J!pl{;5)^LAKEbRevtn%Jg1JwscD~VP!y`*%Zk!r&?Rp-KFwQmNG;0s
zx|4Q^Z*$d>FQ&WSt2`o}7;!XsA_I0R!-mL(_?vmG<2HMuu{aWb<a1tinA5BpBu`aR
z?a;B~u*Kg9vbi$M;Kn{+v=+y{kSEV(YbeC@ZCjpik#}6Ip?%NlPDojIl^l>thl#7c
zg;lOpH%!>0HQP-SBE*6y`apRec<@c85A+0nWO3oWglFnFYgctq(sG@XByG(<i&Zb_
z)bJ`Fxxo8H9tMD3JkdkMKH$zm<H#S<HWMxgN&NN<?bnOkG0wxVQRt?U4J;dK+GpFb
zF8QYWy-9Xa@QaEowfgFS!YD$4{~l`up4`=F2+yza^LlYWl%Sz&p%{W$nscg#Bwg}O
zXOL4}v?Jpz&Cp70Z{(}0V`$3t_+8fPOE)?7mBWQkhvw*P!#QwUqpls%=QJx;Ig3HE
zN;94`qJ$zTP<QNY(+;*Tb{N=UA47nH*uQ=VePKWGrAFKn`z=#Q1mx~UoOAyzG73eK
zauY%)4QyMr(Xr~Aq}M~z&yZfGX&0407DaJDKG29GfBjN_G2HPZ;TVi4qW22NxE`O@
z=5psf99*rWfw>{ATC|k?n6EP`S#QtGzo7kP4LOYAT~F-Sgkz`&nV>(>zBFX0dF^g)
z$hbCT>U%vUNlwwS?mXFstjp1uc9lt&raZlPaD}1m!Vs9y#3A}fLxy<6`ca#mL?pVu
z+v*tftQdO5`w7&{*K}mZG&Supa<$Z~lGIAz47}*Nv_#&_-Ctus#lBkXkDa(qwhp>m
zS;Dz9Q&ZrT;X&zQO811eW0MWpB$rIeCf)MIzQixe5<j|6@UDmEOLRvc!mWP_a(}B7
zbec5Z4!Gmp6|xXq^DQMT)upVEYUo6cxmd}(Ou0NRs|*)+9YiBc*eAr_kS9*epX#mF
zJ$@eRrf|8n9Rsep%&5#D!DXH<#WZJq&ko9)$z*L>Onkh|RqVc71m@dL;1g3*9|;?I
z=%R^nKyFUY9XHb@+EU3Il`0S!On5wsmCrff`LLV(+$zB%lZ@Lcf0RZ6u<!%iC+cgE
zLZ7kMPqBSMAbuD3Z|Uo<XXOcR>bZqs>_=XZt}OE*PwM?x29_Rjo-VwYYdKEOU=RIw
z-zf7S3T7Vir1N%a2E_q&(0OBy*VFQ1-4$8c+V2Haswg2Js*FIobCfl$v^#IqCN+aO
z;K>JsgQCCAhI)<0{>6EG6!c+;u}S7!tgN`EKh8Bv4$-Y>O>|yl70=Ujs%xF#Y(WjT
z>CMz$S%D}zjaB{U?il%)pMLMC5+aNd-0P^~8tCMxdL-J8Emgf~Cf4+zX@imykFsor
zOCA@Hs|J6>2zzq_`K1nf<V!V(KBT&mFedE&;@maW^(b>m6kR9LLYnT=I-)@+wx(-c
zCemg-n%ePFoS*CVC<y%@?#zdAE{z}Wq@7!7cjN7NpfXNK(2|p(s`){P98oq_GMP7~
zk1Q|jbz=tXqA6ms>flXd^w(C>z#rTf0l+hBkAj;`Ra}G3)<&QvpHWlgP;lN<q7bRv
zL{clZ?8_y#uQYasgCO`wx{iH-jh}9p|M)yESQ4@0Ci{YqE@_u>V`D3}WIB4yXOgY+
zS`>UA8+*Mx2roiW=8%2Y_VlH!E%If1YO2$xhPO0y1-|1VoiWrafs><TWm6@r-<Kxq
zyJjiKR26Mz7i*CXJ|e(S{I2!JD?OSh^hA+iKRM0+df@-J|MRc^_8<T9vn@TQe|XiS
zp9H=MhMOH(*w;g>C;#zj{`p~DxA#`PCe1O82o+nR6Ee?~?R}GXvp9;vp1#9Hbt()a
zf^ZyuKm<JYkRGsaoAxv$2=KkbcgG_dJnrTy5P5bGX0kw@)JfB~S#y+)+K$pv{*K`)
zI22K8zVjbABmiPxKz}P1dTKI|x1;}}7U~%AY#rAzUuGz$vR2y&q`^2Zs~p!$N)mNZ
zgN~xB!yY9l3je=x*n0tWf*)4*k;(t>uI`y@b*WOwByH0rStm|fRi!;{SF!@@Gm2zx
zPh#UZxG-#j0ELu&pt|=_?lJa=6dzp3HSZqijstu{)6l7uuG2KOMOxr$@9H#}#l(S1
zd9l!B^dcZ=?rnzO)DnA*7a#iy@c6MbK^Wiey2czA_*pFpO}cd4x0UdHWd+ZRaV=1u
zj+iAE&lW;$qx&F&uX(&*{v7sUsmS8siPB6M+-$nWV#h?PiYql%WLoO1!Kvtzc3%+N
zj;_*0Ic39zJI8EMe?;-Sj!dttvPC}h-C2wt2REU2>yCVR4Ldy0d!%xeu&xsohsES-
zg=C$^a+0Lvxs{@u<J1anbCrf)Vnd#}vA$08=%M2|#y8yFztrchMP^jD43kbVnzA)Z
zwOEfy?!2DFKy{H_EARNywFv;lF~uJ+Jtv;F+M?irve4O{$ArMW5grAOK_9o0A6uh(
z4h0ONRDxGEOR*rLQ0vgx0`Ioq2nJ#RBcJHbdpOU}N$amox}Wg*sY{0Nul>2Rw+s~D
zEGlL`&9y;i9__0&w?fs**5vVcKUmjb$)|DPWJ(iNc34}QV==Y0BmroQKSIOsW#$xx
z_~EG5oLoR|PVUX~9B22k*^5Ii%fiu?<Rag;Ho>V%nbh67QTuqfjONdtC_(T6`A`~p
z+IWl}x~2mJ;oUia<BV@O27|C7T~fDfAIDyH`y|W0?UQu@Y&T`;WjKGbn<>E`*nMNj
z)3)QEfPd4m2}pQr$Hq0>S;d(|dkT%p<k<Iw)sXUZTDPs=>T$L^HYm7GTQH_y@&<l8
zHbLm2I~SqHN|L6qM0c+<o98(W@Ur6wY1M8tZQEWh<-w#_`i10#w_IHoV=e(6$Am`j
zCiyS<ru$GEiyrN-n~xDAdb_D|gq+(jViV-h4^5YiZAR0CANA1gd>%BPhQqGmuMv*V
zGV4vcl_?h4|M>nuH@|bn_&<JXzJl|o=Yj5F^DT-V_vg-0z};{=4sR)0TTW}qwQM!*
z@{H|@&y$wR%*qs7{kbT<5NJa%$191j{|=q`+2`Osxs(J4H#g{9qm2?;Hw3M7QYUg0
z%~3ZQT6s$55-kVsZM4Cz-cRY`H_h2zO3uwk@qu;xMA!cU_6@P^noL<PM3Y6(Y!LY1
za!ST_9x>?_2CEv8eRp5fBLfx%C=Nf7tod@|Ge_FP107?y-GTAT1kGXBWgbPBms8hP
zjGDu}O>`pmrO`cI*Fhf_{h9cpMsl|8KA}buydXOC66kS=o@<Q-D0HDU7Ke`Ovnk2e
z>S$VCmkH^cvX^Z$CQ=iX6r9wf&7zGjj2Tm-m>~QBecD{=?vMBweMg=Axg`(5&GJL$
zkv|^dScE8>`ku}p1n4o7YRdV15Ck)CXHp5<NgLROH4}#+iUIovJ`9-;;L)SI-F%c7
zhxaCOv1|85k#do1M!KUPbVjBHGu^gHHL%gt<wtJy-9lUL|Gai-_yJ-Zi#@0i#qe}V
z0?fy8pbH#3R;_?tS9Ouk`L+&Q(M}UjC}Mf9Raa(wENofe(8fH5IEsQ#NYaF!?sf7+
z>pwix5_G@GgX@HD>9a1M)HtRUnmL9(=P0S9mU(fktFmV*(RC%toU;Z#_&`EOJ+xfE
zmSQgRl-SgcCO&S}gLb_L)5vnc4OF;bdn*gB@k+9Zq7E~VDOmmWD6&HwVn$-Z{I4>w
z*QCZ?o1n$)v3w)|+>5wl4lHk$jbW}t&WS|znv1PWr@ULMl*u-+5f70yF*QfBNm<zk
z#%Hl7*{PU4kevb?VS1<RlxwWFzQ%2t7qwVtMS-yvA(Cff-xozzCW}2ii)=O|#wNjj
zSBdBq*{J}0Rp!yd8~lfr2Lvu|aK~-eq9aX;hn3Wc>f1%nRo+8Brm9)@ywUayjWA0A
zJf@7%;7!fYmuj<sdKjU_@l)^Qvkw=&KUn!zi6(a3f$f^60=BI%99=TAG>5)ZFtmK1
z$7-H!SGMrFvlfE6`rmbUc<FqnkvHhSUucfarwMW7q7Ua9_GH}@sb{<ZYLC8L@--W2
zfoY+JDnX-Nsj-WiB#8s^C7<JUh6<7UX3SsNWCrvHhY|ntr7*8%z;5l)eJwI$>%o2(
znah&xL#@g*@0(SP(qx51jm1oMx-vlf#d@1vd?JD{ViEd4_79$f<JmW-#ee(1fBVmW
z|J%QWKZzQhyUq8X8tl&}ITo(l+M`Z2Ick*lNjKz0(t<=YOj{@B-12-QB)AOiz*Gdm
zTMVmLrR!q%1Pm5jPLDrR_@AOTj4gsS`mq$s?j+lpPjaPKn+N+kFc!|rJXct=OchF^
zA=R*Mc}}?M4q4hRkd$1ww&s_@ulL8ZuZ)LPIu?8{i*z!pF}e8yalAz*%W7e1)uBu?
zwJS<$&E%1uKA=aJEw=3d4zBXl5eCHGWZ}K0f#n73AbdQ<C;09yS@tDA<S-jhWaQ<f
z6Gh8<>BgkyLM{UoOs894TfP2>!DXIju4>HU4-^iFU=M(Y<k^VF;1faUAO{FS*WQoj
zE(JA=nl=4)3?kp>s%dvB(yiE5n_+$SdoNianA|=_{y96y!^*4y;PE~@!|&_R+kqZB
zE*1B+!ev47Z5cXDRx+=h8jn5Q%#DtlPFxuE0CvkCF@!(hCxb&jJ;C#BegHWQ2~dP@
zhTJv7dLyUE#d35)j=JVUI_$H?Q`cABigMjv%tb83aTG>0_<$Zg2JjHz-;eXobr~Fl
z!OeM_YxVhj-qe(BR4h9m=e(|pOlQm32so0o+iV6VyGYf>A*Elo-hNMWQ_^|ahx-TM
z*ZB_6@J?G1=V+6CNoBd^(2HSRdq6FaElJ5*6uM6{tL<k{wFBG4CB`2Z@0fi3rRnV}
zy7Mex4+0z^jPIS^vcT~~Z{KCN?YI=h&P|C{9BZ@9ZBAxjT?YlWn|1_QgiB(IB!-ZG
z9u{G-hqIiqhw2Amh;VRsS>{@?N_RzB9&J7}Q$r|ceMJu{^aNv;E+&Js&U1z?<Z6mf
z%s$}d3x8dD{KfN}J(0XH3Ht4|ICH%<lZ|9)CXqLsvotYS=iMkE+cGJ#E|V9~>6L(G
zU=QIFpfgXPN53h@v5P?-3!H1*kVPyQZRsYu>>!oUnhmK**CpDjWw)zweA#|AsTYmt
z2L$R6^)!<Sz6f~VidbP1#CONLYZ9LB)=Dk~SH;%tB5nF=+cG8kO{|2B8ZL&u=&E9Y
zXdJ#v)On>SC)iWKUzBcsQHQ<Galf=^!k-myNO-#@E&KC1*26u|a@&+=N^3bxMCK%K
z%W>*?38)_q)s*ukEu<Hl;J|!$qBo_`UKGD^??LqH+w+TFk~v#ky*=ooZ%<Jn)*~{`
z!zq9-QwbTLw`w?s3DiQ%i|%oJ83B{XppT*tSjdB?TPF;EM;ar5m<!Sv3ti8C)^g8T
zv(<3yYqvqI%6U*Y-HW=ZGHv@!BNBhJlTY!x9^<dfeuxJTl;1#q?)QW-iX0f%IY-`9
z7Uh9Jvt25lAylJMPH1aby|<`dD;s%xcNfPYg?GJgUI}~TL3)FQ=#kM;2>9;Ku<K3T
zxmPn%&@?(NR-Hka%evG3DUMh+vRy9=o8;0-0Ei<*KEd8VuXPLm{u1cVD58=1HzE#J
zwa@1|7H1$;-)Dl9YoZUn>SHT-ip%PlGM%qWZ<m%=?Q>=h02;;ql~-^Co-TQKxU_4o
zxA10drLPW+%UN$e_Ia1<kwQZY-7a-1J1$dB(xbl^S_ENCu4;K_Bk2QsyU2s_IQt@X
zTt`9FoOa|^@}6rRN4^N!m06+^)+TghY8wl(FEmkeLCxiE8`;qdfd}Il7)2kL22meL
z9C^5qAL0<*&e#fx;|qO3vz%pGl6k_gYr>Lg?)WyY8*QhA*}7?P5!(r4dY-W#(7Oc|
z_#6M3TH)!=$JzNnE-rNHnxt7IBHwg<)Lqv=w@$nnvV0rMUhYdV=eG9BbxeSw9}*;=
z;O~1F28J|zHX|_aW*j=n<f!ASZGd7pG+tCcm2EQgjUG@rwMkh`sTzg83<;vEL2Zl?
z{lpYF2s~wSPX@t(x##Xa?H$j7ksP;`qcY#2ovWghEnBO3Q8{mN&YA5=99(s->5oi~
z`LEs(@lmROZ&G!NCKAH#<n*{kTI}0098_mqPc-RevsF!&tW55j=2|J6h;1|Pu}QN~
z@B!~>MyL;*pU!>J>F45N?i;$E`OkfqvpGR^!&}Nqjk^3`NJBcddSaEb&vbNY!N-8k
zX50tPbnJnK9Y*0(D`JA#`|O_YfR7ws=6gB!1u|)TG8bAbYVRxPwzlOmNsDc|tnOX~
zaU&LnU)Fhk>A8d=AHbt$>ASggAPjHU);b^S+JZW%*Q1`hxt^y?SLM*QogSB2<DDH~
z2_eHpD;3VcDG>j;JH=j5$4^mb1i3-ov0q8wH~G+xl}P8VT!)2rL%U{`WKgeD1=cZ7
zE)KI`4uCj<PoVCjM-x95zdpObcPH(RJMO9KcstGV$RHaA+E+(O3zZxg;ArS%fgK0e
zJDoBb!JFc!FC}w`cnEUz&_Mdk+k>}9su#9}<0Bm{B%Ow|@5gG$n`|wR94KaeJ$5=n
zWqN71U&z^TN}$Id*qQaDt#zi2PxALuN+HJ4{pY%Qtm9B$GkG8kdyAT`7}!`YyqV^i
zt3@lm+d9Y><Pjk_jy_-^O#<Qz`S3aN1l#<odysdWzgJ5(bX(2pbm;Mr;e2OPt#yTy
zwVSw2p&(%p*%k*ZBySDaUPj(Sy^fyeaVFnzgSzWHZcjVjEp>tbkBj13RQ<eW3jixe
zp=^N!leF1g8dI&Zca3LXkXxc2d@am(A0Am01rboVdyI}E$8+>DIql^-G!$B4zLZ+>
zrYw(Mc4?<eZEfM0D&jIm#}Om=BY8XW<7>h2Lp=<Wb%b}P?vBHIA*8R<vE?h<79p7`
z8Y0-<u_<dh+1pmb0lSV^D5i0UBmb00Oo&g!ZSKUmgAwESR_=uB!+a6der&TSb+yg9
z8?=_`(xUVr3~P*RwBxI(B!-X@`T-;H7q;wPMfzKnbMwJY6ZJQ*@QXyMYsk}`EGd*F
z*EQiqH84IT0wmfyd8mxo%qa6k+RRsTkr4#`0T01bsfGjmm<$JDaQ7{a1IL*2q8~MB
zmzIxdGv{@)k*2|-AW5fXZ`&C#%q}!{N>4882gc@rBX4Tw48xNy9J<?}$~?|7O=iGZ
zHg9^%YN^VstE;hF5nTz_{V*liCdS2AI|D>wQ>J{NEfd6kmg_K}hl)3V2?}q=+;J<8
zs5V0j8HT<VYE>&P>#i!wELC$k=knqrYx^36hyXU9GWf()E%bE2KNh|@*Q)MaZ@`Xs
zXuEbP$ZCr6T=l$$?3h|HDk(`W=^<-o1CA~Udwfon0_J~lnqp5YY?#sKHbr6h{)*!_
z-5AUqgI^<nE=SXdOWh_b&!CsGCUrg6{ZcNM?&~#wk6Cb1SwCP^L_Clua1=kcA2grF
z1rrjxHXIeOrNfw~b-B=KtH(?X{aDs{t@M)QYOsO7=$;2)jsg+~{%LVEMxLTRetfsn
z5WQ_oW?${G<Ewp0R*{wo%Gokhyxb*Diz6?aE*I<C3!4fF$aW<&85Vp(&5mIY8!hl?
zruqYI`o68jWvJ>neHVR~sa1+h=Vek)L%YB{%@nO|DXX%->@dN_UpB;XOmX;uR1Pyw
zH~VAM&xJ(_^zKQzYtU!0?sDZdFSS<b*7UO|8=4&1Jg{-HWzNirYERY3$$^FstSbKX
z&4za%|F$PbPu6n?xA){6gI;BN&RK$vDsRS_A<}EqXB$Y=q!kg{RR+fzvk;78_U?Y_
zD{&q|^l{Klpa&6(Z#S!Qje4rfbX6V6>**-T&W_q#?t9g!9m)-5=@s=$@{VFe5e@tY
zdk}dVwZNlwmLFzSVR&~>4qR_J$hK;=m@&=EPS>PS>yBte3eLs^Z&yj;?<7Y;7Sj*N
z%@gclgbv?JPn<^(iEwbMW~u9593>@hnx<=;DM?_M(_Ye@93?DklX1*1;#BcfrZ&Qa
z_&?Wa?6K|s0P=G^8Q;Kt^^1A46o;0B*v5fPTRssrFKL5Uv>s|`P<F-KO5kFXvr`h#
z4|HTG@d!GJp7PwIQ>)EEX9kGleWq?Dqav_nX<zk&C<Gfwe=s4M70)G;7h8#|5n&u*
z6h<GQ%n%RD$?&}hxyj;41h+0Mf@{fnt{_nqDScE_mVC+jnRG2JyBwt(FncxCUSI+f
zrC;Zf-|Q^{53N^V54B1uL4@3$xH-<-YJzxDiczkclEaquxE!mV99h>5s=sz)*tO$o
zum*V3VBj_X5b&_V0`a3oWb@YD%ZdWW&GjOisv|R%RY5yBw`;b`wV0+I=lPVB!)oW~
z(Pig6KJQfgf%TP$de}K951Vf0gb4|`Uu)K}giu{=D-pZivZd_NoQ$eShqYWQrT1f1
zs~z0*!g@4^JD6<s1GFgY!(M<q<-wV+o8I4kag6z)wgx41r(&!Z&`F=}tRBjCM`~-2
zJhw3?7_Q2}F(R1y$J~UupY{t0@NXo9E@QM?vUK8_5_e#{FF9n;SEyoqERoL9h9<o7
zmJty4I_lNZGr*J~_JJ&&P)|xSrYd|W90ukkgqu@15<1>hqij5uoQkcJAhNz`li?5~
zmF*_byv~+zSo}3B{e|sp-VK63ARI>iy5rw#qG2R_<}qM?`*zSBS7{UEx;B}+Oc6(w
z-litsCC=()-G-xCh|Q0J3+NEXl)byq@RG%VkDVm~k4X}Du;FaH9ZyyA;^26m${FUd
z8EV?EGd-lp7hNswa`4Ll^^&}sZ$8Ce^`!5qxd%f4LW1W8G6*^GbT`j+OpifpneD?q
zQH3FIcfC*{x$e5W&<d@)tqK^h%VZ@of4{kf{t^+=1ihy#oj#&Ok-${y_-0BJp^m%l
zT~khqidIxRS{8h$W6zG%T<@ePu_AV*4pD4t$xzB7{0Ze(58F$G{w{kbh~B@0OsMO%
zH7FQaL740NSb1?|kZN<{^O5)KR91%_={7Nn;B%RX`cK`Xka$3yJsg>%fUw*3eu--<
zz@@_LAV@isAheQOI`>W03pHd-IwglSQDKqo;v1Sj5fEk{=(MxQ(@F!iZGL|3r~G8H
zg96*(ConZeNN*=i(Qh1nP7xGO-aaYh2~H=`v=yo|&Lui_S>#G%mFo^!tLqW9g+nnR
zQAj_L4ET_fe7FIF0{r%!@ax3gaec>;NV^HTq!?F7Ql^fnkUc?Y+;xfyyLW4@>-eHW
z6321qA87EUQ1I=<^^AK{=%8CCGp=o)b(wBts1ur2po>nm1y7f(T4*~TbAH%Zhv9`i
zWdH+0KY_N7KK&m^|KI=opWlcRoK@$$VE^<d`@p;J%a+$e)0IUz3p|K=kgZ->kxq<4
zcUfkPz~<6mYEo|Ozjec651HPV%=?8a7YC6^apQYWao5uBy;#Jd2bkM*D8$m!Z5SmK
zMCt~#SnR${VE5@DfSA4M*YZ+Q&wQ|E=tG6b5TSDnb#qcrT}wm`ZB|v8s3Z(i-B%<R
zInTOc2AL*FZ(F~{EDkOwd2Fg{%=~K-c-dT}Pb5LXeChPwPK|TCr*@)K1?|?>d0x#2
zsCh?oI!RIGO|x9^ww0s+P=pBc&#0hY?rj`Cc5*khE4@3svE$=>O{;ZE7}9G=bS^un
zm|o|yF8ey!+I+ONC!&k?#Hox((FbfBUTDU?062Whf}|nE@V-aKuQ{6IiOUM45rnIG
zSvp3mhRz!2Jl!dtHP^zH3=6*~k3aWk5REW}4{W9ep(jltO3+gU0u0gnS|i`|VySC0
zF2S0XiKIW4BPBgwwz6SEmSs!AN2)4mFQSK+sS6EA6fo?6rp_4g1%C99NP$dJfp5Oc
zT~pl0Ny~(0djrdWxhO<M3e<LEyY0|reQ)z4ZAVpVZg+w|;J6+I$d9ZLrB6MxNkCBi
z{zm$@&dJnqO|EJ>Piiasfy~8LiYd)|N{Pz5bf#5j^;Idm7&4t3Yy=Sfz|iflOZmST
z@GO2jf-x5$yE)*Q<K%tb*CS<HleE=V$Q^io^h?$@eaSn-6RYnQMfOe$jwp&gv6LQB
zUq^iWQ26&$cE7t?bBy=4C2hV+SplDCl`rOOXEQI@oM2inBeC(O79E=Y5cB$gMN9P8
z8B?zv@a)0-1R*dl<E@=H$J12|I%#H=9ovBN3e~728)Ai0NG0+BxTNo)wb%j}6L@o7
z?KN#k<SBV)k3~j8Y%X$qx5$WN$P1Y%S*(XX)?wN<vXA9BQ#r#{>5XUlsw`vO;pRIZ
zMltcff)0Tvq7)0FCt9E}zMBTi0>?Q!U8ZiQ-IU0=tEUAwb24-wQauiGB=(9+9AAAj
z<A}vkOh3?pi#*6j{R#N@T&Xi{gTRGZvUA`&%955(nF5`rwdM(;E$@U#NSV_-uWY-u
z__Ep*ozea-ANG~(%@6SCsWxPAvWL+9Bsqp0*J-C84~#Xf_@3p*taXxBbzX|(Soe(R
z{Nj~tbzmtmhj57f56aDH?*Vo4NW(u2NO<QKy6ZhQ+N4-g$fu^B049n{)$cjrt<Xn?
z<i(;Rw&^eC^$y?F5PE5e4Lq!>GWxI(Hy<Osx%1|l57ENhFj+0-F{pWO8OIEd=`j|p
zo@HnEUc!*rO739NXN*5^ln2OD=Z!s(mk2Siw;Qd$2DWSRi#n#V&9?c-x@}EFTLU@v
zN$gG59qB^tEIkVBk!gg8Nn8A9>E>UavUK`zFZqX<Hx0?{v{u)!tGrcNMN7O+ea5j`
zx18!D?bCg#Mpj*#>(m;kpqN1Xrsn5M_co3_Y%j6sxol93*xRo6-(_o&<1D?env|+B
z#r<fmaw^r7mswfptWz5k2eDTgY&r}H4Q}shi@eftGe7Wv`XeQ0WJ*c`w=bnK*HX^M
zfx4_DX*qWDKuVP?Ib%sWj_Bx2u5M{RMi?&DIE!Kw1<1d9V&FqzBtpUCJvBnYyDfMk
z*EXq0)paWX&{WMb>H1ccMLP1t{IhLXnpjynx!S6QaPB5Y{-<V<ub$hNW9Flw>Dg;F
z-vK8>Q`fGU)THX;R?p3_ioIP`JK|keW4*L{y=IvuH$lT7xWxN8TL?ao%(2)59V){3
zX%psb`a5t-jj(H(kzphU#Td4xuErgU6=Nx2Uf48dc(e*Og3)ER5{5A%{*$>N@W5Y>
z$nOFk-=H$`eZV{J%7|&9bFWxgC+S4@T$HRj#+e@p-Pd`x1OAJ$^GmxuM3`doiGcTz
z(Z!DoH}e)^bJE{0C>6VQMpj)4-H!P<>1Az_MX0RPV*%5ibV^<8^^4L7#WBM12RN^$
zp77J2i3594^&dTzpVmaf$l6gg?*w5ezO#K32jA?cng{#ZPo>*j_1TcFi5Ti~q}#CV
zawDej-$7Ao34xmm)ZTY7amxNbc~@R|Pr~0_4J5*Da>3X!HNHIZ4o`WpDyS>Mrh(vH
zY$`kUBU^j0teYri*HYl5(MEy)t06)jT0CF1{#78@V2<HdYP|C@f2fPxTnUA#?GxIq
z4D)S0rakL=UXXdVV;o<$AWp$p#6IBgVD2X$P~*o-PMD&*r7Fzx91m!gvRh<I`kbbX
zx%@XYj@8(~A~x3Qqp<*|?4l`2V@AG|t9>iSQco!Wdg94<wjto6N^=X-B1VoAK;Fom
zb!gK0Hgi_;Bj-v^Ft@nfx1KciDnxKO*du@df)6mGBj%yVkKuQu_}~U1+3)Xk$2(B9
z;`^+mL3xLCUpCz)8)S{beLt;@OfIf2mvWENb6FjI0D1)8pucRY8_XdN*u54XuEACd
zomvgM&~;xmdpC|PQM_C-iiUdN7Gsvik*x%eC`CZt<y^c5wwE{$A4^J_AKmTQ6occ8
zoo}5ySC-2}hy$5iJ*Cq&(y}2*oAe{MS6;%)!H%e@-`;KBzqH_pJdmm4@5xl>s3v+_
zSnAh=-ErGak0e`XmFiURq0Z-Vt?0xi6W29ryTVeTh>`85jH1Zon4$l`4t))2;>YT8
zp-Cq3-IKZ4H5pzHVlLHrbThVRm}h;RBhX#l?ER4avB~uFX@2qbI45(62F!ms9wHA-
z`Z$7zfRoc(<Zi$t$Jci^@+|9hKG3Rx4u<KN`H(Lw6sXJBbh2}`>nN5|Q(>VG^j|{a
z-pD0-nxx0(yrFM1Y`)9U9TRMLGPUWv>?@Uc(6xe!Xf?C8XKS~rwYMj6wsM$B+2gN8
zX1@d*Oo=DVzp?HK?rpj|##o5HWoaviWZ#!!OHtFdYuA&ZB57$*zSy_~7xQFumSgO{
z`9hc<#$@!&MmIE>OL#Y5(lO+E8B39@`L;tV3N?;9llwa589}Y4g)R4PzD9ace?<7*
zW%O4XtmuVh^#Ap@|NQHa2M-9*rUJcJ{V{UPp{jV3w0eS-rMkphSF)6iQ(m=GQ_8)y
zyXgS&Ws@ml7=q{n*0~;7l99;=AMY&U2yWJhJD=xx4SgucK)bXWR7G=M$`Tcd&ZO65
zSqM$-x;u)ltf|<P#vf1(!;E?W9HYmzSP<TwnxD^eEhe<Kf-p?>eyV0MH>IkfT2nl)
zV@m4Y9-rWgcj_sA6NMj$aKMqD8$1B|L@F*O=x)$m+o+0NY`E<SSM?%}T_jSVF6(O8
zjzOk!w>=!<t6>YA&;|af5WqatW5H9F+z+}`95@-9d~Fmt9G4zUVV3m`$Nij(edkS4
zq=@bFgf_HTrMUT8F9$qE7~bAeeFb_NFdxuAiFFKcd#n@3u|Coi6@1?Z&FZW`xMVZ#
z2SO`diK$YDO^6`2T3m4Q<KRut#g_p0lftow+?VM6q4=-Ky5qiTkCI`S<`R=>Yk8pw
zQu{XUNl~F?X`73`CcxEG^=yie4{WQxpx*rw7vj`Ce8PJtVT_|7x}Ep_r`)2;B}Ohw
z(#oCUiby^R-M1qeM<m;37`N75XR|eh2*D6j>VLb*q?BHK77eWU`645jA2>kX^`?v1
zhP=k>u8#qFy!D-s?O4mSoO!d$y|-m2s7-4{)SS*ASY)KsM=lq|zj5TEZ@1vSMcpy=
ziDqe@92HWPN=)sxf>b(@ayONnPO8OLfi=-)p?(UdQThqg-K%>?4{RDD6qq9_yp{YC
zIi^BvHSOeqjzts=$@7E@JS<H$ahPz1)AF}!abXB&=MjkiTO9%)SmP(spC)U+SNijO
zoNIM&1pBg1Y{8S3JCt48joUP(W3vtwwJlhf?W#!w6h-I*(w_u*D9}Q}9#fq#zS|=E
ze4bmllc`umyO$E<W~t{@bZb?msKNQc4qi95<4$~KtQ*LJ@B>=z#Dk?~6h77yGFM6v
z-i^28dYl%lYkRV`TP^4$<h&_DGYv;xj50kk`#48%WxuePG8Xv{a2y7HI<Dat1LjeY
z7M<H^_Y>C7=ek8-vRrj4L3Q6Ia#*_oVDF$S#-o^ugcg^qjb7c<PIdK9)M<oz0zZzQ
zSLo=HvEKuJ?D%3=hg9O=$<VazAqKthu3Ax&=KM(XaHO^_B)&)z#3u?Q`T+Q`AF^YF
zp3o&iY;t#U`<8O#c*Isud>r#CCHzo=iUJ0e&qcvVF_ow*tP4H{biLpaGjHc7=#HU>
z4y^fx{U+XTkR<pf-oJoys6a!KO*XPpm~~>rnLcO+O>=DPM7wRM?RdY=S{MTq(GN%t
zfhQIJvqF1*)1S$v6Yw2Jz06lpmt%P}+nOZvmMVaTn(#-PP{X>};KN0l0HT0|Zz++y
z3_kM({zI3Zlh5(KB88RPBiG8$3+{n8v{A<}9QCZGDJux*HOV`fcbQFe26`bn2WJtB
z;!l|6dT7R?r@?+o4uvk#dW2j{jg<`_IWCX=SdTv6pv2WgRgsJ&&9%4)KcmZxm7QxP
zvHw`d5%B?g_;~5u9P!b;9Xf;@w`7Z~(8E-$gODk3DS1xn6?5IQ0%dw?FK%46#uQ+N
z8GL~B3?BNi2tQs%Btd+$0(69&8*3J0a{%S}MtTZ!yX?!f^yL8~Ti2Y|c7x9Lali=T
zF#f<MB8fb;YY;rX#shk{bmUiW+o7yfzKs>`+lDk9Qb|TB?MXVM8`<~dAQ#Vja^=j#
zQE+z6J|GE<<5w_$ZK968RsKHB00||*t=t*c-VKL=d@1u@Y<MoGL?%f_dYtuD&(bnI
zn0=(j<kFZ6V-n*Jm}*A88gq!UC!=(8xI>6z7wH>yJc3yjtyY+FIQqRJD6c@u9OQ`g
zwCJ@+FOI4g@CiD5#~(Q3UvNhM@BjX<e}C}>cszO|1QUAqIq%w(OJqpuYHBuxTQuyn
zP71Yjds|eP6w`1S#a!eA(I2yj4~*V0_;Gjm6Z40pDH4H`<{Wb^9oaWjPNY6+U3W(h
zNztQn=(l~F8$F~Ky4<B?BPNIc+MM>hp6WpjFhbFztKAeY_tIjK<E9K7Tf`R*yc+g)
zVS^}^164vLYrV)_^%u(fH<EBPA|&|4)gF0(I)1wCaPFwG(1|8+<XRt076+Y)&PP3I
zNkw+#$w4bd3nVCFJ+k)~X?%g60;0hOtTrk0<D49QRqK~XKef*xzBSTaSL(ZNN-}JX
zR!ObZ+{{Z-bQ_|C;)2P;a$IDXT|6Ezj?RPEKipB|UM4ES=r@w@VTc{v<*s)aD?|=D
zp@Js$S~N8QF%Jy3U9!St^E|)Y<=6B*L~-yY1^TtFy9ehz^ZjSfXKaAM!O8=6p1-5Q
z{BI&T%X8f8?nva8P^1|eR@T|7a0F4?!3QG3q7O`0DfKW`$G`RV2$>r_XXhRdOFtxu
zEEPTKl4LYbc}|3!=7MA$$*bBv=gC!;fQ1YY_RpxGv8SbF{3QwaIOq|k4uambG9YbX
z?2jfrdh-`;GL;W`iiho(vTQnv*`BLkMBLAmF8%<2&iu!|kbf{$|6vSDZ`UZm;JAR3
zYmIUtrnxnRTc6Z`$`<R1mVHtQl;(DCHn@a4J4av``FC8UJ_<NY9*Id|O71k^jIiVF
zbj1_h=eTUfdEa%PsZLH)wX&LPK9{iBrFvj>Wspg|1NeZNRKz?{W-uYok9B-uM&EL*
z6UWGJ$<8H3X)^R^oU58-hs;`x7v6V659C6ju-8|S$vR^Az_CsNwl_)0JTc`SZaI;F
z;OKU)l<O_0tdnKkm+K~~sRG{fvJ$1>{hSr~zVDr_`%2+5aASzkH=Vj(QhvqE8|3(R
zg<I%?9EoGc2|OPZ>11BDSwAgFvf@!@>7Y$6S68~2sU7X)0=`M8gReQ9-*}G#A2)g&
zJ*PyUa#K!#cbv+>q?t-4R(DFQ3qB;*EhcHVFg5K}GTD<>@=ZgQGW^yR|0?jI2ZAKn
zUR}R#EBxe}Mc5x^TJX<R_V}Do-oG9JUk|dL?#s1nYX&~kf>(%ETUWN#Ob6P5f{G3c
z>d9sQ`Fc~FlT-S(l5EKS$M?m)`JJ=D_m7{V;Kxr-#Uc-rItZfQkZJ+BU}b=7GBxjU
z-emGnO-1;;;ANdiU5KKQU9l^H?e<=HVPO$UA^OBwL1IrC0))?Y<-!n~SJ4Uhq2u%r
zQ$31fuJJk_`HXlu<sDX<uXR!vT#j~zz^;6(m;$4*|Di4Qu?7$5>CpCv;sbFrv<27u
zauVk~&FXeC|IhS-XHiUOWV_yqMorpk0>trUM>e1_W<lV;4Zu+31N!iJ%$p?1#TEs)
zrqyGW<a5=seg)BGTPdMmhn5su(+if@*pB(D_$&}py2S8-m?u7Ndi>j%XE<;Z^NtI`
zu9<VZqCupl^q*B$m%ZMr!PJ5UN>Fyu9lq?v2be_Xx8M^oAA5uT5eqLeF;88Dykpqe
z+U8v80huI!K|7gIiDXk0TSk*KZQF}<8M{vILj*YR&%y)nanxh@%~2l&Zg6+JVlmWc
zChOXWW0I;&Ye89GZ)Lv>Ra)g0vnd-8d^5p4w+udT)JNb0c=8;0Y*KJ1z&q~qA9Olo
z2@*DqXH(UQs?7P+FHG@#=%>zZ0A23*5Th8=Hyt})1m44{Bs^3*3S$zXyJxq~mB#ZU
z%_L?`HZR>UCyNkuSJb*C(Bpk+Y)M*%F0<R1nJ@d@+3joMbv_z?ls$HkIHi$q2i!3!
zt5n0H+AhaMHs@Ryv~1S8B(U##VO?Web%NdDjZNtm5rRID$VEPKc=j8zwZR;_k(LM7
zTU6~V@kXI1^H{d68alaTNF;QqhZ;|ovRMRIAv+SsVGOZ<_ASHM8}#2_>2Qkt5EnBY
z*RZp>DHh1ZumNd7t7OhlT~(=`#s+|1bNKjbzz)&ZZk6ANKU=%bVJE?FRHp+79KcQ-
ziyIv?-$+)l1mPVYLqai6L?&Ub2^pX$?L_XXHE%9<Q+j<scN%;+1rhWuDeDw248wa(
zz=-39?4%B+ay*ThT$RXpy^Fjhd|L{n50PHXm@n?z<~z;|WRZUh2@~QTpvLSmH7CH~
z%>u;cagHgrGO4n;(5+zg)T#ZL#<7r#-W9D&Ew_t3P;ikJXN*z*#2iLrKVvrn4;Ys~
zg7<|<e+_QOotRm4q@qPPRXZ7nrXSjl>Q<I2O~~Fzt3r$75MMn*2%>K)$-i`cn`6Zj
z-1O-xg^6<WBjO}!cWn>Uqq40A&boHu&3-V1#k!Yh@5`K|(=pm!+)?n&${b}e{zSB6
zU+_o2Q6r857c@LVBiFGn*gEx9w@>quP6=rMK?!}+<5i9}>6V0-_Ip4h7RB%Z+HC~L
z7x?khvW?*AZFBB#v3D&-jK`zIoXLricAC|s8c39A)^=QVtLzSZ$gFA|$EKcs(^KNL
zQ$O^DJbSV(`$P7F*{R(<Vb2`r^Gu{FpZlpfTHI(P$CT)8pVutuGe#?0`vPBwFN9GV
z#UHQ<i+o9wny>J&WFcn2Ztlx|X#_f?QPQ61B&F*HQ;CEU3^iPsUs=0_u*tTOF)7W(
z=@pquli}bK+clvdu^YmktKFOy-jS1#cU;nC8x~2P7tpU<$$887wx&$+jiN~jm~Ad4
zyK*T{3T+hn@76@j(|J!HO3(igAt&hFb=fPm+HuUwM3A-ETUzBSFWROouw0g@XmdTK
zQ$}s-G!Crd&SYjdMxp=o&fEa*`!+OqK8p!VUE+vOMICo%;W!$UGdjsyY-Lt;HHK}&
zl&h-iHScU&Z+fZfO$N&FyZnk*Br#YN`GEe>j&%HEg%aJ{vZKzq@>;8X;9L*$w(CXY
ze5mI=W7%==CB>G;RUF$Z(%58U<lQ0r3mX#5mxntI@x!Hf1`)bDpQE8;>Ks~z4e06Q
z-0Wl@^w#Nh-Hy6j#<bGHVo93-zxoRVr&C<)e<|Kv^sl6I?*ad)ey8Y$Gya>D&iM;4
zZkX@{i=irXHm@6%YTugzAGAZLXwZc%eWA%mA!8B!KnefK3-BWN@O<VD=Id|*zT>Wa
zn<R@lL5HN5#2oqKR_=8|%Iz4&VoYat0iRrl?lB>6uE)FxK6nBjJrK6TnBjXTu+(wK
zrb+SKh-08Mo2Ly_yDX{B@?8!Zx(&~l3G6o>ku3PC>ikk`0w2S6`eiKgjRJiL=N{nQ
zx4Uack#2xm^sL(llvE059V2Mqu<CZ<1eN+CM;=_&5l(@G571<pFX2jx@I%mXK*Qj6
z&>i3CbQYLz+1zz9sRZmrS@U%m>mK%5KvvnHU-zG4Fc=W>3DDuc0O%;X+g!vs=2MyF
z<G{ONq}5WJWDXtcGNL@m@WBc){?1B<gqTEc3zoiuxUUsw`p8}6>=6bbMz@E#<J|3R
z!5*9s%bXl2>zc7|#<o$1u2w0l1zpbei}W~VaL&Q~_hQ*=$~Uhy<0%e*BRwBGnZHrz
zGR4hW9<-Kd8#04<wqT{_F|Bz&LZ^nzZpO!#9T=0pVuU`?jQ6n<L22}mPe+3Ylbg?Y
z*E9=``Bb%C*NI|ntE3PD$s|LhpKCd0t0j69M~K+Xx!})V^vkd@KlgOTf4L3(>)-$O
zzklHJfByB~{^MVMLOrB6(CYs2r++>2$3q-5Y{sM{Bh7NYb@f)&s%$8dyQXQ<)hW4n
zhh3#BV{^q(9Qy~~e24si&uq=3AHV%?|MB;Kz6n1|58?O^J)-bu9W+YbP6K{<>K~u$
zkLOqq|KkJsQa|cYn`feG7Z5Y9kFsmQl!N=$t!qb0jxQcH7o(CeI{A5TWecyW;4lwD
zD32|P=-KGG_o{F_r9V_L?S~e9Hzb&C{R%2Sj=fkH+7`XAIT~RUSeXH^2))a*f60yr
z5cUQ2KaTOAS=ab|`Ga4t2ggVQUkT3=hH?sh+R1gy8_^G_o{O$zsJK`R;)|#mg@8u!
z2efWY?cuKoVD$Nn-qe32c-Oq(+Y!BMLKdHUQO$IzkG0B(7!+D2+zY)?HEmf+Y;PL7
z+k+!yDwPlDTY)b^4vU^*e-bnT;)b8W9G3)XE=haNYuYT&Io`9mPHIN#6lcXs!Lk^Q
z*wv}Vl!YcQ#{O5TA|LW*(IpZ5X<Q$K<XwKoCE0U~Hy*P*ReEc%oEte1=%!W=s!e3E
zm&0hE_rYac4-gRirli?R!+OBr3-0fzcW0j`q$IkXdgmDMWZZ|XsJkYq_x8}5jjhId
z9(y!4?Y`JMbdjC5V?YeE59k`1oWRfN9)-U<-GPwU$>|<BZt%%zNt?3etRBl^7*a09
zzRkeW1*;ZzYhgAD*)_Q{H#?=_2Tph5fp{6A-&qq83U2o4BFBT<eph=}9RoMW=g9=s
zx=t)jAkhO>Xw5GNJzSQhO|?#<5d3=+MLy&ZBJy0>3ZW>#_wQ3ht_>{uvQB{)RVK1y
z!Lmh#P?Id`B}GNv)YcyDxe#w#mz;{NAMhA8@cTeLdZ=r4a`2*i`!wcpj>&hLw;O{r
z1Cil*Q+duNQI9aM>5|iCvia2{vaRO`X7Bn&zY^nN=s^%6iXP4A5yls<!M7*2u5-D$
z8P-8BSZ|Y5eODYU77Zj_mbG(1Qj2WIg6L{havD9p*{gYpeMSDdIO%^kAMmwaP5fBN
zjKp`hVjZu?qHRdC8PRswWHO_rOwdT_Smcn>y*#WGE=1JM;cygDirEL+bI21hBYs$;
zQ&VcjIJ&z=cMSOei)fY1a;%q1HSMBw-lb(L#-T{}w7T?U5w=&NgD`lLa`#&I9eaiR
zQJs$C(1HDkYt*w@YFX>P%x5)@YbGd3wb+_u-x@-*i$Y~|q2t66AR0v<sMV2&Vl56H
zyGf$pcKTK9cr&h@tCUS^)^3Q;fR08s+0-pvJ@BHL#CWlUzbX%(jfwCBW|D*;e}k7e
zpwD$L%-;@7qvOEw*afY)STt~XY_h5wl;#{wqo@E418l9dHz(}+98*jK_6gk!>Y?u*
zhw)>2Z5Y|hGH(aFYa5vnw?|s<-M-N|ov_OHdfrDa7eT9Z7K`l^Z7bZ6m{NGR5BEw{
z9uQA$*chWHX*(k~SLQKx+<?mj;HFB)gOMRQ&~hxQ9qN@Wu;=}ttp;55HB<Q~;tWUT
zF8{z-J@jEL7{f!l41oaOU75#@snq$NaXHm}T_i)vSq*rcvMpN|AY+o%g)KRZFLr|Q
zsj>wh$k_>@o&uc0a~d^{iHnPzI>!D;aAk71^3Zv9s8&@%>>UN5O0jBF?ZqC>7O+An
zA_4KAwId%RmY9+!k&f<<bn3XjK4)DkI??GQ?NOcyH1(8Vjn`!-Lw#81dQ2}ug$6Q0
zaTxdy^%q8}uK@nI!;Z~;bbFoVT%2&7=4}~NlZ$<tW+XbY)WhD?dM?UI5qswqUA82^
zU><*@$sSQ3fX9zVDu}+{in##pI9IRry6Aeq^Qe(*N4#$3o&v#5Lk5M>aRK~d24yNU
zQ>4V70Nh7y#vYATOvV{tLhc6KH3=@M_o>=Nzp#FxaEyB<i&KD>Gjos@tGbxJ!G#2O
z3VhQKP}@=HNry0wpUl$Cr@MQ}Id<&;UUqp6>!2u4J2I9;ro)!DYD>~}%a3-jb!*5)
zw<ZJt1cCoy8e;C9{^D;r?x)&lK;Jh5`i0}}_&De53{_TD!@$Zh8N{&Gc}EAeO`M62
zN_(6VMEL6CO3zlQf0<F@sr&Lh+CN-?i0$w8UmEPJ6aCn2TS80JF{Jsq*_h8=*0)@?
zRd)gVGA<3HC}zZeP)D8=$R18h&yPmv+v1Y;wA3-+I%k|x+;ml6l?&aHb=2uVIqMUN
zmaf0Z$zm(I2|2~bLjQn6Ogx?9-%5#|_m}zWZa%YPxTk!b2hQsp;dI=SrKf{fhc-id
zo-blbY`DJ~`#-@QoD!<oznmoUz+e9wk$%6f5S^T>yO&d4Pe~EVbiH;NFHlqN&0Zz5
zNcCJ(K{%Z_x^5y~1cT32#5n%Q#)6;D>KE$YvLQ?&fn$Pik8;PbCo)T$Qma!|P!xm`
z-NRIl?b4;VtX5$)*@%6M0~pXgv893nUzi8aT>MOd7!ns=Am?)(`$3SREA&dBEH_w|
zwv$>6vu4mAcx`RdCx}^im4~N5*$0YofY8GcACkw;ynyk|My==b9IK6GbW`IY=XF9n
zse7I7Nu_jBr#suWi}4c%yF5E70T4zXD9?Zeo}wK+PUKDsO!$7Re{;sW7L&wXGp3`M
zSTAZ`<yD{3e31Fr4j?cjHk}z=7*Ih>qnLicuru<&fid6z@S)&XjBf9<p3id&_(GPY
z-|$qGpn;PL<;AGxUa69@GLu#(CJHVhG$EtrI0Ecl9^70rz5@M`-AnjK;dm<xCjMdx
zJA^zN7uBHbsM~>7^#PjAY9D6kN8KKKZpSzaY$`M0F!(^ZMmz|Km~a2%RRxoR+^qh8
zKF%?RxxzAm&V+R`cBDv-?P$|A>lLZd%7%*;yv=FFET%#90S8Bds0Xz1Zx)Szj1*jK
zo5q1-_0T-uWexkFQmS@Awx-R;qT19jDOuH-Rj)<pI!wVP|AKdQp<h`vHgBN^=;1L7
zhMq+3yRUL^oU}8&v7_CK235dQxlA*iRacj3o-S>n3frzTut%nd;IlLF3BsEvyUsYE
z_^};x$S}Jbbm}<DQ##RU$CJ>4(yk}<v6O>Ue5iSrv3$AgA6}R+gaz>BB<xp2kb1e!
z*>^(!XX_PE2zLto$F93D<$zUPp}yz~p%fjfI-$^%b3e|IFI?NH`b8Ejz$l7w5czMx
zMK2IqU)fCg6YlT2?WYrS4D9YvnrqZ)g$i9S<2vQAFF7T0N>{S+MGs;s>dUAcGh6qM
zm~a2Pg3zzTH};aiJ@MisK^W4T({<O%Z_CoHV9xS6-&d-HSRmD1U+t^d`o12?Wzm#a
zJ4iG<zjpASuT$oJM<EV_-{tEV-d{WXHeU}N&sXMYs|l<V&4(1{^SID@Yu3K0B}2MR
zu)Ta3T*O?@26>Fh2lDk8d_W&P7l(nEklS|^&c`}V+t)@9tEtl0W?Ra&uefM3&bGc=
zHo=rdkAa9@d^j;-Z{}|=t)UTyJfI%N&o@-g+s6Uwu9pw@{%B>pPYusAvCB1QV<TvH
zsJa*BN(S3vJ+x6rIHVEwzo9|{AF=*B5ir2`eVgs?k9o%v7Sb1Oy>}!V(7;*V&wbHU
zf@aC4I@+hDy>$xLf(@OvRmeY+oyOD$^zg9Tetxi<?YhqAITrjA04c&09aJ`L$)_pb
zwAzzRS9BRNdspR4jO-VxD~aN_ots{2xKj_q^Di65Z>cgr0zC|Gr^>jtU|jNkX~hOJ
zYqFvxbwM?kX;;pw8&jRB%WAom#3Pe|v+x5Ujy(wk83f|zTp9C&(80Y9j_-B0vx-aJ
zOf9K;*qfp&a6cznv{O3E+V<}WNpMl_Mqduheu*;F*Els~&wN)&7~di7`W^HPT+8}4
zbGa_fw4{u|q^Bfrjyf-JNtzwki@kJ=F21W6o2(9hfF;F3A2&N=&w(e%Ndd<kcj)p4
zWCyJ6nkn6YQJRoVwo_6QO*WES9Xb-&hdnv9+R-Oak36k6gwdnTrQlREzjt#fbX>2K
zU8Q?3>m=FcG=Z)<_NLp$WL?J{cx7)UMptj`5Jkb;?B`dwaV!Wtgn9Iv;~jA1Aj%!1
zKD8Yde5mlud7E^V06G)0jsK6kFI$q^$g=#Ec`1&K)iew69S?i};Mg3SV_#lqtYT_P
zU6QEgQr-IdaU_#s(h(6UM!*4)GNX)<$wVOI;9kG$Ig7uCK@W5zcaW~diKqkF0YXb;
z7tHPRj1tfW*49azX_j_TpfE(kl+=~q_3;cNoW>(4!^$sQ80Wf?gH<usS$27Vvwtsr
zFAa6acHqT=EV4FGUOQ##j^Unq*{dvVj;msh`Ys;BKqO%|M-e1^D#Iw#$K5S_LVyKW
z>=3Qx9fn|ShnydxfDCTjb5n0;nD!Be0Uxr-tzp@RA>`h|8iPQZ62BUwa#fPkayAvW
zB8QR#WEd@bFH=7!rKdu;r3<vRe|HSW?Ae@VnZ&K1ps8zy$)BP@$RI67RFJHYPx6VV
zD`Fems=awt5XW{X%3auPSUfw0+mrb^rVH<gR6JFN9(XXKG7vNYUNeIvYb)Q6BE7S2
z!xOs=Do+Dw{|2jy{Pr<)V1cu)9l;F>Gn%0T(+e$8+jOJr)g(!99=hFFhNPUi9J`$J
z&Lf&{XPB;6*DUPZs+)O@cgJ|A^c;XESO5{Vh=D*3m~OpfDoaoJP)4N}dtTU1nNXn5
zJWorWM-u5t+iD_KB`*YkTPI?#YO{hJn(F|tv)fEdWoGMM8vus0^aAqGmr2odJ`RZ=
zXLUqUKck7~Hhd(RzU%<jBa)0MH^+_ue1{S&fEQ@O?AtpoI^NJQ-iYTzon*ckBNSx3
ziSmlnCCcSgPrQudr@}a>96Pbe0o|58hUL`zou%hz3r*S9=8X*>=2bmnl#dW}b6Q8B
z^rM~*LyQwVjak9#Rq0iO+i?J*)N%G7fTs3N3l4x@Abvz(^Z3nhp2m|B6Ds}5ojZ;Q
z3>y+95{)W;cL~W`EqtSRRfnT!nV30%_Yqk;tT({3<L(RdfQlhECzml?djq3{L{vdG
zXPt`E``OP>UI-at7k3_9jk`ZkdVVQ>P5=Y;0n`I<2M$1JUl7aNTtCf$h70Y<L`5?d
z6(D4)=`ixK$R;-}Q5m<zq@Um_U$j?D6U0Hz5yY+tusz_uu&{<Lh&RXEuz|a%9m`e*
z0w=V{QvnbcNnEDb&Bp-O^-9`)<<Wsd?OXTHuUlB#ft>x5<i@#iIBeg(n7S^#nHJt?
zx`uWlFNz^<a$1tA&E_s^;+Yp2X@sY*raEh3B^5~%hwg9X7TJkU20pclZb1UgtfE81
zHXo<lod!Sl8k|d!#RO%z9LKKkBINN*XO$tqIl=ZyYykJKye=JB^EQv**|glj4uadJ
z<qvdC=J3u%)$};$eG$5Dp+ff*mh&Y0Y#3aG6P<H{GVM@b=G!4UU<i_uo$Blmq4QxJ
zR8Qa5h#Ri74$`YUQKykNPaWqI@j^GAhM^wjC~O2=A+9sNs>IxK4j6c*WG8Y!NWu9Q
zDzeem#TfN|hQ}Tyq<q;{4Wl`U<|$9J3Pr8k`!P%k>FKnuV7=I&qItj&+dord*U^Cf
z-`95^Hbj2m@<uAG+1S=i1K%c1+Y~LxGw4%y@_kxPeNW=5qs2Txx&mIOcZR@L5%vKj
z{S4C`VSkv3JJ(fX0NpH^c%rEWO^?RaUO_UM`C}SPpeU-k$WWQbu}|DOhI$`;Ve-}|
zA)(6Z?EO0|)=o;uXLa<HqgSEE)=f3jJ=A0j>jncFMKX)Ipk<$jq~Lub-MaRLZtZZz
z5NJ_I7nZ;S3UW5v6Y=$YyRA|yz_y)lH@&VnWqk}PF8P>Y0m>;UY1X(XlD^M*rjhrn
zOx;@d%pIh1xC7uua96lBP9dyrz=F5tYF|(a8OB<0n7cHcByiov4XB5Phy=Be$&mIv
z?^Z$$w$ABI03(M?K7t*#&`-lm78Y-`Ep?P(oFM{UL1j3GIHS#wdt=`Bx#x|3P?it`
zE1cJDGzJ}Yma+q=;r3{%Ad8-rwg%AIyvmMDvqqH?6_wycHV>pgM0Qm_Q8Z7n@VsOS
zHN8CepwRh+ULIh|wAub6?1b&0!Gi2lw*8Us)5e>+aKqtv-iR{ng1+W4ZmPMDsw9uI
z7E3=QX`cwawz^{Tg%%(;c1y3StXgCjoSztN#LPCZW{yk~45XwIW8aU`mu=+bw3W3x
zh&FT+Qi39tI%yEqcTN#y7Pj_J!YJEet`S`vXazRI3}FKUt;qC1YmqlRb0-hVc8rS9
z6}dZh0iLU=8Y9rSdhWeq`&^b5RE&DW1QgmMVuRo;8z5TtHMTy-O*c;ct{ZSS26+|@
zMeXNV+rybwEd@m|Q8H=S7_!L<a1}uVdH^3FrEm|xFOEl8Y;(X(?;fTFN=H7I;{d!N
z8%i9Ld_*lNo3V^DU+<JdvJTuJuy14myecQ7bQcRp=ND8E+gkH>c|XI1G44d?g8DL;
zdD1mW7X_W`i-ZqB+*O3E0AGzpsB8%nfQ|qh?+5sqEn~}CcT2Z9%S{76&z)NmUN#X2
zF%Kejs*eJfO$*XFuj*Jo%h75m0^2IXqF{esuq%LH=$x-Cwn2O$m}AR;ghdU6@X#<_
ze^P)n4l-WO^VCt$&iT|q8G-`wN|tD~Wv&mxK|l~D2aLHgw2Rr3%ON}fw+};|gx&D6
zIq}O{P;V%vyqCBtOOlf)A^pUwW*R)I!;V(snTSA$Fg+lI--BELk@Fj<#I}*W^#M-|
zhw!r`>U>6S0BRCWb&ImJ8hzg8UQqi`FVGOW_Vf0#c}%SXs_c6W$Kdk<*eboSZXSSJ
zZ7~@3?IZ2S8lxr%Mitd@pOU!6S&D=|&GqOeTH5x&aPgSkSLLeE+Q0a!tYIg_?Tgc{
z3)kxgW%rZQuGnxz*3H8TrBRU7a2DBEd9tc&T9k8Hlp!rO@l1N6_P!+5&aJ{r*93Oz
z%s21h@ddS1h_)w-!lu<y`wCZbbepCMhOX?QIf#?8aJkGqZ;r<m;Os=sjxYlFfbmDV
z(@f06Dylvrv8Z$`vD~d4moFwHOs}D4Fc*ZjWgDh2N3)yvu?*#yh%_j}C|`}lpp_&G
zpb#_b0F6|<6JZdB@N(Zp{T>GTF4%N=t_TLuPVQ9YV=$(CC~6F*ya@W4lCDe=J$kqG
zZX2RY-gdz7+a9$27+#j>fXk_FAZf#<c?S9h(y;7MQ^wMR!65szuSfu+t_LBHnpLf4
z)puF+6|Ey8I)<!0fOpQ%PXMsFEHZ|MX}krHV_9U#qrDh{QqCyN1}-@VuEcOy5s9p4
z+ZEcjP0<m6@8#psh29IKm~K1Qj!kbZMR6meLPlPM)2yrWxWoRKh5~ocLo~xWRTR;T
z9OC<Jtpn0@wnJU!Jle!209u<z?WW<DUDlODKGZS-95xZEL=8Bdy%2N1igY2C2ZrG<
zX5tVf_{RGCRWosH4}DyW*@a#@LtE?PKCmtsJjDIH!xL#|Sa+zdTOu$939djDB#0I(
zAr^bZ24+#Hto{HkY|GkVY6g>&GjX<MVHLM+ITMEs*VsWcqI@W(p`MEj(29>9^_GIW
zh$`vj+FY}<(pUoQemrge`ipJZd*IA2<z@@s7#hgUh++HoJR-Ap4!wG&U7zqcpcN|I
z5vOo&n`&4E=~`|E9LIu)?w_04)?P(d`lQ-D)4OUL)m#nFI|Da{dEv@FYD6HW)Scrd
zkubd{8_AHCpfRXVQ6LEM0~hJOQ?O_c5k*Wd<>mJt9vWz&V`|vqId6dLjY*2~azb^}
zcwi!d@J6`McZY>8wuCgE0Z0+G06Boq7w)vF^bo^cuy}+lLv0qr;J2RZRb$$Zbv@*D
z(DK+LGi@=9Bi~1Hpr>mmSo$5PPF}V@{A>@dPkd?r_+BX4!3Oq^vFZI|nfXav$g1X1
z6MLenk}0odm&d&;azy==(dz=)Pz8K8-M=tnW4f2o<FmY<RHf=06AoZzxW7h(?}r@m
z)JGl2<F1B0&eK{3A_iH#5@Vq{dlVwjrnhS4UNbOb+dGUvW5>EM0*x%Nb)N1R7DBIa
zGp59iM;De{mKk?(NwO}T>4=daE3&Zl%sV0oQ+fbpyS>-KIXTPwxlsEO8*I+|X*gvM
zdDzBoEXLgLIyj~|m3@{cQBcnz2d=NLol~9Kms0g4K(fD)BXm{vwhY8xf%_%NC1fK&
zOw7U(!=>1&a%Vm?r9S~4Q8X2<n0!FS-fu=6wRklOtH<#wlwlS-V8_MYp}9ujx#i@A
z6Oh_l6N(UMI9VT4FuQG^Om3YHu_xzNresW%s~>tlNms1xY!$hyLkME$fXLmlc4C7h
z_-sS<zRa{W=7vMK(o1j_2|pHoKJ|UsC$eZO>A7=U*0~$${nQi97Hbg(K0s0pgB`}*
z3AQgOaaeeBybWh*18(A}#fi*QubxPikZG0@N<vhkK6t)P^Sk18Rvwlha%*?(s!<vI
z^;6I42Co4fp6#%aMRsU&&`o#Hy%~4F6SRxEHpxkW{egGm)RR~S&8W-XJ7`5SVnfJm
zY#-2J+e>VTT&~D1tsw`PsmPgbzywX$x>GimGN#Q$>aop1+}1Sd%A|@y?ObQrUTJMD
zMD7+npz(GEGvL+GuV!GE0=#uQ0qB=Qu%^Kl2*|pYU`PS)+@PAE2n$q34R#w?cZtqB
zves#^9TmnM!RgHK9w)kUjwDRohO=cioj9f$0Fz+$l46V~AtE8E#7UA*-BbjH&ttBe
zwXSck+%W*qKA;-27vUpu@a6s*W+wV;#P}Lh6^u!Q@qh|9?dm*CMt7J7PaWz)mUFt&
z&%-NLXN;T!x~c&0P<W-MNgsjD&;~2%UwU(Dx~Gz(t|~kZ`?egCq6>;F?l_-w5RFNx
zYoh{ZrH5<T7%<?VBkFJDnq~AW@V1^3Xi)cLo0y)UhAZyzJjR0{t_uYewU0VDc6o^c
zf1=Z%4tafD5o&Qe!jQ6Chug2Qa}0KBsi`#K5(xpYA%d2H%?4^24&&wkj~R&OWE5l5
z<ERUZkk&m)@>Gyy$X7&SaGj?sIN$+vuZ%c5fp4?(#ki$vux&q;+NSfgoO&U5Cqhe+
z#zD`=&P(A`w_)9<G?`a}u#T>psSb5`KnL9dJB&wCa*3{=Y(Do)O%o6_0gN%0`BZp*
z>LzZ{PmK&<KL{D+ZPc!ISyq`Epp-Fi0Aat4cGyRz7pEc@*7oIoj8tT(;kYj2ycCt3
z3Y^y5@56B9G_2h)DXMwIg*GGQSoW&Z!WgrNbpUt!E=w(xo$ahG9fz%VT1?MF))Vn~
zlk%}72^>f-;wqlgKB1ip-PzUauL!LsCmh1mpCcl<J#@AxJHykj{0~7J^Yohr8^M8!
zs>2<eg2)R?+2g^V+BS;@*Dq3E-$FmJqv+hvf6^n2dxrr?>Rim%mMtb?J7)a4;gVdG
ziHwY6Pm>Hq9%-vAm`1J+_-VvJmm$rsGixoVhoEC4cmM?fb9RINlpu$SCDF!)ZWwGd
zpn909g-6KG<51Lc0{ujgC#o^=`aw5zx>jIOAG$?s^i7=NSLSFAxIiic;MM~Z)G-{j
z7b;MzgDT~H6wxg4Bo?Ul$p}EogSn`*s2#6~V3o;X<{UsO0}$8?^e5QeAvVJEO-&1S
zfN1cu+C^y+1Uc?RnflO+RJP`qSfu4@#(iCtaU4S65z`ak>v_Jf1D~BOze51*ZC$+K
zP>v*|MxEbOAsH$@1?d2V*ZFPTwq+r@UKhQG>;&GJGH}TFE8P?CQzOp{-Gps9n~yvj
zMjem58j8$Mx}dMPi(I!)!&)V3ydgXYT|J0{tDXx}W@lRmbXL*6Mt)KZU4<A+UGT=*
z>skxlFzQp;hzeq_9x4)*BpOl=z_P2xuy7L+WGnSd2k2|cfIz_Zw{&3dKq1Az<zk$T
zY=EGVq>UMl=<qQ0!0l)VMbOuE2BSXD5ORZpj65xLQc#TSb#+F$d2&ERXYH}b!~ndw
zu!xkaW7|(rFkpBp5{km>gVL*OkknI1i+Ku33Hu<dc%25T?FOWa>{*OHEIIAHu((5&
zh9UNZLX*0612O!A?zF*~in^ymlC`o7KqGugIqu34WL4_rMG|W@8VpuKnigaW#rpvw
zO*Y=^c*p3%*gHmB7vR<VnO;iINbN;KQHe;Bn8#r`dtp>0-1FzSrcd|UAX91ktwM`e
zfzEc~jbp^RVDb0znwAM_e?~0RYixBirXK9GC~Z6#4r3ER)K?S^NQ@$1W$i11DI3v6
z(_?=|F<`O1z(*Ihl^wLTLKh>3Exw%F6#HRWbRox}M6#R7Ogpbny&)-yzRbp)wTuhE
z1fl~(bb-AC_Y5QFwimI@Fobk-z)jCein5PE7o%Y=i=y{4;&S2-GZB4OwTaFf2v&kk
zHl&V<$8NE5rVJT_=j`;B!?FW`5&r!pu<l<jfbTH)&gl7^U8Qg8X2AA2yJ5^Hh4)xQ
zp+o`9Q5xmB+Y#7iUes4*xY}67y4)s&$RfzzKXJoo7sSa~6L+u;H;>||VKM?Cx?z-F
zPR3lgY1)*9>q$AJA`=aab!jHbbWL4{Igs9l_q7&|c3OF0>>TR|1GakBHzxmO%y8`H
zH?2>)DoK4ZlDta&oO@jyf_mg_n|y4fJPzFTVl0A7^m2e27jSk8+aG9V&ieJ+S6tS9
z-89uq;tyVz4SrR-ZA|-`lztR(;g40=l`3h|P)B;74Z>vxf*s)3$qrK#j(u(tRyiEo
z0&H6wS8r#y5Z7YVOht%;DEGW_>N}puhQqLy)l8u7){)LT0UWBHa<;!$R}te5XrCXT
zK*+YYPRvZtPt+LuBukSdicr>7tuHY21#jBQ8?l>=I*Syw*D6elT*U!F8`&dFcOIm&
z&+DoJ01Q-N9Mh87f~T}5ZR_W0?R#SElDTMI>A9eQ^_UE+D$ELam7WoH>tga%^v{&-
z06aQ>j^8uJ-K@5E;v6?zgyE&1O;ej@CG4Y6KtBgn4YDX3aE~gP>jM;6pL|9Rgb*Jf
zv55CjNp}!CFPgm^Gh6$1)4i3{pRt$w)dboi3Tni8Qt&COc{X%z8YH@NC-#Yz7VB1`
zkt>UCJ7s9jIZC1X<pzSb=7lt_t2h=}%W)NnxR<jesGd?ld69q|)uf8*)!N#6yJ1nK
zxt03$s(p00N4SnJpXm2eOeRir(|UVR%x4f1+150G@fa6j77!rIpd_(dz-h(!yDG6e
z2qAXk%*<6MI@m*f>j~g(b+DNb+xyeuuCJwI$7U2Cpt%OEJ<Oe)mt4auYVX_KyWyJa
zTy|qn2rr>Ip-tra!yHM`1~boTQ@GWtt+Jku!bs)M2f$72UEsd3;INS8ZH~9;wdB5n
zNuR~Et#MvR0{W(tr5BYrhHjgCD-~6?;)Jvo${9=!*l?gbETTJ%Ty*OyxIiZ6Bp&pM
z4RS-yHO)dXPGl_FtnYFHCfX-K3A&nd>a7OibecemV1^&q40rbIyHw&HTBv8wb6W+m
zMu0cmM)ikL@YI8COPaEbV4m?A4@J@z?kJmn(#b}^YLSh=WoE!W0{9&UWPW<{@dJJF
zF>`yTK5X?$m)=_~vwb!8k1qV|^LrYei~}l)LzC>Qa?0zdiVIlOVL3FwFIx|4lW~wi
z4SNC@uy5oNyKZ3>88-Rf5dh~=SHbPg)KVu=H$C&-g~dR-u?X|T%QD)gy^m%=d*OSN
z%HuWEsXh`18K8urBTzS7iv4}#=+Qola&P!Xkndj^uESvAHm-<k2nM$sF!k{ub6Jgz
z=k|4x>FSF5Ix?g-y_pa4ngtd@>AsjQMHfgQ+GI1$usCWylyOpyK^Np4r?9ODF8aJ}
zf}9K^m~>EA1nm|EWKonlpvD5gPOv_Ecc<RxpD%y><>jw;Z-0FA0@|Ox^!~SB?_R!o
z_piIxFBCR+>R-Qp`SDwi(lnbPvdOdX^t+z8Rl^TZ8;F2+v6r>5mafbiTDKJ@BB0)g
zhg2`gJ1aI4sDf*3(fzYIXqt`WBW^#u`E|L%v-|(6c$<Fa6@yUy?PkxvdIQ7cQhC?$
z9E&FDV9OIyR9zw5A<a4QstO40Y=219AC>0_wH-qCXBD%6WghRJ-@Lth`S$MJho9cR
zd-n62*LN@eb@$tUzj^!m+51=j@7;?x|9bY}-QC-l>L=g+ri}O3zx)IK<(2dH$2)c5
zN2wm5_RYLR=WpfFEd=ToeE1jl;TAsKrQr&17c?La3Y?FK&gsB$mKB7Oyvc&PbG0E2
zX0J%Zmz79@k4OlCX{qL~eu&=vrl9-le|~uPUmyPW{nKRqRk_r^zWVp`zy9a*|M<uA
z#~U^)(N8lERrC3l{sQRz^Y!_r#Pk2~pYQXWb(N^W2r3zm5VS#1))Npz6%=)wio(~)
zR92H;5H8F1@PNG>VmJ+1kbC*+haX<3KQG_?`17wn-DwfTlabBhXfXgcxv8h)ne#Vl
zcto^9^-S|5FC~y^+PUc*gPHO^!xNBRs5PMoqidZ5^#Cxs|2apf;l9KgwJ(5qT(q)o
znkstYjSLT)h+&2}f^{83Sj=Ot9LDJ8ctCwK_QKU06}GNr1So`rSqBs`fDy)qw{QOb
z=KZ_p@Bioh|9X^iUzO*6zSJMb@Qd$$#tm6W%Sha6_Nd=_RU0apQnxOBA5TRy)2^KH
zq$`x@;sw-3XdBVkkH4k*CI7f`Ec-kqbTuN*6<UygB0zx7GS3{#J_rx>*0<rI9H5FF
z;rE0GbnwRp&CLUJXYn{YMYjbW06_3<dn_%~P!BBGNcH&Z5xLo8Eio{@hL82ne1>4+
zux-})&mwX*ci04xRmJif^I5u5@F#Wn1Ms-nXMG&>!QZrnV5YZqEgNi8^F52m*~0J5
z7P8dzZR`6w)iDD0L3nInA&%`J=bOd@=^APnY$L970grR+%^TpctTBGu9!uZ!R*#r-
z6e2f!tcCswWA<$$qAzbTV!>^wj?W@;fi~-QL@>BwxaUvovs9+;SO?*8v(IuC-t=!g
z>eXlp$kOw?5f7U_zi^~49~yx8_m{xBf4L1DHh|x_!_q5R&ce2L3?R4qs|SU0^j)3l
zRHY%z*<^I-93mICzHdduUKl&A@5*Drg(K}CJZ^Pa_cH_R8?U`<c;K69DL)NaoW<kp
zq{S9^fU6Xl|HLsb#@L4JAVhBWSipwBrr%Y}>rezX>G7Y(<6NWvb_-EgrqKSb&U8%F
zr$rA!<Yo(5s06?jGogQC3xSM4v<dgZSv<}XFx+e*OORzD`hC^j7mYCIAVhAq5VS~v
z*!a7OdZ~@J*>F3H$N5>ITP<Y4gIM7Ein0iTj2wi>%@(pGK@@`TtAERGIzv7aFrLNZ
zEDPh!7NQ;o3*v7)55ao>mO3^)2$8R}kau@KsgLJ=p!C&;_itXl`|$Ule|-Pqmp9M;
z@#?3a?%uxm;mzBhU;g{mPap2yJySP-_wv;*@9*CJc=zG$-HYEoeeL1jKKu36+gCr^
z_fk?X@4ulw<hSoXei^*D|H|vTzrXzZ`(K{@_dj2~f1!Tv?w8l<YHuH}_1g9om9$5{
zh<53-zsVJM{rEE~%GC!l1&!h5kiqq(-)AHs4M=8C_#&_R(S;)lz?{$8eh~y~ISmKm
zTWQy?8oWhcsh9PcDd3lX{-U1RH?M#E_y75uLi+uy|9SJvo1cICoBG&){+n&t^!K{B
zib$DtvM#>-^z-FP%d>LwA~(B{wS=V{d{WI>8qLV3ktc|Z=oltlScZr~jggPhl`4Y8
z5VkPAQKQ%a>^Zbg3*V@FR&V?HCA@#B{5mB!P&+&U7=WJvQ;)@I@Bb8FU!zd=M*$mo
zQ^E}JJb_rs$WPlU4S4Q>5cVjqr4E?0+G`+$5{rQS0aIDFLBQ~5z?6xd9ua*KFuXlr
zsFM&*$ry(9%&SEsbV}o@7fnRcSrCn(o-ykLp)pzbl8yijn*;2Tf!P3@7MpkqFK7a;
zIc!iImO(gXoFp0IUYP=S@XChzv2I@uT(estb$Z>{mAVctY|g%b^(p#+mIH`&jXwm|
z_HYeePMTTy!x7d)0#byktPv#-nufR}^mOYYD^4o9aAw~)e$6c4JZGoZyx{T&!{1*n
z#{#~e39^APxFGrB__D6?hLCIz7cC?nhLC!_6u9Ul7jsr)6muDnF5@}}i49kjpok&{
z>;s&k`YB^@A@Il<Vs@Ie{|UGdFyIXRw6DqRwo}?pf%HTlw0P>h3dbbq3DupUg;sms
z>Q_RRbpTujqeBKBJ40|f6?_6NW&kc3j8z^CVDOV_n5Lw5yEyC9xEE1PV^FT(S}Bv`
z`&|yQzcYlEWehIIdK4NijKWvI<rp}-io)-t<QN5U8F6nUV>5uH7H(a5FfKbCE_`A|
znLq~|;0z%!<_rP)onQs3XUPUvz@@ISJzQ7_3<#cxmkJn!aZ&IR%cLb@pm>aQ>tc8%
zAV?^MHolP+&BD%eLQh+lO(3)J=a<g?%Z1L`Sf~N;-+s8ed;K{1vhg*LeZ0<N*d7<3
z-oAVHsq}QQNcHI7U4qgRA*4RcX`Op0#?m8g)Q!070PN;z(pSTobAt59BDX3?U1fQX
zXbt}mJWRt!Wlh#q_^=%T^5TjhEQT<_`2^bz=TWR4RU$={qBN^lB*Sa!c*roNM<mVI
z`6_^%N2X&ji(CPXW1ub=QpA%)a5=gvw<=_oi74{LP(bJbp`T5Jz}49VAt2-c0D!}c
zIXmZZl?h!Hr~}79k*P@<8HS*o`P_K(BoG%O8&F(TRJvKzuBsNRPy!-G*{!NsS2;At
zSdj_RM|ss!W1?RV7o-LPb%Dbs&*M0Xy#UP=lw%T%&0KX7<bujbgA1>VOu&H{S?~zB
zY;$mZ(Iv6$tKc#a`Sl|g5c{-Ax*;g!*hV<3;{u?7WL=B(A`@MoMi60@cpPF~#?oN;
zMH&o|b%is8Ceq+`=-eR=r8|I7#SJrRVUJ3;<UtZgqSY(z1g|(znT?h}d;c^T0b_wW
zg4Sn}8GB(h`Fgkzv`mB=UKI?(ESri<3CP^KY`Y|-vMtlJOOWmiiLTmg*+hlnH+CQ)
zqtDfMP7)Ja4tm540BnFhG6Sdp#~50OJ<fuy(?h;bp!GF!ZhsUlzwELoYsPk@i3oi+
zs#1v?b%?ncc43+8XrWbipI{Z*Gq8Ua42iKwL;2><a8cl(D|{hx4EVw!?53PFxyYcX
z=DFlk;^RQjIH=_mgpF2kx9k;M*3$1GWPiAnQJR7aKdv#+MKSj4;ld_rOraYicNm(i
z%4Y6LZ}cH(#vEr=Ka;wUtH5y8EMEBBZtd=01s4L?99-=4(Pb@cU)R88z!}zUfT|8p
zyqNuLDziCtVVHM(E{m#7+D3;<*CA(YA*La0|Dy|;JGwBYTFFU4hOda_KV4{_l2e@o
zA_@G&_vqLFfpgyGp$hz4E=8D!NH00*6P32*IA|$)>>uP)`>Se#m^|tZFHAVsm=iJ3
z9WG^*^cAk~+*I7pTp_%&oZBu9$y~L((9OwNRoE>Ds}Jyiv=}jC_N0Q_$IX1_n%N6=
z4Fm1QtO+|gk8znsr3}kC?|Pr8<hTlxeCXmokQO`4Ib>7@BV&gZd0fziSB+i}0|nh`
z3ZjssqMrMjBv~BSz92{h{an{26?!Y5(pAaHv6)Q~Il#8eCB;<Ti{8Eh*97mMF0{{C
z)ioHv!L8iV^`^8eNmmv@Sam%}c_5({cR;j~R8~Mb2$2H{QjaAV{|G?nQDViG^YsdB
zOpM0F6YlCdlOT<0J^PJF+>W<pB>Eu=bE#L{DPHNG0`(C>#12TT%yok)hL7Na(7GbA
zqS(M#XPkDl85<nXdMX=V1UxRJ%v}#csa}Z{Tq}z~0I5&VIsh(;%)#Y64lOVw*T7}q
zw8GQSd$b7MK10GseVq7J!l$Uo+{q0SU0{Tg_23y?h@}o_KVoKVl1XKXj{<k~-!;}n
zOyt4R^GMo?j!#1{Q9`F`E?^RkR7A-0R$C;iZn3rSA|dC1IYDAy3)lY#009600|3j&
Js-DWK2mr`%wlM$z

literal 0
HcmV?d00001

diff --git a/tests/test_cli_filter_cdx.py b/tests/test_cli_filter_cdx.py
index 92c9fab..6beec00 100644
--- a/tests/test_cli_filter_cdx.py
+++ b/tests/test_cli_filter_cdx.py
@@ -5,14 +5,18 @@
 
 fixture_path = Path(__file__).parent / "data/filter_cdx"
 
+
 def test_filter_cdx(tmpdir, caplog):
     # check if expected number is reached
-
     index_path = "s3://commoncrawl/cc-index/collections"
     index_glob = "/CC-MAIN-2024-30/indexes/cdx-00187.gz"
-    whitelist_path = fixture_path / "whitelist_10_surts.txt"  # matches on first domain and after 100k and 200k lines
-    
-    main(args=f"-v --limit 1140 filter_cdx {index_path} {str(whitelist_path)} {tmpdir} --input_glob {index_glob}".split())
+    whitelist_path = (
+        fixture_path / "whitelist_10_surts.txt"
+    )  # matches on first domain and after 100k and 200k lines
+
+    main(
+        args=f"-v --limit 1140 filter_cdx {index_path} {str(whitelist_path)} {tmpdir} --input_glob {index_glob}".split()
+    )
 
     assert "Limit reached" in caplog.text
 
@@ -22,13 +26,21 @@ def test_resolve_cdx_paths_from_cc_s3_to_local(tmpdir):
     base_path = "s3://commoncrawl/cc-index/collections"
     glob_pattern = "/CC-MAIN-2016-30/indexes/*.gz"
 
-    input_files, output_files = resolve_paths(base_path, glob_pattern, output_base_path=tmpdir)
+    input_files, output_files = resolve_paths(
+        base_path, glob_pattern, output_base_path=tmpdir
+    )
 
-    assert len(input_files) == len(output_files), "Input and output count must be the same"
+    assert len(input_files) == len(
+        output_files
+    ), "Input and output count must be the same"
     assert len(input_files) == 300, "Invalid input count"
-    assert input_files[0] == base_path + "/CC-MAIN-2016-30/indexes/cdx-00000.gz", "Invalid input file"
-    assert output_files[0] == tmpdir + "/CC-MAIN-2016-30/indexes/cdx-00000.gz", "Invalid output file"
-    assert input_files[-1] == base_path + '/CC-MAIN-2016-30/indexes/cdx-00299.gz'
+    assert (
+        input_files[0] == base_path + "/CC-MAIN-2016-30/indexes/cdx-00000.gz"
+    ), "Invalid input file"
+    assert (
+        output_files[0] == tmpdir + "/CC-MAIN-2016-30/indexes/cdx-00000.gz"
+    ), "Invalid output file"
+    assert input_files[-1] == base_path + "/CC-MAIN-2016-30/indexes/cdx-00299.gz"
 
 
 def test_resolve_cdx_paths_from_cc_s3_to_another_s3():
@@ -36,13 +48,21 @@ def test_resolve_cdx_paths_from_cc_s3_to_another_s3():
     base_path = "s3://commoncrawl/cc-index/collections"
     glob_pattern = "/CC-MAIN-2016-30/indexes/cdx-000*.gz"
 
-    input_files, output_files = resolve_paths(base_path, glob_pattern, output_base_path=output_base_path)
+    input_files, output_files = resolve_paths(
+        base_path, glob_pattern, output_base_path=output_base_path
+    )
 
-    assert len(input_files) == len(output_files), "Input and output count must be the same"
+    assert len(input_files) == len(
+        output_files
+    ), "Input and output count must be the same"
     assert len(input_files) == 100, "Invalid input count"
-    assert input_files[0] == base_path + "/CC-MAIN-2016-30/indexes/cdx-00000.gz", "Invalid input file"
-    assert output_files[0] == output_base_path + "/CC-MAIN-2016-30/indexes/cdx-00000.gz", "Invalid output file"
-    assert input_files[-1] == base_path + '/CC-MAIN-2016-30/indexes/cdx-00099.gz'
+    assert (
+        input_files[0] == base_path + "/CC-MAIN-2016-30/indexes/cdx-00000.gz"
+    ), "Invalid input file"
+    assert (
+        output_files[0] == output_base_path + "/CC-MAIN-2016-30/indexes/cdx-00000.gz"
+    ), "Invalid output file"
+    assert input_files[-1] == base_path + "/CC-MAIN-2016-30/indexes/cdx-00099.gz"
 
 
 if __name__ == "__main__":
diff --git a/tests/test_cli_warc_by_cdx.py b/tests/test_cli_warc_by_cdx.py
new file mode 100644
index 0000000..593ac12
--- /dev/null
+++ b/tests/test_cli_warc_by_cdx.py
@@ -0,0 +1,28 @@
+from pathlib import Path
+from cdx_toolkit.cli import main
+from cdx_toolkit.warcer_by_cdx import (
+    get_caputure_objects_from_index,
+    get_index_from_path,
+)
+
+fixture_path = Path(__file__).parent / "data/warc_by_cdx"
+
+
+def test_warc_by_cdx(tmpdir, caplog):
+    # test cli and check log output
+    index_path = fixture_path / "filtered_CC-MAIN-2024-30_cdx-00187.gz"
+
+    main(
+        args=f"""-v --cc --cc-mirror https://index.commoncrawl.org/ --limit 10  warc_by_cdx {str(index_path)} --prefix {str(tmpdir)}/TEST_warc_by_index --creator creator --operator bob""".split()
+    )
+
+    assert "Limit reached" in caplog.text
+
+
+def test_get_caputure_objects_from_index():
+    index_path = fixture_path / "filtered_CC-MAIN-2024-30_cdx-00187.gz"
+
+    for obj in get_caputure_objects_from_index(get_index_from_path(index_path)):
+        break
+
+    assert obj.data["length"] == "9754"

From 3496c9381559666a9ae0794d970a53091d2ac2a9 Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Fri, 22 Aug 2025 09:53:41 +0000
Subject: [PATCH 04/74] Adding more unit tests

---
 cdx_toolkit/filter_cdx/args.py                |   8 +-
 cdx_toolkit/warcer_by_cdx/__init__.py         |  15 +-
 tests/test_cli_warc_by_cdx.py                 |  28 ----
 ...t_cli_filter_cdx.py => test_filter_cdx.py} |  60 +++++++-
 tests/test_warc_by_cdx.py                     | 136 ++++++++++++++++++
 5 files changed, 205 insertions(+), 42 deletions(-)
 delete mode 100644 tests/test_cli_warc_by_cdx.py
 rename tests/{test_cli_filter_cdx.py => test_filter_cdx.py} (52%)
 create mode 100644 tests/test_warc_by_cdx.py

diff --git a/cdx_toolkit/filter_cdx/args.py b/cdx_toolkit/filter_cdx/args.py
index 469eeca..02eddb3 100644
--- a/cdx_toolkit/filter_cdx/args.py
+++ b/cdx_toolkit/filter_cdx/args.py
@@ -1,10 +1,11 @@
 import argparse
 
+
 def add_filter_cdx_args(parser: argparse.ArgumentParser):
     """Add command line arguments."""
     parser.add_argument(
         "input_base_path",
-        help="Base directory path or remote URL for one or multiple input files (e.g., URL to S3 bucket)"
+        help="Base directory path or remote URL for one or multiple input files (e.g., URL to S3 bucket)",
     )
     parser.add_argument(
         "surts_file",
@@ -12,11 +13,11 @@ def add_filter_cdx_args(parser: argparse.ArgumentParser):
     )
     parser.add_argument(
         "output_base_path",
-        help="Base directory path for output files (directory structure will be replicated from input_base_path)"
+        help="Base directory path for output files (directory structure will be replicated from input_base_path)",
     )
     parser.add_argument(
         "--input_glob",
-        help="Glob pattern relative to input_base_path (e.g., '**/*.cdx.gz' or 'collections/*/indexes/*.gz')"
+        help="Glob pattern relative to input_base_path (e.g., '**/*.cdx.gz' or 'collections/*/indexes/*.gz')",
     )
     parser.add_argument(
         "--matching_approach",
@@ -32,4 +33,3 @@ def add_filter_cdx_args(parser: argparse.ArgumentParser):
     )
 
     return parser
-
diff --git a/cdx_toolkit/warcer_by_cdx/__init__.py b/cdx_toolkit/warcer_by_cdx/__init__.py
index 333f853..dc20273 100644
--- a/cdx_toolkit/warcer_by_cdx/__init__.py
+++ b/cdx_toolkit/warcer_by_cdx/__init__.py
@@ -19,12 +19,15 @@
 
 
 def run_warcer_by_cdx(args, cmdline):
-    """Like warcer but fetches WARC records based on an CDX index file.
+    """Like warcer but fetches WARC records based on one or more CDX index files.
+
+    The CDX files can be filtered using the `filter_cdx` commands based a given URL/SURT list.
 
     Approach:
-    - Iterate over CDX file to extract capture object (file, offset, length)
+    - Iterate over one or more CDX files to extract capture object (file, offset, length)
     - Fetch WARC record based on capture object
     - Write to new WARC file with metadata including resource record with index.
+    - The CDX resource record is written to the WARC directly before for response records that matches to the CDX.
     """
     cdx, kwargs = setup(args)
 
@@ -35,7 +38,7 @@ def run_warcer_by_cdx(args, cmdline):
     info = {
         "software": "pypi_cdx_toolkit/" + get_version(),
         "isPartOf": ispartof,
-        "description": "warc extraction generated with: " + cmdline,
+        "description": "warc extraction based on CDX generated with: " + cmdline,
         "format": "WARC file version 1.0",
     }
     if args.creator:
@@ -82,7 +85,7 @@ def run_warcer_by_cdx(args, cmdline):
         writer.write_record(get_index_record(index, index_path))
 
         # The index file holds all the information to download specific objects (file, offset, length etc.)
-        for obj in get_caputure_objects_from_index(
+        for obj in generate_caputure_objects_from_index(
             index=index, warc_download_prefix=cdx.warc_download_prefix
         ):
             url = obj["url"]
@@ -139,11 +142,11 @@ def get_index_record(
     )
 
 
-def get_caputure_objects_from_index(
+def generate_caputure_objects_from_index(
     index: str, warc_download_prefix=None, limit: int = 0
 ) -> Iterable[cdx_toolkit.CaptureObject]:
     """Read CDX index and generate CaptureObject objects."""
-    for i, line in enumerate(index.splitlines()):
+    for i, line in enumerate(index.splitlines(), 1):
         cols = line.split(" ", maxsplit=2)
 
         if len(cols) == 3:
diff --git a/tests/test_cli_warc_by_cdx.py b/tests/test_cli_warc_by_cdx.py
deleted file mode 100644
index 593ac12..0000000
--- a/tests/test_cli_warc_by_cdx.py
+++ /dev/null
@@ -1,28 +0,0 @@
-from pathlib import Path
-from cdx_toolkit.cli import main
-from cdx_toolkit.warcer_by_cdx import (
-    get_caputure_objects_from_index,
-    get_index_from_path,
-)
-
-fixture_path = Path(__file__).parent / "data/warc_by_cdx"
-
-
-def test_warc_by_cdx(tmpdir, caplog):
-    # test cli and check log output
-    index_path = fixture_path / "filtered_CC-MAIN-2024-30_cdx-00187.gz"
-
-    main(
-        args=f"""-v --cc --cc-mirror https://index.commoncrawl.org/ --limit 10  warc_by_cdx {str(index_path)} --prefix {str(tmpdir)}/TEST_warc_by_index --creator creator --operator bob""".split()
-    )
-
-    assert "Limit reached" in caplog.text
-
-
-def test_get_caputure_objects_from_index():
-    index_path = fixture_path / "filtered_CC-MAIN-2024-30_cdx-00187.gz"
-
-    for obj in get_caputure_objects_from_index(get_index_from_path(index_path)):
-        break
-
-    assert obj.data["length"] == "9754"
diff --git a/tests/test_cli_filter_cdx.py b/tests/test_filter_cdx.py
similarity index 52%
rename from tests/test_cli_filter_cdx.py
rename to tests/test_filter_cdx.py
index 6beec00..d3e3377 100644
--- a/tests/test_cli_filter_cdx.py
+++ b/tests/test_filter_cdx.py
@@ -1,12 +1,12 @@
 from pathlib import Path
 
 from cdx_toolkit.cli import main
-from cdx_toolkit.filter_cdx import resolve_paths
+from cdx_toolkit.filter_cdx import resolve_paths, validate_resolved_paths
 
 fixture_path = Path(__file__).parent / "data/filter_cdx"
 
 
-def test_filter_cdx(tmpdir, caplog):
+def test_cli_filter_cdx(tmpdir, caplog):
     # check if expected number is reached
     index_path = "s3://commoncrawl/cc-index/collections"
     index_glob = "/CC-MAIN-2024-30/indexes/cdx-00187.gz"
@@ -65,5 +65,57 @@ def test_resolve_cdx_paths_from_cc_s3_to_another_s3():
     assert input_files[-1] == base_path + "/CC-MAIN-2016-30/indexes/cdx-00099.gz"
 
 
-if __name__ == "__main__":
-    test_resolve_cdx_paths_from_cc_s3_to_local("./data/tmp")
+def test_filter_cdx_nonexistent_surt_file_exits(tmpdir, caplog):
+    import pytest
+    
+    index_path = "s3://commoncrawl/cc-index/collections"
+    index_glob = "/CC-MAIN-2024-30/indexes/cdx-00187.gz"
+    nonexistent_surt_file = str(tmpdir / "nonexistent_surts.txt")
+    
+    # Test that the command exits when SURT file doesn't exist
+    with pytest.raises(SystemExit) as exc_info:
+        main(
+            args=f"-v --limit 1140 filter_cdx {index_path} {nonexistent_surt_file} {tmpdir} --input_glob {index_glob}".split()
+        )
+    
+    assert exc_info.value.code == 1
+    assert f"SURT file not found: {nonexistent_surt_file}" in caplog.text
+
+
+def test_resolve_paths_no_files_found_exits(tmpdir, caplog):
+    import pytest
+    
+    # Test that resolve_paths exits when no files match the glob pattern
+    with pytest.raises(SystemExit) as exc_info:
+        resolve_paths(
+            input_base_path=str(tmpdir),
+            input_glob="/nonexistent-pattern-*.gz",
+            output_base_path=str(tmpdir)
+        )
+    
+    assert exc_info.value.code == 1
+    assert "No files found matching glob pattern:" in caplog.text
+
+
+def test_validate_resolved_paths_existing_file_exits(tmpdir, caplog):
+    import pytest
+    
+    # Create an existing output file
+    existing_file = tmpdir / "existing_output.txt"
+    existing_file.write_text("existing content", encoding="utf-8")
+    
+    output_paths = [str(existing_file)]
+    
+    # Test that validate_resolved_paths exits when output file exists and overwrite=False
+    with pytest.raises(SystemExit) as exc_info:
+        validate_resolved_paths(output_paths, overwrite=False)
+    
+    assert exc_info.value.code == 1
+    assert f"Output file already exists: {str(existing_file)}" in caplog.text
+    assert "Use --overwrite to overwrite existing files" in caplog.text
+
+
+def test_matcher_approaches():
+    # TODO
+    # a = 
+    pass
\ No newline at end of file
diff --git a/tests/test_warc_by_cdx.py b/tests/test_warc_by_cdx.py
new file mode 100644
index 0000000..b405809
--- /dev/null
+++ b/tests/test_warc_by_cdx.py
@@ -0,0 +1,136 @@
+import os
+from pathlib import Path
+from cdx_toolkit.cli import main
+from cdx_toolkit.warcer_by_cdx import (
+    generate_caputure_objects_from_index,
+    get_index_from_path,
+)
+import pytest
+from warcio.archiveiterator import ArchiveIterator
+
+
+fixture_path = Path(__file__).parent / "data/warc_by_cdx"
+
+
+def test_cli_warc_by_cdx(tmpdir, caplog):
+    # test cli and check output
+    index_path = fixture_path / "filtered_CC-MAIN-2024-30_cdx-00187.gz"
+
+    main(
+        args=f"""-v --cc --cc-mirror https://index.commoncrawl.org/ --limit 10  warc_by_cdx {str(index_path)} --prefix {str(tmpdir)}/TEST_warc_by_index --creator foo --operator bob""".split()
+    )
+
+    # Check log
+    assert "Limit reached" in caplog.text
+
+    # Validate extracted WARC
+    warc_path = os.path.join(tmpdir, "TEST_warc_by_index-000000.extracted.warc.gz")
+    resource_record = None
+    info_record = None
+    response_records = []
+
+    with open(warc_path, 'rb') as stream:
+        for record in ArchiveIterator(stream):
+            if record.rec_type == 'warcinfo':
+                info_record = record.content_stream().read().decode("utf-8")
+        
+            if record.rec_type == 'response':
+                response_records.append(record)
+                
+            if record.rec_type == 'resource':
+                resource_record = record
+
+    assert len(response_records) == 10
+    assert resource_record is not None
+    assert resource_record.length == 568010
+
+    assert info_record is not None
+    assert "operator: bob" in info_record
+
+
+def test_get_caputure_objects_from_index():
+    index_path = fixture_path / "filtered_CC-MAIN-2024-30_cdx-00187.gz"
+
+    for obj in generate_caputure_objects_from_index(get_index_from_path(index_path)):
+        break
+
+    assert obj.data["length"] == "9754"
+
+
+def test_warc_by_cdx_no_index_files_found_exits(tmpdir, caplog):
+    # Test that warc_by_cdx exits when no index files match the glob pattern
+    with pytest.raises(SystemExit) as exc_info:
+        main(
+            args=f"""-v --cc --cc-mirror https://index.commoncrawl.org/ warc_by_cdx {str(tmpdir)} --prefix {str(tmpdir)}/TEST --index-glob "/nonexistent-pattern-*.gz" """.split()
+        )
+    
+    assert exc_info.value.code == 1
+    assert "no index files found" in caplog.text
+
+
+def test_generate_caputure_objects_invalid_cdx_line():    
+    # Test invalid CDX line parsing (line with wrong number of columns)
+    with pytest.raises(ValueError):
+        list(generate_caputure_objects_from_index("invalid-format"))
+
+
+def test_generate_caputure_objects_with_limit():
+    # Test limit functionality in get_caputure_objects_from_index
+    index_path = fixture_path / "filtered_CC-MAIN-2024-30_cdx-00187.gz"
+    index_content = get_index_from_path(index_path)
+    
+    # Count objects with limit=2
+    objects = list(generate_caputure_objects_from_index(index_content, limit=2))
+    
+    # Should stop after 2 objects
+    assert len(objects) == 2
+
+
+def test_warc_by_cdx_subprefix_and_metadata(tmpdir):
+    # Test subprefix functionality and creator/operator metadata
+    index_path = fixture_path / "filtered_CC-MAIN-2024-30_cdx-00187.gz"
+
+    main(
+        args=f"""-v --cc --cc-mirror https://index.commoncrawl.org/ --limit 1 warc_by_cdx {str(index_path)} --prefix {str(tmpdir)}/TEST --subprefix SUB --creator test_creator --operator test_operator""".split()
+    )
+
+    # Check that WARC file was created with subprefix
+    warc_path = os.path.join(tmpdir, "TEST-SUB-000000.extracted.warc.gz")
+    assert os.path.exists(warc_path)
+
+    # Validate metadata in warcinfo record
+    info_record = None
+    with open(warc_path, 'rb') as stream:
+        for record in ArchiveIterator(stream):
+            if record.rec_type == 'warcinfo':
+                info_record = record.content_stream().read().decode("utf-8")
+                break
+
+    assert info_record is not None
+    assert "creator: test_creator" in info_record
+    assert "operator: test_operator" in info_record
+
+
+def test_warc_by_cdx_without_creator_operator(tmpdir):
+    # Test that creator and operator are optional (lines 44-47)
+    index_path = fixture_path / "filtered_CC-MAIN-2024-30_cdx-00187.gz"
+
+    main(
+        args=f"""-v --cc --cc-mirror https://index.commoncrawl.org/ --limit 1 warc_by_cdx {str(index_path)} --prefix {str(tmpdir)}/TEST_NO_META""".split()
+    )
+
+    # Check that WARC file was created
+    warc_path = os.path.join(tmpdir, "TEST_NO_META-000000.extracted.warc.gz")
+    assert os.path.exists(warc_path)
+
+    # Validate that creator/operator are not in warcinfo record
+    info_record = None
+    with open(warc_path, 'rb') as stream:
+        for record in ArchiveIterator(stream):
+            if record.rec_type == 'warcinfo':
+                info_record = record.content_stream().read().decode("utf-8")
+                break
+
+    assert info_record is not None
+    assert "creator:" not in info_record
+    assert "operator:" not in info_record

From dd1e4c6e51a7718c71cfbfb9ed69e5da9e630f51 Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Fri, 22 Aug 2025 12:09:53 +0000
Subject: [PATCH 05/74] Added unit tests for matcher

---
 cdx_toolkit/filter_cdx/__init__.py          |  28 +-
 cdx_toolkit/filter_cdx/args.py              |  17 +-
 cdx_toolkit/filter_cdx/matcher.py           |  25 +-
 cdx_toolkit/warcer_by_cdx/args.py           |  18 +-
 requirements.txt                            |   1 +
 setup.py                                    |   2 +-
 tests/data/filter_cdx/whitelist_10_urls.txt |  10 +
 tests/test_filter_cdx.py                    |  34 ++-
 tests/test_matcher.py                       | 318 ++++++++++++++++++++
 9 files changed, 409 insertions(+), 44 deletions(-)
 create mode 100644 tests/data/filter_cdx/whitelist_10_urls.txt
 create mode 100644 tests/test_matcher.py

diff --git a/cdx_toolkit/filter_cdx/__init__.py b/cdx_toolkit/filter_cdx/__init__.py
index da38e5b..6df2556 100644
--- a/cdx_toolkit/filter_cdx/__init__.py
+++ b/cdx_toolkit/filter_cdx/__init__.py
@@ -4,6 +4,7 @@
 import sys
 
 import fsspec
+from surt import surt
 
 from cdx_toolkit.filter_cdx.matcher import TupleMatcher, TrieMatcher
 
@@ -12,8 +13,9 @@
 
 
 def run_filter_cdx(args, cmdline: str):
-    """Filter CDX index files based on a given SURT whitelist.
+    """Filter CDX index files based on a given URL or SURT whitelist.
 
+    - If a URL filter is provided, it is converted to a SURT filter.
     - A index entry's SURT must start with one of the SURTs from the whitelist to be considered.
     - All other index entries are discarded.
     - All input/output paths can be local or remote paths (S3, ...) and compressed (*.gz).
@@ -36,16 +38,24 @@ def run_filter_cdx(args, cmdline: str):
         f"Found {len(input_paths)} files matching pattern: {args.input_base_path}/{args.input_glob}"
     )
 
-    # Load SURT prefixes from file (each line is a surt)
-    surt_fs, surt_fs_path = fsspec.url_to_fs(args.surts_file)
-    logger.info("Loading whitelist from %s", surt_fs_path)
+    # Load URL or SURT prefixes from file (each line is a surt)
+    filter_fs, filter_fs_path = fsspec.url_to_fs(args.filter_file)
+    logger.info("Loading whitelist from %s", filter_fs_path)
 
-    if not surt_fs.exists(surt_fs_path):  # Check that surts file exists
-        logger.error(f"SURT file not found: {surt_fs_path}")
+    if not filter_fs.exists(filter_fs_path):  # Check that surts file exists
+        logger.error(f"Filter file not found: {filter_fs_path}")
         sys.exit(1)
 
-    with surt_fs.open(surt_fs_path, "rt") as input_f:
-        include_surt_prefixes = [line.strip() for line in input_f.readlines()]
+    with filter_fs.open(filter_fs_path, "rt") as input_f:
+        include_prefixes = [line.strip() for line in input_f.readlines()]
+
+    # Convert to SURT if filter file contains URLs 
+    if args.filter_type == "url":
+        logger.info("Converting urls to surts ...")
+        include_surt_prefixes = [surt(url) for url in include_prefixes]
+    else:
+        # Filter is already given as surts
+        include_surt_prefixes = include_prefixes
 
     # Create matcher based on selected approach
     matcher_classes = {
@@ -56,7 +66,7 @@ def run_filter_cdx(args, cmdline: str):
     matcher = matcher_classes[args.matching_approach](include_surt_prefixes)
 
     logger.info(
-        f"Loaded {len(include_surt_prefixes):,} surts using {args.matching_approach} approach"
+        f"Loaded {len(include_surt_prefixes):,} filter entries using {args.matching_approach} approach"
     )
 
     # Process each input/output file pair
diff --git a/cdx_toolkit/filter_cdx/args.py b/cdx_toolkit/filter_cdx/args.py
index 02eddb3..40bb79e 100644
--- a/cdx_toolkit/filter_cdx/args.py
+++ b/cdx_toolkit/filter_cdx/args.py
@@ -5,27 +5,32 @@ def add_filter_cdx_args(parser: argparse.ArgumentParser):
     """Add command line arguments."""
     parser.add_argument(
         "input_base_path",
-        help="Base directory path or remote URL for one or multiple input files (e.g., URL to S3 bucket)",
+        help="Base directory path on the local file system or remote URL for one or multiple CDX files (e.g., URL to S3 bucket)",
     )
     parser.add_argument(
-        "surts_file",
-        help="Path to file containing SURT prefixes to match (one per line)",
+        "filter_file",
+        help="Path to file containing URL or SURT prefixes to filter for (one per line)",
     )
     parser.add_argument(
         "output_base_path",
         help="Base directory path for output files (directory structure will be replicated from input_base_path)",
     )
     parser.add_argument(
-        "--input_glob",
+        "--filter-type",
+        type=str,
+        default="url",
+        help="Type of filter entries (options: `url` or `surt`, defaults to `url`)",
+    )
+    parser.add_argument(
+        "--input-glob",
         help="Glob pattern relative to input_base_path (e.g., '**/*.cdx.gz' or 'collections/*/indexes/*.gz')",
     )
     parser.add_argument(
-        "--matching_approach",
+        "--matching-approach",
         choices=["trie", "tuple"],
         default="trie",
         help="Matching approach to use (default: trie)",
     )
-
     parser.add_argument(
         "--overwrite",
         action="store_true",
diff --git a/cdx_toolkit/filter_cdx/matcher.py b/cdx_toolkit/filter_cdx/matcher.py
index 75c8af0..64899d1 100644
--- a/cdx_toolkit/filter_cdx/matcher.py
+++ b/cdx_toolkit/filter_cdx/matcher.py
@@ -17,6 +17,23 @@ def matches(self, text: str) -> bool:
         """Check if text starts with any of the prefixes."""
         pass
 
+    @staticmethod
+    def validate_prefixes(prefixes: tuple[str] | list[str]) -> tuple[str]:
+        valid_prefixes = []
+
+        for prefix in prefixes:
+            if prefix is None or not isinstance(prefix, str):
+                raise ValueError("Prefix must be a string and not none.")
+
+            # remove white spaces
+            prefix = prefix.strip()
+
+            if len(prefix) == 0:
+                raise ValueError("Empty prefixes are not allowed")
+
+            valid_prefixes.append(prefix)
+
+        return tuple(valid_prefixes)
 
 class TrieNode:
     def __init__(self):
@@ -29,9 +46,9 @@ class TrieMatcher(Matcher):
 
     def __init__(self, prefixes: tuple[str] | list[str]):
         logger.info(f"Building trie matcher based on {len(prefixes):,} inputs")
-        self.root = self._build_trie(prefixes)
+        self.root = self._build_trie(self.validate_prefixes(prefixes))
 
-    def _build_trie(self, prefixes: tuple[str] | list[str]):
+    def _build_trie(self, prefixes: tuple[str]):
         """Build a trie from a collection of prefixes."""
         root = TrieNode()
         for prefix in prefixes:
@@ -56,11 +73,11 @@ def matches(self, text: str) -> bool:
 
 
 class TupleMatcher(Matcher):
-    """Tuple-based matching approach using startswith."""
+    """Tuple-based matching approach using the built-in method `str.startswith`."""
 
     def __init__(self, prefixes: tuple[str] | list[str]):
         logger.info(f"Building tuple matcher based on {len(prefixes):,} inputs")
-        self.prefixes_tuple = tuple(prefixes)
+        self.prefixes_tuple = self.validate_prefixes(prefixes)
 
     def matches(self, text: str) -> bool:
         """Check if text starts with any prefix in the tuple."""
diff --git a/cdx_toolkit/warcer_by_cdx/args.py b/cdx_toolkit/warcer_by_cdx/args.py
index 7d40ea6..3c9368f 100644
--- a/cdx_toolkit/warcer_by_cdx/args.py
+++ b/cdx_toolkit/warcer_by_cdx/args.py
@@ -8,6 +8,15 @@
 
 
 def add_warcer_by_cdx_args(parser: argparse.ArgumentParser):
+    parser.add_argument(
+        "index_path", help="Path to CDX index file (local or remote, e.g. S3)"
+    )
+    parser.add_argument(
+        "--index-glob",
+        type=str,
+        default=None,
+        help="a glob pattern for read from multiple indices",
+    )
     parser.add_argument("--prefix", default="TEST", help="prefix for the warc filename")
     parser.add_argument(
         "--subprefix",
@@ -34,14 +43,5 @@ def add_warcer_by_cdx_args(parser: argparse.ArgumentParser):
         action="store",
         help="prefix for downloading content, automatically set for CC",
     )
-    parser.add_argument(
-        "--index-glob",
-        type=str,
-        default=None,
-        help="a glob pattern for read from multiple indices",
-    )
-    parser.add_argument(
-        "index_path", help="Path to CDX index file (local or remote, e.g. S3)"
-    )
 
     return parser
diff --git a/requirements.txt b/requirements.txt
index af525d7..97d61be 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -4,6 +4,7 @@
 requests==2.25.1
 warcio==1.7.4
 fsspec[s3]
+surt>=0.3.1
 
 # used by Makefile
 pytest==6.2.4
diff --git a/setup.py b/setup.py
index 8d57c1d..a32e4d5 100755
--- a/setup.py
+++ b/setup.py
@@ -10,7 +10,7 @@
 ]
 
 # remember: keep requires synchronized with requirements.txt
-requires = ['requests', 'warcio', 'fsspec[s3]']
+requires = ['requests', 'warcio', 'fsspec[s3]', 'surt']
 
 test_requirements = ['pytest', 'pytest-cov']
 
diff --git a/tests/data/filter_cdx/whitelist_10_urls.txt b/tests/data/filter_cdx/whitelist_10_urls.txt
new file mode 100644
index 0000000..475f73d
--- /dev/null
+++ b/tests/data/filter_cdx/whitelist_10_urls.txt
@@ -0,0 +1,10 @@
+example.com
+si.edu
+youtube.com
+archive.gov
+census.gov
+onlinedegrees.741.com/online_university_degree_program.html
+star.72pines.com/2007/06/25/%e6%8f%90%e5%8f%96%e5%85%ac%e7%a7%af%e9%87%91/trackback
+bibliotheque.missiondefrance.fr
+biodiv.mnhn.fr/fr/taxonomy
+wip.mobilierpourchr.fr/produit/t-837
diff --git a/tests/test_filter_cdx.py b/tests/test_filter_cdx.py
index d3e3377..86fcc38 100644
--- a/tests/test_filter_cdx.py
+++ b/tests/test_filter_cdx.py
@@ -1,3 +1,4 @@
+import pytest
 from pathlib import Path
 
 from cdx_toolkit.cli import main
@@ -6,7 +7,7 @@
 fixture_path = Path(__file__).parent / "data/filter_cdx"
 
 
-def test_cli_filter_cdx(tmpdir, caplog):
+def test_cli_filter_cdx_with_surts(tmpdir, caplog):
     # check if expected number is reached
     index_path = "s3://commoncrawl/cc-index/collections"
     index_glob = "/CC-MAIN-2024-30/indexes/cdx-00187.gz"
@@ -15,11 +16,25 @@ def test_cli_filter_cdx(tmpdir, caplog):
     )  # matches on first domain and after 100k and 200k lines
 
     main(
-        args=f"-v --limit 1140 filter_cdx {index_path} {str(whitelist_path)} {tmpdir} --input_glob {index_glob}".split()
+        args=f"-v --limit 1140 filter_cdx {index_path} {str(whitelist_path)} {tmpdir} --filter-type surt --input-glob {index_glob}".split()
     )
 
     assert "Limit reached" in caplog.text
+    
+def test_cli_filter_cdx_with_urls(tmpdir, caplog):
+    # check if expected number is reached
+    index_path = "s3://commoncrawl/cc-index/collections"
+    index_glob = "/CC-MAIN-2024-30/indexes/cdx-00187.gz"
+    whitelist_path = (
+        fixture_path / "whitelist_10_urls.txt"
+    )  # matches on first domain and after 100k and 200k lines
 
+    main(
+        args=f"-v --limit 1140 filter_cdx {index_path} {str(whitelist_path)} {tmpdir} --filter-type url --input-glob {index_glob}".split()
+    )
+
+    assert "Limit reached" in caplog.text
+    
 
 def test_resolve_cdx_paths_from_cc_s3_to_local(tmpdir):
     tmpdir = str(tmpdir)
@@ -66,8 +81,6 @@ def test_resolve_cdx_paths_from_cc_s3_to_another_s3():
 
 
 def test_filter_cdx_nonexistent_surt_file_exits(tmpdir, caplog):
-    import pytest
-    
     index_path = "s3://commoncrawl/cc-index/collections"
     index_glob = "/CC-MAIN-2024-30/indexes/cdx-00187.gz"
     nonexistent_surt_file = str(tmpdir / "nonexistent_surts.txt")
@@ -75,16 +88,14 @@ def test_filter_cdx_nonexistent_surt_file_exits(tmpdir, caplog):
     # Test that the command exits when SURT file doesn't exist
     with pytest.raises(SystemExit) as exc_info:
         main(
-            args=f"-v --limit 1140 filter_cdx {index_path} {nonexistent_surt_file} {tmpdir} --input_glob {index_glob}".split()
+            args=f"-v --limit 1140 filter_cdx {index_path} {nonexistent_surt_file} {tmpdir} --input-glob {index_glob}".split()
         )
     
     assert exc_info.value.code == 1
-    assert f"SURT file not found: {nonexistent_surt_file}" in caplog.text
+    assert f"Filter file not found: {nonexistent_surt_file}" in caplog.text
 
 
 def test_resolve_paths_no_files_found_exits(tmpdir, caplog):
-    import pytest
-    
     # Test that resolve_paths exits when no files match the glob pattern
     with pytest.raises(SystemExit) as exc_info:
         resolve_paths(
@@ -98,8 +109,6 @@ def test_resolve_paths_no_files_found_exits(tmpdir, caplog):
 
 
 def test_validate_resolved_paths_existing_file_exits(tmpdir, caplog):
-    import pytest
-    
     # Create an existing output file
     existing_file = tmpdir / "existing_output.txt"
     existing_file.write_text("existing content", encoding="utf-8")
@@ -114,8 +123,3 @@ def test_validate_resolved_paths_existing_file_exits(tmpdir, caplog):
     assert f"Output file already exists: {str(existing_file)}" in caplog.text
     assert "Use --overwrite to overwrite existing files" in caplog.text
 
-
-def test_matcher_approaches():
-    # TODO
-    # a = 
-    pass
\ No newline at end of file
diff --git a/tests/test_matcher.py b/tests/test_matcher.py
new file mode 100644
index 0000000..527467c
--- /dev/null
+++ b/tests/test_matcher.py
@@ -0,0 +1,318 @@
+import pytest
+from cdx_toolkit.filter_cdx.matcher import TupleMatcher, TrieMatcher
+
+
+@pytest.mark.parametrize(
+    "prefixes,test_strings,expected_results",
+    [
+        # Basic functionality
+        (
+            ["http://", "https://"],
+            ["http://example.com", "https://example.com", "ftp://example.com"],
+            [True, True, False],
+        ),
+        # Empty prefix list
+        ([], ["any string", "", "test"], [False, False, False]),
+        # Single character prefixes
+        (
+            ["a", "b", "c"],
+            ["apple", "banana", "cherry", "dog", ""],
+            [True, True, True, False, False],
+        ),
+        # Overlapping prefixes
+        (
+            ["test", "testing", "te"],
+            ["test", "testing", "tea", "other"],
+            [True, True, True, False],
+        ),
+        # Unicode characters
+        (
+            ["café", "naïve", "résumé"],
+            ["café au lait", "naïve person", "résumé.pdf", "regular text"],
+            [True, True, True, False],
+        ),
+        # Special characters
+        (
+            ["[test]", ".*", "\\n"],
+            ["[test] case", ".*regex", "\\newline", "normal"],
+            [True, True, True, False],
+        ),
+        # Case sensitivity
+        (
+            ["HTTP", "Https"],
+            ["HTTP://example.com", "https://example.com", "HTTPS://EXAMPLE.COM"],
+            [True, False, True],
+        ),
+        # Very long prefixes
+        (
+            ["a" * 1000],
+            ["a" * 1000 + "suffix", "a" * 999, "b" * 1000],
+            [True, False, False],
+        ),
+        # Duplicate prefixes
+        (
+            ["test", "test", "demo"],
+            ["testing", "demo version", "other"],
+            [True, True, False],
+        ),
+        # Prefixes that are substrings of each other
+        (
+            ["ab", "abc", "abcd"],
+            ["ab", "abc", "abcd", "abcde", "a"],
+            [True, True, True, True, False],
+        ),
+        # Numbers and mixed content
+        (
+            ["123", "4.56"],
+            ["123test", "4.56789", "789", "test123"],
+            [True, True, False, False],
+        ),
+        # Whitespace handling (note: whitespace is stripped from prefixes, so " test" becomes "test")
+        (
+            [" test", "\tindent", "\nline"],
+            ["test case", "indented", "line break", " test case", "nowhitespace"],
+            [True, True, True, False, False],
+        ),
+    ],
+)
+def test_matcher_approaches(prefixes, test_strings, expected_results):
+    """Test that TupleMatcher and TrieMatcher produce identical results."""
+    tuple_matcher = TupleMatcher(prefixes)
+    trie_matcher = TrieMatcher(prefixes)
+
+    for test_string, expected_result in zip(test_strings, expected_results):
+        tuple_result = tuple_matcher.matches(test_string)
+        trie_result = trie_matcher.matches(test_string)
+
+        # Both matchers should agree with each other
+        assert tuple_result == trie_result, (
+            f"TupleMatcher({tuple_result}) != TrieMatcher({trie_result}) "
+            f"for prefixes {prefixes} and string '{test_string}'"
+        )
+
+        # Both should match the expected result
+        assert tuple_result == expected_result, (
+            f"Expected {expected_result}, got {tuple_result} "
+            f"for prefixes {prefixes} and string '{test_string}'"
+        )
+
+
+@pytest.mark.parametrize(
+    "invalid_prefixes,expected_error",
+    [
+        # Empty string prefixes
+        ([""], "Empty prefixes are not allowed"),
+        # Whitespace-only prefixes (should be stripped to empty and raise error)
+        (["   "], "Empty prefixes are not allowed"),
+        (["\t\n "], "Empty prefixes are not allowed"),
+        # None values
+        ([None], "Prefix must be a string and not none"),
+        (["test", None, "demo"], "Prefix must be a string and not none"),
+        # Non-string types
+        ([123], "Prefix must be a string and not none"),
+        (["test", 456, "demo"], "Prefix must be a string and not none"),
+        ([[], {}, set()], "Prefix must be a string and not none"),
+    ],
+)
+def test_prefix_validation_errors(invalid_prefixes, expected_error):
+    """Test that invalid prefixes raise appropriate ValueErrors."""
+
+    with pytest.raises(ValueError, match=expected_error):
+        TupleMatcher(invalid_prefixes)
+
+    with pytest.raises(ValueError, match=expected_error):
+        TrieMatcher(invalid_prefixes)
+
+
+@pytest.mark.parametrize(
+    "test_string,expected",
+    [
+        ("test", True),
+        ("testing", True),
+        ("demo", True),
+        ("demonstration", True),
+        ("example", True),
+        ("examples", True),
+        ("  test", False),  # Leading whitespace in test string shouldn't match
+        ("other", False),
+    ],
+)
+def test_whitespace_stripping(test_string, expected):
+    """Test that whitespace is properly stripped from prefixes."""
+
+    # Prefixes with leading/trailing whitespace should be stripped
+    prefixes_with_whitespace = ["  test  ", "\tdemo\n", " example "]
+
+    tuple_matcher = TupleMatcher(prefixes_with_whitespace)
+    trie_matcher = TrieMatcher(prefixes_with_whitespace)
+
+    tuple_result = tuple_matcher.matches(test_string)
+    trie_result = trie_matcher.matches(test_string)
+
+    assert tuple_result == trie_result == expected, (
+        f"Whitespace stripping test failed for '{test_string}': "
+        f"expected {expected}, got Tuple({tuple_result}), Trie({trie_result})"
+    )
+
+
+@pytest.mark.parametrize("test_string", ["anything", "", "test", "a", "123"])
+def test_empty_prefix_list(test_string):
+    """Test with empty prefix list - should never match anything."""
+    empty_prefixes = []
+
+    tuple_matcher = TupleMatcher(empty_prefixes)
+    trie_matcher = TrieMatcher(empty_prefixes)
+
+    tuple_result = tuple_matcher.matches(test_string)
+    trie_result = trie_matcher.matches(test_string)
+
+    # Both should return False for empty prefix list
+    assert tuple_result == trie_result == False, (
+        f"Both matchers should return False for '{test_string}' with empty prefixes, "
+        f"got Tuple({tuple_result}), Trie({trie_result})"
+    )
+
+
+def test_empty_string_against_prefixes():
+    """Test matching empty strings against non-empty prefixes."""
+    non_empty_prefixes = ["test", "demo", "example"]
+    empty_test_string = ""
+
+    tuple_matcher = TupleMatcher(non_empty_prefixes)
+    trie_matcher = TrieMatcher(non_empty_prefixes)
+
+    tuple_result = tuple_matcher.matches(empty_test_string)
+    trie_result = trie_matcher.matches(empty_test_string)
+
+    # Both should return False when testing empty string against non-empty prefixes
+    assert tuple_result == trie_result == False, (
+        f"Both matchers should return False for empty string with non-empty prefixes, "
+        f"got Tuple({tuple_result}), Trie({trie_result})"
+    )
+
+
+@pytest.mark.parametrize(
+    "test_string,expected",
+    [
+        ("a", True),
+        ("1", True),
+        ("!", True),
+        ("ab", True),
+        ("12", True),
+        ("!@", True),
+        ("other", False),
+        ("", False),
+    ],
+)
+def test_single_character_edge_cases(test_string, expected):
+    """Test single character prefixes and strings (without empty prefixes)."""
+    prefixes = ["a", "1", "!"]
+
+    tuple_matcher = TupleMatcher(prefixes)
+    trie_matcher = TrieMatcher(prefixes)
+
+    tuple_result = tuple_matcher.matches(test_string)
+    trie_result = trie_matcher.matches(test_string)
+
+    assert (
+        tuple_result == trie_result == expected
+    ), f"Mismatch for '{test_string}': Tuple({tuple_result}), Trie({trie_result}), Expected({expected})"
+
+
+def test_performance_with_many_prefixes():
+    """Test with a large number of prefixes to ensure both matchers handle it."""
+    # Create many prefixes
+    prefixes = [f"prefix_{i}" for i in range(1000)]
+    test_strings = ["prefix_500test", "prefix_999", "nomatch", "prefix_1000"]
+
+    tuple_matcher = TupleMatcher(prefixes)
+    trie_matcher = TrieMatcher(prefixes)
+
+    for test_string in test_strings:
+        tuple_result = tuple_matcher.matches(test_string)
+        trie_result = trie_matcher.matches(test_string)
+        assert tuple_result == trie_result
+
+
+@pytest.mark.parametrize(
+    "test_string,expected",
+    [
+        ("", False),
+        ("a", True),
+        ("ab", True),
+        ("abc", True),
+        ("abcd", True),
+        ("abcde", True),
+        ("abcdef", True),
+        ("b", False),
+        ("ac", True),
+    ],
+)
+def test_nested_prefixes(test_string, expected):
+    """Test with prefixes that are nested within each other."""
+    prefixes = ["a", "ab", "abc", "abcd", "abcde"]
+
+    tuple_matcher = TupleMatcher(prefixes)
+    trie_matcher = TrieMatcher(prefixes)
+
+    tuple_result = tuple_matcher.matches(test_string)
+    trie_result = trie_matcher.matches(test_string)
+
+    assert tuple_result == trie_result == expected, (
+        f"Nested prefix test failed for '{test_string}': "
+        f"expected {expected}, got Tuple({tuple_result}), Trie({trie_result})"
+    )
+
+
+@pytest.mark.parametrize(
+    "test_string,expected",
+    [
+        ("🌟test", True),
+        ("café au lait", True),
+        ("𝓤𝓷𝓲𝓬𝓸𝓭𝓮 text", True),
+        ("regular", False),
+        ("", False),
+    ],
+)
+def test_unicode_edge_cases(test_string, expected):
+    """Test Unicode handling edge cases (without empty prefixes)."""
+    prefixes = ["🌟", "café", "𝓤𝓷𝓲𝓬𝓸𝓭𝓮"]
+
+    tuple_matcher = TupleMatcher(prefixes)
+    trie_matcher = TrieMatcher(prefixes)
+
+    tuple_result = tuple_matcher.matches(test_string)
+    trie_result = trie_matcher.matches(test_string)
+
+    assert (
+        tuple_result == trie_result == expected
+    ), f"Unicode mismatch for '{test_string}': Tuple({tuple_result}), Trie({trie_result}), Expected({expected})"
+
+
+def test_with_list_and_tuple_inputs():
+    """Test that both list and tuple inputs work identically."""
+    prefixes_list = ["test", "demo", "example"]
+    prefixes_tuple = ("test", "demo", "example")
+    test_strings = ["testing", "demo version", "example.com", "other"]
+
+    # Test with list input
+    tuple_matcher_list = TupleMatcher(prefixes_list)
+    trie_matcher_list = TrieMatcher(prefixes_list)
+
+    # Test with tuple input
+    tuple_matcher_tuple = TupleMatcher(prefixes_tuple)
+    trie_matcher_tuple = TrieMatcher(prefixes_tuple)
+
+    for test_string in test_strings:
+        # All four matchers should give same result
+        results = [
+            tuple_matcher_list.matches(test_string),
+            trie_matcher_list.matches(test_string),
+            tuple_matcher_tuple.matches(test_string),
+            trie_matcher_tuple.matches(test_string),
+        ]
+
+        assert all(
+            r == results[0] for r in results
+        ), f"Inconsistent results for '{test_string}': {results}"
+

From c8dbcf01d0db6068d4913df14aa1dbb10128eb98 Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Fri, 22 Aug 2025 13:03:13 +0000
Subject: [PATCH 06/74] Include subpackages

---
 setup.py | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/setup.py b/setup.py
index a32e4d5..d4da901 100755
--- a/setup.py
+++ b/setup.py
@@ -2,12 +2,10 @@
 
 from os import path
 
-from setuptools import setup
+from setuptools import setup, find_packages
 
 
-packages = [
-    'cdx_toolkit',
-]
+packages = find_packages(include=['cdx_toolkit*'])
 
 # remember: keep requires synchronized with requirements.txt
 requires = ['requests', 'warcio', 'fsspec[s3]', 'surt']

From 77ae6ca8e0a1f62a2494e7900acdc9bd4a0065dc Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Mon, 25 Aug 2025 11:50:05 +0000
Subject: [PATCH 07/74] Added parallelization to filter_cdx command

---
 cdx_toolkit/filter_cdx/__init__.py           | 135 ++++++++++++-------
 cdx_toolkit/filter_cdx/args.py               |   6 +
 requirements.txt                             |   1 +
 setup.py                                     |   2 +-
 tests/conftest.py                            |  22 +++
 tests/data/filter_cdx/whitelist_11_surts.txt |  11 ++
 tests/test_filter_cdx.py                     |  31 ++++-
 7 files changed, 157 insertions(+), 51 deletions(-)
 create mode 100644 tests/conftest.py
 create mode 100644 tests/data/filter_cdx/whitelist_11_surts.txt

diff --git a/cdx_toolkit/filter_cdx/__init__.py b/cdx_toolkit/filter_cdx/__init__.py
index 6df2556..9cdc2f4 100644
--- a/cdx_toolkit/filter_cdx/__init__.py
+++ b/cdx_toolkit/filter_cdx/__init__.py
@@ -2,6 +2,8 @@
 import os
 import time
 import sys
+from concurrent.futures import ProcessPoolExecutor, as_completed
+from functools import partial
 
 import fsspec
 from surt import surt
@@ -69,57 +71,49 @@ def run_filter_cdx(args, cmdline: str):
         f"Loaded {len(include_surt_prefixes):,} filter entries using {args.matching_approach} approach"
     )
 
-    # Process each input/output file pair
+    # Process files in parallel or sequentially
     total_lines_n = 0
     total_included_n = 0
-    log_every_n = 100_000
-
-    for input_path, output_path in zip(input_paths, output_paths):
-        logger.info("Reading index from %s", input_path)
-        logger.info("Writing filter output to %s", output_path)
-
-        lines_n = 0
-        included_n = 0
-
-        # Input/output from local or remote file system
-        input_fs, input_fs_path = fsspec.url_to_fs(input_path)
-        output_fs, output_fs_path = fsspec.url_to_fs(output_path)
-
-        # Make sure output directory exists
-        output_fs.makedirs(output_fs._parent(output_fs_path), exist_ok=True)
-
-        # Read and write compressed file if needed
-        compression = "gzip" if input_fs_path.endswith(".gz") else None
-
-        with output_fs.open(output_fs_path, "w", compression=compression) as output_f:
-            with input_fs.open(input_fs_path, "rt", compression=compression) as input_f:
-                for i, line in enumerate(input_f, 1):
-                    # Read CDX line
-                    surt_length = line.find(
-                        " "
-                    )  # we do not need to parse the full line
-                    record_surt = line[:surt_length]
-                    lines_n += 1
-
-                    # Use matcher
-                    include_record = matcher.matches(record_surt)
-
-                    if include_record:
-                        output_f.write(line)
-                        included_n += 1
-
-                        if args.limit > 0 and included_n >= args.limit:
-                            logger.info("Limit reached at %i", args.limit)
-                            break
-
-                    if (i % log_every_n) == 0:
-                        logger.info(f"Lines completed: {i:,} (matched: {included_n:,})")
-
-        logger.info(
-            f"File statistics for {input_path}: included_n={included_n}; lines_n={lines_n}; ratio={included_n/lines_n:.4f}"
-        )
-        total_lines_n += lines_n
-        total_included_n += included_n
+    
+    if getattr(args, 'parallel', 1) > 1:
+        # Parallel processing
+        with ProcessPoolExecutor(max_workers=args.parallel) as executor:
+            # Create partial function with common arguments
+            process_file_partial = partial(
+                _process_single_file,
+                matcher=matcher,
+                limit=args.limit if hasattr(args, 'limit') else 0
+            )
+            
+            # Submit all jobs
+            future_to_paths = {
+                executor.submit(process_file_partial, input_path, output_path): (input_path, output_path)
+                for input_path, output_path in zip(input_paths, output_paths)
+            }
+            
+            # Collect results
+            for future in as_completed(future_to_paths):
+                input_path, output_path = future_to_paths[future]
+                try:
+                    lines_n, included_n = future.result()
+                    logger.info(
+                        f"File statistics for {input_path}: included_n={included_n}; lines_n={lines_n}; ratio={included_n/lines_n:.4f}"
+                    )
+                    total_lines_n += lines_n
+                    total_included_n += included_n
+                except Exception as exc:
+                    logger.error(f"File {input_path} generated an exception: {exc}")
+    else:
+        # Sequential processing (original behavior)
+        for input_path, output_path in zip(input_paths, output_paths):
+            lines_n, included_n = _process_single_file(
+                input_path, output_path, matcher, args.limit if hasattr(args, 'limit') else 0
+            )
+            logger.info(
+                f"File statistics for {input_path}: included_n={included_n}; lines_n={lines_n}; ratio={included_n/lines_n:.4f}"
+            )
+            total_lines_n += lines_n
+            total_included_n += included_n
 
     logger.info(
         f"Total statistics: included_n={total_included_n}; lines_n={total_lines_n}; ratio={total_included_n/total_lines_n:.4f}"
@@ -158,6 +152,49 @@ def resolve_paths(input_base_path: str, input_glob: str, output_base_path: str):
     return input_file_paths, output_file_paths
 
 
+def _process_single_file(input_path, output_path, matcher, limit: int = 0, log_every_n: int = 100_000):
+    """Process a single input/output file pair. Returns (lines_n, included_n)."""
+    lines_n = 0
+    included_n = 0
+    
+    logger.info("Reading index from %s", input_path)
+    logger.info("Writing filter output to %s", output_path)
+    
+    # Input/output from local or remote file system
+    input_fs, input_fs_path = fsspec.url_to_fs(input_path)
+    output_fs, output_fs_path = fsspec.url_to_fs(output_path)
+    
+    # Make sure output directory exists
+    output_fs.makedirs(output_fs._parent(output_fs_path), exist_ok=True)
+    
+    # Read and write compressed file if needed
+    compression = "gzip" if input_fs_path.endswith(".gz") else None
+    
+    with output_fs.open(output_fs_path, "w", compression=compression) as output_f:
+        with input_fs.open(input_fs_path, "rt", compression=compression) as input_f:
+            for i, line in enumerate(input_f, 1):
+                # Read CDX line
+                surt_length = line.find(" ")  # we do not need to parse the full line
+                record_surt = line[:surt_length]
+                lines_n += 1
+                
+                # Use matcher
+                include_record = matcher.matches(record_surt)
+                
+                if include_record:
+                    output_f.write(line)
+                    included_n += 1
+                    
+                    if limit > 0 and included_n >= limit:
+                        logger.info("Limit reached at %i from %s", limit, input_path)
+                        break
+                
+                if (i % log_every_n) == 0:
+                    logger.info(f"Lines completed: {i:,} (matched: {included_n:,}) from {input_path}")
+    
+    return lines_n, included_n
+
+
 def validate_resolved_paths(output_paths, overwrite):
     """Validate resolved output paths and create directories if needed."""
     # Check if output files exist and overwrite flag
diff --git a/cdx_toolkit/filter_cdx/args.py b/cdx_toolkit/filter_cdx/args.py
index 40bb79e..818412b 100644
--- a/cdx_toolkit/filter_cdx/args.py
+++ b/cdx_toolkit/filter_cdx/args.py
@@ -36,5 +36,11 @@ def add_filter_cdx_args(parser: argparse.ArgumentParser):
         action="store_true",
         help="Allow overwriting existing output files",
     )
+    parser.add_argument(
+        "--parallel",
+        type=int,
+        default=1,
+        help="Number of parallel workers for processing multiple input files (default: 1, sequential processing)",
+    )
 
     return parser
diff --git a/requirements.txt b/requirements.txt
index 97d61be..f958c0d 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -11,6 +11,7 @@ pytest==6.2.4
 pytest-cov==2.12.1
 pytest-sugar==0.9.4
 coveralls==3.1.0
+botocore>=1.39.11
 
 # packaging
 twine==3.4.1
diff --git a/setup.py b/setup.py
index d4da901..38d5c61 100755
--- a/setup.py
+++ b/setup.py
@@ -10,7 +10,7 @@
 # remember: keep requires synchronized with requirements.txt
 requires = ['requests', 'warcio', 'fsspec[s3]', 'surt']
 
-test_requirements = ['pytest', 'pytest-cov']
+test_requirements = ['pytest', 'pytest-cov', 'boto3']
 
 package_requirements = ['twine', 'setuptools', 'setuptools-scm']
 
diff --git a/tests/conftest.py b/tests/conftest.py
new file mode 100644
index 0000000..7a5dbd4
--- /dev/null
+++ b/tests/conftest.py
@@ -0,0 +1,22 @@
+import pytest
+import boto3
+from botocore.exceptions import NoCredentialsError, ClientError
+
+
+def check_aws_s3_access():
+    """Check if AWS S3 access is available."""
+    try:
+        s3_client = boto3.client('s3')
+        # Try to list buckets as a simple check
+        s3_client.list_buckets()
+        return True
+    except (NoCredentialsError, ClientError):
+        return False
+
+
+def requires_aws_s3(func):
+    """Pytest decorator that skips test if AWS S3 access is not available."""
+    return pytest.mark.skipif(
+        not check_aws_s3_access(),
+        reason="AWS S3 access not available (no credentials or permissions)"
+    )(func)
\ No newline at end of file
diff --git a/tests/data/filter_cdx/whitelist_11_surts.txt b/tests/data/filter_cdx/whitelist_11_surts.txt
new file mode 100644
index 0000000..a2ee272
--- /dev/null
+++ b/tests/data/filter_cdx/whitelist_11_surts.txt
@@ -0,0 +1,11 @@
+com,example)/
+edu,si)/
+com,youtube)/
+gov,archives)/
+gov,census)/
+com,741,onlinedegrees)/online_university_degree_program.html
+com,72pines,star)/2007/06/25/%e6%8f%90%e5%8f%96%e5%85%ac%e7%a7%af%e9%87%91/trackback
+fr,missiondefrance,bibliotheque)/
+fr,mnhn,biodiv)/fr/taxonomy
+fr,mobilierpourchr,wip)/produit/t-837
+fr,tie-up)/
\ No newline at end of file
diff --git a/tests/test_filter_cdx.py b/tests/test_filter_cdx.py
index 86fcc38..7d864f9 100644
--- a/tests/test_filter_cdx.py
+++ b/tests/test_filter_cdx.py
@@ -3,10 +3,12 @@
 
 from cdx_toolkit.cli import main
 from cdx_toolkit.filter_cdx import resolve_paths, validate_resolved_paths
+from conftest import requires_aws_s3
 
 fixture_path = Path(__file__).parent / "data/filter_cdx"
 
 
+@requires_aws_s3
 def test_cli_filter_cdx_with_surts(tmpdir, caplog):
     # check if expected number is reached
     index_path = "s3://commoncrawl/cc-index/collections"
@@ -20,7 +22,9 @@ def test_cli_filter_cdx_with_surts(tmpdir, caplog):
     )
 
     assert "Limit reached" in caplog.text
-    
+
+
+@requires_aws_s3
 def test_cli_filter_cdx_with_urls(tmpdir, caplog):
     # check if expected number is reached
     index_path = "s3://commoncrawl/cc-index/collections"
@@ -36,6 +40,7 @@ def test_cli_filter_cdx_with_urls(tmpdir, caplog):
     assert "Limit reached" in caplog.text
     
 
+@requires_aws_s3
 def test_resolve_cdx_paths_from_cc_s3_to_local(tmpdir):
     tmpdir = str(tmpdir)
     base_path = "s3://commoncrawl/cc-index/collections"
@@ -58,6 +63,7 @@ def test_resolve_cdx_paths_from_cc_s3_to_local(tmpdir):
     assert input_files[-1] == base_path + "/CC-MAIN-2016-30/indexes/cdx-00299.gz"
 
 
+@requires_aws_s3
 def test_resolve_cdx_paths_from_cc_s3_to_another_s3():
     output_base_path = "s3://some-other-bucket/filter-cdx"
     base_path = "s3://commoncrawl/cc-index/collections"
@@ -80,6 +86,7 @@ def test_resolve_cdx_paths_from_cc_s3_to_another_s3():
     assert input_files[-1] == base_path + "/CC-MAIN-2016-30/indexes/cdx-00099.gz"
 
 
+@requires_aws_s3
 def test_filter_cdx_nonexistent_surt_file_exits(tmpdir, caplog):
     index_path = "s3://commoncrawl/cc-index/collections"
     index_glob = "/CC-MAIN-2024-30/indexes/cdx-00187.gz"
@@ -123,3 +130,25 @@ def test_validate_resolved_paths_existing_file_exits(tmpdir, caplog):
     assert f"Output file already exists: {str(existing_file)}" in caplog.text
     assert "Use --overwrite to overwrite existing files" in caplog.text
 
+
+@requires_aws_s3
+def test_cli_filter_cdx_with_parallel_processing(tmpdir, caplog):
+    """Test that parallel processing works correctly and processes multiple files."""
+    index_path = "s3://commoncrawl/cc-index/collections"
+    index_glob = "/CC-MAIN-2024-30/indexes/cdx-0018[78].gz"  # Multiple files pattern
+    whitelist_path = fixture_path / "whitelist_11_surts.txt"  # Additonal entry for cdx-00188.gz
+
+    # Run with parallel processing (2 workers)
+    main(
+        args=f"-v --limit 10 filter_cdx {index_path} {str(whitelist_path)} {tmpdir} --filter-type surt --input-glob {index_glob} --parallel 2".split()
+    )
+
+    # Check that multiple files were processed in parallel
+    assert "Found" in caplog.text and "files matching pattern" in caplog.text
+    assert "File statistics for" in caplog.text
+    assert "Total statistics:" in caplog.text
+    
+    # Should have processed multiple files (pattern matches 2 files: cdx-00187.gz and cdx-00188.gz)
+    file_stats_count = caplog.text.count("File statistics for")
+    assert file_stats_count == 2, "Should process exactly 2 files with the glob pattern"
+

From bfded06b034bc75bc7922b00fd2d16acd108404d Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Mon, 25 Aug 2025 11:51:38 +0000
Subject: [PATCH 08/74] removed test file

---
 tests/data/warc_by_cdx/cdx-00187 | 1140 ------------------------------
 1 file changed, 1140 deletions(-)
 delete mode 100644 tests/data/warc_by_cdx/cdx-00187

diff --git a/tests/data/warc_by_cdx/cdx-00187 b/tests/data/warc_by_cdx/cdx-00187
deleted file mode 100644
index 70ecc69..0000000
--- a/tests/data/warc_by_cdx/cdx-00187
+++ /dev/null
@@ -1,1140 +0,0 @@
-fr,missiondefrance,bibliotheque)/index.php?id=319&lvl=bulletin_display 20240716153155 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=319", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "D5K3FUWDRAOMMTJC2CTWV7L2ABFIJ5BP", "length": "9754", "offset": "111440525", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00337.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3195&lvl=author_see 20240718133156 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3195", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5MLMHDQBJHBS5JOG3CQYRL4KT4O3P4LG", "length": "6870", "offset": "3241425", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00254.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=320&lvl=author_see 20240715050657 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=320", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LZKPLQ53PRFNQJPVWIKPNY4LJIKHBCEZ", "length": "10778", "offset": "3365888", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00517.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=320&lvl=indexint_see 20240718213058 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=320", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3A7T4X637S4NEG2LTUHE2HNTCY7KTIFZ", "length": "7228", "offset": "110658803", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00004.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3202&lvl=author_see 20240725190426 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3202", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DFVLVMRCEGVF2UPFHDCM35YYZZNEMP46", "length": "7712", "offset": "3636501", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00033.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3207&lvl=author_see 20240719171239 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3207", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PNERB34T6HSUZ73VNH3625HHWTYPJ4T6", "length": "10232", "offset": "109644433", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00017.warc.gz", "charset": "UTF-8", "languages": "fra,lat"}
-fr,missiondefrance,bibliotheque)/index.php?id=321&lvl=author_see 20240712181238 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=321", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4CZ2F4QQVSQJYGBCMCSV26XTNCI6CGRP", "length": "11074", "offset": "101668117", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00031.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=321&lvl=bulletin_display 20240712182607 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=321", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TANZBWJVSMNAZVTBFCHRUXXWYJ6C6RQC", "length": "7512", "offset": "6207916", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00007.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3211&lvl=author_see 20240715060529 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3211", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PMKUAOHC67VJZNRLU5NKJDUBF2CXEJ5A", "length": "6579", "offset": "116903011", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00042.warc.gz", "charset": "UTF-8", "languages": "fra,ile"}
-fr,missiondefrance,bibliotheque)/index.php?id=3214&lvl=notice_display 20240721141815 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3214", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AL3XQXGL5VJVVZDXL3YUCCLU43QEYDAY", "length": "5171", "offset": "104033233", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00045.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=323&lvl=categ_see 20240721224004 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=323", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XRL4Q5EV5R3CTLPLHJVAB5HMVSIKHRYU", "length": "11126", "offset": "103147750", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00360.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=323&lvl=indexint_see 20240718134355 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=323", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BNAPPBLALPVKY5HX46VKOK7L3JSD2GO5", "length": "10478", "offset": "109213036", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00007.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=325&lvl=coll_see 20240719185127 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=325", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DQXVMOSQBNCAPXF4HYJVMHXQDLAQMMYB", "length": "9934", "offset": "5404195", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00541.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3250&lvl=author_see 20240712184727 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3250", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OPD54ULURX3SFX6SAFDSKJ64QU4C2IZ7", "length": "7972", "offset": "101781185", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00165.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3257&lvl=author_see 20240718140811 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3257", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TZ3OHCPGGHBRZBHQ32KQOANJGSVNTMXW", "length": "10635", "offset": "110151404", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00172.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3257&lvl=author_see 20240719100624 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3257", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VLQDVYWMJPQNC43WAO776XZFV6D6UHYH", "length": "10618", "offset": "3189587", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00193.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3257&lvl=notice_display 20240716153007 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3257", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FKJQY5S3Y5EN6NUJ5SHQ6UUZ7Q5XCDWS", "length": "5201", "offset": "111695995", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00172.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3265&lvl=author_see 20240719085015 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3265", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FHYMN3G5X7TBVS4DHNW7FVN7P7S7DUIS", "length": "8315", "offset": "6668861", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00222.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=327&lvl=indexint_see 20240719080658 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=327", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4GAIJFCWIJSKRCW3WV3HM3VD3DKRWW2W", "length": "10350", "offset": "5818330", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00022.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3270&lvl=author_see 20240721225817 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3270", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GWVEY7Z44QEQEUP2DWNBN5UO2IGKFRCQ", "length": "8774", "offset": "112555391", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00227.warc.gz", "charset": "UTF-8", "languages": "fra,deu"}
-fr,missiondefrance,bibliotheque)/index.php?id=3289&lvl=author_see 20240712164225 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3289", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "V6UWTQQIA6J2CN6HYIWYZ6MZ366T5HUW", "length": "6848", "offset": "98596750", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00267.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3294&lvl=author_see 20240719082544 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3294", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AGDO5DYYWCQHI6GFEVCAUSMYIV4P2KZJ", "length": "7330", "offset": "3988723", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00314.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3298&lvl=author_see 20240724152346 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3298", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DNZBTPTZZ2V23SDPATYKCXHMQVNFAJ34", "length": "8208", "offset": "106718478", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00297.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=33&l_typdoc=a&lvl=categ_see&main=&nbr_lignes=90&page=2 20240719081240 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=33&page=2&nbr_lignes=90&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ECM3RMASSMOFX3ELTTM75KM36QLVFXKB", "length": "11107", "offset": "4641382", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00050.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=33&l_typdoc=a&lvl=categ_see&main=&nbr_lignes=90&page=6 20240719100237 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=33&page=6&nbr_lignes=90&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HSF4MSLRACRVC3Q2JPUPLX33TYPXQUN7", "length": "11227", "offset": "4029291", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00030.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=33&l_typdoc=a&lvl=indexint_see&main=&nbr_lignes=75&page=2 20240719083242 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=33&page=2&nbr_lignes=75&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VX2BZQ5TUZE3EO56GKUYRWUIVIQD2ULH", "length": "10297", "offset": "101301987", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00197.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=33&l_typdoc=a&lvl=indexint_see&main=&nbr_lignes=75&page=5 20240719084107 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=33&page=5&nbr_lignes=75&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2UH4UV7UF4GY6FCXU4SNGWZ5ABWQOOGK", "length": "10175", "offset": "115498821", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00818.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=331&lvl=bulletin_display 20240718213832 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=331", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LVEINXI2U5DQALVD2WWW76T7RCTDULX3", "length": "8323", "offset": "118792214", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00391.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=331&lvl=categ_see 20240712185739 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=331", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "W7VHSBYM2MPQ3OW4MQV6S2XI4MHP6WTR", "length": "10942", "offset": "103787910", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00389.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=331&lvl=publisher_see 20240716144215 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=331", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TZZJGK75ZQVUGOQ6NZMO3AI7YA3UFNYY", "length": "8368", "offset": "4640756", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00018.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3319&lvl=author_see 20240721124130 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3319", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VAFI4Y22EKGYZKPN23GWR7JVXVKJU5IC", "length": "8608", "offset": "108528806", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00111.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=332&lvl=indexint_see 20240712172818 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=332", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HFP23ZMUSJ3CRPOKF7XHVYAOQTCPDZ5X", "length": "9888", "offset": "4383961", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00048.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=332&lvl=notice_display 20240721214207 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=332", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4NOO5NO7PWRGZS54BXGE6OELAKMGOJMQ", "length": "5244", "offset": "117089991", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00111.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=332&lvl=subcoll_see 20240721233314 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=subcoll_see&id=332", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4TKSFK5ZSAH2YO4XGC4B5JPNQW7M6DGS", "length": "6652", "offset": "3512793", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00651.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3328&lvl=author_see 20240721224401 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3328", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QVWSNPZ4JZOSG64UFQQ5NAUJFLVTSVYH", "length": "10766", "offset": "114497217", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00141.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=333&lvl=coll_see 20240721014429 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=333", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "37IQIIUAR5L6T6RQVXCQHFFTGOME6QKL", "length": "10034", "offset": "110695616", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00579.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=333&lvl=publisher_see 20240721141441 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=333", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3IPNBZJBBRVPDSMUYKUKLBI3MFLTCTW6", "length": "7230", "offset": "103322354", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00595.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3336&lvl=notice_display 20240716163001 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3336", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VZJLHLKFOEOCQ5TF5V4CM4MBOTJ6NLZX", "length": "5291", "offset": "115716368", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00170.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3349&lvl=author_see 20240719085604 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3349", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HKYKSUK3O7VLVRP57JFYORVZM3BYH276", "length": "9038", "offset": "5762377", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00225.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=335&lvl=subcoll_see 20240715045851 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=subcoll_see&id=335", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BLNS3DRJ3OOGJNLQRE3VINJ4UYQXUHW3", "length": "6840", "offset": "113001478", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00633.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3357&lvl=author_see 20240724155059 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3357", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KLGPRZFAEVAQXT5HAOJX5JVTG7L5U4QC", "length": "6717", "offset": "115078936", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00233.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=336&lvl=indexint_see 20240715050735 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=336", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AFM7J6VYG25TLBTVXQLJBEO7DU3XUPFS", "length": "10535", "offset": "4406404", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00052.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3364&lvl=author_see 20240716143953 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3364", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "H4P2RN5XO6TOBRHUWPKT5ZCGJV4DELOJ", "length": "6591", "offset": "128783727", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00261.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3372&lvl=notice_display 20240724144930 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3372", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NXVGLK736JFAUHXGKP56ZN6TSUCQSY42", "length": "5261", "offset": "3307445", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00359.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=338&l_typdoc=a&lvl=indexint_see&main=&nbr_lignes=44&page=2 20240712171210 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=338&page=2&nbr_lignes=44&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DQVMSHNRHBSJWDAFEC7NEDO4TB7JIFJN", "length": "10666", "offset": "99134830", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00745.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=338&lvl=indexint_see 20240716154649 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=338", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MWSKS37DNC6TVQP7MMV2HFBYGMIGUXHU", "length": "10123", "offset": "121782940", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00043.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=339&lvl=author_see 20240718150551 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=339", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5WKBW5OOPVEAUQEG6HVVSK4RKVPNO2FW", "length": "8700", "offset": "112867508", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00070.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=339&lvl=categ_see 20240718143421 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=339", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HTFY5I5RPRCDYM3GJ3PK2LUI3JELMW4W", "length": "9374", "offset": "3651513", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00430.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=339&lvl=indexint_see 20240721005217 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=339", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PHWTCZDOIHRTOREXE52KO4HQV5TPQI6L", "length": "10049", "offset": "115428364", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00044.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=34&lvl=categ_see 20240718201326 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=34", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KZHT6K4KCVSERUBGSCQ2G5X7C76D2H2Z", "length": "11179", "offset": "115532168", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00257.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3407&lvl=notice_display 20240719083554 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3407", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3W6PAA4K3AYAEOIU2CLV7HHJEL5JEKHM", "length": "5039", "offset": "4567515", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00208.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=341&l_typdoc=a&lvl=indexint_see&main=&nbr_lignes=31&page=2 20240725194516 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=341&page=2&nbr_lignes=31&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6B2DOKLOGV4OEXOQIWPP6M47ELS2UDT2", "length": "10882", "offset": "3686476", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00886.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=341&lvl=categ_see 20240721135840 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=341", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LXVIRECQI5F2B6KBWBJVQ7NHMIUCUWOW", "length": "9620", "offset": "6007166", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00453.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3419&lvl=author_see 20240716151912 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3419", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ANU4ZEQAY4Z6ZLLP6GQQ6BYCJJEZ5LJW", "length": "6603", "offset": "111688390", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00172.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=342&l_typdoc=a&lvl=categ_see&main=&nbr_lignes=38&page=3 20240725191055 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=342&page=3&nbr_lignes=38&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HW4NEXWCFF6QFETOI6KVSERJVULW2OG6", "length": "10302", "offset": "105817623", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00213.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=342&l_typdoc=a&lvl=indexint_see&main=&nbr_lignes=33&page=3 20240724150356 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=342&page=3&nbr_lignes=33&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "V2VR7UQOSKDIPW2YOR3NAPLA2KGM67UP", "length": "7627", "offset": "104405410", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00181.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3424&lvl=author_see 20240718143448 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3424", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EPAM42EAOUOLOTJXDQRZZK77CNO4QJYC", "length": "8599", "offset": "104514050", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00198.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=343&lvl=indexint_see 20240718195946 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=343", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6UBAC57HXVBMZMFPGPRR5OSWO33FCFET", "length": "10263", "offset": "107175133", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00069.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=344&lvl=coll_see 20240725185302 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=344", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YPRDKFR3W7E2M3O2S6PALYBPJQY2SUJY", "length": "10550", "offset": "102887989", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00611.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3445&lvl=author_see 20240724162904 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3445", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "P7RNC43RMNJKQW6JD6SC5KRVIVNYT6WZ", "length": "7206", "offset": "110805878", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00261.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3451&lvl=author_see 20240718203605 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3451", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5RUWSRSPYOB5BVL76PDHFQQ5XDMNWPAW", "length": "8990", "offset": "4163840", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00309.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3459&lvl=author_see 20240716162809 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3459", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OJSTHTHHYELHXUUDZTQNNYN2VO36NT3H", "length": "9419", "offset": "111121813", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00296.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3459&lvl=author_see 20240724153644 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3459", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HZKCH5K26OJFZ4XU7F22AHY5JVMMOMRT", "length": "9378", "offset": "3913523", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00317.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=346&lvl=publisher_see 20240718150444 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=346", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6NNVCH7PQQ7LDJM5P65FLKHOT7JZ3EFS", "length": "6714", "offset": "115464847", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00629.warc.gz", "charset": "UTF-8", "languages": "fra,lat"}
-fr,missiondefrance,bibliotheque)/index.php?id=3465&lvl=author_see 20240716151219 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3465", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PWGKH3YQPZ53GREEMMHOOCTSMSY6V222", "length": "9580", "offset": "3808067", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00344.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3469&lvl=author_see 20240716161347 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3469", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PCFIBEYIIPIDOBBCTQ37MCMR3LBEG7JE", "length": "6660", "offset": "114064199", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00327.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3469&lvl=author_see 20240721140900 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3469", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FE7LAYNAW4Y2HUDT7YZTQHZV4AVS5KV3", "length": "6616", "offset": "4395083", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00348.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3471&lvl=notice_display 20240721140157 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3471", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "35AQ4YR4NPQ26274TEMQMOEZMXO33LBB", "length": "4979", "offset": "4408008", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00419.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3476&lvl=notice_display 20240716162107 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3476", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "B32OTBA3Q2DAIU3BRFLEDRMW3O55BYPS", "length": "5108", "offset": "125784975", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00355.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3477&lvl=notice_display 20240716144858 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3477", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XICPUFQAGDHIAJEW4XILKAKGZ6FXNPVU", "length": "5116", "offset": "120790101", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00356.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3478&lvl=author_see 20240719082335 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3478", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4INMESTVFLFOSFZAQCOHGAR7FZWXCRDC", "length": "11354", "offset": "3902615", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00378.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=348&lvl=author_see 20240724143540 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=348", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YUA3W7AKFDGRQD5MQ6RJEYQTZ2TN62QJ", "length": "10991", "offset": "3627080", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00587.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=348&lvl=categ_see 20240721005147 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=348", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TWFHO7BHPHOQ4NICWDABKSLVLI64ZFFX", "length": "10590", "offset": "3973419", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00460.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=348&lvl=indexint_see 20240721004659 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=348", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OK4PM4BHKR77Y3YKDLLN7EZMIDMIGGNP", "length": "11080", "offset": "5054144", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00085.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=3484&lvl=author_see 20240715060450 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3484", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GM4PQKM3DT7TD554I5374N2XAWEJ5QVL", "length": "7022", "offset": "4380430", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00405.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3489&lvl=author_see 20240722111346 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3489", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YOC3PF44P2QNTEIVGU263YFZYJ5HMJE3", "length": "9321", "offset": "106063616", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00389.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3491&lvl=author_see 20240721130750 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3491", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NNYBGSFEHZIXW3GFNSPPJEBDCJN4WSHC", "length": "7328", "offset": "106114157", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00412.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3498&lvl=author_see 20240721020253 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3498", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ETPJP4JTGOO456GHPWXGADPH654LL2TE", "length": "7185", "offset": "108548300", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00419.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=35&l_typdoc=a&lvl=indexint_see&main=&nbr_lignes=32&page=2 20240725192325 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=35&page=2&nbr_lignes=32&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OH77GUHKEVJQDH3T2C775N25F2SNM4V2", "length": "10840", "offset": "102289291", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00178.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=35&l_typdoc=a&lvl=indexint_see&main=&nbr_lignes=32&page=3 20240722111709 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=35&page=3&nbr_lignes=32&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2F26KLIGYPIJGRBIZ63JB7QP6AVBO4CC", "length": "7174", "offset": "106682890", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00385.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=35&lvl=author_see 20240721015846 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=35", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2SW6T26LV7UH4PMMIDC7WJGNHDE424IV", "length": "10313", "offset": "7229516", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00266.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=35&lvl=publisher_see 20240718142747 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=35", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "N6VKPG4BE45HJ7ZAZD6BLGRALWWN5MUF", "length": "8622", "offset": "3478668", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00025.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=350&lvl=categ_see 20240712174144 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=350", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XRS6UT2K773O6UQEDCLNNKI536UQZRQN", "length": "11482", "offset": "4941278", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00483.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=350&lvl=coll_see 20240725183643 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=350", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "H6GLBSZCTXV4NMCL5MC7U2VV72WQJEUK", "length": "9912", "offset": "4893977", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00629.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=350&lvl=indexint_see 20240716152208 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=350", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MFRQAPQM4CSMDDVOL2S7U64XRQG7QJEG", "length": "10978", "offset": "125820055", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00097.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=350&lvl=publisher_see 20240718135611 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=350", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AHROEWCW7XKGFEXQPHHULL3GZBLMFBUM", "length": "10925", "offset": "3252567", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00079.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3500&lvl=notice_display 20240719100713 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3500", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HAT4BTIIK5WOXV54E7BD7CZX5XH2MGSR", "length": "4960", "offset": "104059794", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00193.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3503&lvl=notice_display 20240721135609 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3503", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "V65WTUQB7C4GTXZEPOJVYJDLQSP6AYLO", "length": "4918", "offset": "103641308", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00196.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3505&lvl=notice_display 20240721125540 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3505", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EOJEKRJA2M2B4Y53DJJGQ5UAPX6MUFC5", "length": "4998", "offset": "112003401", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00198.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3508&lvl=author_see 20240721010831 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3508", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LFGOUBQ53GV5BDOZ5ARPVGFV6RKZIYVN", "length": "10026", "offset": "3453451", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00222.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=351&lvl=indexint_see 20240715053453 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=351", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3FZNHI3UN47XDTP3WUINB5Z4KOTUNSWQ", "length": "9006", "offset": "5115337", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00109.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3516&l_typdoc=a&lvl=author_see&nbr_lignes=51&page=4 20240725190244 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3516&page=4&nbr_lignes=51&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AIYQTZZC6UUYUL7FRG55INVT4IWY2KBV", "length": "7820", "offset": "6036684", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00381.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3516&lvl=author_see 20240719171535 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3516", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FHDYB6HBFNRWMBX4R6BARLOYOUT263ZC", "length": "9831", "offset": "106664963", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00230.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3518&lvl=author_see 20240719081328 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3518", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HB4A5YLYVEYJ6V6MA4MKHYG6HVA6W6ED", "length": "11339", "offset": "112512378", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00232.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=352&lvl=categ_see 20240718193752 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=352", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RO7LKCQKFCHOBMCV5RS7MIBUSA2I4HLL", "length": "11550", "offset": "120184872", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00452.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=352&lvl=indexint_see 20240718150741 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=352", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "24PFP5ALHYKTOHWFYPIQKTAGR4GO52UN", "length": "10700", "offset": "111689310", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00099.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3521&lvl=notice_display 20240721011841 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3521", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SQVTQBQ67BY2IAMVOIEWYNAFQMZNDVPL", "length": "5047", "offset": "115209813", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00256.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3534&lvl=author_see 20240722115116 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3534", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3VEYUZRYIRWWRF2RMMMRQA2QJ6X3OUTN", "length": "8792", "offset": "108016873", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00290.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=354&lvl=subcoll_see 20240721215420 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=subcoll_see&id=354", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WIJZ4JPPKD7YSR2QAVMGJSMZXNXO37ZF", "length": "6988", "offset": "3025884", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00715.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3546&lvl=author_see 20240724155638 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3546", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FRQCPI67BD3BYLL5XBFJVAJPXZYTIT6E", "length": "6852", "offset": "100665454", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00323.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=355&lvl=indexint_see 20240718143244 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=355", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Q7Y4JP3LFUIALIIC4ZORFFNUU6ACP6P3", "length": "11837", "offset": "5131478", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00113.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=355&lvl=indexint_see 20240718200749 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=355", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DQ7HNNGTZGHUC5BOXQCAF77XDGXVSAIV", "length": "11846", "offset": "114700386", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00102.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3557&lvl=notice_display 20240721133011 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3557", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "47DJJYCT5K2TYA5HLPKCQJ2GWD2AM47B", "length": "5189", "offset": "5832253", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00424.warc.gz", "charset": "UTF-8", "languages": "fra,deu"}
-fr,missiondefrance,bibliotheque)/index.php?id=3559&lvl=notice_display 20240725185110 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3559", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "N5ZL3CRRWIH4H3UAVTIPUH5CHXCCXBSK", "length": "4997", "offset": "107332037", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00357.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=356&lvl=publisher_see 20240721234016 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=356", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KYL2NKK23YK6AVOA2K7EZ4BRB3FFXZWO", "length": "6890", "offset": "4637976", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00085.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3563&lvl=notice_display 20240721141515 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3563", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6Z2SHNCC5D7VYPKNEJQHDAIRCN57TC5Q", "length": "5009", "offset": "6715817", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00451.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3569&lvl=author_see 20240724160749 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3569", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OMLHNHEWUIVWICDLYVQZCHP2OWZFKFP7", "length": "7189", "offset": "3505866", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00409.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ile"}
-fr,missiondefrance,bibliotheque)/index.php?id=357&lvl=categ_see 20240718193446 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=357", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YU6ISPV67OHN4FS23X3GGOQG56KBJAMB", "length": "10816", "offset": "4469056", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00490.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=358&lvl=categ_see 20240718140346 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=358", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "V2NSUMH3MP6RKCP75CUJ74R3DXTIGO3D", "length": "11547", "offset": "110223098", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00458.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=3586&lvl=notice_display 20240719082143 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3586", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "T66REETLOXMD2TQPILVF7O4TGB7Z3BEW", "length": "5036", "offset": "111484535", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00447.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3587&lvl=author_see 20240721231828 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3587", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SGIP2ELHPYAPINBW662KU5CUCJTZCAHB", "length": "6812", "offset": "108319504", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00448.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3589&lvl=author_see 20240721221112 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3589", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DGHTMUJVBHLUPOWNKAUWYFPPEP6A7IOM", "length": "6443", "offset": "4632456", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00471.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=359&l_typdoc=a&lvl=indexint_see&main=&nbr_lignes=73&page=2 20240721223414 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=359&page=2&nbr_lignes=73&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7BLK64K4WWASOABT5JTIAASFFJIMFG7T", "length": "10406", "offset": "5612361", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00871.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=359&lvl=indexint_see 20240718202337 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=359", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RSHTFCCM4ZX2BGKFTT7YCZ4FL4L6JW3C", "length": "10732", "offset": "113289062", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00106.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3596&lvl=notice_display 20240721004941 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3596", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZWFNAXVFFV7IN5VLVHBINTS5SCUBKMG6", "length": "5110", "offset": "101721918", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00478.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3597&lvl=author_see 20240718205913 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3597", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SMY5S3IAO3ME6GMMUBFUNA2YLAM6LFO6", "length": "7285", "offset": "111644616", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00479.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3598&lvl=author_see 20240716153802 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3598", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CYQSNETBLT7LRTUNA3I6ICUITJUJKWJ7", "length": "6473", "offset": "5124833", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00501.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=360&lvl=bulletin_display 20240718211421 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=360", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UBE5KDPOEE7QVVCFVHZ253MPTUXRBPVO", "length": "8821", "offset": "104937437", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00483.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=360&lvl=indexint_see 20240716143904 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=360", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2XVHZ2WYEJKG4IKO5XHZCBHU5YQMTKKX", "length": "10639", "offset": "4792802", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00139.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3611&lvl=notice_display 20240716160423 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3611", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3TBBKTUGGNIDWCPJ4Q75KHYNJ4ANYX5K", "length": "5192", "offset": "3359051", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00355.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=363&lvl=categ_see 20240724161814 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=363", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DHZJG3WDPZZJ7YAT65MMVC6WHBVNGW5Q", "length": "11698", "offset": "5171068", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00517.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3636&lvl=author_see 20240721001422 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3636", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5X74HFLPBCALBWPA6OTHTAZ373O2ZLWA", "length": "8439", "offset": "112628692", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00353.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=3637&lvl=author_see 20240712170828 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3637", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "V7BS2HLTX3BDR3LMJ55RLCF4KQYQLBZC", "length": "6551", "offset": "4096472", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00375.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=3637&lvl=notice_display 20240718203435 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3637", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OWUJXASTJHNXCX2ORGBAX7ZZRDBBCAYY", "length": "5126", "offset": "117005264", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00354.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=364&lvl=bulletin_display 20240716151643 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=364", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "35IXN3BLJ4YNVNV6DYN57KVWOSW6IFRA", "length": "6778", "offset": "2915926", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00134.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=364&lvl=categ_see 20240721232543 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=364", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TPEYTR2NA22BT3KERZSTGJOXPVIOCME7", "length": "11137", "offset": "4899425", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00518.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=365&lvl=notice_display 20240718195355 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=365", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7PTQ6IB33PXHUMKYXMFIGSUHEU75XIG5", "length": "5068", "offset": "3382824", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00346.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=366&lvl=author_see 20240719100648 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=366", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "R2UT7KZL6IRIPNLSCTE37KHQQWLRXSG3", "length": "10507", "offset": "112809809", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00160.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=367&lvl=author_see 20240718212646 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=367", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PDNBRU5AIAWG7S2KOYE4MWVMUFRPUZML", "length": "11010", "offset": "112746073", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00161.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=3680&lvl=notice_display 20240721004017 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3680", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6CHGWTQ77VIBC3VM6KYRC5EEUQJZ3G46", "length": "4993", "offset": "3064377", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00571.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3682&lvl=author_see 20240719100630 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3682", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "64NZYKOHGZ2UKZZ6LJUAT4IEO7HBVAWS", "length": "7503", "offset": "4664034", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00525.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=369&lvl=categ_see 20240718141554 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=369", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3QIZE7FVUXAPFIZTDYJ6WRM7IYTN6MAY", "length": "10824", "offset": "3385965", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00523.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=369&lvl=indexint_see 20240724162326 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=369", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FHMENI6KPOZWWJWRLGUO3EHROLR6QD2V", "length": "11845", "offset": "102840436", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00137.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3691&lvl=author_see 20240721125800 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3691", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3R54H5PXUBHZT6C2G7FKPI5UHDHM2BGT", "length": "7191", "offset": "4450552", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00555.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=37&lvl=bulletin_display 20240719094934 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=37", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "T3UF6XZL3GMXDJ7DOKNZW3RWGYTIDYS4", "length": "5113", "offset": "103786248", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00642.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=370&lvl=categ_see 20240719090509 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=370", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FI6PG2NWHMMLUJEDLMRV73XFH5JSOBQW", "length": "10636", "offset": "112579439", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00512.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3705&lvl=author_see 20240721140120 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3705", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WK3FMK2LL4W4MNPTADYNW6JV73G46HVI", "length": "6593", "offset": "3320019", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00341.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3713&lvl=notice_display 20240725183244 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3713", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7LZYELUUV3SWSS2DV5GZRXUOUASXQA37", "length": "5175", "offset": "116389243", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00349.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3717&lvl=author_see 20240721000443 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3717", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "A4KWHEWWQFXEMX4TO6MXIEAVIY4OZ2O4", "length": "9445", "offset": "112638161", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00353.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=372&lvl=categ_see 20240712185712 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=372", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JL2JBCRQEWKAT4OATUIF2ORKPD6Z7S44", "length": "11582", "offset": "100858271", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00514.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=372&lvl=indexint_see 20240719100559 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=372", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YC5TLIAMUZPDKK7AGGKQEXENJEANTY5E", "length": "10525", "offset": "3948413", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00172.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3730&lvl=author_see 20240719170547 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3730", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4FACZOUQBBEEP553LR2MK7UOZ7A3KGSE", "length": "8067", "offset": "5452087", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00429.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3738&lvl=author_see 20240722104448 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3738", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UTGYCHTXONXPVSVVHPMM3T34V4GRBBLA", "length": "7397", "offset": "102302620", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00416.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=374&lvl=categ_see&main= 20240719175718 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=374&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "H6LIOWKYQIOE6H7TO5STNW4G65UTVVD5", "length": "11075", "offset": "3083611", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00071.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=374&lvl=indexint_see&main= 20240716142846 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=374&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2CH2NEULNOX4EIYCQKMYQFGJJPYANFJU", "length": "10598", "offset": "4556137", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00160.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=374&lvl=indexint_see&main= 20240721001740 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=374&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6XUFA5WXFQH3KG7ES62CG5ETXQ7EGA7G", "length": "10603", "offset": "112441831", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00361.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=374&lvl=publisher_see 20240721214936 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=374", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YSI3QL3UJSBPZKACHN3JXBQEE57QLMM5", "length": "10667", "offset": "104494029", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00720.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=375&lvl=indexint_see 20240719085816 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=375", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DECLAA24T7C7YFMX4SH6N7IOTYUSDZ4N", "length": "11037", "offset": "4489277", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00175.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=377&lvl=categ_see 20240718134953 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=377", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PU3GUKFJZZ234ZZUKQR36PCQWKRN5UQB", "length": "11106", "offset": "3813574", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00552.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=377&lvl=indexint_see 20240725191028 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=377", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6RJWALYEXWNCB774MWG656VV4E3MMHT3", "length": "10834", "offset": "3100272", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00177.warc.gz", "charset": "UTF-8", "languages": "fra,eng,lat"}
-fr,missiondefrance,bibliotheque)/index.php?id=378&l_typdoc=a&lvl=indexint_see&main=&nbr_lignes=39&page=3 20240725185934 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=378&page=3&nbr_lignes=39&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6F4VQBPWW3CQTEFNYR2PBJBLBSSOFYD6", "length": "9702", "offset": "104367076", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00406.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=378&lvl=indexint_see 20240721234118 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=378", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KMIYNWMCX3MKD655WRHC2URUEQHFLBUD", "length": "10540", "offset": "2962080", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00178.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3783&lvl=author_see 20240719082745 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3783", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6UZ4NLA4BD43PLMVWDEE6R3QALZC3IVF", "length": "7927", "offset": "106242709", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00566.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3787&lvl=notice_display 20240719181604 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3787", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BQOPOSTVFX66KVBYKUVXXAU5O2TTPMX4", "length": "5464", "offset": "4286393", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00639.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=38&lvl=categ_see 20240724143909 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=38", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HXSV7ZRVZH6RDF5ZON4LDQO7LY3GQD5T", "length": "11468", "offset": "110814077", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00261.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3801&lvl=author_see 20240718135536 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3801", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JDVHXQBJBUGKTRQK6TL4LZKGJAKLNY5Q", "length": "7542", "offset": "111466347", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00377.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=381&lvl=indexint_see 20240716151528 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=381", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NECNGS2GEMEBN2RCDC5ED5DAK4PDUW2G", "length": "9968", "offset": "3528059", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00202.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=382&lvl=indexint_see 20240724152313 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=382", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JKP43QQMNDQ4D3ZUNDBI2SNDWCF724OP", "length": "12129", "offset": "108389621", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00192.warc.gz", "charset": "UTF-8", "languages": "fra,ile"}
-fr,missiondefrance,bibliotheque)/index.php?id=382&lvl=indexint_see&main= 20240718193006 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=382&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "B3O2MLZDZQQL2LJVK7DDPXZ6ZB5KV4DH", "length": "12134", "offset": "116442035", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00834.warc.gz", "charset": "UTF-8", "languages": "fra,ile"}
-fr,missiondefrance,bibliotheque)/index.php?id=3825&lvl=author_see 20240725183347 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3825", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CGPKURCN2W27ZAMXCYPBPBVBG2QZXXAT", "length": "11030", "offset": "4188396", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00464.warc.gz", "charset": "UTF-8", "languages": "fra,eng,lat"}
-fr,missiondefrance,bibliotheque)/index.php?id=383&lvl=indexint_see 20240724145807 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=383", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "O5WY3RZPCQALG23AIPJRWW6QLBQ32COI", "length": "9768", "offset": "111025716", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00193.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=383&lvl=subcoll_see 20240725195536 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=subcoll_see&id=383", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "K3VY627EOAZPMMKFCUXLDOEIG73F7BCK", "length": "6851", "offset": "118622712", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00786.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3847&lvl=author_see 20240715061331 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3847", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JLWZXOJ3SWFRU4PDOD5ABII5FQIW7JUQ", "length": "7896", "offset": "109567616", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00507.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=385&lvl=publisher_see 20240718150626 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=385", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LQZJVNX3GTI2QS4GN2CESE6SYOWSIXRH", "length": "9015", "offset": "118760371", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00752.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=386&lvl=bulletin_display 20240722104707 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=386", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "V25XTWWII5GZ5KMEYZVHCOUHASUJVYD3", "length": "4945", "offset": "109898310", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00551.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=386&lvl=indexint_see 20240716154530 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=386", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JGV47BMDXJ6Y7LMRLMBSAHI67K2XLINL", "length": "11755", "offset": "110550922", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00196.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3864&lvl=author_see 20240715043955 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3864", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QZNE7SFPHCRPGXSFFB3PVEMHOLLU3VIA", "length": "8133", "offset": "4299732", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00587.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=387&lvl=publisher_see 20240718200153 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=387", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SMQMWJFZBTZUPQUF3B3HAYA7Y3WOYID5", "length": "10568", "offset": "3485202", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00179.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=388&l_typdoc=a&lvl=indexint_see&main=&nbr_lignes=31&page=1 20240718144526 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=388&page=1&nbr_lignes=31&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AV4DKDQ527GZ7TIETJGYW45ECOXB4S7L", "length": "10766", "offset": "3829055", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00894.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=388&lvl=categ_see 20240721221455 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=388", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7ZWP6XIQVKBBBS4YHAXEF3JW23KZDRV7", "length": "11969", "offset": "114950107", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00551.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=3889&lvl=author_see 20240712174648 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3889", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CR4MDVP3V6EN7KFFEJTSSLCFEVUOFM3T", "length": "6990", "offset": "99986181", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00633.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=389&lvl=indexint_see 20240715050200 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=389", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JNZGLAEYJSP3N3BQ5VTI56OSKBFT6DLQ", "length": "10193", "offset": "4146151", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00210.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=389&lvl=notice_display 20240718213730 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=389", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YZMYWYB4KQ3GKI2KXFCL3J5VAFXDHTCM", "length": "5087", "offset": "116173519", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00273.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=390&lvl=author_see 20240715041828 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=390", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "REI3RBX4DB5XZCRZRECSJ4G2MWRSEHRX", "length": "11351", "offset": "3732112", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00734.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=390&lvl=coll_see 20240718205130 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=390", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "E5ZGSWVGACX4NJYUSLYJBYOLQNASVBHB", "length": "6512", "offset": "4985868", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00753.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=392&lvl=categ_see 20240712183844 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=392", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4LEM7RXOYWFCRA5A2H45CDSFELFP2W3A", "length": "10489", "offset": "103047443", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00576.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=392&lvl=categ_see 20240718144548 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=392", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6UHO7G37SBVMAP25MD4TIBGSIKD42CFI", "length": "10451", "offset": "4107890", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00609.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3924&lvl=author_see 20240721221152 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3924", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NWPJHHMUDNR24HXMLXO6GUDFRDHHX77I", "length": "6676", "offset": "3049006", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00524.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3929&lvl=notice_display 20240716145225 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=3929", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OS5IW67KA6COHZEFFHRVKTP5BT3LVL4C", "length": "5115", "offset": "110689686", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00508.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=394&lvl=categ_see 20240721004234 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=394", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YDYQH723HKA22VLZVUZZ5CFZN23NMZ7O", "length": "10603", "offset": "119318859", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00578.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=394&lvl=coll_see 20240718132800 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=394", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KUSA6NUAREPMOPVYDX4J32DCYB2U5LPT", "length": "10430", "offset": "4323060", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00757.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3941&lvl=author_see 20240718191950 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3941", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TEPHQ7WL6QXAQIT2BF3IZOHZ672UDGWB", "length": "7065", "offset": "4924766", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00583.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3945&lvl=author_see 20240712163144 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3945", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WDCEVHK5PASE7BFXYUNXADZWUQUQLYQP", "length": "9476", "offset": "113921519", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00566.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=3952&lvl=author_see 20240725182243 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3952", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PCUOS6K3RHLG2R4UBNKHU7BT5MZKV4W7", "length": "7523", "offset": "2885015", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00615.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=397&l_typdoc=a&lvl=author_see&nbr_lignes=47&page=2 20240721233626 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=397&page=2&nbr_lignes=47&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7HW6Q6GOZZMEYEPELUPORJW7Q4IHUJLW", "length": "12634", "offset": "113324759", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00883.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=397&lvl=author_see 20240724152546 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=397", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2BF6OG5DURNESDFEKHALZTIUM7SZ2XLK", "length": "11746", "offset": "109874011", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00254.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=398&lvl=categ_see 20240715050903 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=398", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ERL256BMHTIYVY6PJQFXANUGU7WKISM4", "length": "11084", "offset": "4128266", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00615.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=399&lvl=bulletin_display 20240722111329 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=399", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CLNDFB5BSK5Z37BSMRVT4QTIXQVVQN2H", "length": "6299", "offset": "102171867", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00585.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=399&lvl=categ_see 20240718140219 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=399", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DODC3JH3KGB57EPX7XBPE336A6D3G4D5", "length": "7692", "offset": "102976697", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00583.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=3995&lvl=author_see 20240718205800 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=3995", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TUJFC5YGSQMJVMGSLHGLT26DEBRU45EP", "length": "7097", "offset": "5626233", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00742.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4&lvl=categ_see 20240716155311 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=4", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3I6R72ZEFRFQ5GPYQ5K7JJE46MEJJBAV", "length": "10757", "offset": "113580701", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00548.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4&lvl=indexint_see 20240718192824 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=4", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QRJJWLMLQFRSVAPT7DIDWCPY5US7LCFJ", "length": "10370", "offset": "4480850", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00490.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4&lvl=publisher_see 20240712162424 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=4", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MYSWVMUXA46V3HRXVLQD3QSEKXEPDLNU", "length": "11249", "offset": "107766283", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00156.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4&lvl=publisher_see 20240716151334 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=4", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZZWHGBJJJ4Y4BH34WW6ZSEM7FHAMP7GB", "length": "11210", "offset": "2854114", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00229.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4007&lvl=notice_display 20240712182048 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4007", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AA4JHGHUXJFOMOTYYSNNLGDNBMYL3N6Y", "length": "4986", "offset": "3335481", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00055.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4008&lvl=notice_display 20240721222257 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4008", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KFNOE2WRJTXGZPBVX6L47PLCQ3ZZWFFM", "length": "4903", "offset": "105678995", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00887.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=401&lvl=categ_see 20240724144629 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=401", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EY53JS7HVRSU6AZ25FGPJAO4CU6YQCU7", "length": "11034", "offset": "3081328", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00390.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=401&lvl=publisher_see 20240724161328 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=401", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "25GYNXQ2OTA3TOLCMX3YQUJQP5LCOG56", "length": "6767", "offset": "113719408", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00561.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=402&lvl=subcoll_see 20240721222757 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=subcoll_see&id=402", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "M4MSJOXPDHMRRAQZGJAKB7VIIPHTVXC6", "length": "7446", "offset": "114784702", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00598.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4022&lvl=author_see 20240722111311 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4022", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AEWY3YIEA7IRQCRIS5FML2GQXKWFAV2T", "length": "6459", "offset": "3849146", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00064.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=403&lvl=bulletin_display 20240722110014 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=403", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UDSKLGQTRRYZI73TCFQG4QVG42RNKPG4", "length": "7455", "offset": "107111223", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00361.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=403&lvl=categ_see 20240718193646 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=403", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AEYTYVS2MWMDN3VYQWVYJ7MB6C3VIDW2", "length": "10465", "offset": "3353245", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00392.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=404&lvl=bulletin_display 20240722110045 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=404", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EA4J5IUETUTKVJIKQWRWJKDAZM2XCRAL", "length": "8109", "offset": "112563006", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00362.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4049&lvl=author_see 20240725184122 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4049", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PQJ2TYQGZ2367BVLUMM7E6CRXO5Q4MIN", "length": "7248", "offset": "3615714", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00133.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=405&lvl=author_see 20240721003944 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=405", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZFE3DNL6IK2KXTIJLBT7RIVO42J7ANWJ", "length": "8059", "offset": "4291474", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00521.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=406&lvl=indexint_see 20240712173901 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=406", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JOPDHN2P4FCTTM6HMYNFCPDVQCS36R4M", "length": "10979", "offset": "109546284", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00009.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4065&lvl=author_see 20240718212117 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4065", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "STKZRTKRPMSYWAPK4I2ODWQH5SQVTB5M", "length": "8849", "offset": "107343433", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00170.warc.gz", "charset": "UTF-8", "languages": "fra,ltz,lat"}
-fr,missiondefrance,bibliotheque)/index.php?id=4065&lvl=author_see 20240725182544 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4065", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CHJCJKFHFCFEMMJPHZFMAV777LJPZDR7", "length": "8839", "offset": "5502851", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00191.warc.gz", "charset": "UTF-8", "languages": "fra,ltz,lat"}
-fr,missiondefrance,bibliotheque)/index.php?id=4067&lvl=author_see 20240721015708 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4067", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HCDJ4FCI3XEQQIGSYKFAJ6LNAXMCG3FV", "length": "6738", "offset": "4203794", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00193.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4068&lvl=notice_display 20240725191500 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4068", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "423WYNPU2GDPJFZDQKLBRU4DMO3RGEPS", "length": "5019", "offset": "114925039", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00173.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=407&lvl=bulletin_display 20240718140620 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=407", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KIHS3USI6ZV6NEVFHU7U4BNW4UWES4PV", "length": "8153", "offset": "105917796", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00365.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4071&lvl=notice_display 20240725201326 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4071", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GMKG7ORTL46CU57UVZAJXM4EERL2PPU2", "length": "5017", "offset": "113975326", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00197.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4073&lvl=author_see 20240718143258 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4073", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JXWAX3GDC3QZYZGS63VYBCS2DNIHDF2A", "length": "8141", "offset": "117416741", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00199.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=408&lvl=bulletin_display 20240722110315 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=408", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RZV4LG2QQEFNG3N4JLRFY2TIHCC2PCVM", "length": "7101", "offset": "112122325", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00366.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4082&lvl=author_see 20240716144556 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4082", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FU6INYWHNJIPAZYH3HDXI7R4RDC4GXEW", "length": "9569", "offset": "120621075", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00229.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=409&lvl=bulletin_display 20240722110416 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=409", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Y3MADDW2CSJM4N67QLX2SUVL7XWZZD73", "length": "7700", "offset": "106001986", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00367.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=409&lvl=bulletin_display 20240725191220 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=409", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SS533UOVLN6DC6HH2KSGPNOJ55GORGFG", "length": "7687", "offset": "3107290", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00014.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=410&lvl=publisher_see 20240716145629 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=410", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3D34YSTD3Z3SNMLDKMOW6454N4UQ7R24", "length": "10237", "offset": "3350164", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00016.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4100&lvl=author_see 20240724144245 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4100", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TWV4YL2MWOTZM4MISYVPPV3XG6Q2NHD3", "length": "11634", "offset": "108207086", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00040.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4101&lvl=author_see 20240721012626 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4101", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VUEWNSLNXO7GUSD5QWMKLCE45NUXN55O", "length": "10247", "offset": "107456155", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00041.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=4113&lvl=author_see 20240715052748 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4113", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Y7H6PSM7RCIHTP7D3U3JRBP2AGV3D7EV", "length": "9338", "offset": "113492048", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00074.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4113&lvl=notice_display 20240719084030 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4113", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "P75C6PSHAKSNFAOAAFBM2XYRNCGNKZGR", "length": "5024", "offset": "110928237", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00074.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=412&lvl=bulletin_display 20240724155518 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=412", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "IKHGDUGCPPGT57H3ZEWYYYSJAK4TVDEQ", "length": "21798", "offset": "111309438", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00391.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ita"}
-fr,missiondefrance,bibliotheque)/index.php?id=4129&lvl=author_see 20240719090635 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4129", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AG7J4SQJFOM6YCLWK6APVTQEDEEPMRVX", "length": "7100", "offset": "105754336", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00111.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=413&lvl=categ_see&main= 20240721012316 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=413&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5POYDA4IHGOAYS64CCTREMN7MFIZZTKX", "length": "10649", "offset": "114201003", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00136.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4130&lvl=author_see 20240721020356 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4130", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GOX5JATARRSINEHVDVJGHPVQMPLHNEMF", "length": "6633", "offset": "3258959", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00154.warc.gz", "charset": "UTF-8", "languages": "fra,ltz,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4131&lvl=author_see 20240721232837 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4131", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TSEYMHJENCFT3G5ULQARGNFRHG5DPQZX", "length": "7196", "offset": "3084584", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00155.warc.gz", "charset": "UTF-8", "languages": "fra,ltz,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=414&lvl=author_see 20240715042232 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=414", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3RO5XGSGPNJIYZCTX52EXR57DU45MUZ4", "length": "8498", "offset": "110917246", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00064.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=415&l_typdoc=a&lvl=indexint_see&main=&nbr_lignes=36&page=2 20240721011018 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=415&page=2&nbr_lignes=36&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CLRJAUP7EDQPZZX4TOBSBO4IQELU4AVL", "length": "5138", "offset": "113282529", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00170.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=415&lvl=indexint_see 20240721005046 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=415", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XIVOXIIN5MJPZHOTEPE5RBMK5V3ROLSX", "length": "11275", "offset": "4265356", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00050.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4151&lvl=author_see 20240721002643 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4151", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7XVVIMXVBWS3K3TIOT6DDREHVUCEAIFO", "length": "11058", "offset": "113206898", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00196.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=416&lvl=categ_see 20240718203535 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=416", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EOKTL2GKOM3PIP6WR4GKBDXKE7LCRHKA", "length": "12004", "offset": "4531351", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00426.warc.gz", "charset": "UTF-8", "languages": "fra,deu"}
-fr,missiondefrance,bibliotheque)/index.php?id=416&lvl=indexint_see 20240718145543 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=416", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MSC6KVQXQOU5AKNMKTEN7QX5KICZ4RXE", "length": "9831", "offset": "5792512", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00051.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=417&lvl=categ_see 20240721000847 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=417", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KBTM5JSKIMXVWCMNRMSBI7NZ2UNURH4G", "length": "9245", "offset": "105099721", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00394.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4176&lvl=author_see 20240721005905 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4176", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CCIZRGLGKOPOJ3YEGMAQP3RRDKT2VCQ3", "length": "6436", "offset": "120476322", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00263.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=418&lvl=indexint_see 20240715060948 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=418", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6ZNXTGAUYZUXZDHS3H35GJ6RPVYDTQKR", "length": "10069", "offset": "5425601", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00053.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4189&lvl=author_see 20240721015235 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4189", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FFGWO32NEUXJE5TT73HA6SBU63I6NOIE", "length": "9079", "offset": "117800461", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00297.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=419&lvl=categ_see&main= 20240719074559 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=419&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3VZ4WCFRFCO3E43WHKHJSAV7CVBQV5KJ", "length": "9944", "offset": "118377379", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00426.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=419&lvl=coll_see 20240719081108 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=419", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "X4P7JA5S3VVCONXEMTRF7M4QGIV4ZZNJ", "length": "7554", "offset": "116454212", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00584.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4192&lvl=author_see 20240721002025 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4192", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DC3N6WOFAJD4PHKRDGBM3UCHDIJRJ3IG", "length": "11016", "offset": "3590832", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00342.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4194&lvl=notice_display 20240718195516 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4194", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EEKNPXUD7ZDJZO4VKT5EWXAWV7764EFX", "length": "5130", "offset": "116048737", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00323.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=42&lvl=categ_see&main= 20240718213737 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=42&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HKRJZ7MY5DCDIHBUW72CLYTCJTUEKYHP", "length": "10781", "offset": "113915068", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00364.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=420&l_typdoc=a&lvl=categ_see&main=&nbr_lignes=66&page=1 20240725200541 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=420&page=1&nbr_lignes=66&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Y6DEFEXSXA35HFWK66RTM7RCNLCVM7SA", "length": "10270", "offset": "102825030", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00469.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=420&l_typdoc=a&lvl=categ_see&main=&nbr_lignes=66&page=4 20240725200729 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=420&page=4&nbr_lignes=66&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Q3JH2WEUXYHTTQC37OZVALNURVDQTGJW", "length": "10638", "offset": "107193371", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00190.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=420&lvl=categ_see&main= 20240725201536 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=420&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "H5ICQFLECTLFVE5JVTOJ4DTFRHG6GHQA", "length": "10249", "offset": "104893866", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00376.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4201&lvl=notice_display 20240721013655 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4201", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "U5GAMNKUPD56FUPRUFA5KLDSOAEQWA4Z", "length": "5005", "offset": "114650137", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00102.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4208&lvl=author_see 20240721010152 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4208", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SGSIWZMHDUK3PNMIXWUOXFD7F6PEJOYU", "length": "7959", "offset": "106394584", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00109.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=421&lvl=indexint_see 20240718141802 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=421", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RFACXFTMISICRT3AEZRTP2J5LFX5V3FP", "length": "8916", "offset": "110382169", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00066.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=422&lvl=categ_see 20240721232947 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=422", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "H7NX3CDPJ6WYLSKH27XJM5DSXC5H74QP", "length": "11172", "offset": "103514199", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00420.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4221&lvl=author_see 20240721230115 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4221", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BYJULGG5N5AFYFMHG6YVRCOR33Z627R3", "length": "9204", "offset": "111655969", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00164.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=424&lvl=coll_see 20240715061845 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=424", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MWK43CB5JRXC2VYAIXA5QTJWGKW6ZX36", "length": "6718", "offset": "114887043", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00610.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=426&lvl=author_see 20240718132040 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=426", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TBRCH4ZCHFUDUVUJER6AZ7USNNYVHLDJ", "length": "7953", "offset": "106355434", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00097.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=426&lvl=coll_see 20240725194954 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=426", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ESXOAP2KBQPAQ2TMTW3ZWZRZ4YMGFFPM", "length": "9124", "offset": "3040732", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00603.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=426&lvl=indexint_see 20240724160507 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=426", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2YDW7VNN2EHDQLIEXJC343XOL6LJDXAI", "length": "9120", "offset": "5404793", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00082.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4260&lvl=author_see 20240722113832 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4260", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "W3OCSG7DGULUTOB6HWVTE7XIXBH5TIBY", "length": "7045", "offset": "115516692", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00287.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4263&lvl=author_see 20240715044812 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4263", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7TH7PJZOP6YV4S52QRJ2A6YU7446O6TR", "length": "6653", "offset": "4864414", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00311.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4264&lvl=author_see 20240715043351 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4264", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SW3YQGMLUOF2DWQ4DJIOUE553WOCRK6Y", "length": "6651", "offset": "4389433", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00312.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4265&lvl=author_see 20240715041709 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4265", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ARSEAXZIMERT2ACJNWPVB4RYTXGXTZBX", "length": "6649", "offset": "3443205", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00313.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4266&lvl=author_see 20240715061254 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4266", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "36OED2IQRJ62RVE453ZMQTEJNDVRIFX5", "length": "6649", "offset": "5301822", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00314.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4266&lvl=notice_display 20240725194108 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4266", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GHLNDZJKP6AOFI6TVODA2XPKDFF3YEIK", "length": "5063", "offset": "2944203", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00362.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=427&lvl=indexint_see 20240718135108 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=427", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "E6R4QGBYCVEY53WKDW564U2GXFYGBCBI", "length": "10411", "offset": "3558063", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00083.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4270&lvl=notice_display 20240724152805 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4270", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZJ5H6T2LGQ6TPRDEX6XIBBA7OFEVTYVS", "length": "5268", "offset": "3380821", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00387.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4271&lvl=author_see 20240718194433 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4271", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ADPOAY5VGLRYCHVNGBFVKRT74R4HMOO4", "length": "8176", "offset": "118967593", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00319.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4271&lvl=notice_display 20240721231350 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4271", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SVM4JDZS43VRFLQFA72CBXJTF35ZMV4E", "length": "5293", "offset": "3188135", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00388.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=428&lvl=indexint_see 20240712185910 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=428", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UPWAERD3NBJ7VOLDLEARW3QXHTX6X6RD", "length": "10750", "offset": "102415846", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00073.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4294&lvl=notice_display 20240716151410 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4294", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "H2WSJFZP4EK2LKL2GMF3OMU4NTMUT6DO", "length": "5228", "offset": "125623261", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00384.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4295&lvl=author_see 20240721134017 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4295", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2STM75BKWYT7CBNIQ3QNHIS44QWOTF53", "length": "7036", "offset": "3158940", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00406.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=43&lvl=categ_see 20240712175906 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=43", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ING446HAADYFIKAKWYF6MKEXH2FYKTGZ", "length": "10625", "offset": "3089604", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00330.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=43&lvl=categ_see 20240721000945 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=43", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VX33Y7V4UOFYEYLEYJC6XEDKTDK5JHAE", "length": "10631", "offset": "108570574", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00287.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=430&lvl=publisher_see 20240721123328 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=430", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7GOZKB355LKGMW3K73QTBFIYUQXJ6ISD", "length": "7021", "offset": "116667812", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00653.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4306&lvl=author_see 20240715051701 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4306", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5WUQUTY5BXQBBMF2A6VJEKDLVDALSWQS", "length": "8149", "offset": "3795675", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00189.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4317&lvl=author_see 20240721214637 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4317", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "F6YZOOJPKDF3WO4K2XKDB72URMILSCSK", "length": "6501", "offset": "116444997", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00200.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=433&lvl=categ_see 20240721213731 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=433", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TD7X3KGQDM6IHE6VRVEATKEFBHYRCAF2", "length": "10640", "offset": "111891058", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00452.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4332&lvl=author_see 20240716154759 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4332", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FCTBROHYAHEM5FGGLCLIPHNCDDNYZTOR", "length": "9624", "offset": "6113166", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00278.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4332&lvl=notice_display 20240724150506 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4332", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Y6DJPLOVIX64VI3EFQA34JSBE6XR5RKT", "length": "5215", "offset": "4186864", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00326.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=434&lvl=categ_see 20240719083321 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=434", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DDMWEI5LY2HSXLNTZLSO3FEAHCOL3YUM", "length": "9405", "offset": "111432011", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00453.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=435&lvl=indexint_see 20240724144349 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=435", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LOQTOK467FSAGPTY6MFXVYT7G4S4RPWP", "length": "10586", "offset": "114049479", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00101.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4357&lvl=author_see 20240722111738 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4357", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7T6URKW3B2ZOR6GYA63LJJ5REZJJIB3X", "length": "7895", "offset": "110381132", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00324.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=436&lvl=publisher_see 20240721230336 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=436", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ACFWQU7TVWLJFRDCWTLT6DQFMUJUUZOV", "length": "10656", "offset": "112149653", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00659.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4362&lvl=notice_display 20240718200353 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4362", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SQOIBPOV5JOQGNC57ICZ5QG5V5DLSG72", "length": "5206", "offset": "116620355", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00350.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=437&lvl=author_see 20240722111058 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=437", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UFNTYPAIHDFNF4AGXRVTS2DTWUL7KNI5", "length": "7741", "offset": "4911037", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00616.warc.gz", "charset": "UTF-8", "languages": "fra,deu"}
-fr,missiondefrance,bibliotheque)/index.php?id=438&lvl=coll_see 20240721232034 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=438", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YGVUTOM2INQ5KIQ27GTDYYO2MRDPYBHS", "length": "10061", "offset": "4683126", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00636.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4396&lvl=author_see 20240721131850 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4396", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CI5YEQMC6RHHU6V4PVSQVCLARQPHEHUR", "length": "6813", "offset": "4331517", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00468.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4397&lvl=author_see 20240721130823 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4397", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EQDVLR7IUFGRRGUWIJM2I4WF3OTX452F", "length": "6820", "offset": "3866150", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00469.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4398&lvl=author_see 20240721125725 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4398", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XYZFKIXBR26W3HH76GW5VRGUFGRBAZBD", "length": "6818", "offset": "6255220", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00470.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=44&lvl=indexint_see 20240712164421 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=44", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LJ3WREDNSXCQAM54KCZV4YUEXTYFKUQR", "length": "10052", "offset": "99197642", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00285.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ile"}
-fr,missiondefrance,bibliotheque)/index.php?id=44&lvl=notice_display 20240718211555 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=44", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XGXFA6NY4BLSZZ7BA5BAUATOP3NJKHJR", "length": "6107", "offset": "106856202", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00767.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4401&l_typdoc=a&lvl=author_see&nbr_lignes=17&page=2 20240716160725 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4401&page=2&nbr_lignes=17&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DVLL7U4L6HXUDLTXSHAENLBQ6XIRBYWE", "length": "6794", "offset": "118535754", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00350.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4404&lvl=author_see 20240718145721 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4404", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YYARGYOSMCTQBGWFAKWVFYK2TBYRIY2O", "length": "8029", "offset": "104521666", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00227.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=442&lvl=publisher_see 20240721122949 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=442", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XHIN2FTO2ZM4ADT2E3DQAKF2LKO5I6RV", "length": "6821", "offset": "109686369", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00686.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4424&lvl=author_see 20240721215503 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4424", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NPSHWJNIBRL3JTGMCIXCX4DUZACFDYRR", "length": "10346", "offset": "4440590", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00310.warc.gz", "charset": "UTF-8", "languages": "fra,lat,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4433&lvl=author_see 20240716152629 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4433", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ULFHJL6VR2LDZUDGRDVUAGR5YKOERTI3", "length": "9421", "offset": "3411795", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00340.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4437&lvl=author_see 20240718132528 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4437", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RXL6V2QJWYN7HGF3JPADO2URFKCQQ45Y", "length": "7873", "offset": "115858238", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00323.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=444&lvl=author_see 20240721140353 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=444", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "42YJPQIDCRQOMOILMMWLN22HXKIOBP3I", "length": "10362", "offset": "3098068", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00644.warc.gz", "charset": "UTF-8", "languages": "fra,ile"}
-fr,missiondefrance,bibliotheque)/index.php?id=4446&lvl=author_see 20240719084257 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4446", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VC7MUO2JWVLYQMVFQ626ZATYK2NIZEHQ", "length": "9123", "offset": "3917754", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00374.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=446&lvl=categ_see 20240725193819 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=446", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "W3UDNLH7I6UNYGDCP6K7NZJDAD2N5U7F", "length": "9908", "offset": "109940269", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00486.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=447&lvl=indexint_see&main= 20240721014209 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=447&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JZZOZVDUGVF4O32SVTUT3W4UICHCN2VD", "length": "10696", "offset": "113747762", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00332.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4470&lvl=author_see 20240722100835 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4470", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LBZTYNGRGCZL6DWKKYUWOLJ6GSWZ2C73", "length": "6541", "offset": "113283925", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00440.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4483&l_typdoc=a&lvl=author_see&nbr_lignes=26&page=2 20240718213743 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4483&page=2&nbr_lignes=26&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DWEPE5VWCK7RSJU4R54DFCSMZLZ7JYYC", "length": "9819", "offset": "112085249", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00866.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4491&lvl=notice_display 20240715054844 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4491", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GM4WJSVFWWCCGGWHI2MCPUFTE4P47AGS", "length": "5146", "offset": "117255373", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00503.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4496&lvl=notice_display 20240721122509 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4496", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3TQIJUUOVIRH7YXUQ562I3R23STOK4XE", "length": "4912", "offset": "105355406", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00508.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=45&lvl=author_see 20240721010520 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=45", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7RVX7KV5K5TZSLVELLNSZZMFPEBKHCKY", "length": "11367", "offset": "5050717", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00297.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=45&lvl=publisher_see 20240715052541 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=45", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MVL3PWOM5FVHM34CBA657SF5RQK47FPE", "length": "11409", "offset": "112778453", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00893.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=450&lvl=categ_see 20240724150318 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=450", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KW3NMHJT2SNSYUXXHZVZ2COD5OME53QA", "length": "10359", "offset": "4100157", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00544.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4506&lvl=author_see 20240722102036 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4506", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LNCY4DEDP53IPY6NVFG665BVS32CGMFP", "length": "6785", "offset": "108026625", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00290.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4515&lvl=notice_display 20240719083358 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4515", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CIDC4GT6UCDSDMHN4O7AGLXXYI7XUZJO", "length": "5146", "offset": "106985095", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00320.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=452&lvl=indexint_see&main= 20240721223516 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=452&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UA4NM655UKLY6ECZG7SASHVLWUHWJVO6", "length": "11549", "offset": "4571182", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00009.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=453&lvl=publisher_see 20240712185520 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=453", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GRXKERT4WDUNGKKKCPCCCL6TR2BMTKTU", "length": "10588", "offset": "98357235", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00718.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=454&lvl=author_see 20240715061447 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=454", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "C2CENUZNC6KAWIOBQKHJKUGK67YWTC2A", "length": "6659", "offset": "112427277", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00188.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4544&lvl=author_see 20240725191342 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4544", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ANHF7VOEURH2DT57ET4DPRFVXKITHEZS", "length": "9399", "offset": "3895423", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00433.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4548&lvl=author_see 20240725194643 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4548", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TMMFUPNQRXPUXCTHSFBY5G6JGYHDTCJY", "length": "7193", "offset": "116295744", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00416.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4548&lvl=notice_display 20240725183521 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4548", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TF57DEQK3LFEEKHLUQBLI7H2RV66FKK4", "length": "5089", "offset": "3671559", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00485.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=455&lvl=publisher_see 20240712162637 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=455", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BU7ZPAUROHTXHTXYLSCNAPU4CTJKSNIF", "length": "10134", "offset": "3198139", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00145.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4551&lvl=notice_display 20240725200619 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4551", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4J5HSUTM3PT5MJFFGNCDN3KRLDT3XIMT", "length": "5018", "offset": "3415137", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00509.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4554&lvl=notice_display 20240725190928 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4554", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BC5KSJ3ULMVQ4KFIDH32MBRRDX466ARI", "length": "5268", "offset": "4377364", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00512.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4587&lvl=author_see 20240712182513 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4587", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "22RDJ63QWZXW4BX7SPYOMNUDQ5R2WM4S", "length": "6952", "offset": "101185119", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00539.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4594&lvl=notice_display 20240718142306 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4594", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GVXZABHMAJHPU5VN2FK6KET6DMCQ36JD", "length": "5045", "offset": "102615813", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00567.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4595&lvl=notice_display 20240721123644 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4595", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RCQCGYHYXMKHR765DN2UJ22U5HYFTNIH", "length": "5050", "offset": "4750920", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00637.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4596&lvl=author_see 20240715043046 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4596", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JMLVZYBBVWXBOVFSUPD73R3TQ3XLL6TY", "length": "6673", "offset": "111021015", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00569.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4597&lvl=notice_display 20240721130716 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4597", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4YYL4MPQAMAC7EPJXO3PVK3YJGV4Q6ER", "length": "4992", "offset": "112478571", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00570.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=46&lvl=categ_see 20240718212721 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=46", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QJLTXGDTBW7YWW7NRQLITC5GAODZONZZ", "length": "11741", "offset": "112129653", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00290.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=46&lvl=publisher_see 20240716151835 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=46", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UPVS6VMWRW2DAVVDPL5ANUJHFLZFVL4K", "length": "10970", "offset": "118014779", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00894.warc.gz", "charset": "UTF-8", "languages": "fra,ile"}
-fr,missiondefrance,bibliotheque)/index.php?id=46&lvl=publisher_see 20240718132400 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=46", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YN7XQU5VFDY67EBP3NE74VY3NXQG67FX", "length": "10925", "offset": "2813055", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00057.warc.gz", "charset": "UTF-8", "languages": "fra,ile"}
-fr,missiondefrance,bibliotheque)/index.php?id=4613&lvl=notice_display 20240719095950 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4613", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YJ3RAHBBFW4Z66EEHE73GDLAGID2E443", "length": "5019", "offset": "110705289", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00379.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4616&lvl=notice_display 20240721011534 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4616", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FJ532SCL2OJ4WLJVFTW7R2PQP5HDRWPS", "length": "4958", "offset": "110739080", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00382.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=462&lvl=publisher_see 20240721133426 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=462", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "R4QADWEC6TEDBQDP3UHLYWFKRZRPPNER", "length": "6562", "offset": "115706769", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00748.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=463&lvl=categ_see 20240719094354 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=463", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "624YCVBHXO7NPEHGTZCDP44NMFVSFTXE", "length": "10502", "offset": "3616941", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00578.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4637&lvl=notice_display 20240716155104 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4637", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KOWCFUZ5GFQAYRL2LD722DTY4ILQAWC5", "length": "4992", "offset": "4150417", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00514.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=465&lvl=categ_see 20240718142456 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=465", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NIQUWR3WTVEESIFN3QLWJRSTZ7VVNMG4", "length": "11135", "offset": "3299786", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00580.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=465&lvl=categ_see 20240721222111 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=465", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5UYGQR4HLDLIXDPVSVIKSBCOSY6RTUFU", "length": "11150", "offset": "110102085", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00547.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=465&lvl=indexint_see 20240718143432 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=465", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VPL7YIIYW75MSCLYWOA2O7VKAWXMNJLK", "length": "9094", "offset": "112097473", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00194.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4650&lvl=author_see 20240715054633 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4650", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XIZRG4EHZHQFMNL63264FUNVP4UD2PPS", "length": "7177", "offset": "112919060", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00500.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4652&lvl=author_see 20240715054927 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4652", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "M7FDRTDGWKL4XNVQ7LULG432K2LE5GFX", "length": "6532", "offset": "117710644", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00502.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4663&lvl=author_see 20240716145428 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4663", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "B5JYBQJYHPWSKH7LMPY42XTMYBHEXNWS", "length": "6605", "offset": "113852114", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00534.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4665&lvl=author_see 20240721215954 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4665", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3ACXUVKZFGB3A76I4AVJHVSKMD24XJ5R", "length": "7477", "offset": "109457203", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00536.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=467&lvl=categ_see 20240722114021 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=467", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AE6BWHD5WIWIYH5NNQVZNBQK6JPLFDJ7", "length": "9182", "offset": "112076855", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00549.warc.gz", "charset": "UTF-8", "languages": "fra,deu"}
-fr,missiondefrance,bibliotheque)/index.php?id=468&lvl=categ_see 20240722120455 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=468", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VEU4KZ5QMMDQOXHR5GBGKWAMXP6DWQXP", "length": "8771", "offset": "116500634", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00550.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=469&lvl=categ_see 20240721130857 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=469", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HWTHRCJORVGJJQZR6BIFLQGTHUZR2EPY", "length": "11007", "offset": "6605945", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00584.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=47&lvl=author_see 20240718204602 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=47", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VR7PYMFBEGBWSICPJTFIBLFKXBBK3ZGY", "length": "11170", "offset": "110484190", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00266.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=470&lvl=categ_see 20240721215708 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=470", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WPTCU2STZ4VZ4YCACQQE3IMJQ4XEOXRQ", "length": "10688", "offset": "111296051", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00573.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4700&lvl=author_see 20240712175242 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4700", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZYBTSCHPR2WYI5UADNSNZDPVGZJVQYKS", "length": "8167", "offset": "107009667", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00406.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=472&l_typdoc=a&lvl=categ_see&main=&nbr_lignes=22&page=2 20240721123245 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=472&page=2&nbr_lignes=22&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DZY337BYTHNLT7DYVNINBORU4SENBPJN", "length": "9805", "offset": "108692265", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00013.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=473&lvl=author_see 20240719181103 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=473", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "P3TPZMDXZHGPZNCMEYIB73PMCS7BU6BY", "length": "10141", "offset": "3696337", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00736.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=473&lvl=publisher_see 20240718203258 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=473", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Z4L3FYY5WRDH6M4RKGJNB2MEK2K74JLX", "length": "10503", "offset": "116421052", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00780.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=474&lvl=indexint_see&main= 20240721221308 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=474&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SHD6QFBH5K5DB57NP4B3JOJIFSDIX4US", "length": "10421", "offset": "3331599", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00397.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=475&lvl=indexint_see&main= 20240716160459 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=475&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QABEWJQSBCE46HAAOGJFURPGSGVXSFJR", "length": "11279", "offset": "4057758", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00578.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4757&lvl=author_see 20240715051553 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4757", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6MFFQJATGJYPVUHPCL6KFNY6WIYYZK4V", "length": "7385", "offset": "111685130", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00568.warc.gz", "charset": "UTF-8", "languages": "fra,deu,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=476&lvl=indexint_see&main= 20240719174543 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=476&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KEAX6PVCPLPCXIEUSY4VGQMTM267EYUN", "length": "10865", "offset": "6217865", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00759.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=478&lvl=categ_see 20240721001646 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=478", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "X53P456LB7CZXNSAMYUCEXSQPJB6SOSH", "length": "10457", "offset": "4788129", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00614.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=478&lvl=notice_display 20240719095042 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=478", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SVFOZWIJZUG6C6LKDHL4ZCLMV6BIZWD7", "length": "5038", "offset": "3181949", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00441.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4786&lvl=author_see 20240718205630 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4786", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XBG2SUJ5KAKXYZMJEPTYZRR36BYZPWD6", "length": "7306", "offset": "103492728", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00660.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=479&lvl=bulletin_display 20240722115843 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=479", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BD4BBLGAAHEIG4TIWTEKBNE2OLE6ORPI", "length": "7127", "offset": "3125345", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00231.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=479&lvl=categ_see 20240718131103 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=479", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "63GYSFWFV7MSK36DTOFDMF5JH5UJUR7G", "length": "11129", "offset": "5534152", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00615.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=479&lvl=coll_see 20240716160339 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=479", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "N5WO3JGHA54DQECETQI56B6GEVVUKBAG", "length": "11205", "offset": "116111467", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00770.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=48&l_typdoc=a&lvl=author_see&nbr_lignes=85&page=5 20240721002719 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=48&page=5&nbr_lignes=85&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "22XKXI5NWHQ3FH2ZDVL6J5JPGTTUNY2Z", "length": "10697", "offset": "5136492", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00204.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=48&lvl=author_see 20240716161702 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=48", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LBEYZX2TW6TLYNX7C6SB4K5OIQYEWDF6", "length": "10069", "offset": "122862730", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00267.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=48&lvl=indexint_see 20240712172020 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=48", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5R3N5SJQV2FOV2FZ45YJVTRJ6MKBRYLA", "length": "10864", "offset": "5475317", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00310.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=48&lvl=indexint_see 20240721220530 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=48", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TTNU4GC6KYIQVRHBQLES4BGFT6AGWUEW", "length": "10869", "offset": "112277997", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00289.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=480&lvl=bulletin_display 20240722114847 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=480", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "K6LZWQDQQPUAVXN4GYIOVGBZM7AJHZED", "length": "6943", "offset": "5237620", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00253.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4809&lvl=notice_display 20240712172910 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4809", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "INT5CPH4AVASNMVK55BNFVYWEHM47Q6Q", "length": "4975", "offset": "103428511", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00476.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=481&lvl=publisher_see 20240724152029 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=481", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZPRH6RU6V2ACRYSEV3EPUKKY7ZCET2RT", "length": "8367", "offset": "4321397", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00234.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=482&lvl=publisher_see 20240718133555 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=482", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "J72HM2CFBVCXIZAVPCGAPHP3OAZW2OBY", "length": "10733", "offset": "108924862", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00810.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4822&lvl=author_see 20240716153413 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4822", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZQ2JRKANG7Q6H67WGXDRXX5FMV7VA3XV", "length": "10208", "offset": "109417392", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00531.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=484&lvl=author_see 20240712180317 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=484", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UMJ74KEXLVN27AXTCGL2OAN2X7RFK6VX", "length": "9539", "offset": "3547608", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00768.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=484&lvl=categ_see 20240712185645 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=484", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VIAQIXBLGP575ZIPTZSEI34FXOBELY6Z", "length": "11408", "offset": "106182215", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00608.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4849&lvl=author_see 20240718145504 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4849", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EUPG72JT53QTHTNQAOHECOA2AYVSKJEY", "length": "7183", "offset": "112130157", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00600.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=487&lvl=indexint_see 20240712180513 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=487", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PAOPG52WDXPBJ6Q2KE3BMYYW5UKRWNQY", "length": "10992", "offset": "2930430", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00269.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4886&lvl=author_see 20240718150945 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4886", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QUMMQUOGQ3SFIXZ6GNFTUSQKWSKRNDKN", "length": "7883", "offset": "3948921", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00742.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=49&lvl=author_see 20240724142510 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=49", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KFWVWP2UXFKLMROPQNXJ3TDFWGYCQUXA", "length": "11197", "offset": "107762694", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00268.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=49&lvl=publisher_see 20240712181856 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=49", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ITNVZ3NRZ6TGYE6M27RRJM6T5XRUKW7K", "length": "11389", "offset": "103369292", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00897.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=49&lvl=publisher_see 20240718204325 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=49", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "44CRTIMLNE3WSSR23QHRCEU7FVNM6RLB", "length": "11345", "offset": "4483037", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00060.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=490&lvl=author_see 20240721225303 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=490", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GCOQ6APENARFQI52QODHSWSZKV4YJ3SL", "length": "11167", "offset": "3548455", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00795.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=4907&lvl=notice_display 20240721134029 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4907", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "X4XO3GH5SQLIK7PSUT2YK7PZ7L6LD5QT", "length": "4967", "offset": "3857127", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00604.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=492&l_typdoc=a&lvl=coll_see&nbr_lignes=17&page=2 20240724151426 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=492&page=2&nbr_lignes=17&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JAJUCF6EH2TPYFN2J3GOMD2ZTLYQ62LI", "length": "7435", "offset": "112649908", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00623.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4923&lvl=notice_display 20240722105259 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4923", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XHMKKLE5Z4F2WOL3TWLDTCNSH5WOLNPR", "length": "4963", "offset": "99306201", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00593.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4935&lvl=notice_display 20240722111418 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4935", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LHCQJRTVUKEA2E5B4L22JM42OXH2X7VG", "length": "4920", "offset": "4603608", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00695.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4944&lvl=notice_display 20240722110744 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=4944", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZXR6ZYFKHBHV4S2SYOR3PNOOR427H2PW", "length": "4932", "offset": "4239625", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00725.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=495&lvl=categ_see 20240716145308 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=495", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6NBJSH4KKEWBENTR3OO6YBTQ5UTIUBPW", "length": "10995", "offset": "111991573", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00640.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=4977&lvl=author_see 20240722113907 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4977", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GZRY6NJG7VCMTACF23TBSNKBIMF7YWJ6", "length": "9735", "offset": "109220945", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00752.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=498&lvl=bulletin_display 20240716144318 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=498", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XJ2QRCGI3MIPS4PYV67XRJV2ZHVBIT4B", "length": "8879", "offset": "5895298", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00292.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=498&lvl=categ_see 20240719095117 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=498", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "L5HNZF5SC5N33IORSF3DCLBVKWHMPKZ5", "length": "10435", "offset": "108750990", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00643.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=498&lvl=indexint_see 20240715061930 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=498", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5C3JNL23NNBLVR6OK43XQ3W4VFWS2ZZW", "length": "11064", "offset": "3026240", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00301.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=499&lvl=author_see 20240721225251 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=499", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "R5ZARFVTM2GYYQVQC7OXPIG2AR4OLR7I", "length": "6659", "offset": "4565854", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00804.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=499&lvl=coll_see 20240715061754 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=499", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SK3SMQRGSPNWZEUM7KA2IIK2YDESAKC4", "length": "6714", "offset": "120325520", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00832.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=4998&lvl=author_see 20240716143302 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=4998", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7XY2W24Q6NSFSOH6EZFB7DGUKGQNDR6Z", "length": "6793", "offset": "117784267", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00815.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5&lvl=categ_see 20240716151141 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=5", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "V55MJ6A7OXFSRNXNKDCOCY6BIDNMQHH7", "length": "11171", "offset": "123432233", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00549.warc.gz", "charset": "UTF-8", "languages": "fra,deu"}
-fr,missiondefrance,bibliotheque)/index.php?id=5&lvl=categ_see&main= 20240712185414 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=5&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZMRGJ2ZSQCDM5AQP2ZP3ZPMLFZTFEMJN", "length": "11178", "offset": "106265194", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00787.warc.gz", "charset": "UTF-8", "languages": "fra,deu"}
-fr,missiondefrance,bibliotheque)/index.php?id=5&lvl=coll_see 20240716145144 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=5", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3JVJZPVPBDERXK6BBI2J6YDRPPAEUIJ4", "length": "10648", "offset": "4037199", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00568.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=50&lvl=categ_see 20240712180418 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=50", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CZL2XFZTVMMQPVDSB26C3PZX4U3S42WH", "length": "10651", "offset": "5852308", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00358.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=50&lvl=categ_see 20240718211919 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=50", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3TIHSBDSPRZRKTZLNWZ3Q5YZ7N64OBY4", "length": "10661", "offset": "107357616", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00315.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5006&lvl=author_see 20240724162550 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5006", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UGDW5T346OABJ4ZBDC7HKN7KBVCTOZJC", "length": "6624", "offset": "107217293", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00076.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=5011&lvl=notice_display 20240721131636 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5011", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VPPAL2EWE6VNTNAKISHXUBK7V5IRDPSR", "length": "5001", "offset": "108410504", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00102.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5016&lvl=notice_display 20240721135753 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5016", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6JIZNHHQYIP7MHPLQ2ZRE2XEDDEMO3M2", "length": "4996", "offset": "103275280", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00107.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=5018&lvl=notice_display 20240721125912 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5018", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VOXLJA7FFOVY2OFXD5CQBMSTUPYPBTD4", "length": "5261", "offset": "105901939", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00109.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=502&l_typdoc=a&lvl=indexint_see&main=&nbr_lignes=17&page=2 20240721011721 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=502&page=2&nbr_lignes=17&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5J6Q4TCQY675HN4S5654OF6GY6P5HM3B", "length": "7311", "offset": "107513370", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00622.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=5022&lvl=notice_display 20240718201853 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5022", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2IULTTOH5VBC5YZ4MP5US5HEI64V23TJ", "length": "4919", "offset": "4367002", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00203.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=504&lvl=indexint_see 20240721231436 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=504", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CP5BZVTOIFLHLV5VZPKQFPBLX74N7ZFV", "length": "8761", "offset": "103770150", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00068.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5042&lvl=notice_display 20240722105220 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5042", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZUFFZCRUD22YG35Z4WFDLO3Q4H6ZNCAM", "length": "5030", "offset": "112494741", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00196.warc.gz", "charset": "UTF-8", "languages": "fra,ile"}
-fr,missiondefrance,bibliotheque)/index.php?id=505&lvl=author_see 20240712181144 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=505", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "B7CS2GCTAZZ7TL5KRVRERT7E663R5LKR", "length": "10019", "offset": "103580848", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00095.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=505&lvl=coll_see 20240715055810 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=505", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "N4BHRQO3IBNUSLQ4BJ4KJ5X5LP64CJVK", "length": "10266", "offset": "3165524", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00601.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=505&lvl=coll_see 20240721010735 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=505", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AHKGPZQMZNDEWQXP7UVJGLDMK5IMARSF", "length": "10274", "offset": "116975271", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00610.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5054&lvl=notice_display 20240722101749 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5054", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BAYRY2FHCE4UWBDO7POC4XGHCL65VBDO", "length": "4989", "offset": "4250945", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00298.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=507&lvl=coll_see 20240716152348 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=507", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "STSBLWHNR3A7M4D4PMYJ4AVQBODY4G5C", "length": "9342", "offset": "118348780", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00612.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=507&lvl=publisher_see 20240724162823 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=507", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "66M4SBHZZ6B4F3QQOYHFNLJYVLQOTZYD", "length": "11920", "offset": "118096390", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00628.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=508&lvl=indexint_see 20240721015528 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=508", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WMKEDZ2JEQQCNG7KKA6RAXVBHVPBLCNI", "length": "11240", "offset": "108847858", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00072.warc.gz", "charset": "UTF-8", "languages": "fra,lat"}
-fr,missiondefrance,bibliotheque)/index.php?id=508&lvl=indexint_see 20240725183926 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=508", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WVLUNIUSAHNMBE2C5VDXVKQHZKORO64V", "length": "11230", "offset": "3415321", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00083.warc.gz", "charset": "UTF-8", "languages": "fra,lat"}
-fr,missiondefrance,bibliotheque)/index.php?id=5082&lvl=notice_display 20240725182844 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5082", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "P4357GT5TCFJTGWWPDNBG7CGG56XSAPB", "length": "5040", "offset": "104472525", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00320.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=5086&lvl=author_see 20240725181539 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5086", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LGOPEJH6SXEAQ4AFUQ6DHD24LKPSEAIK", "length": "6602", "offset": "3392814", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00345.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=51&l_typdoc=a&lvl=author_see&nbr_lignes=63&page=2 20240724143951 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=51&page=2&nbr_lignes=63&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Y47DY4Q47GGIUBESY7QVJWYB3NYYPRFJ", "length": "10864", "offset": "109728217", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00542.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=51&lvl=categ_see 20240715044155 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=51", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QY3ZJDLKXI5VMF7ROG6DRYZS26PKDCIG", "length": "12713", "offset": "3095804", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00359.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=51&lvl=categ_see 20240721014133 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=51", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CGCTG5MY6UV4RGL3TSN4YEREVH5VHEEI", "length": "12719", "offset": "116211483", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00316.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=51&lvl=coll_see 20240718213557 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=51", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "URPGROH3LYWHYFXT2FAFHNYWOXPM2YAL", "length": "10106", "offset": "5950915", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00697.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=51&lvl=subcoll_see 20240721014505 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=subcoll_see&id=51", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LVZYPIYCX4ELKNSWL4C46HUHTKKKT2HU", "length": "8079", "offset": "114271960", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00728.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=5109&lvl=author_see 20240722115730 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5109", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "J75XZYBIUTSTJIDB5HTBWWUXQDFCA5PD", "length": "6427", "offset": "3703058", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00161.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=512&lvl=author_see 20240718133857 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=512", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3PHXI77MOY6RO6CUN24TT7GJKR757NPG", "length": "6576", "offset": "123894680", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00123.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=513&lvl=author_see 20240718193915 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=513", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TEMOXFSQRL6FV6HX6UGF5QVS4HXZMPNC", "length": "10850", "offset": "111497444", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00124.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=513&lvl=categ_see 20240712182659 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=513", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YBZXPBGPX2JPRVKYDZ5YBZIGIKFC2QD3", "length": "11354", "offset": "101718726", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00451.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=5143&lvl=author_see 20240722103101 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5143", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MHQZA5UGSBZFNDXCXWK2XJGYJ45Q2HUC", "length": "7447", "offset": "106944307", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00258.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=515&l_typdoc=a&lvl=publisher_see&nbr_lignes=22&page=2 20240718200908 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=515&page=2&nbr_lignes=22&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZUCVYBN2Y3DWR34D2EDNRJSLCNXRVIKJ", "length": "8751", "offset": "119617632", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00357.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=516&lvl=categ_see 20240715050123 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=516", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QSLO4G5IPKOBKT3H2SZKNDALVXLNAUUU", "length": "9744", "offset": "2709942", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00487.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=516&lvl=categ_see 20240721223306 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=516", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BXFLT4PZHRHQA2RS6MLBAXPCG2RVXJGH", "length": "9751", "offset": "106652797", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00454.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=516&lvl=coll_see 20240724145508 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=516", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "35NDPBCK3P7GSZEI3RFLK2DK77A6YOSU", "length": "6850", "offset": "5291347", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00633.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=516&lvl=publisher_see 20240718143357 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=516", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2LWVYFM4NRGWPRPEPZUZ7UOYXT2TBEZL", "length": "11307", "offset": "3569393", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00083.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=5169&lvl=notice_display 20240722120826 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5169", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "A2JNXH5LG5IBIBLI2UGZEPXZYWLSJKWT", "length": "4992", "offset": "3840011", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00395.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=517&lvl=categ_see 20240722112108 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=517", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EQLZW4JIZ3BXJX2VD2G4GT2AKHGYI52G", "length": "11768", "offset": "108705581", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00455.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=5176&lvl=notice_display 20240722110810 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5176", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NG7OHT3NSW6QPCQXUGHRTNF7TXW5ZEFJ", "length": "4944", "offset": "4709567", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00423.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=518&lvl=indexint_see 20240718201551 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=518", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LYGEOPZT3FB3OWQZLTXSX5I7RHBNXMWW", "length": "7153", "offset": "112119686", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00103.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=52&lvl=categ_see 20240721015000 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=52", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DWCDAMCES4Q5EXRA72364OAXUMFIJUQX", "length": "10268", "offset": "6394200", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00360.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=52&lvl=coll_see 20240722111035 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=52", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UJRNWXHSI6UGFVXP7HJMGUTDBJJ56CBJ", "length": "10209", "offset": "105854640", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00413.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=520&lvl=categ_see 20240721213926 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=520", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GZNM6CLWCRU7KLSITQDG4M33TZDN3URQ", "length": "11409", "offset": "105769618", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00479.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=521&lvl=categ_see&main= 20240721124325 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=521&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5R4FGNUYTAUQQUHRSQ3PXR3KHRSOCE3K", "length": "10890", "offset": "5775650", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00863.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=5214&lvl=author_see 20240721225314 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5214", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "F6VPABWY5M3DDO4HVJI46HYHYPJROHIR", "length": "6775", "offset": "2931061", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00248.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=522&lvl=categ_see 20240721223932 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=522", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HXKTBXCNWOT2LCZEJMC3OIRQXEH4VQJ5", "length": "11477", "offset": "106612139", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00481.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=522&lvl=indexint_see 20240716150523 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=522", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "V6OWNTDN74U4F7YCL4HED2QSOPDVPXOZ", "length": "10245", "offset": "118148601", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00128.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=522&lvl=indexint_see 20240724162513 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=522", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "COOLJFMHRNRBZAGSDDCLBL5VXSKLGJ5H", "length": "10202", "offset": "4116636", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00139.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5237&lvl=author_see 20240719091103 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5237", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FINGB7JM3IZDLHCXN2VD5EULFZ4M76RB", "length": "8921", "offset": "108658303", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00292.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=5238&lvl=notice_display 20240722104052 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5238", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5WKZFNUS42N23QGSFJJTSSS4FAGIZJPO", "length": "4979", "offset": "3003893", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00362.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=524&lvl=indexint_see 20240715055642 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=524", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AUMMGHHTCWWCC2T44HCAFW3H45SZ545Q", "length": "7220", "offset": "111029095", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00130.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=5251&lvl=notice_display 20240716144128 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5251", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UTKENZS5JGM7W4A4VXA2T4PDYBVKQUX6", "length": "5219", "offset": "3943745", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00417.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=526&lvl=author_see 20240718213712 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=526", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XLPP4XZL4I52GJKEBU4RLPR3GIKBI5IZ", "length": "6678", "offset": "107166828", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00158.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=526&lvl=coll_see 20240721134410 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=526", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TU5QZ647WN2G3ANEJOP43IUVC44RCSJ2", "length": "7511", "offset": "104070025", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00673.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=5278&lvl=author_see 20240718204946 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5278", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HA5I4DZXZAIQ3QREWMINAGOZHEOVQN2K", "length": "11034", "offset": "113469743", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00417.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=528&lvl=publisher_see 20240724160632 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=528", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "S44FNHSIGQISSQDYDWKDFDLPGNXCSLCT", "length": "8964", "offset": "6275933", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00116.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5283&lvl=notice_display 20240721133448 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5283", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HGUDCBBWLXRFW6UHZVTXSYBJ6XSTT7BM", "length": "4994", "offset": "102123870", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00443.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=529&lvl=indexint_see 20240712175335 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=529", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Z7H4P3R5OHMWKDLC6ICVTJ2RAXXFX5B3", "length": "9693", "offset": "7295653", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00146.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=5297&lvl=author_see 20240715060759 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5297", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OZNOOJD357XBTQQZOCRRWIMF3APTTMY7", "length": "6922", "offset": "122390100", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00478.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=53&lvl=categ_see 20240721225438 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=53", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TVIB6FODXOQSZ2R7PIC6UUXF2QYIUTIA", "length": "11490", "offset": "110279183", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00318.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=53&lvl=categ_see 20240724151026 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=53", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EOQSR2KDDQXQJTNWJBJ5KN3PJ6PX7VSO", "length": "11480", "offset": "5314577", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00361.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=53&lvl=categ_see&main= 20240721224500 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=53&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "B3IGR323RPZWNXOX7BG4NMNBRW2UH5BE", "length": "11507", "offset": "103844697", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00584.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=53&lvl=subcoll_see 20240712180010 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=subcoll_see&id=53", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5K4VMWQYNIEZUKA3RZSF7AV3PGOCDWL3", "length": "6704", "offset": "105828510", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00730.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=5302&lvl=author_see 20240715052717 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5302", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MP4EOWZNHZ4PXROMF2Y4XK7HBWXEH7A5", "length": "10829", "offset": "111730327", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00255.warc.gz", "charset": "UTF-8", "languages": "fra,eng,deu"}
-fr,missiondefrance,bibliotheque)/index.php?id=531&lvl=author_see 20240719190025 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=531", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TU7TXG5UQNJTQP3O35TYJST7FZBFX7SV", "length": "6687", "offset": "110095550", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00184.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=531&lvl=publisher_see 20240721134056 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=531", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CBCSOYC2R6FJHY4YUMN7ZBXMTWBZHAWY", "length": "6624", "offset": "112248205", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00715.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=5326&lvl=notice_display 20240721224527 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5326", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2MLSEWNCOYCU2KU4SWB4VR66MF53SG44", "length": "4965", "offset": "5021281", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00390.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=533&lvl=categ_see 20240721011736 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=533", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LB5O72QY75KG6CX2YFQIRE63CXSFH6WI", "length": "11652", "offset": "108229386", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00513.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=533&lvl=publisher_see 20240715061028 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=533", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FOVAZED2VV562BN54C6AUKNCIK6FDGZS", "length": "9301", "offset": "114011156", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00717.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=5335&lvl=notice_display 20240721125128 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5335", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GULNSKXKFS6JX4MKZNJSTWLV5OGCH7MP", "length": "4991", "offset": "111638627", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00351.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5338&lvl=author_see 20240722104415 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5338", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CSDEYCWVUYB23G7LUDKMXIKAIRE7HZRP", "length": "7430", "offset": "107911046", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00354.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=534&lvl=publisher_see 20240718213808 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=534", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OQE5HPZWU3OPSKQPUPBRMPCGAPYEZK5C", "length": "7528", "offset": "110555806", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00718.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=534&lvl=publisher_see 20240724144116 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=534", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MSZ72RY5MXGNSIA2XMJK2Y2JYU6ZTHSE", "length": "7513", "offset": "3902939", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00143.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5349&lvl=author_see 20240721012829 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5349", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PDHIUM3KIQN4T4FXF5554VCQLRGG6JQC", "length": "7421", "offset": "110170410", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00386.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=535&lvl=categ_see 20240712162942 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=535", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZHWQPJV57ZJQW2B5X7H7IZGP5VYDCZUR", "length": "10896", "offset": "98375314", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00515.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=535&lvl=coll_see 20240712172633 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=535", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WQS7ILRAJEPPZFS4NLUKHBZ72IH5RQJF", "length": "7046", "offset": "3288943", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00694.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=536&lvl=categ_see 20240718200550 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=536", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CDNHWRWNCWOSWHD3QF2EDPFNLXPBGE3B", "length": "11674", "offset": "112538987", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00516.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5371&lvl=author_see 20240725184458 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5371", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UQZG6DA6A36WXMZKXLOU4RXQ6U3WT72S", "length": "9303", "offset": "109611628", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00471.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=538&lvl=coll_see 20240712165723 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=538", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2XEK63M73PHDZ3X2OKY5OU7QGV4PD2EF", "length": "10781", "offset": "3885099", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00697.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5380&lvl=author_see 20240721224842 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5380", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RV63CXTH3SEHVSI7AJQ2KXSLYQCLZIOZ", "length": "8821", "offset": "4728558", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00522.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=5380&lvl=author_see 20240725194200 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5380", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6TB2ASGLII2S2BB3GRCSM34SNPXZHME4", "length": "8825", "offset": "110876702", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00501.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=5386&lvl=notice_display 20240719172925 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5386", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3DMQQTGLYMXFE2OVQPS2ZSVTVYRO7XAC", "length": "5099", "offset": "3736918", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00576.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5392&lvl=author_see 20240721132844 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5392", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TZPJ2IVBLSAMA36TRBQZXG3UVD6S32GG", "length": "7115", "offset": "106763114", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00534.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5399&lvl=author_see 20240721124053 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5399", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EIMUT32IIZSXPCJD3BB6V4ZGBXB3EHIT", "length": "8924", "offset": "101926228", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00541.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=54&lvl=author_see 20240712184448 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=54", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QX65I2VJJAPNZHKLCBBNJR77NAA3ROF5", "length": "6995", "offset": "96226783", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00294.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=54&lvl=coll_see 20240721135424 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=54", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "L6WQBINDYZWUGJB5O3AAL5IXSD3RBREY", "length": "10272", "offset": "106550717", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00415.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=54&lvl=indexint_see 20240712162531 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=54", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KZC43F3SHOOFZUFKYFXUAXLSUJN3C6NS", "length": "11475", "offset": "105652051", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00316.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=54&lvl=publisher_see 20240712185234 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=54", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "67ZXMQDYL6EKX7VXAMF5P76FLDZOPO25", "length": "10961", "offset": "2893911", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00086.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=540&lvl=categ_see 20240724162145 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=540", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6CHTLE5FRE6MF7QCAJGHCVAETUNYGT3Z", "length": "10663", "offset": "108729886", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00541.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=5402&lvl=author_see 20240721140437 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5402", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FX5NZBHJO6FV62QUHHIDJ6B65CLRTXO6", "length": "6608", "offset": "111567839", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00316.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5409&lvl=notice_display 20240721134403 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5409", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4RE3BIKI7FTDEUUIQM53DCD6JIAYSTXV", "length": "4953", "offset": "4751248", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00392.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=542&lvl=categ_see 20240719084503 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=542", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "53IOJ2K4OYH24MY2UZQTOFHSUYFNRKBZ", "length": "8511", "offset": "112955894", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00543.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5420&lvl=author_see 20240715052336 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5420", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "A3RR7FNQOLUOWQ7VKE7KPG4BY5MLIGS6", "length": "7733", "offset": "114620117", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00376.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=543&lvl=categ_see 20240721222618 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=543", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DSCXJNJVB26DU3TIHUJLNIOHQOCP5O4W", "length": "11036", "offset": "4445616", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00577.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5436&lvl=author_see 20240718143748 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5436", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2N64EOX6X4MLF3YLN4IA3SP37GCZEK2D", "length": "6764", "offset": "4084464", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00434.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5437&lvl=notice_display 20240718204813 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5437", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZJHPDUIXKEKLWPUFNKLF4YIUIF57XAVO", "length": "5004", "offset": "3646633", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00483.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5440&lvl=author_see 20240718142547 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5440", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WB4DSN3NUCY5ZWUU2CQRTOXUIPJUWBZG", "length": "7952", "offset": "5142949", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00459.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5444&lvl=notice_display 20240721123854 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5444", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZSH4LUTCNQ57SEFBFORQ7JJ6S6LNBIL6", "length": "5077", "offset": "7059141", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00511.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=5460&lvl=author_see 20240715043223 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5460", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "P733B25S5PJPJI73DGRCMNVQIEFRW7H3", "length": "7387", "offset": "112927223", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00500.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=547&lvl=publisher_see 20240715041153 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=547", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MX5A22JXFDWR45MJVMJEZB4G4R75IFQZ", "length": "10467", "offset": "5802100", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00177.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=548&lvl=categ_see 20240718143231 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=548", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6UMPP5DUAZ7OUFUTM47LEPUH3DIYBFBD", "length": "8523", "offset": "109584666", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00549.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=548&lvl=coll_see 20240724161133 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=548", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MSYV7B5K7MX5VMAZN4O4NYHGTIRRD7DP", "length": "8096", "offset": "110041700", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00737.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=548&lvl=indexint_see 20240715055603 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=548", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2CAHFD2AM2G266KE3K45ZBJILCT57HWL", "length": "7772", "offset": "4143863", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00207.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=549&lvl=categ_see 20240712185003 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=549", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VMTEV6VYUVMF6ZNCXUAC2HOU6VGOGWWQ", "length": "7456", "offset": "106446610", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00550.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=549&lvl=coll_see 20240724160237 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=549", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YLWPKHYPESZMPOSI3QFNVCU3DDOMNEA4", "length": "7585", "offset": "121831271", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00738.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5490&lvl=author_see 20240715055524 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5490", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "D5HSHKEMPJR2DKFPXPUBQKN67Y2TAXIV", "length": "7606", "offset": "113566454", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00593.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=55&lvl=indexint_see 20240721224553 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=55", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "W3E7DDLX3FSB4R7XXM2MPKA2KWVN2F7A", "length": "11169", "offset": "103898599", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00317.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=550&lvl=author_see 20240721222146 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=550", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HE3SURGF6DJ4VQFQE333HDF2BBCDGVTL", "length": "10713", "offset": "114295200", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00245.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5509&lvl=author_see 20240725192319 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5509", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OTJ5TSOB4MOMX2PUHQPMNHD7ECO2QBYX", "length": "9431", "offset": "110768117", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00384.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=5518&lvl=notice_display 20240721140520 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5518", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MXBEUROV5BKHARMBMAZHO34EGG25D25G", "length": "4951", "offset": "113084687", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00414.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5518&lvl=notice_display 20240721222723 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5518", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MXBEUROV5BKHARMBMAZHO34EGG25D25G", "length": "4936", "offset": "4666421", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00483.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=552&lvl=author_see 20240715061408 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=552", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JLJQN6WNQ3GN2B6K5H7QBPI6ZFFXTGLI", "length": "7507", "offset": "3744383", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00734.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=554&lvl=categ_see 20240722114106 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=554", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SIZ7NK4WF627LK3CH34T6Q6XAT2IC3MI", "length": "6824", "offset": "110373991", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00576.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5540&l_typdoc=a&lvl=author_see&nbr_lignes=16&page=1 20240718141700 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5540&page=1&nbr_lignes=16&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OFCBDUWPYQCX7HXUBJADDYVXWT5KW76X", "length": "10063", "offset": "3546211", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00572.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=556&lvl=categ_see&main= 20240721013340 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=556&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JQDSYAV67RFTLDX6QG2IPJTKBXUY3WLI", "length": "10647", "offset": "4026870", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00881.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=557&lvl=publisher_see 20240724161553 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=557", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6RQONWEC2NYEACJHCOTH2ZF6URX3JSAG", "length": "10123", "offset": "107985396", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00783.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5576&lvl=author_see 20240721132745 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5576", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EY5JZTKJQRRE23D66C4L55QYTAJU5Y5F", "length": "7110", "offset": "3808741", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00619.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=558&lvl=author_see 20240721130932 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=558", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CXBRZ43P4CIP4INUGLIKSQJBIO3O7YQZ", "length": "6935", "offset": "118110255", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00253.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=56&lvl=coll_see 20240716163417 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=56", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4OBO2JJRY5DXLZAXVTRZFSBY23MGDJNL", "length": "8428", "offset": "109713923", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00417.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=56&lvl=coll_see 20240718134432 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=56", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "IUL7AT3JYGFXKEUNQ6YE4KF36YUITDH7", "length": "8395", "offset": "5438670", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00702.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=560&lvl=author_see 20240721131039 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=560", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "V6CDX47EWUVAITYPNJZ36GH6QEOH4ZUE", "length": "6544", "offset": "3136971", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00763.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5630&lvl=author_see 20240721125834 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5630", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AU7R5AE6YUWJCP7TO5OEBI3ZWAH25Q73", "length": "7848", "offset": "4903010", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00550.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5639&lvl=author_see 20240721125615 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5639", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QIXEOEE3PW6MXDBCTZLFE66OGQYJX6PV", "length": "6502", "offset": "3785357", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00559.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=564&lvl=coll_see 20240719174900 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=564", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6377HKFQ3LHR4JNTHHPMXA6TS5SGJI4P", "length": "10732", "offset": "113443365", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00795.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=565&lvl=publisher_see 20240721223825 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=565", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PYZ3YM264EZQKVHLD5ZZL76PCOPCKM4D", "length": "8586", "offset": "6708131", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00237.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=5652&lvl=author_see 20240721131922 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5652", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "J6Y5LV5ZASGHAG3W7LHCESLYCFRKA5K5", "length": "7678", "offset": "5921204", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00614.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=5656&lvl=author_see 20240721123202 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5656", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TYNEJBJRIFZPFWDE4TJBIMGJZUB5MJCS", "length": "6762", "offset": "4846503", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00618.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=566&lvl=categ_see 20240719082046 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=566", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "J5RT5EJQBETV77T6OANYYQSM4BNZTFJW", "length": "9485", "offset": "101461631", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00609.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=566&lvl=categ_see 20240721005702 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=566", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2KABMN7PLW5GLHKTFQDFYHBZKRFLM6FX", "length": "9470", "offset": "3665020", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00642.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=5694&lvl=author_see 20240721003912 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5694", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VACDFWJA6AV74HZC7PU7IPTVTCZVCIQ6", "length": "7317", "offset": "117049466", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00719.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=571&lvl=categ_see 20240719175757 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=571", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "56OYMOWQVETE5H6BQ54PRFRBTCELOKPY", "length": "11231", "offset": "3203606", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00668.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=571&lvl=categ_see 20240721233942 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=571", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4JDTXKGD5OFB2ZQFCQDXAUIHINRZIE4V", "length": "11250", "offset": "109572022", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00635.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5716&lvl=notice_display 20240712175646 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5716", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NCQAWRFD4RJZOSRQLQ7HVYDAWRNPIW5L", "length": "5050", "offset": "3202641", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00603.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5742&lvl=author_see 20240712170248 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5742", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NCQREKCGGYCRNN4UDY7VIWTHMFBRKIGT", "length": "8286", "offset": "2690151", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00644.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=576&lvl=author_see 20240721012619 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=576", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "IZBJSGCAVVEMEEAX5VGJCWWY5CYWMSLS", "length": "10330", "offset": "3707587", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00800.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5766&lvl=author_see 20240715044322 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5766", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7R2CRDCJJL3LIICYWHZXTHFNPAQOBMKU", "length": "7266", "offset": "4275288", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00710.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5769&lvl=author_see 20240725185657 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5769", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BZXJCKSPZXVVQGKKAF7A7JXZK4JFEIGS", "length": "7690", "offset": "109057002", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00692.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=577&lvl=author_see 20240718213249 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=577", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EJC3LVTBAKK7UHXKQU77LQXL6SIFWUFC", "length": "10478", "offset": "5426776", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00801.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=577&lvl=categ_see 20240724150156 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=577", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VKECCZ75SVRYB2V5WW57OKLPI4MTKLRF", "length": "7821", "offset": "110267829", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00641.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=5783&lvl=notice_display 20240722112426 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5783", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3ELBJYLJBO3HYOTL3QAZP5ONZTSHQQOA", "length": "5028", "offset": "3942336", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00817.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=579&lvl=categ_see 20240718212757 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=579", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KLKPFGUIIZWFKOHVBFA5H4XMSL6URLRD", "length": "11421", "offset": "2925838", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00676.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5794&lvl=author_see 20240721002532 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5794", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EAZP45EDDJCRTMCWQYGXHGEEWQTMNDMS", "length": "9323", "offset": "4526835", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00801.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=5799&lvl=notice_display 20240712184632 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5799", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "72VEJWNYISO3OC3JDFYIQMRWALWLSI2G", "length": "4981", "offset": "108428117", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00785.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=58&lvl=indexint_see 20240724143454 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=58", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FFWEOPJVN5CMFSU2KZ52X4JWBAMSD5PS", "length": "10950", "offset": "116636408", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00320.warc.gz", "charset": "UTF-8", "languages": "fra,deu"}
-fr,missiondefrance,bibliotheque)/index.php?id=5802&l_typdoc=a&lvl=author_see&nbr_lignes=50&page=4 20240718205958 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5802&page=4&nbr_lignes=50&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5ZBKKQOVAFDNVCDWAWU2GKGOWBMZSTRV", "length": "9351", "offset": "5131982", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00336.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ile"}
-fr,missiondefrance,bibliotheque)/index.php?id=5802&lvl=author_see 20240721230326 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5802", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DS2OJBUXCD6HAH4TLJ4A5TWXPYYIBHF7", "length": "11657", "offset": "106913113", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00560.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ile"}
-fr,missiondefrance,bibliotheque)/index.php?id=5807&lvl=author_see 20240712170345 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5807", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XXSUBXBKV4FUCZEDE5DMHIJIW7I5NY7S", "length": "10086", "offset": "103634993", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00565.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=581&l_typdoc=a&lvl=author_see&nbr_lignes=20&page=2 20240719094201 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=581&page=2&nbr_lignes=20&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5GRQWG3BN4AW7REZBXLR5EIPRK26IYVK", "length": "8119", "offset": "104518713", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00885.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=581&l_typdoc=a&lvl=author_see&nbr_lignes=20&page=2 20240721125502 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=581&page=2&nbr_lignes=20&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LDJGKQLFTWSGPCTSPTFXQ3SCVO4A6ISR", "length": "8092", "offset": "3146769", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00536.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=5810&lvl=author_see 20240719091016 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5810", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QPZZIV2MIUYPQCMBQXNDIJKI5XV2OP3L", "length": "6743", "offset": "117529527", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00589.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=5841&lvl=author_see 20240718143815 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5841", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GLUP24S4CP4YK2COM3QVBV3I23YCCY5E", "length": "6957", "offset": "116142202", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00683.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5857&lvl=author_see 20240718145306 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5857", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WOG2DOAGBDYWAUT77QQBO6FBYJJH6UKN", "length": "6533", "offset": "4427791", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00741.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5858&lvl=author_see 20240718143559 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5858", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7KI4JX4NKACH7NMLW46KQ6DK6CUGLJCG", "length": "6532", "offset": "3957725", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00742.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5864&lvl=author_see 20240718140019 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5864", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PKWY5OWQ6RRYI7O4EOO2WK6CXIUN7KZ7", "length": "6684", "offset": "4280666", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00769.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5864&lvl=notice_display 20240721005535 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5864", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CS4AGVCEWC7LR76KWJ2IVIA5FY2RSHKM", "length": "5011", "offset": "4400042", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00817.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5866&lvl=author_see 20240724144158 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5866", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4XROISUZC6ASRJOTPVXQGPO37WLL2PWD", "length": "7118", "offset": "3081955", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00771.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=587&lvl=publisher_see 20240712165441 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=587", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5YRD4NX6VCDVPIQSDAOB4IBNASDEIXPM", "length": "7273", "offset": "105951183", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00876.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5886&lvl=author_see 20240718142240 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5886", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YGNQADWVH3SNVE2M2TIMLB2PJIJQOVPR", "length": "6509", "offset": "3123935", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00833.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5895&lvl=author_see 20240715061641 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5895", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UB5U2ALWFJIVDORCZSSAPUHF5GPOLBOD", "length": "6508", "offset": "3706743", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00863.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=59&lvl=publisher_see 20240718195308 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=59", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "L2OTKUTJMPMEXZ466JNMHI6HLUDS5YE5", "length": "11626", "offset": "117780098", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00028.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=590&lvl=categ_see&main= 20240719082251 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=590&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "R7DSRDRRS72HL44Y66OXGH67DFAE5XIJ", "length": "10298", "offset": "112834723", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00418.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=5901&lvl=notice_display&seule=1 20240718201248 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5901&seule=1", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PWSAF3TWDFLQNCJAAMVZEJ4BEZ6TH5TC", "length": "5617", "offset": "114783976", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00802.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5904&lvl=author_see 20240715061955 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5904", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NJRQ4ZZDMNLJ4OMFCEHGVMBJDILN2UCI", "length": "6712", "offset": "5365277", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00644.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=5908&lvl=author_see 20240715052129 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5908", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HQV7QVNJKXSJDZRJGNNWXVQQA3PYUP5U", "length": "6567", "offset": "4619898", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00648.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5921&lvl=notice_display 20240724153702 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5921", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "W7WVANFAPJV7UM54424JMJ7AOLNVMU6P", "length": "4991", "offset": "105801604", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00682.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5929&lvl=notice_display 20240721140315 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=5929", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FTQLXRPR6Q5XO6Z3BXR7PY4L7OJDTK7I", "length": "5019", "offset": "5410878", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00759.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=594&lvl=author_see 20240718210920 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=594", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XVGOTGCMQTQNOUFDISTDWN7WCH2JFOAG", "length": "10391", "offset": "111088405", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00373.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=595&lvl=categ_see 20240724155841 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=595", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "E47UQAEAMPVELXYNRGWFPZA5XHKBEKDF", "length": "11860", "offset": "105959780", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00701.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5955&lvl=author_see 20240715061948 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5955", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QKCWJN3TD4M42D4HHQJG2GS47KQ76HU4", "length": "6581", "offset": "4563210", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00800.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=5979&lvl=author_see 20240725194758 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5979", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FZPMC2SSX6MJVD3NLV3P4GJND7GDB5R7", "length": "6998", "offset": "97354147", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00845.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=598&lvl=categ_see 20240721005315 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=598", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4MKR2Q557RFWE4S3WG5LZ6N2FXN7WVUF", "length": "7639", "offset": "115416969", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00704.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=599&lvl=categ_see 20240712180900 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=599", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EU5CPQMIC3BZJJJ6XYWPMEAFZF4L5IGL", "length": "10879", "offset": "104303430", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00705.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5997&lvl=author_see 20240718142902 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5997", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XKVLOPZEIBCFXMXGLLGM7VRLIQ4BKHJN", "length": "6505", "offset": "5801882", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00026.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=5998&lvl=author_see 20240715052056 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=5998", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6UKCJJZZ7AK6CZF2HD5A2LQENU4BNKAE", "length": "6504", "offset": "4408898", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00027.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6&lvl=categ_see 20240719190252 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=6", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7K6TMKOSG4ABWD7A2WNQDX3EEMKWUCF4", "length": "10984", "offset": "4962335", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00835.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=6&lvl=coll_see 20240718141522 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=6", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZMW46Y7TVCE7NDJPD4XYKVJ3FDVOIO74", "length": "9882", "offset": "3372248", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00569.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6&lvl=indexint_see 20240716152704 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=6", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4NE3O7JMJX5FLHJEHJN6FKWXKP3J65BU", "length": "10473", "offset": "4007356", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00492.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=60&lvl=categ_see 20240716152255 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=60", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MRXLFRONGPNFYDXHYW7CDTFE265JWTVH", "length": "11041", "offset": "120494594", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00346.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=60&lvl=categ_see 20240721005828 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=60", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TMFLF6BEU5NDS7TWEDAAKXS4GPAL3TVY", "length": "10985", "offset": "2961718", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00389.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=60&lvl=categ_see&main= 20240712171307 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=60&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LLBD3SKDEHGILTBEFALDQUWAUYBSB6SM", "length": "11037", "offset": "102521711", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00824.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=60&lvl=indexint_see 20240715053808 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=60", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NO5UJJXICVBKFZCYNALQYSQS6EQBVI3O", "length": "10794", "offset": "4261296", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00364.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=600&lvl=author_see 20240715050005 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=600", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "APDGMJZEW5OL23BIXGHKQYVSDNC7PMCO", "length": "10747", "offset": "5061280", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00638.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=600&lvl=categ_see 20240721014055 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=600", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "D2FI7SXYQ6KEKBHE5WOG77YIYYFW4R3W", "length": "11687", "offset": "101709208", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00478.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=6008&lvl=author_see 20240725201215 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6008", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OMTT3KJDQDM7NIXZOHEYSGYFTJC6BXWS", "length": "7222", "offset": "114159557", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00169.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=601&lvl=coll_see 20240724160550 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=601", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MKVG3LNFZSLBTUVP2YFXGZTQHPTL47FN", "length": "11467", "offset": "4765630", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00658.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6017&lvl=author_see 20240725184535 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6017", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XCDF5IQENOCE32RER4MKJVGNIXFZJZ7F", "length": "7594", "offset": "104853085", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00199.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=603&lvl=notice_display 20240721141213 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=603", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LAGF2OLO477275RU2ZP46Y35JSDBFNMB", "length": "5027", "offset": "3327559", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00341.warc.gz", "charset": "UTF-8", "languages": "fra,ile"}
-fr,missiondefrance,bibliotheque)/index.php?id=6054&lvl=author_see 20240721130104 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6054", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SBFP3IV4OAMFJXB56RNQFAW3RGQR4GOD", "length": "7087", "offset": "114218642", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00320.warc.gz", "charset": "UTF-8", "languages": "fra,ile"}
-fr,missiondefrance,bibliotheque)/index.php?id=6057&lvl=author_see 20240724162111 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6057", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FYOIYCTO5RFEXRFGJMJ7UZTXCFWLLD5B", "length": "8708", "offset": "4276944", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00344.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=6059&lvl=notice_display 20240721011549 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6059", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MPAHGI6CZSWKJOVXZPU6VWWA6TPVECAS", "length": "4974", "offset": "3868716", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00394.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6060&lvl=author_see 20240719100534 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6060", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7H63IDTEAISA24JH4UW73LAMIRWHJS5Z", "length": "6774", "offset": "4104079", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00368.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=6061&lvl=notice_display 20240712163339 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6061", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RTV7GRVY4BQVBNBFANRRB7WNRQY7QHGL", "length": "4996", "offset": "2708376", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00417.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6062&lvl=notice_display 20240721004520 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6062", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BH3RYM4XBAO7BU4RL3Q2JQIVHVNTBQQY", "length": "4989", "offset": "4622632", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00418.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=6065&lvl=author_see 20240725185532 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6065", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5IEL7QZWPOTQ6P23ACXELVQPB7EMQP5V", "length": "7189", "offset": "2776816", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00373.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6066&lvl=author_see 20240715044650 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6066", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XC62ZNTKWER6KGIJ377AW25EWGQGKKZQ", "length": "7087", "offset": "4325073", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00374.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6067&lvl=author_see 20240715043306 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6067", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4S47LSTDSOFL2CKGWOQRRUJXIEMNFXMB", "length": "6771", "offset": "5136070", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00375.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6069&lvl=notice_display 20240718210447 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6069", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZFGLEJZKQT2BVPUSP3WTQVPMNLHB4PTH", "length": "4906", "offset": "4959370", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00425.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=607&lvl=categ_see 20240716153904 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=607", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "APK3LDZNM5UMRGCGRT7OSWZNDYXT7O3J", "length": "10968", "offset": "3144085", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00518.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=607&lvl=categ_see 20240718200708 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=607", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LFNA7VQCCFQSZNRVWR6TICNPRR2CXHJI", "length": "10976", "offset": "116109818", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00485.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=608&lvl=categ_see 20240715051517 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=608", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "L5Q4PWKSWF5O2UBL2RAGKN4VJHMZMKNR", "length": "10723", "offset": "4192569", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00519.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=6098&lvl=author_see 20240715053818 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6098", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TOTGFIURT2KADMY37QNLKYU3M4PTMK6W", "length": "6545", "offset": "3380806", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00469.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=61&lvl=author_see 20240721215830 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=61", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UV4YGACSCHDT5RYBE2Z2ZAZA5ZJ7XIAC", "length": "9915", "offset": "115780996", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00322.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=61&lvl=indexint_see 20240716153935 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=61", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OQQUBHT325KRDVRFAKRX3FIAXIFE52NC", "length": "10547", "offset": "4781265", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00365.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=61&lvl=indexint_see 20240721223024 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=61", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GUYGKU3WK2C4OWBG5SLPHLCUQCITGJPG", "length": "10570", "offset": "113698731", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00344.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=61&lvl=subcoll_see 20240719100719 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=subcoll_see&id=61", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KI2IP5C5KY2NWI2MHCRLVIDFGAHHTONN", "length": "7339", "offset": "121766225", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00759.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=610&l_typdoc=a&lvl=author_see&nbr_lignes=17&page=2 20240721125240 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=610&page=2&nbr_lignes=17&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OXWUKUKUQPINFFRZNSLXXDVHQ5H4PGWP", "length": "7035", "offset": "8188181", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00355.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=610&lvl=coll_see 20240718131404 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=610", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "G7OJQWHM4IOPVLXU7ROSGVF32U2NIGKP", "length": "11753", "offset": "4517045", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00688.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=6105&lvl=author_see 20240718204729 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6105", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7N427TDZD3YLZAFZOEMIBKGNULRBOEKI", "length": "6634", "offset": "108264018", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00227.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=611&lvl=author_see 20240724152710 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=611", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TKXFUIG6LBSIVWJ7ECXYJ2QLFHVJCARD", "length": "8158", "offset": "4933645", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00670.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6115&lvl=notice_display 20240725183436 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6115", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BUBQSCK5FDBVRV7DS7AEQTCNWATECBXI", "length": "4978", "offset": "5256482", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00327.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=612&lvl=author_see 20240722102121 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=612", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "G3BNB4ZU4G5IGV6HDI6TE46ELFTPKI2V", "length": "10399", "offset": "109853221", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00184.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=613&lvl=categ_see&main= 20240721141740 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=613&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "I4H2GHRHE6PDY244EG2WK5WPMAN63TWC", "length": "9024", "offset": "102257206", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00506.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6134&lvl=author_see 20240724160421 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6134", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GYZHAIIDKQLA32HTS6UKTWP5ZYTABUBF", "length": "8314", "offset": "102721625", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00319.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=6134&lvl=notice_display 20240721132300 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6134", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JKPLGHWKQAE7GU3ZJDIBGUK74YF6UFZN", "length": "5001", "offset": "108239707", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00319.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6137&lvl=author_see 20240722104310 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6137", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FYNIHACE3JCIJIP5MUQWLDDS5EDVH26A", "length": "7891", "offset": "103935638", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00322.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=614&lvl=author_see 20240718133935 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=614", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5ZUEW3GDWE2UTCQI7ADSXIGZKTJQN5IU", "length": "10840", "offset": "3752736", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00673.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6150&lvl=author_see 20240718142658 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6150", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NXZ55GTENDC4E6TRC7Y27UG5J47UZEKT", "length": "8721", "offset": "3546619", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00398.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=6154&lvl=notice_display 20240721141851 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6154", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NSVECZ6FQER7HEPKOCB2RCB4GYRDXE56", "length": "4916", "offset": "107530314", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00381.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=616&lvl=author_see 20240716155434 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=616", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "J2Y7XC2BN6KDWRXGGQEMFN7XICYBKU4E", "length": "10010", "offset": "116214134", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00188.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6172&lvl=author_see 20240715045244 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6172", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WYBFNHLM5O6PYROPEX763PXQ6BZGYFAD", "length": "6865", "offset": "112871439", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00441.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=619&lvl=coll_see 20240724160827 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=619", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SU5BS33KK2PS4L3WQBOUXZ4DUSNEKYSY", "length": "7730", "offset": "119843304", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00706.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=62&lvl=indexint_see 20240716152555 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=62", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UODEBXBEZDMHI3EMYUOEEXHJE4B3XVE2", "length": "11501", "offset": "4742825", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00366.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=621&lvl=categ_see 20240721015349 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=621", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "F2FYJN44TXF45MGFV4LSSXIVEK3P66HM", "length": "10864", "offset": "111588899", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00541.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6212&lvl=notice_display 20240725185616 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6212", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5SPJ7RKLS5WIA2SKU6W34CLHS4PAMWKK", "length": "5231", "offset": "4901254", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00385.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=6216&lvl=notice_display 20240712164529 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6216", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RMQYOLUGHAE4ET4X2IQCTTL3BVDHBO2A", "length": "5321", "offset": "2968992", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00389.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=6219&lvl=notice_display 20240719094550 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6219", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DC2LAFR55QE2MFOCEODZM37NNQKXORTR", "length": "5285", "offset": "5305077", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00392.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=6221&lvl=notice_display 20240725194327 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6221", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BYLXMZVFD2RYNM56MHALDWE5J2VU36ZK", "length": "5509", "offset": "111449043", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00346.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=623&lvl=categ_see 20240722095224 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=623", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TEGYH4DEPN7UJISQZ3AK6QL7HIWLENCX", "length": "7511", "offset": "5807652", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00576.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6233&lvl=author_see 20240719095152 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6233", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2J4NKTHRNKAIHY3MJQDIEK3C4WEDS6GF", "length": "6812", "offset": "3700510", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00400.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=6235&lvl=author_see 20240719091124 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6235", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DGNBXRM7V5B72GAX5SR37M3BNNUWVZEE", "length": "6813", "offset": "5129878", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00402.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=624&lvl=notice_display 20240719090340 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=624", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3GTUROIO2JUZAXVNTC4YOLYAKF2GPSRB", "length": "4976", "offset": "4876915", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00404.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=626&lvl=categ_see 20240718212234 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=626", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7KGVJU2DTXBUEUQM5YEQ46BPQLMHEKOB", "length": "7206", "offset": "3276464", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00579.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=626&lvl=notice_display 20240719093803 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=626", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DNICTMUZOCV5WTHQNAGSBSEQVLWUYU2S", "length": "5032", "offset": "2902723", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00406.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6281&lvl=author_see 20240715060912 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6281", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EMRYVINHUNKET2JLREL53PGDC7ZIXNAD", "length": "8424", "offset": "111549563", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00532.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=629&lvl=author_see 20240721010951 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=629", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "IPXPWAYFZ4ZPH5IXCJUJ6PEUZHJJH4FX", "length": "10858", "offset": "105253112", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00222.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=63&lvl=author_see 20240719183551 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=63", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QSGP56GAQCGI62XFMBRNBWVV55OFDTBV", "length": "10592", "offset": "107050879", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00324.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=63&lvl=categ_see 20240716151028 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=63", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ODYI46YVDLF3WSFH6Y3AHNDCQZ7YPLI4", "length": "10788", "offset": "119373318", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00349.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=63&lvl=categ_see 20240716151104 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=63", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LBG6EDT6RDBATV4UWLCP7LIOII6CP4JI", "length": "10748", "offset": "3704160", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00392.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=630&lvl=author_see 20240721220624 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=630", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UOBU77ZSIRQ3GPK23E6TFHQC4KHUUBT3", "length": "10092", "offset": "3359942", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00731.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=630&lvl=author_see 20240722115004 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=630", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HBZG5FJ6NX5O4AJBRLUGRHOUNRQ2BLRX", "length": "10094", "offset": "112756324", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00244.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=6311&lvl=notice_display 20240719091144 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6311", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "B2JK22DWBFSAKHRMMZ5C3L5AGI2A7NVV", "length": "5025", "offset": "106507934", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00376.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=632&l_typdoc=a&lvl=author_see&nbr_lignes=99&page=7 20240718200944 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=632&page=7&nbr_lignes=99&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "IOSELULJ5AYIPOICSH7PY4KWWQNYZCIY", "length": "8826", "offset": "114194002", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00361.warc.gz", "charset": "UTF-8", "languages": "fra,lat,ile"}
-fr,missiondefrance,bibliotheque)/index.php?id=632&lvl=author_see 20240721224903 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=632", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MRWFZYTB4ITUWXW4QQECIH2TF6YY76C7", "length": "10339", "offset": "107594002", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00246.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=6328&lvl=notice_display 20240724151351 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6328", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UDYCLIZYKXFXELR2JKFS5B2QS6OWAYFH", "length": "5130", "offset": "3408514", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00483.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6333&lvl=notice_display 20240716153550 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6333", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SD3FUS47RPJFMIX5XDW3IM27SHTV3PZL", "length": "5021", "offset": "3641956", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00509.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=635&lvl=notice_display 20240721020428 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=635", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KBE4XMXWYT546ZX2Y2UNTIVMOUJO6TZF", "length": "5064", "offset": "117810572", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00297.warc.gz", "charset": "UTF-8", "languages": "fra,deu"}
-fr,missiondefrance,bibliotheque)/index.php?id=637&lvl=notice_display 20240712172728 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=637", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HTDBDGNYGYDZ3IFQUXQ6K3R2KNG5HMR5", "length": "4962", "offset": "99448193", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00299.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=637&lvl=publisher_see 20240715060116 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=637", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PARGZRKI3B4SQVCDA4MKUDUPSJBME7ML", "length": "11218", "offset": "112236195", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00782.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=638&lvl=coll_see 20240722100922 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=638", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "IOMHCPIUFK5KM6RMUKUMI3PDXYIAKHJ5", "length": "6798", "offset": "105516623", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00767.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=6387&lvl=author_see 20240718202010 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6387", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TXFOHXAHUBR4L63SBZ7PRZ4J37EF6KFW", "length": "8682", "offset": "3716677", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00620.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=64&lvl=categ_see 20240716162532 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=64", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "252DC6CKOP5KGC2IMHTEKJZHR7I7LZIL", "length": "10425", "offset": "6223218", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00393.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=64&lvl=categ_see 20240721220723 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=64", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7ZGENKQ4L7WPPJ2KGU5WOSRDXW7R5FT2", "length": "10442", "offset": "109653792", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00350.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=641&lvl=categ_see 20240719180032 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=641", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "46G7SSDHF7SGUL4XRW5QS2RUSLZSUE5G", "length": "10425", "offset": "5541226", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00636.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=642&lvl=author_see 20240721232201 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=642", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5PWXOEDDGQHSKH6LZEPIEDR723ILKM5M", "length": "11533", "offset": "112064778", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00277.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=642&lvl=categ_see 20240718150704 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=642", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DD2MRDM4KMQX2TQBT2PUHJA3G2HXLPNY", "length": "10984", "offset": "118782835", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00604.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6427&lvl=author_see 20240721001553 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6427", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZFHZARKWX6QEOOUC65JXDTRAUUTE675B", "length": "9549", "offset": "122573511", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00474.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=643&lvl=author_see 20240712183313 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=643", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NY3E67VYV7LWEQG2GEB3XCGZRVXGLUPH", "length": "11154", "offset": "4031015", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00765.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=6433&lvl=author_see 20240718143107 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6433", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "H7H35NRB5GIIB6VKMB55K7FHY77GV6ZK", "length": "6682", "offset": "5150482", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00522.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6443&lvl=author_see 20240719095301 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6443", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Y2RYVTQ3YBKO2JAOGU34IYLB4UGGOSCZ", "length": "6569", "offset": "115297166", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00532.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6444&lvl=author_see 20240719083952 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6444", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "K2JIHFC4TCPJJCHA6DV3HHDD4YIN3PK7", "length": "7443", "offset": "108212048", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00533.warc.gz", "charset": "UTF-8", "languages": "fra,deu,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=645&lvl=categ_see 20240725182415 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=645", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "N63XMOUN75ZYJYUAIJJM3PQTSKL4QMOY", "length": "6624", "offset": "2290240", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00640.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=646&lvl=categ_see 20240725181440 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=646", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KB2CSBDBSLOQZUFGZPNVTPBSFMJY5LW7", "length": "10087", "offset": "3100114", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00641.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=647&lvl=categ_see 20240725175733 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=647", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2DKV2TNWFK4EA6N6HQPE3MI5DKDWEOQA", "length": "11262", "offset": "3153832", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00642.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=649&lvl=bulletin_display 20240718203635 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=649", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "25KLTKALPP62NRHLYW75FETQJ3QM2T3I", "length": "6988", "offset": "4007850", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00260.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=6494&lvl=author_see 20240721135530 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6494", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RMTYSZWN6TPPFSKUBPBNHYBPC2BLIA63", "length": "7173", "offset": "107961441", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00688.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=65&lvl=indexint_see 20240721002457 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=65", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CRK4LYONOMXUNB2V2VLBT5423E5ZT6UU", "length": "10893", "offset": "4503698", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00369.warc.gz", "charset": "UTF-8", "languages": "fra,deu"}
-fr,missiondefrance,bibliotheque)/index.php?id=65&lvl=subcoll_see 20240721132437 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=subcoll_see&id=65", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FMDLIPZRCLRELRJYZE2NDHEW73EZTYB3", "length": "8697", "offset": "104789300", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00763.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=650&lvl=author_see 20240721003837 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=650", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PJA2E6TXMD6SICUBUDFAQ3E67CJ7FWFV", "length": "7314", "offset": "117342965", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00306.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=6517&lvl=notice_display 20240712171741 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6517", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6IA4NFHZSQH4HX2O6DYQIICTKZFJGEES", "length": "5017", "offset": "103600651", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00504.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6522&lvl=author_see 20240715054946 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6522", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LO3JA5GLLX6DABWWAOEGS7CKQSNUVYET", "length": "6895", "offset": "116276084", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00530.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=6522&lvl=notice_display 20240718134657 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6522", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WSFPHQCWRZKRH4YEYM5ZBQVHL2KHNSRP", "length": "4962", "offset": "111521355", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00530.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=653&lvl=bulletin_display 20240716150123 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=653", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5BSQGGT4RHHE6QAARE2ZFBUUKWYO6RWG", "length": "7454", "offset": "3331826", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00285.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6536&lvl=notice_display 20240721134221 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6536", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6QC4G654QBME4CVQOXR6CQU4ZVBUZRBT", "length": "5014", "offset": "2918941", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00634.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=654&lvl=bulletin_display 20240715050818 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=654", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZQV2C43BSPQTGM47JZGV2J7ZYQTRWIUV", "length": "6192", "offset": "3979338", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00286.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=656&lvl=author_see 20240724153147 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=656", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GJKJPD6KHNJPHY4FHQ3WJ65C4DBMPNBD", "length": "11380", "offset": "112236896", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00312.warc.gz", "charset": "UTF-8", "languages": "fra,ile"}
-fr,missiondefrance,bibliotheque)/index.php?id=6563&lvl=author_see 20240721004159 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6563", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PFKP35FQ5VJCVYVBVH55GJJ4PQFYCWPK", "length": "6536", "offset": "3746272", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00676.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=6564&lvl=author_see 20240718195020 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6564", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JLUMNZC6GUY23DR3YO3VBFBBMPKIVEWM", "length": "6597", "offset": "5598244", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00677.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=6565&lvl=author_see 20240716144422 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6565", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VCXUTRKKCQHPKVUQSIALV4NZZLP2CXVA", "length": "6551", "offset": "6244772", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00678.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6568&lvl=author_see 20240712182418 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6568", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CDOGXGYNC6LNASBJPIFUPNSGANRB6S7T", "length": "6873", "offset": "3225612", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00681.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=6581&lvl=author_see 20240721132616 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6581", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2PSCIDBCHARQR4TNP4ITEFRPDUL6MIO5", "length": "6961", "offset": "112240285", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00715.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=659&lvl=publisher_see 20240715052646 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=659", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JGGFG3FQNQ6A2TT5RENORYUANLDTH2G6", "length": "10472", "offset": "115727987", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00846.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=66&lvl=publisher_see 20240718212156 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=66", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Z4LREXPG5IVNU5XESABFOOIII4VYUSJJ", "length": "7109", "offset": "5058240", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00119.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=660&lvl=coll_see 20240712172446 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=660", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BNAW4FFSFCUV2BOOXHCLWCRTWKZPXGHV", "length": "10982", "offset": "112165569", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00852.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=6603&lvl=notice_display 20240722111251 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6603", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5AX3GZACZETEIM3C6DIOPCBSAIY4M7ZZ", "length": "5152", "offset": "4574507", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00599.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=6605&lvl=notice_display 20240718213634 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6605", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2YYDJMGPPJMIPO2SBORCSNL4VPV6XK7G", "length": "4985", "offset": "4827088", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00601.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=661&lvl=categ_see 20240715052613 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=661", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SJFH6HVTAABLVTAFVXUBRKCIEQCG3YFW", "length": "8446", "offset": "4741273", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00698.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=661&lvl=coll_see 20240721015921 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=661", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OOW64MRH7O7DOJ6NDWZVUEWXNYKAYGFC", "length": "10360", "offset": "4218820", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00844.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=6614&lvl=notice_display 20240722112503 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6614", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7537BEC6SOABUEMXD4E6XFLQ7C7BD2V5", "length": "5264", "offset": "111696998", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00562.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=6616&lvl=notice_display 20240721221823 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6616", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TBDFVPTGOP7IX7CAKGH4FAF2MZYLKLOR", "length": "5100", "offset": "4940309", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00633.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=6629&lvl=author_see 20240721132056 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6629", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5QGS5AHWGGXAK4WWIW6QINKANXOANT4B", "length": "6538", "offset": "107889055", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00598.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=663&lvl=categ_see 20240718132626 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=663", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JOOWCN4ZCSV5K4TK5LSUXPPNQEVT2H7N", "length": "11055", "offset": "108194652", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00667.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=663&lvl=coll_see 20240712165106 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=663", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LNNXRAAE62UVYCAWODME2QBMI256REB4", "length": "10116", "offset": "101773129", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00855.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=663&lvl=publisher_see 20240715055858 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=663", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DFONSCNR4STCVBQ7ZRRKLZQCSUJ7IP65", "length": "7732", "offset": "4503520", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00296.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=6630&lvl=author_see 20240721140822 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6630", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KF3V73OSXFRBYA6LQKDODRPUDPPKBWEU", "length": "6543", "offset": "118213412", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00620.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6637&lvl=author_see 20240718140057 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6637", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5U53JCWB57BXHPI2SK6R5ZTFV5TUREPZ", "length": "6896", "offset": "112683575", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00627.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=664&lvl=coll_see 20240715055100 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=664", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6Q2HD4A3HEBUFRTDNN7Z6CKRPPNXGRCQ", "length": "10946", "offset": "8406254", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00847.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=665&lvl=categ_see 20240716153305 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=665", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "P2WBPCKSBS4GD4R3QZFVCTECYCOYT2HR", "length": "8108", "offset": "126680471", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00669.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=666&lvl=bulletin_display 20240722105549 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=666", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ACKJTL4OQNQCF5MHHEOEAJYZUO7BZPTR", "length": "6968", "offset": "107640621", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00672.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6672&lvl=notice_display 20240725181906 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6672", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EFVYS5V7VNYF4ISFH4EOID54BYC2DKLP", "length": "5166", "offset": "3462554", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00815.warc.gz", "charset": "UTF-8", "languages": "fra,ile"}
-fr,missiondefrance,bibliotheque)/index.php?id=668&lvl=bulletin_display 20240721133814 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=668", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TJ7AZGMV2VAXEFDICEBBRJJXA3DU2KCM", "length": "6692", "offset": "4881275", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00321.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=668&lvl=coll_see 20240721233242 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=668", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AZIN2GLM7UIJWX7GVBZ6BK2AH3QPHKOQ", "length": "10052", "offset": "109875784", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00860.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=6681&lvl=author_see 20240725195722 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6681", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZHEP5S6VRGL4BBYRVQ2OGS7VBVJHAPG6", "length": "6633", "offset": "110549201", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00776.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=669&lvl=author_see 20240724151531 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=669", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QR2G6HC5OIJCZ55PQ2DQIPATW7XZDEFG", "length": "7747", "offset": "117071042", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00346.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=669&lvl=categ_see 20240722105803 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=669", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7VKG2KET2KIE4FCCKIGFGBPWGAJS7UYU", "length": "6631", "offset": "112730001", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00673.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6693&lvl=notice_display 20240721122125 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6693", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "U3ZMALUQW7QLGWARZNXCT5DVTVFFCYQK", "length": "5001", "offset": "104055956", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00809.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=6696&lvl=notice_display 20240716161125 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6696", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "772NSG3AZH7HKIA7NYUKDNMKUF5RIFLD", "length": "5181", "offset": "125472935", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00812.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=67&l_typdoc=a&lvl=categ_see&main=&nbr_lignes=36&page=2 20240719085344 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=67&page=2&nbr_lignes=36&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "P2VXVAKZRQ22FWAXA5TT67YNKEMTGZFF", "length": "11417", "offset": "111852391", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00596.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=67&lvl=coll_see 20240716152436 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=67", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3QYFFCGEDZ575PQCAJAKNLDKZHKSWZHY", "length": "9462", "offset": "118664315", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00449.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=67&lvl=indexint_see 20240721223654 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=67", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DVQVQEUT4HRHJSWQ45K33EHIE3JUB5AS", "length": "11288", "offset": "109665281", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00350.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=6753&lvl=author_see 20240725185802 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6753", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HGPABLBUAVRC5LSIBN3LV5V47ND62PEZ", "length": "6990", "offset": "101002167", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00746.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=677&lvl=coll_see 20240721010858 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=677", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "W2ROMSB6VRRQLFBF3IYMJBATGRC46PP2", "length": "10765", "offset": "113917326", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00890.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=679&lvl=author_see 20240712181953 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=679", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DJP56AMBQYWV5CYV7FCEFQVF2EBQ37A7", "length": "7456", "offset": "99084946", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00377.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6790&lvl=author_see 20240718195103 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6790", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ICSSQI5RUJDK3BGNALYU27WZMIXFHRDO", "length": "7737", "offset": "4026366", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00888.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6792&lvl=author_see 20240712185618 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6792", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WN2SESA7MMGIC4UEHIFP7MX3PRP5HCEY", "length": "7216", "offset": "5201597", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00890.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=68&lvl=categ_see 20240716163358 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=68", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CSMUORXB32RDVDBXGVZRPYCJRGO6XFDF", "length": "11491", "offset": "120429963", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00354.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=6808&lvl=author_see 20240722103554 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6808", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QWHCZWKSNC4F4OGHSGCIJ7B3G5GFSVOK", "length": "7372", "offset": "3454755", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00678.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=681&l_typdoc=a&lvl=author_see&nbr_lignes=23&page=2 20240721124632 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=681&page=2&nbr_lignes=23&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "V4ILPLPP23YZ7MK3PCRQOC5RBASHM3XA", "length": "9680", "offset": "4469375", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00342.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=6813&lvl=author_see 20240724142245 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6813", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DPKYFZPUUUC2WAEGEWWLA3BSB7PXMVW6", "length": "7333", "offset": "105965246", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00683.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=682&lvl=categ_see 20240718144018 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=682", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OZOWLAS5MAJL7YQQNPMYRPHNLNAVU43Y", "length": "9647", "offset": "107156532", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00728.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=682&lvl=coll_see 20240721010051 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=682", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DIC7P2YB4KSDPQNN57J4BCBRVWWNWJQT", "length": "10207", "offset": "111336360", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00016.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6828&lvl=author_see 20240712174326 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6828", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OHMC22XSLW6BLLNPUHZ7PGUNU5E5CLCS", "length": "6897", "offset": "109956863", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00719.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6829&lvl=author_see 20240719192652 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6829", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "253IC74NOKMDQLD6BACZJOLYCTOXCROZ", "length": "7207", "offset": "113172242", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00720.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=688&lvl=author_see 20240718192520 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=688", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PP7LHRVHCXPLX6MED7YSCTRXPUT7HB3O", "length": "8952", "offset": "114560583", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00407.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=688&lvl=author_see 20240724155308 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=688", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2A6JK52VTAJAPQGKZJKD2VCB5TH2UZCN", "length": "8942", "offset": "3656865", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00894.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6889&lvl=author_see 20240721004308 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6889", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7HU5X5UG6DOG3ZCPRAQLTQ35MU74VSQ2", "length": "6882", "offset": "107802910", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00006.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=6895&lvl=author_see 20240718133437 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6895", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VTQGMEHRMLI767LHLAXAGYUKXN6VVOXZ", "length": "6539", "offset": "108737252", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00033.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=6912&lvl=notice_display 20240722110213 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=6912", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RADVIZKLCJHA5NKHNPLKQAPX5SAFC5JQ", "length": "5098", "offset": "104320251", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00743.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=692&lvl=categ_see&main= 20240722103406 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=692&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JDRNN6T4GG4XQDPSRECTZ524TCLT5IG3", "length": "7470", "offset": "109112943", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00117.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=6922&lvl=author_see 20240721221931 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=6922", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GBCGEX75MZNOXD5RU37XLLAIO7QE5CZE", "length": "9161", "offset": "3560611", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00795.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=694&lvl=notice_display 20240721142004 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=694", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4YXIJFETEWVOWFLRRCA627ENXSMHDCQF", "length": "4911", "offset": "3949880", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00621.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=695&lvl=publisher_see 20240718135142 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=695", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UNDMERSQQBI2TC34NEC2AIPXPEFZVVS6", "length": "7831", "offset": "110392074", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00066.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=696&lvl=categ_see 20240719081627 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=696", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KPHU3K4I3F7YLPFCX3V5DR62M374PB4T", "length": "8811", "offset": "4975957", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00796.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=697&lvl=categ_see 20240718132444 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=697", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CKUW73CSGEC5P2JVEGWHBREMVIB7PLAT", "length": "8123", "offset": "5174067", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00797.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=697&lvl=coll_see 20240715043836 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=697", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WNJ3LHEFJGVTS6477L225EDQNNFFDHAU", "length": "10837", "offset": "3384671", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00043.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=698&lvl=publisher_see 20240722111402 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=698", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FM5KB3OV5JASNLUXTIEN4EQBSKVYEKXS", "length": "6574", "offset": "96776029", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00069.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=699&lvl=bulletin_display 20240718133820 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=699", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MKKI47WV4OZMAT7BE4NMS4OLCYTQITT5", "length": "6162", "offset": "111437473", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00768.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=699&lvl=notice_display 20240719181138 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=699", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MAVWS5JT3U42LZNHUEVDQ6F36FSOIA2Q", "length": "4976", "offset": "115905668", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00487.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=7&l_typdoc=a&lvl=categ_see&main=&nbr_lignes=42&page=3 20240719100707 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=7&page=3&nbr_lignes=42&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HH7YOJSHBENKVSQPW735SQFT5Y6V742Y", "length": "11374", "offset": "110187827", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00498.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=7&lvl=notice_display&seule=1 20240725191524 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7&seule=1", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EWLZJBX5ZJ2BNAMOEFAL4P2T4RWMGTEV", "length": "5502", "offset": "104740060", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00890.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=70&l_typdoc=a&lvl=coll_see&nbr_lignes=19&page=2 20240722100217 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=70&page=2&nbr_lignes=19&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UC7HEES3X7DSFSP2OBX4VWEE5CSMZPHJ", "length": "7653", "offset": "106531502", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00577.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=70&lvl=categ_see 20240724142357 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=70", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PHIU7BIM2DX7SYS65JX7PZBZ4LRZMDU4", "length": "13096", "offset": "118342763", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00377.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=7001&lvl=author_see 20240718135353 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7001", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HS5QCHRXAS6HJUMQAJCGPUO4F7XBWNJF", "length": "8740", "offset": "107433793", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00253.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=7015&lvl=notice_display 20240721001841 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7015", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "25544SOQX7KNWZOGEYTIKLY6GBWFWVQT", "length": "4975", "offset": "110470292", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00288.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=7019&lvl=author_see 20240712173100 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7019", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YVI3HF5EWUOM35V5TVMSQZYBWSP23KMG", "length": "10244", "offset": "4927239", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00313.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=7029&lvl=author_see 20240716154623 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7029", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "W5JBATUZMGPQXJCOBOYTX3RMNIMV2EXL", "length": "6544", "offset": "3818601", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00344.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=706&lvl=categ_see 20240721013010 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=706", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AETWSRDW6GUYCQTEJIFDXDUQKG4ZABMW", "length": "6873", "offset": "119166982", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00545.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=706&lvl=coll_see 20240715044610 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=706", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5YUBPHWE4NGOVVN42L45WAB5VFFXNBDQ", "length": "9824", "offset": "3514331", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00724.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ile"}
-fr,missiondefrance,bibliotheque)/index.php?id=707&lvl=categ_see 20240721223344 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=707", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YYPMWY3HGFYCIU7FZVKWTLE5T47MM4F3", "length": "11528", "offset": "5819722", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00579.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=7077&lvl=author_see 20240722111230 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7077", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XMFHHZLEOKRK56C7NI6Z6GXR4QDBUUOM", "length": "6729", "offset": "106376358", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00476.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=7078&lvl=author_see 20240722101003 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7078", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2DQ5UKRGEKCC7BA4QDEMQG4DWDPGDMDP", "length": "6726", "offset": "110363714", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00477.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=708&lvl=notice_display 20240721001338 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=708", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CS5UGU32WBWGMDZ5IGXX7OBTX3P2WIUY", "length": "4937", "offset": "105446866", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00268.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=7096&lvl=author_see 20240712183509 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7096", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XMVIPUFCSFWMYGBKNIWWDSGNWGV55QX4", "length": "11023", "offset": "105269171", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00537.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=71&l_typdoc=a&lvl=indexint_see&main=&nbr_lignes=41&page=1 20240721124514 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=71&page=1&nbr_lignes=41&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HLBCDSXXPOR5PE5ELHQRNCH42NOZSKHT", "length": "11566", "offset": "100451897", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00341.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=71&l_typdoc=a&lvl=indexint_see&main=&nbr_lignes=41&page=2 20240721124835 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=71&page=2&nbr_lignes=41&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FI27N25QTOKUF5PBP4DCTWIOZOR4SU6H", "length": "11292", "offset": "105851728", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00548.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=711&lvl=bulletin_display 20240718135427 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=711", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HVHYE7KWJ4ZYVMW4JSHTOS3BYFJKIDX5", "length": "7259", "offset": "114566329", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00573.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=711&lvl=bulletin_display 20240721141928 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=711", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QDEHZ24X7YPSCD22J2HPR2WK7JYL2JVI", "length": "7239", "offset": "3916401", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00220.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=712&lvl=categ_see 20240722114310 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=712", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TNST2S4KKXBFVXD4HEPJMXN4755HKPLV", "length": "7475", "offset": "106449825", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00572.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ita"}
-fr,missiondefrance,bibliotheque)/index.php?id=7129&lvl=notice_display 20240718202253 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7129", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "75INNDG5HVAXZCVXZWFCB3HIZRDXEVUN", "length": "4965", "offset": "117723689", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00384.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=714&lvl=author_see 20240721232912 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=714", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YVEQNEMEXQ64K6FXLUJBPMCPBC5BZNAS", "length": "10195", "offset": "107137141", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00247.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=715&lvl=coll_see 20240715060645 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=715", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EUG6MHDASA7LA6Q7SWQF5YU6ASTF6SCD", "length": "6660", "offset": "103394762", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00763.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=7152&lvl=author_see 20240721131253 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7152", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "U2TPTPBH5TR34YX57ARTMCWQVW6LRA7Z", "length": "7482", "offset": "119618225", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00470.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ile"}
-fr,missiondefrance,bibliotheque)/index.php?id=7160&lvl=notice_display 20240719100452 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7160", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PFAGEWXJZJMMK4MVRCKODEWQHNPYUFTE", "length": "5026", "offset": "112822103", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00499.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=7161&lvl=notice_display 20240721215913 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7161", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "O4FOZX3USNRHLAONKXO2HRLAHIRBSQGX", "length": "4938", "offset": "117093262", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00500.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=717&lvl=author_see 20240722110947 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=717", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2PQWVC2HEY4LTIFHPL7VITUSECKECC7G", "length": "7033", "offset": "106713717", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00250.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=717&lvl=coll_see 20240724155557 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=717", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GYWUOZ6XDCXR6ANPKWIKDAV7PYX6EXSS", "length": "8796", "offset": "3504202", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00756.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=7178&lvl=notice_display 20240721220158 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7178", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TNME7TA2JKCL67HX2MEZ72X4BQLXR7IS", "length": "4922", "offset": "109421640", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00538.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=7181&lvl=notice_display 20240716153730 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7181", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YHTNF2BH5ATFXGUSYNI4MWLLCPABFWRQ", "length": "4952", "offset": "118711677", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00562.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=7182&lvl=notice_display 20240719095411 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7182", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "77AJVZJTMTJTRDXIHOLLMXQUTX3Y7Z4O", "length": "4882", "offset": "4034145", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00632.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=7183&lvl=notice_display 20240719075211 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7183", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NNKEOLQIGBTMHVOU6MOLVDIP74JVRI4S", "length": "5288", "offset": "4495984", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00633.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=719&lvl=author_see 20240724150038 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=719", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BSMCLRTPZD4DOO6NIZH6FSAZ344ZK6RS", "length": "9022", "offset": "106768451", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00252.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=72&lvl=indexint_see 20240724155028 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=72", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2U5BROBNNQIOEKDVF2PO637NJQMXD2HB", "length": "10128", "offset": "5489429", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00397.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=7220&lvl=notice_display 20240725191938 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7220", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BVDPZ234YL2KMFO7QHUCKRTTCSUXSCYQ", "length": "5128", "offset": "2553987", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00505.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=7221&lvl=notice_display 20240725195335 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7221", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "IUDOMWJ7JBON3OD3EY7RJXXI3AVMRCVI", "length": "5108", "offset": "3671541", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00506.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=7283&lvl=notice_display 20240719190335 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7283", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YBMCMUJA243QUSCXGINTVDU447HQGSU4", "length": "4956", "offset": "3730797", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00694.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=7284&lvl=author_see 20240719084642 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7284", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HALNAVM2OFXS3CUHXPCKHHZNPMBMXHXM", "length": "7185", "offset": "103875384", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00626.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=73&lvl=author_see 20240718141418 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=73", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "U55NJBQLCV7WUGP7SFK5G7YM7RDKMPNF", "length": "10738", "offset": "116369138", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00355.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=73&lvl=coll_see 20240712183939 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=73", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YUGIYZWTGHXIWTXMOXXPBUL2BZ573X32", "length": "10947", "offset": "103416567", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00476.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=73&lvl=publisher_see 20240712165201 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=73", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BY5UB4HHCXJ5CFIO7COAG4P2YMPZSD5S", "length": "11659", "offset": "3846524", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00147.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=7303&lvl=author_see 20240721234102 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7303", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CFNQX5LULCQBKTEJKW5KK3GF5AMXPNQF", "length": "7379", "offset": "116605722", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00438.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=734&lvl=author_see 20240724150237 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=734", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PO3DDTWXWDJPSHDMJIQMV26V5CXNORA3", "length": "6691", "offset": "110259335", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00309.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=7342&lvl=author_see 20240716143521 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7342", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5SLD2U5OONJGSVSV3HJMIFHDBSTHTEPS", "length": "6811", "offset": "125433420", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00561.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=736&lvl=categ_see 20240721010548 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=736", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MLUF5VMCMESNCJ4DZRLGQSPP5EP6ZPJ7", "length": "6828", "offset": "119907507", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00638.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=7376&lvl=notice_display 20240721141135 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7376", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "J244ME2RQ3HXLAVCD4NPPJ5JJTJNUHUQ", "length": "5147", "offset": "109701770", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00658.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=7389&lvl=notice_display 20240722115153 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7389", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "G4WBOQEBJHU6RWJQDGONQHJEJSXUAESO", "length": "5176", "offset": "104682590", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00692.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=7392&lvl=author_see 20240716161204 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7392", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OAVGBHA2E7UOICHYP3BFZEHKMEGVVNGG", "length": "7421", "offset": "3724401", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00737.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=74&lvl=indexint_see 20240716161620 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=74", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GNMDSVPGDXEHAJROLU4TRT62VLHPIHNS", "length": "10439", "offset": "113996310", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00378.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=74&lvl=indexint_see 20240718202646 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=74", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GTGVYPVCJCHXXSBWKNTGHK6AZDTO7QR3", "length": "10398", "offset": "3570334", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00399.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=74&lvl=publisher_see 20240716155514 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=74", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "IDXTE7A2ZIEKQT725NX2NDW4P2KBI5GW", "length": "11025", "offset": "5329789", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00148.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=74&lvl=publisher_see 20240718200829 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=74", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BXHBVSM5EJRZH5Y7ZJBHAYIKSY4HW2DB", "length": "11027", "offset": "102926260", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00085.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=7417&lvl=author_see 20240718133117 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7417", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PLILXGT36EHMXJ5KSVY26I5FC7QA3WXL", "length": "6559", "offset": "114517963", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00534.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=742&lvl=categ_see 20240716145830 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=742", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "65HCKKKMLKRAA4OTBNP6Y5ZH4UVKDC3C", "length": "11594", "offset": "3518355", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00698.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=742&lvl=categ_see 20240721133038 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=742", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KUFZXPOGWQO7RWER5STUBK3V2VZSOK2D", "length": "11598", "offset": "99966506", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00665.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=7458&lvl=notice_display 20240719081156 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7458", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MV5QS54WDBNINOGFG7O5NZ7GGKV3TH7P", "length": "4972", "offset": "111983218", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00659.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=746&lvl=coll_see 20240718205847 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=746", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ACS4AS62SXZI6PHCUDNT5ML6HME2BW47", "length": "7052", "offset": "4770742", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00848.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=747&lvl=author_see 20240712165255 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=747", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "J52CAHGQPVWSPOWDN3HQIN5ZDMMOSNNS", "length": "10776", "offset": "107424482", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00343.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=749&lvl=coll_see 20240724151749 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=749", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FDRIZD626F6MPTLVDYPVFRRY3EERAHOV", "length": "6583", "offset": "109515131", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00860.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=75&lvl=indexint_see 20240712171554 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=75", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JIWV5GYXWDUHN2TAQSFBOVHVISXYZVSV", "length": "10638", "offset": "105243304", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00379.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=75&lvl=publisher_see 20240712163046 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=75", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZSWK2A6Y6GQJU4XANBY7JOHLY2SWLZEE", "length": "10534", "offset": "100492536", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00086.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=7503&lvl=notice_display 20240719100204 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7503", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Z33YUE4D4NI2I7CQH2XE2W2R3VCL754G", "length": "5253", "offset": "100367278", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00560.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=7510&lvl=author_see 20240721140004 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7510", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "67QZUE6GWMP4GDNKLAOZG5BPLWG2TVTZ", "length": "9401", "offset": "103754535", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00588.warc.gz", "charset": "UTF-8", "languages": "fra,ile"}
-fr,missiondefrance,bibliotheque)/index.php?id=7516&lvl=author_see 20240712183751 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7516", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "R4EXJAHGPB2C2IXWRKEYP3DJUVWOZKU5", "length": "6841", "offset": "104996738", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00594.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=754&lvl=author_see 20240716160548 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=754", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EFZC3TRHT4TQKOJ6NVT6ZPGEUXIULUZC", "length": "10383", "offset": "113263747", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00371.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=7550&lvl=notice_display 20240721002224 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7550", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "O2VHDYOYR6S34ELYXU6GPCXMMEFXS2VY", "length": "5007", "offset": "114811429", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00712.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=7562&lvl=author_see 20240715041534 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7562", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MKHRS6GLGIY2UU3ZSZYDZBMP45FH3S5V", "length": "6489", "offset": "4066783", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00766.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=7563&lvl=notice_display 20240719100526 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7563", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Y4F75V4GZKUZVCFZD4BXRHTCQCNVRHIZ", "length": "5039", "offset": "5301476", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00815.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=7577&lvl=author_see 20240718205753 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7577", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UI3VOG5HOH4GXSPWBTNKINGSODKBRAZP", "length": "7844", "offset": "120042372", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00781.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=76&l_typdoc=a&lvl=publisher_see&nbr_lignes=20&page=2 20240721015116 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=76&page=2&nbr_lignes=20&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "B4EA3BRGKLI2JDCCP2ZYPFESX3SEXM2M", "length": "8633", "offset": "3558169", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00756.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=76&lvl=categ_see 20240721020326 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=76", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "C2GBMR4MAFQV4AB7SZRFPN522QYXB2FV", "length": "11469", "offset": "3679991", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00426.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=76&lvl=coll_see 20240721012632 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=76", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5XHBW5OJA6BI4XFMSLFCBUDIU6LTZTEZ", "length": "11119", "offset": "112074561", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00479.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=76&lvl=subcoll_see 20240712181422 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=subcoll_see&id=76", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NNHLCJOKMHFHTG3OGJOPLXV7FBR764MS", "length": "6884", "offset": "99360703", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00795.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=761&lvl=categ_see 20240719085309 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=761", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ONGUGZXO4TLBOFGUN6WOQP4F5PXK4XGU", "length": "10041", "offset": "4049741", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00759.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=7619&lvl=author_see 20240721224925 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7619", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OLDIIDGIP4ORJNI5EGECDMFT4PBAANX4", "length": "9790", "offset": "112950437", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00658.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=7619&lvl=author_see 20240724142956 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7619", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RLR6RI4LWLJEEITZ4STY2TBRPGIEKKU4", "length": "9785", "offset": "4428257", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00679.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=7631&lvl=author_see 20240722104236 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7631", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VBIVRA72XVH5XEPM4I7XVTHJHNJAWLEQ", "length": "6681", "offset": "112519627", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00712.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=764&lvl=coll_see 20240716163447 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=764", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "V45KG5CSTUUM76IK6TX3ECBY63TXCXGF", "length": "11742", "offset": "122683641", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00017.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=7652&lvl=notice_display 20240721134821 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7652", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "G7KL7GANZUZB5NCUWHK7ODDDUACQ6SIP", "length": "5117", "offset": "116058073", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00775.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=7658&lvl=author_see 20240721123033 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7658", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QRXPA6DYK4UO3CGFGI5F2LMQLWY4MDNN", "length": "6575", "offset": "6785537", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00802.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=766&lvl=bulletin_display 20240715052920 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=766", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SJ6TRSWHNO5TFWHGRBEN665SEMBT6IMM", "length": "6733", "offset": "111455426", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00733.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=7679&lvl=author_see 20240718201747 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7679", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TYVZB7WKALIWFPY4CEZNUDLKNHCM2CAZ", "length": "8872", "offset": "3862834", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00865.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=769&lvl=author_see 20240719091936 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=769", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WWALEVPPI4CTTSEULMQ7TCF7TA36JUQ5", "length": "8868", "offset": "6005615", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00894.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=77&lvl=categ_see 20240721224819 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=77", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "34XAKTSDZWO2EI2J2H5W27FSS2SAPZ44", "length": "11716", "offset": "4335418", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00427.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=77&lvl=indexint_see 20240718132923 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=77", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FPDSPFVZXZVORWW5YQHQT6PT4WIXWCDX", "length": "10433", "offset": "4271895", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00402.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=7708&lvl=author_see 20240724150931 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7708", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6URMY6MRAPTMJRU3KTAOM4GBXQOPQ5SV", "length": "9933", "offset": "109879896", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00687.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=7708&lvl=notice_display 20240718201402 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7708", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "M67ALCRDS4XBBJXCA26LCMGGA5HE6EEI", "length": "4898", "offset": "108271847", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00687.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=7726&lvl=notice_display 20240721012002 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7726", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "L2KM4QJ6ICYDEZTXXABIJEHGAZVYD5XE", "length": "4931", "offset": "6513013", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00816.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=775&lvl=coll_see 20240712181051 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=775", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6KB3P64ERKJR44R63HSNYE43WFXZD2PM", "length": "7199", "offset": "3002160", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00040.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=776&lvl=author_see 20240718213213 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=776", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "L4TK7PIUHZOSTYL7C373QBZQF7JTPMMM", "length": "11579", "offset": "4220337", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00022.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=776&lvl=coll_see 20240718134733 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=776", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NSZRHLDWTZDMWVAGLJ45ZYRGYKDMZBU6", "length": "10805", "offset": "4825014", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00041.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=776&lvl=publisher_see 20240721010615 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=776", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SELSDI6H3VRNDC3SVWE6XZBNBYRIQ7IN", "length": "6567", "offset": "2954910", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00391.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=7788&lvl=notice_display 20240719092757 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7788", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NIKB6SQB3NQ4ER6PSREHDHFXDMSW7GZ5", "length": "5090", "offset": "5163582", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00104.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=7792&lvl=author_see 20240725185451 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7792", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZZ2MDH5BHQMTO5HSAUE77ABQQ2ZMZTXB", "length": "8343", "offset": "107892802", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00060.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=7820&lvl=author_see 20240715045512 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7820", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2SJJLG442RITPAMNLSHFBQCAHFBLK7BA", "length": "7538", "offset": "111468418", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00802.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=783&lvl=bulletin_display 20240718132841 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=783", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "67C3QWJTKOVGYLVSLQ3YXIQJULYJVDDG", "length": "6100", "offset": "107212204", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00792.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=7833&lvl=notice_display 20240721020035 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7833", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZOQ5Z6334WKJIQY3GV33PG4TU7RQD3QM", "length": "5326", "offset": "4311925", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00005.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=785&lvl=bulletin_display 20240718133004 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=785", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GRU6TNS7HJABR6YEGH7IZQTCZA6YVTTG", "length": "6658", "offset": "109123635", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00794.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=79&lvl=publisher_see 20240722103328 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=79", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YBSMB4MY3CQRXUVKAUGSDMXQF4RYAMSS", "length": "10801", "offset": "106392397", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00090.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=790&l_typdoc=a&lvl=coll_see&nbr_lignes=18&page=2 20240722105729 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=790&page=2&nbr_lignes=18&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6WTINDOBVAGOJHQ6WOWYPW56H3Y4S66L", "length": "7781", "offset": "4794797", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00090.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=791&lvl=bulletin_display 20240718135831 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=791", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HZEM3REFVS4JI57RO53YGWSDZYZDVN4O", "length": "6378", "offset": "111511780", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00821.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=792&lvl=coll_see 20240718213534 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=792", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZOJFE4MYF7ABA6MV73CWVZRYDMNCF5TT", "length": "7731", "offset": "114482270", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00108.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=7923&lvl=author_see 20240724143623 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7923", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LUHMUPB5NE6BKDMXW2QQIQM4UGW7LXZK", "length": "7674", "offset": "106975746", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00866.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=7929&lvl=notice_display 20240715044526 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=7929", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CKPY7M2RXEWTC7HCZECSPR4TL3LYWN5K", "length": "5108", "offset": "118440406", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00872.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=794&lvl=bulletin_display 20240715050046 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=794", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JSCYTSPWN5Y4BYUWXLAW4DKS3NNRVKPA", "length": "6558", "offset": "106699362", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00824.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=794&lvl=categ_see 20240715054907 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=794", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SU6RLX4YGXJNIKYMQQL5SCHUD62OJOC4", "length": "6986", "offset": "126624560", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00822.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=7941&lvl=author_see 20240716162027 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7941", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CWMPITZ4HAGGZ2GWSB6RWQ6HK5ALANQC", "length": "6718", "offset": "112678118", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00026.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=795&lvl=coll_see 20240715045816 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=795", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XQ5DVTSBXBGCOJETQVI6R7R2OJJ2LMFU", "length": "9247", "offset": "2889231", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00102.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=7977&lvl=author_see 20240718141732 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7977", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XOGTHS62OJ77YD3CDNJE24XMJKYNOD72", "length": "6976", "offset": "111462607", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00125.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=7984&lvl=author_see 20240718150034 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=7984", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MQCDDNXEO6IK4M4ORZTCOEUV4F2MEVBR", "length": "6538", "offset": "116683020", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00153.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=8&lvl=bulletin_display 20240719093657 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=8", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CARLBTUYV6P3OXJS4I5XST7LN7VMVSVN", "length": "5319", "offset": "5589575", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00365.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=8&lvl=coll_see 20240724150729 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=8", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GGNL7BLPOAYYUFWB2KLLVMN5OI5BHMVS", "length": "10608", "offset": "3514633", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00571.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=8&lvl=publisher_see 20240718212311 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=8", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XUQHGAVEWY4LGFSQQY7PYVRED52LX6FC", "length": "12126", "offset": "3672326", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00233.warc.gz", "charset": "UTF-8", "languages": "fra,deu"}
-fr,missiondefrance,bibliotheque)/index.php?id=80&lvl=coll_see 20240718145632 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=80", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ICKALXR4V7BXH3WMH7B7QREILRKHPYLT", "length": "7449", "offset": "108873408", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00504.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=8012&lvl=author_see 20240724153845 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8012", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WOF5O6MBIOSI6ECHPH2FS6T5NX5UU56B", "length": "6788", "offset": "107296147", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00376.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=8032&lvl=author_see 20240718140134 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8032", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "G7VLG5735YNRITGTKHSJ4IVB3TVQB5JN", "length": "7632", "offset": "117658818", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00438.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=8046&lvl=author_see 20240722104952 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8046", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GYGW3LN5CSJUGZYGAPG2MDMJ4WZOPBPY", "length": "6493", "offset": "113472070", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00473.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=805&lvl=bulletin_display 20240722103906 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=805", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LZ7S37DNKC3NTEGYYCKFFB27YTR2W2UR", "length": "7228", "offset": "103234013", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00607.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=8056&lvl=author_see 20240722103442 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8056", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Q6B2FCYYOX7JDF23H7T3NO56IXIGRISZ", "length": "7757", "offset": "102397436", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00504.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=807&lvl=coll_see 20240718213826 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=807", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "N2AOORTH35RWLCFX52SYWQYAFI2UULKE", "length": "10448", "offset": "105907457", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00795.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=8073&lvl=notice_display 20240725193808 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8073", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SECPH5LPY63I5PCQGXNLQ2QQ2PLKOQWL", "length": "5016", "offset": "5534966", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00632.warc.gz", "charset": "UTF-8", "languages": "fra,ile"}
-fr,missiondefrance,bibliotheque)/index.php?id=8083&lvl=notice_display 20240719094240 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8083", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GWOEJ3VYXZO4N3WNMGPLQJPBHTCKYPYN", "length": "4961", "offset": "4268462", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00663.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=8089&lvl=notice_display 20240719100611 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8089", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6DBEAZI2SISAYNRV4PSXAPPY35YXAIUP", "length": "5055", "offset": "4122466", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00669.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=81&lvl=categ_see 20240718204521 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=81", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WJ6MPZ2ZUGFK5EEACG3OUKIRC4R3D3BH", "length": "11716", "offset": "114145645", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00409.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=8139&lvl=author_see 20240718202107 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8139", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "V424YUVR7U3RXPY4HMBMQWRRBQKVOI6S", "length": "6707", "offset": "6028824", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00527.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=8157&lvl=author_see 20240716163304 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8157", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ARFVGLYHP33KUJTVGMVIIB2K3EZ7ZCJK", "length": "6891", "offset": "114763011", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00566.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=816&lvl=author_see 20240718204301 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=816", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6F7MLN5VLWJG6RGPTWS56DX4ZEFQPBZD", "length": "11246", "offset": "111796778", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00310.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=8184&lvl=notice_display 20240725182105 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8184", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "P7ESMSA2JNLAPOVMO44YM4MFQZFRFA6F", "length": "5056", "offset": "112021156", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00656.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=8199&lvl=notice_display 20240725192611 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8199", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SZPSGZCAOKLLZGOXUCMIV2ABECZAXOZB", "length": "4830", "offset": "109065658", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00692.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=82&lvl=publisher_see 20240718135215 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=82", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JRCQQEIB5CZSG6GF4OSETFF75FRH2MFK", "length": "9421", "offset": "114278197", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00114.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=8200&lvl=notice_display 20240725192004 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8200", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "25AWPKPIS37MGQ3DXZ6D4KKZWVR6MWOJ", "length": "4828", "offset": "107742862", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00465.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=8202&lvl=notice_display 20240725181722 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8202", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PEVGJHQHZKWVAATWBS44K66GF2WGSOVW", "length": "4841", "offset": "104805125", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00467.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=8208&lvl=author_see 20240721003728 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8208", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "U3N4CK6KSZOOZJTSRRDF54XVAEMPEMDR", "length": "6468", "offset": "110163329", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00473.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=822&lvl=notice_display 20240725200315 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=822", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2SHKCQC3HZYZVZNEW4H3IR6SFAQ5BEXG", "length": "4932", "offset": "102770939", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00385.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=8221&lvl=author_see 20240724141818 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8221", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FDFXORFVOGPB4CPPCE5JV3CXN7F2DXRL", "length": "6576", "offset": "4437374", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00549.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=8231&lvl=author_see 20240716150913 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8231", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VFQKZ46CEW5N64TLUYURUNHZ4Q7VVECJ", "length": "6833", "offset": "3249198", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00580.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=824&lvl=author_see 20240721000612 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=824", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YEWQI3NLK5KM2SAD666N5BOBW5YYAZ5Z", "length": "11557", "offset": "109802217", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00339.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ile"}
-fr,missiondefrance,bibliotheque)/index.php?id=826&lvl=coll_see 20240721125650 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=826", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZWQIUHENGW3THRAPAAD5N3DNIN7BHBZ7", "length": "6595", "offset": "112195933", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00856.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=8267&lvl=notice_display 20240716154139 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8267", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VS6IV4RE4ZNYI52EI4PPE4PQ3XRUXVFB", "length": "5115", "offset": "115281848", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00658.warc.gz", "charset": "UTF-8", "languages": "fra,lat,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=827&lvl=author_see 20240716155356 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=827", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FGD2PXIRKWS3L2OY6JAFSUMYLFI35FRO", "length": "11201", "offset": "122518211", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00342.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=827&lvl=notice_display 20240719095844 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=827", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YBNK6PR5JZJXJMZN4AFN2HONWYWTKXOB", "length": "5012", "offset": "105373984", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00390.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=828&lvl=coll_see 20240721124436 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=828", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7QL2CUC4CIOYLU7OGFUZ2IGSAVJUPYSN", "length": "7221", "offset": "114468550", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00858.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=829&lvl=bulletin_display 20240721231714 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=829", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PFZ6T5XEQXRXP6GDZEAZ6I76F2G627N2", "length": "7469", "offset": "114642608", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00673.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=831&lvl=coll_see 20240721220449 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=831", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YXKH5OWKXSAJXSTKTUAFMW26563F7PZV", "length": "7373", "offset": "103381907", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00882.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=832&lvl=notice_display 20240721020113 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=832", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "I25Z6R2F6AJVFKJ54GTO74WYP7FI52CE", "length": "5015", "offset": "115129062", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00416.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=8327&lvl=notice_display 20240725184348 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8327", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "F2FFFFR5E7EE3NXMZAPWA62X72OV7MC4", "length": "5260", "offset": "5485782", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00664.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=833&lvl=bulletin_display 20240718131731 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=833", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UNOAAPHS6ZJH5D6EBCE5GPRTF5DM5EIJ", "length": "7359", "offset": "108717423", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00698.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=8341&lvl=notice_display 20240725184236 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8341", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6L4QNZKBZNBZN6KDSEOEB3OWZRDDRZFT", "length": "4881", "offset": "4146496", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00720.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=8348&lvl=author_see 20240712161634 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8348", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PVJ2EGGRTLUZ2NAJ42HL3XR6HNAIG2BE", "length": "6509", "offset": "107417032", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00658.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=835&lvl=coll_see 20240724153653 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=835", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SCAXNE3HKQTYYXNDSMPRRIV7JCXCTH4W", "length": "7202", "offset": "2796043", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00877.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=8355&lvl=notice_display 20240725183105 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8355", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WAYCP62BAON2QTIJ5DZPDL33UCNMON45", "length": "4936", "offset": "5283394", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00755.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=839&lvl=author_see 20240715053828 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=839", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DMPHJNHVWGIRI4CNCHIGHGCNTDFEYYYM", "length": "9264", "offset": "112727625", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00375.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=8393&lvl=notice_display 20240725184312 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8393", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "COS5MPEILDNRUAAV3QPDBOXSEOJIXFT6", "length": "4954", "offset": "111600115", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00808.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=8398&lvl=notice_display 20240725191814 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8398", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4RX7SAR7JMSGVU3ZPCXL35BMU7SRYIAR", "length": "5159", "offset": "114667343", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00813.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=84&l_typdoc=a&lvl=publisher_see&nbr_lignes=57&page=4 20240719191201 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=84&page=4&nbr_lignes=57&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WKOCT6FCI26IWMHLIT6O6M4S4I6OU2N5", "length": "11764", "offset": "110716675", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00600.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=8408&lvl=notice_display 20240725200429 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8408", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CN3EKDPZSKI5CTU3UVR5JFGFKPMFYSG3", "length": "5217", "offset": "105664843", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00595.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=8419&lvl=notice_display 20240721130029 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8419", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "36XQGZTJ3VTZET2CHREM3SXCVJAJFCPQ", "length": "4975", "offset": "112964769", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00627.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=842&lvl=bulletin_display 20240724145654 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=842", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JP3EN6DJLRLRLDXU3TGFR2Q7YXWFKSRX", "length": "7996", "offset": "110693700", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00728.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=8421&lvl=notice_display 20240721131145 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8421", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3SAETIL7NV4GMDWHP4NVOL5FWKNG7EJ3", "length": "4988", "offset": "104539394", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00650.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=843&lvl=bulletin_display 20240724145730 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=843", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MKTE3V2OGBYYMTSDJHNXYIOXFTF2A2DB", "length": "6756", "offset": "103587241", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00729.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=843&lvl=notice_display 20240719083116 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=843", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7VLECSXO2WKOU2Y5T2H2PKFFWD6ABBLL", "length": "4967", "offset": "115112430", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00448.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=8434&lvl=notice_display 20240721131006 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8434", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OJ2T5VVKGZRPSHBJG67NJWHNUOIBIEI7", "length": "5040", "offset": "108712565", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00684.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=8435&lvl=notice_display 20240721133841 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8435", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Z6RZPH4P4WX3TCTUGIHECRNU7SCEONRM", "length": "5188", "offset": "113293606", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00685.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=846&lvl=author_see 20240718195824 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=846", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GEZBDP37KDTUMOTAUGGJMFJXL54N3YUK", "length": "10729", "offset": "109782432", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00403.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=8467&lvl=author_see 20240724152209 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8467", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HSOUSLME3FDTECXF6HKVJH54YYXU7MK4", "length": "6459", "offset": "99378552", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00780.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=847&lvl=bulletin_display 20240721222036 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=847", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VLTP3W64N5TQHLLSOMPUD2GA6OJOJ3RD", "length": "8491", "offset": "115991949", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00733.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=847&lvl=notice_display 20240724142754 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=847", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7TKFU4EGOW45L4XSATD2JIIBXRQK446L", "length": "4969", "offset": "106948201", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00452.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=850&lvl=notice_display 20240719094040 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=850", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZTCW5DF7A23Y3ZOA63CAGDP4TJ55O4FH", "length": "5148", "offset": "109781492", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00476.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=852&lvl=coll_see 20240722105112 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=852", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RSZ7SE3RQDPVSGDCJYGEL5CWUF2XZGBC", "length": "6786", "offset": "104771728", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00045.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=8537&lvl=author_see 20240715050317 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8537", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6PAIDTFXLG7JRMSYZRQQFPUXYS6JHXPW", "length": "6490", "offset": "4127776", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00769.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=854&lvl=coll_see 20240724145005 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=854", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TGM5I6FMRIY5QOKNOLM6XLPHSBA5YKPK", "length": "8913", "offset": "105952666", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00047.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=856&lvl=bulletin_display 20240715052025 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=856", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "N2HLIOC7MLRCKYZ723GVYH2YNHE5BRZQ", "length": "6980", "offset": "103386793", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00763.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=8568&lvl=notice_display 20240725182802 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8568", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TGG7VRNIMYRTUBRA5K424H4NKN3VPQ45", "length": "5167", "offset": "106878944", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00842.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=8569&lvl=notice_display 20240724153857 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8569", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "S3QZH3C7PR75LRTSRSK4ASGKVLQVXLS7", "length": "5171", "offset": "3972145", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00012.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=8572&lvl=notice_display 20240718211717 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8572", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7GBSETNRKZL3KX2PQB5XWYTVDAND76IB", "length": "5340", "offset": "105766897", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00867.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=8576&lvl=author_see 20240724143747 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8576", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "W6N5XAB6VW4RH2GSG72KCGXABVMU57RH", "length": "10522", "offset": "112852730", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00871.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=8577&lvl=notice_display 20240719081458 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8577", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DW3GAEEF4NVCSPTWEYLJ67SCW62RSG4T", "length": "5277", "offset": "105166781", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00872.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=86&lvl=publisher_see 20240725192526 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=86", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PAG5VFYL6IEVCFLKHF3PUURFLEXRBRD6", "length": "11303", "offset": "4523921", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00181.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=860&lvl=bulletin_display 20240721014630 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=860", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4ZZK2E76RPJGWHDIMJ34WW36CSIMNXCM", "length": "7663", "offset": "108567365", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00788.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=8608&lvl=author_see 20240719183102 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8608", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CXXSYOCCXOTWYXUGECOJTYD7DZZCUB3N", "length": "9909", "offset": "3485532", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00738.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=8613&lvl=author_see 20240712174827 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8613", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2UOW46NO56KY5YOXWMXVVWZJMUQBIXGX", "length": "6631", "offset": "104060289", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00743.warc.gz", "charset": "UTF-8", "languages": "fra,ltz,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=8613&lvl=notice_display 20240724162630 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8613", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QW35CA3GOIFXDTVW6PSYYKF3Z6M22FK2", "length": "4986", "offset": "118177865", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00743.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=8614&lvl=notice_display 20240724144720 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8614", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LAAU235OANP5OTWQWHYJA5HWZOQFQBT7", "length": "4985", "offset": "106995569", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00744.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=862&lvl=coll_see 20240721233732 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=862", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KB3TKGZO66DTRW4SLUUBXDEYPOX4MW3T", "length": "6781", "offset": "114770277", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00076.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=8622&lvl=author_see 20240721141056 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8622", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MO4JGN7MYO2AIS3DM752OC4VXLUC52HX", "length": "6590", "offset": "112712726", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00773.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=8623&lvl=author_see 20240721130610 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8623", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6TG3CWDTMMPAIG4YFHJCVOQJN4YTG4DI", "length": "6588", "offset": "109451055", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00774.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=8623&lvl=author_see 20240721132813 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8623", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RHDEQOCMOQ6IUJGOI2ZVUQ2EAD3Z7F5Q", "length": "6576", "offset": "5135807", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00795.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=8624&lvl=author_see 20240719100132 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8624", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NVCSZCCOUTAZ2DMKQNKQLKSZXIVPPIU2", "length": "6592", "offset": "103741507", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00775.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=8631&lvl=notice_display 20240719095917 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8631", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YKVHZ6JP2WODPPIDU3SXTQBJCNQ4MSOD", "length": "5298", "offset": "117323221", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00803.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=8668&lvl=author_see 20240715060835 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8668", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "C3CRILMMMGFVLIAFGG2PAD25NTJPQDVR", "length": "9825", "offset": "3409825", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00024.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=868&lvl=categ_see&main= 20240715061605 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=868&main=", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TQAH5Q6DECWMJWIJSHK62PYX6BAMJB5J", "length": "6809", "offset": "109013639", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00868.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=87&l_typdoc=a&lvl=indexint_see&main=&nbr_lignes=39&page=1 20240725184652 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=87&page=1&nbr_lignes=39&main=&l_typdoc=a", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "M2LEDGILU4GT3JZHML4S3DYWMVVM5HC3", "length": "11212", "offset": "118867907", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00577.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=87&lvl=author_see 20240716162337 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=87", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZSFRYZXGNMOA37WNV4SEZZYFVU6LFNGH", "length": "11808", "offset": "4782728", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00423.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=87&lvl=categ_see 20240724145316 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=87", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4CV5CDA72E64NBMPVQEKGNO2JTFMH72F", "length": "11534", "offset": "116406893", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00415.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=876&lvl=bulletin_display 20240721132508 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=876", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CTNGIT6UJZVID5GOS2UR3NGXW6SRWDB5", "length": "7488", "offset": "3826319", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00472.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=878&lvl=bulletin_display 20240722101050 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=878", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BEP5L5HWZLDEEC3YDTJAJ75JB3DFV64Z", "length": "8773", "offset": "105295063", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00827.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=88&lvl=indexint_see 20240712170152 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=88", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3QDEBSXWK3PTKPO54MRLXOSLAPFYHOQF", "length": "10631", "offset": "4405300", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00434.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=88&lvl=publisher_see 20240719091658 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=88", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AQYOWFJMKAJYLZXX7QLX3XTQN2QKLYUW", "length": "6812", "offset": "3427370", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00183.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=881&lvl=bulletin_display 20240722104559 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=881", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PRUBKHLC7JQHFOOBCPGYWT47BU3SL4YC", "length": "8174", "offset": "116319661", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00851.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=882&lvl=bulletin_display 20240718135645 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=882", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NYSYMIZOCQHFEAR4IVVR7BA4AXO3S2VE", "length": "10646", "offset": "106795814", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00852.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=8855&lvl=notice_display 20240721122803 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8855", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NHJB4CFIDGDZU3PL2FGSRPFJUB2FEKJK", "length": "4771", "offset": "2745650", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00160.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=8858&lvl=author_see 20240718141628 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8858", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QXCLW74BD4GD3TWSEE7RGJQ4TVBUE6KR", "length": "7658", "offset": "5453711", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00115.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=888&lvl=author_see 20240721233348 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=888", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TKOVOXU3XWRPSNMFZL3GK4AMDDLTF5B7", "length": "7084", "offset": "112041693", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00529.warc.gz", "charset": "UTF-8", "languages": "fra,ile,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=89&lvl=author_see 20240724155937 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=89", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2WOBDT26LOWPAT2UHA2Q66QFE4B6YHZC", "length": "12674", "offset": "3886637", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00425.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=89&lvl=indexint_see 20240716144938 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=89", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "O4UGLSPDE3XUISKLUSXEMBHLGQOFBYBI", "length": "11523", "offset": "3901026", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00435.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=89&lvl=publisher_see 20240719093911 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=89", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ODTPXPJXNHETSQQVDG65BXGWKAYWK56D", "length": "10782", "offset": "109842688", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00121.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=890&lvl=author_see 20240712162032 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=890", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LTIB7RVDLW2CT42ZKPKDRMUMJOCFKRGQ", "length": "7460", "offset": "108045512", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00552.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=8906&lvl=notice_display 20240724152418 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8906", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2V3FUX4CPZWPIJK2BEC2RQGI42OO4WLP", "length": "4946", "offset": "3636075", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00067.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=8919&lvl=author_see 20240721131820 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8919", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Q3LZBJYMYW6TBR3SEYJTYQCPUG6IBTGU", "length": "7367", "offset": "5966461", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00053.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=8932&lvl=author_see 20240724155758 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8932", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DG43KIBQZ75OAZ2UZUSLOJV7U4YENOXE", "length": "8300", "offset": "7386883", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00108.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=894&lvl=author_see 20240716154038 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=894", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EYDCPRJNJFAOHC7J43QRDWDVU45QADJF", "length": "8439", "offset": "119856846", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00556.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=8964&lvl=notice_display 20240719093958 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=8964", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZA3IW2CHZXEDZSLSIGGYM6446SS7IWSL", "length": "5211", "offset": "3228505", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00251.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=8965&lvl=author_see 20240716154238 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8965", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TDMLGMGMXABN2EDG2RN653X3VUY5OJZE", "length": "9680", "offset": "120756310", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00183.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=8968&lvl=author_see 20240718133042 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8968", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TVRTWUOSKEGYRRT2GM5UJOYKJXTFHRS5", "length": "6728", "offset": "114120911", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00186.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=8969&lvl=author_see 20240718142611 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8969", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JXVUXJO3TQX2PLQ3VWHYB453KK5OS32Z", "length": "6727", "offset": "113603189", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00187.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=8978&lvl=author_see 20240725180355 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8978", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AJYRIYGNU7NU64ZQYDPF723GC7422FVS", "length": "6754", "offset": "105004567", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00217.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=8998&lvl=author_see 20240721231750 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=8998", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HMEJ4VOS6CBM5QH5PBOWBLSWABVWEZLO", "length": "6651", "offset": "101444240", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00279.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9&lvl=categ_see 20240718210609 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=9", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CVT4IDIIOO7HQAOGOVJEM6OSWRC7GM6P", "length": "11083", "offset": "110665144", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00553.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=9&lvl=categ_see 20240721222541 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=9", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DMGNQMWWA6H2M72XCJPQDETMDNLCPLIM", "length": "11074", "offset": "3188975", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00838.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=9&lvl=indexint_see 20240721215626 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=9", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XE7C663KMINIHU6WAVQXBO6C7NAP2UMN", "length": "10533", "offset": "5502891", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00495.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9&lvl=publisher_see 20240721014014 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=9", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "REVTOCCJE23BQYAUN6OGVOLD2YEEUGRA", "length": "10919", "offset": "5019253", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00234.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=90&lvl=indexint_see 20240712180115 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=90", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "22DXJVMDCF2KHYKYIATGBXTJ6G5C6RC2", "length": "11807", "offset": "107827990", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00436.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=90&lvl=publisher_see 20240712173953 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=90", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "APDBKHXSA3GOGF565XN4RHQLUMB3HIVG", "length": "9574", "offset": "4435100", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00206.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=9007&lvl=notice_display 20240725201502 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9007", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "S5FMFXV54HHW4UULMPXGOTX74NZ3VLPW", "length": "4971", "offset": "112864677", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00441.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9015&lvl=author_see 20240718194339 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9015", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6D6WSQZPTVR2CAJNXBYAISXAJBY7WWPK", "length": "8343", "offset": "121134184", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00470.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=902&lvl=publisher_see 20240724152102 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=902", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "K3MKQBQGR7NGJCIEINB6EOPEQLO4G34A", "length": "7020", "offset": "100968961", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00867.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9021&lvl=author_see 20240719192355 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9021", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "U5UUNW3RIH4X4C5I2EFQSTNSSH67HDPP", "length": "8009", "offset": "117601543", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/warc/CC-MAIN-20240719170235-20240719200235-00497.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=9026&lvl=author_see 20240721003034 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9026", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UDQUSK2DZJLO6IJZ4X7TSYOT4NQXLZYE", "length": "7070", "offset": "3943103", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00523.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9029&lvl=author_see 20240724161402 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9029", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OI3PA4MEFQAQM5FAZWZLBVDNS5J2V7OX", "length": "6660", "offset": "3796086", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00526.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=903&lvl=bulletin_display 20240722110144 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=903", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EEYPJ4YOSB6SYG5WKLEQFIWSORSPIJDG", "length": "8251", "offset": "103859477", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00666.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9045&lvl=author_see 20240716160804 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9045", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7XW7ZLYFK2I4CBPURT6TSMJHBEBULFSF", "length": "6904", "offset": "125373956", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00563.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=9063&lvl=author_see 20240715051737 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9063", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "B6R6RY3RGXG66MN5JZUHOPSCOJCDD7EU", "length": "7088", "offset": "115704854", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00623.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=907&lvl=coll_see 20240712184214 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=907", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HO3SJI2NFNFGSS6QIJA64KHTNQT4EUCX", "length": "8034", "offset": "103289308", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00856.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=907&lvl=indexint_see 20240715052947 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=907", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6I2FXJUQVRE4YUE65PRBV5WCUXOGRFJP", "length": "11378", "offset": "4508507", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00326.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9076&lvl=author_see 20240724150116 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9076", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UUMV4XG6TEYV6SGGU4BXMNIYVGWNNJQ5", "length": "11556", "offset": "6107244", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00678.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=910&lvl=bulletin_display 20240722113432 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=910", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TRWJ54VR6EOB3ETQU6JWKVNKJP72XLA3", "length": "7402", "offset": "111452935", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00694.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9108&lvl=notice_display 20240721124955 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9108", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7VKXOVI3PVKWUHVNICGKDC7WNMUWG7SM", "length": "4863", "offset": "4535754", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00572.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9119&lvl=notice_display 20240719090409 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9119", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YNZLPLYRKCEDGYPVE7QKG6MZSJNGHV5O", "length": "5113", "offset": "4231683", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00604.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=912&lvl=bulletin_display 20240718143347 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=912", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5NFLJYM5DO2OC7ENTNFKIG6DAWSM6NBH", "length": "7348", "offset": "115241052", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00696.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9124&lvl=author_see 20240721013046 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9124", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PG44B2362Z6PKLHCRREWXSYAWXI6UOD5", "length": "6855", "offset": "110589055", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00561.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=914&lvl=publisher_see 20240718143311 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=914", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UENULGW4T7KDFL5JF6XCPBMHTSMQBXDS", "length": "7366", "offset": "2830712", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00325.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=9149&lvl=notice_display 20240725200241 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9149", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7Y7ICPCKRL5IN4YKFMF3NTAXGLRBTPJD", "length": "5150", "offset": "3822909", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00697.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=9174&lvl=notice_display 20240725194559 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9174", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AQKTHVUKRUB774RXRAEKZJEF3H5KY3JU", "length": "5225", "offset": "103323137", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00716.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9177&lvl=notice_display 20240725195255 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9177", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EK4PM47LMKRBW4766A5WPLRAJ5X5W5EP", "length": "5066", "offset": "5506327", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00788.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=918&lvl=categ_see 20240718200631 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=918", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5YSBYNPJAAWTBA4MIZYKMWQAVVQY4CIS", "length": "6886", "offset": "111280990", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00700.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=918&lvl=notice_display 20240725194438 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=918", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RLM3GCOI3TCCLAMIG46T55WQVUKR3EV2", "length": "5094", "offset": "5147938", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00560.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9181&lvl=author_see 20240716153120 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9181", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JN4FF4WYIRQCUVHZ3G5KHX2OFQCNA3HM", "length": "6822", "offset": "119014029", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00744.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=9193&lvl=notice_display 20240721140652 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9193", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OVMQBZHQNZGVUHXFEJIFUZGG36DYOFGL", "length": "4905", "offset": "105292085", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00777.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9196&lvl=author_see 20240715053836 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9196", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "L5FEDWLYAR3OVFF3DB5OJZ42KK6CQXGO", "length": "7340", "offset": "5254976", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00801.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=9197&lvl=author_see 20240718202503 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9197", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LZKLLP5TCI4YUSWYCYGWJPEKNX4N6LNP", "length": "6727", "offset": "120051239", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00781.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=92&lvl=publisher_see 20240722114731 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=92", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "546QDKEDWEB3G7PEJ7I2BSZ2ILTQCCGG", "length": "11130", "offset": "100932724", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00145.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=9202&lvl=author_see 20240715043559 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9202", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GTSUXABR6II5MFAUXOF6OZDPXUMDDUB6", "length": "7857", "offset": "112805928", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00558.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=9224&lvl=notice_display 20240719094706 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9224", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LPJAIDWOGOBHBBFTYLJDDUZDMKODMGP4", "length": "5004", "offset": "115362256", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00622.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9228&lvl=author_see 20240719100636 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9228", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "N3DFCPINSUC5F6CHLRG6KCL7IBASDX6L", "length": "6624", "offset": "103883558", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00626.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9238&lvl=author_see 20240725181241 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9238", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4DMWRILCJXG4ELDSGMQ6RO4MPYRYDOHH", "length": "6727", "offset": "3928616", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00678.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9252&lvl=author_see 20240712180217 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9252", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QRX54MX32UZKRG2OCGV7WWH5I5YXLNDR", "length": "6887", "offset": "99247799", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00713.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=927&lvl=author_see 20240718142429 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=927", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DIO567PCYAZUD463FS6GIP4X7PEA66MT", "length": "7752", "offset": "117411529", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00403.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=93&lvl=indexint_see 20240718194005 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=93", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2XP36JQELZLUOZDVZCL4MNJPF5A5UB3P", "length": "11189", "offset": "116462821", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00439.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=931&lvl=author_see 20240718141348 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=931", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "IY7JSYNQ266YR7WXDXNLYAKO4OHTNYHH", "length": "9201", "offset": "121694989", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00428.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9313&lvl=author_see 20240715055035 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9313", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "A4TXOTPEJ5I7NMKJ24DJIHOK5AMXE5RR", "length": "7482", "offset": "112971103", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00651.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=932&lvl=publisher_see 20240718145104 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=932", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SUS7UJMNNWHSM7O6QTLZULSHZDNL6SJB", "length": "6990", "offset": "108175697", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00060.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=933&lvl=bulletin_display 20240722103634 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=933", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HKDAYWCHBS5MPJLH64L5OXXUNBG4BDLA", "length": "7629", "offset": "110666123", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00759.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9343&lvl=author_see 20240725195943 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9343", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MJQSV5MDVNFAANAZUK3OZYPVLWWA45IX", "length": "6781", "offset": "4105349", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00765.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=9344&lvl=author_see 20240718143125 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9344", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WPBQBJRKGBZYUDDY6BFAHYWWRWZGFSJ3", "length": "6783", "offset": "5247092", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00766.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=9372&lvl=author_see 20240718204147 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9372", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EP37DUMV4FGZIGZYMKLQ4GTAVCH3INPB", "length": "10255", "offset": "112012848", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00836.warc.gz", "charset": "UTF-8", "languages": "fra,eng,deu"}
-fr,missiondefrance,bibliotheque)/index.php?id=9372&lvl=author_see 20240721224756 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9372", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TISTSNT2ML3C7AYCC7OYVV6HQU7NZW37", "length": "10233", "offset": "3214090", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00857.warc.gz", "charset": "UTF-8", "languages": "fra,eng,deu"}
-fr,missiondefrance,bibliotheque)/index.php?id=9381&lvl=notice_display 20240719082420 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9381", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RBN6LPLCXKEY2NNQRNL4OMHHC6ARH3GG", "length": "5028", "offset": "5137481", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00035.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=94&lvl=author_see 20240718205206 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=94", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LIXFRS527GGPLHDJ7OVMF6NDVIPARRCJ", "length": "10309", "offset": "107371760", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00418.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=94&lvl=categ_see 20240718193328 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=94", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PYLVH2QDPDXL5J2OYIO7LSA4GPCCDDLN", "length": "9900", "offset": "115394762", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00443.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=94&lvl=coll_see 20240715044033 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=94", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JD3MA7KYP2AASAE7B4WG6ERJPIWKVVDU", "length": "10514", "offset": "4628676", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00824.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=94&lvl=coll_see 20240716150244 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=94", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "342BN7PFXF5L7SWMBXMVVMBBXCEOO32E", "length": "10552", "offset": "118397198", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00539.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9407&lvl=author_see 20240721123935 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9407", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OP4NQJDNLZW6N46PUQVY74ZYHJBBIYFZ", "length": "3965", "offset": "113288678", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00685.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=941&lvl=coll_see 20240722110115 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=941", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "MSJOFUEVRDH5SQZVGQIMHLT5PCF6KVIJ", "length": "7670", "offset": "3302621", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00065.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9414&lvl=notice_display 20240719095811 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9414", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "K6QJXVVXPCPTGBM7TPRAWJTFAI6O2NKP", "length": "4876", "offset": "5478050", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00782.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9424&lvl=notice_display 20240712185845 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9424", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NMSDLAYB3PTXGNFAJMAXUE5ZQYQXG2SA", "length": "5088", "offset": "105120339", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00744.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9432&lvl=author_see 20240724145123 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9432", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CUUW5UXEMLGWNRCMLTV3Z7QT72NEY76Y", "length": "9416", "offset": "105409274", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00773.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9433&lvl=author_see 20240715055008 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9433", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OKN4KXDZOXW2BWLWO5H6MX4T6OSXOHLC", "length": "6936", "offset": "113232135", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00774.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9434&lvl=author_see 20240715044850 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9434", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "7AY7ZN7CPEZDIUSIUGEUACJIDWEHUQ66", "length": "6930", "offset": "107165624", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00775.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9434&lvl=notice_display 20240721003125 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9434", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZZUAO6DOSGD2HDEGYB3XJ5OST2KZMQRH", "length": "5049", "offset": "115117772", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00775.warc.gz", "charset": "UTF-8", "languages": "fra,ltz,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=9435&lvl=notice_display 20240718195907 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9435", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "IN2KHELDOZZYU72TZMYU3PF2N4DQPO4L", "length": "4982", "offset": "3264561", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00845.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9436&lvl=notice_display 20240712182234 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9436", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6CORJ7BWNYMVP5QOO6M6GI6VYDQSYWB7", "length": "4947", "offset": "104633457", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00777.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9462&lvl=author_see 20240715061141 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9462", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZP66564AE2R6FYRT4LKQXCDTMBERC3IJ", "length": "6749", "offset": "111100970", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00866.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=95&lvl=indexint_see 20240721140043 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=95", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "X7VXR54SEEXZDIDC76HT5LK4JCYZRXAI", "length": "9196", "offset": "4212330", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00462.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=951&lvl=bulletin_display 20240721013935 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=951", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "AMFQ4KGEIR3ZJLXQBPQRR7NOZONOF7OK", "length": "7965", "offset": "112414977", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00819.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9515&lvl=author_see 20240718134120 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9515", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VQ5QPXASSQEWUOUGZEHIONADPMBBZHXK", "length": "7986", "offset": "113245425", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00775.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=952&lvl=categ_see 20240724151822 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=952", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "L3MJ67TOTFK3M4ZAMVHPFPXIJKEOFGMJ", "length": "10478", "offset": "4273580", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00851.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=9533&lvl=notice_display 20240719091721 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9533", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "NEW2TYAYQMXEXKDWNR52YMNEVZ76UOII", "length": "4910", "offset": "3473264", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00004.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9538&lvl=notice_display 20240721130139 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9538", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VS37FOU4SOHPB3EWPVKVQ6E3GUV2FDGS", "length": "5048", "offset": "108251030", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00840.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9539&lvl=author_see 20240721122255 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9539", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "J2PXONL4B7VJWEOPZ4KLWDPDD2AP53WL", "length": "6655", "offset": "111031174", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00841.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=9543&lvl=author_see 20240715053757 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9543", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GHSPGNPGBG5KLURMHU5CXKFJ5U3B47L5", "length": "7868", "offset": "3551959", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00887.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9543&lvl=author_see 20240716162300 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9543", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PULUOWMWRPG2D3SG4QJR2D7ZBF5DCQGH", "length": "7918", "offset": "118476572", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00866.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9558&lvl=author_see 20240724145844 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9558", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VCMU5Y6TZ3RU4RRT6J552I5Q2QEI47N5", "length": "6814", "offset": "110738686", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00002.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=956&lvl=coll_see 20240721005013 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=956", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2GX4MWNYWRZNL27QDXB7BNYMVJGQPBMU", "length": "9348", "offset": "2800065", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00101.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9568&lvl=notice_display 20240719100553 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9568", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "BB6PLTZFBRZ7UVIDHE7Q4NAX5K3ZTSQW", "length": "5040", "offset": "2990347", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00102.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=957&lvl=bulletin_display 20240722110834 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=957", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2AH3MNAPVGSJEJYKAZHSIP3K4TXOTL4S", "length": "8330", "offset": "4335202", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00472.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9578&lvl=notice_display 20240722100537 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9578", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DDS2ABXIK4MOY4RSSB2Y6EJBX3JZ42FN", "length": "5141", "offset": "3747026", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00133.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=958&lvl=bulletin_display 20240722114405 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=958", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TBABQXKVXRRWMRETDHB6Z7T53HGCC4HE", "length": "7805", "offset": "105930258", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00826.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9581&lvl=notice_display 20240721134950 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9581", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PLCIHNPQRDGSHBJQQIYMQZADHVAJM47C", "length": "5146", "offset": "6393417", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00157.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=9585&lvl=author_see 20240712172306 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9585", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6JCCFD4DKC4U2MHUR3DHMKRPEJH2LRHM", "length": "6790", "offset": "4631783", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00113.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9590&lvl=author_see 20240715055402 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9590", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "R5SXK6AHXA3ODPOLDA5O6LUKZ7X54J6B", "length": "6916", "offset": "104645778", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00118.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=96&lvl=indexint_see 20240712180612 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=96", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "FDFTHAHJXMCUU3XKM7PVLMIGERZFD2AC", "length": "9977", "offset": "97769136", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00442.warc.gz", "charset": "UTF-8", "languages": "fra,eng,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=963&lvl=notice_display 20240724142607 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=963", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QQAZDWSOCY2DG74YNAJYC26XVCSX5GT5", "length": "4981", "offset": "3495808", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00710.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9637&lvl=author_see 20240722103716 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9637", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XK2ZATVIYARKWHBPZTPK6XIPOLWVCIKH", "length": "6785", "offset": "109593598", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00000.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=965&lvl=author_see 20240721135149 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=965", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OBI5LGJCHJCMYVVOVIPNTQPBAZHORMAG", "length": "6618", "offset": "118094555", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00525.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9651&lvl=author_see 20240719100605 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9651", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "W5SHYT5IPMKBRY6QI6YZPP3P66TDHWBC", "length": "7401", "offset": "108164672", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00056.warc.gz", "charset": "UTF-8", "languages": "fra,ile"}
-fr,missiondefrance,bibliotheque)/index.php?id=9653&lvl=author_see 20240724162805 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9653", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GBZ5U2BJ7UGUTIM6N5CWDUXYV6HPESXS", "length": "7942", "offset": "111338151", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00058.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=968&lvl=bulletin_display 20240720235925 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=968", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ESFTAYLXOPH7SY6RXTM2HTR7IUOIQGFH", "length": "8517", "offset": "114989075", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00857.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=968&lvl=categ_see 20240722100047 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=968", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "J42PRRP2WK2DUAEQY3JFN4OGS5AS3RUI", "length": "7689", "offset": "111995923", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00855.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=969&lvl=coll_see 20240715042509 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=coll_see&id=969", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LIIEZBINXG766JI6KP5IIMYUYNENCDHD", "length": "8566", "offset": "3042231", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00135.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=9695&lvl=notice_display 20240722105837 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9695", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XQEXIG55W4NAKURMFIXAWYWBWDUJPOZK", "length": "5005", "offset": "5245492", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00253.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=97&lvl=categ_see 20240712184125 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=97", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PLM4UQNBD3VTOWINUENLHUDDZM2GXIOG", "length": "12927", "offset": "101528294", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00446.warc.gz", "charset": "UTF-8", "languages": "fra,ltz"}
-fr,missiondefrance,bibliotheque)/index.php?id=970&lvl=bulletin_display 20240722101911 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=970", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "HZXHWJ6AA3J3JRC4U3XUMO4ECY7YWRRP", "length": "9132", "offset": "4537830", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00527.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=9708&lvl=notice_display 20240718213430 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9708", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZE5XL2GZIXJXSV5GUFNF7RV4IMKJ6IWM", "length": "4873", "offset": "108112532", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00869.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=9718&lvl=author_see 20240721130431 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9718", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "EM7BFDAY67OJKHEVDXUBK3YRTFRVK7IZ", "length": "6819", "offset": "3949237", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00021.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9762&lvl=author_see 20240721224644 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9762", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SE3H55PMYNBCKAIANVYSPE3VWJPGMTGT", "length": "6659", "offset": "112778820", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00149.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=977&lvl=bulletin_display 20240718200030 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=977", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LDDOJQPYN5KRDCVFFXD7FRAFINQZX5NE", "length": "9015", "offset": "108880600", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00887.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=978&lvl=author_see 20240722111800 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=978", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "RY6BDSKDXO6I3W6VJHQHZKVI7UA3AZAS", "length": "7446", "offset": "109680960", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00559.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=978&lvl=categ_see 20240718213648 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=978", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "43W7JQU5U3YEGBFOPV5WCYTTLGWACNKC", "length": "10655", "offset": "119211447", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00886.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=979&lvl=bulletin_display 20240724145619 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=979", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GLJL6XXV7IL4GB6TQLEYXDYNBYX5EUL4", "length": "9809", "offset": "110439143", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00889.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=979&lvl=categ_see 20240718195154 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=979", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "4W4RWYQDIDCCMHFJRPY2VY64BJQXIBVW", "length": "10709", "offset": "108890614", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00887.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=9792&lvl=author_see 20240718134239 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9792", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "N7FRREQKDVGG7LIBP5J4RC6X22KDEZNQ", "length": "6536", "offset": "111705895", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00242.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=9794&lvl=notice_display 20240719093545 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9794", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "2GWCLRA4KIEEM5UJOKC3BGGMTCO5JKOC", "length": "5173", "offset": "109966372", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00244.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=98&lvl=categ_see 20240712183221 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=categ_see&id=98", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "6I6R4UCSQF6WQDYEKW3JBUCTRTTONJUV", "length": "11383", "offset": "109957826", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00447.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=98&lvl=indexint_see 20240715053109 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=indexint_see&id=98", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5XDQWNLCIUEVQDA4AAVKFR3AZDS6DEFA", "length": "9837", "offset": "108910101", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00444.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=98&lvl=publisher_see 20240712175151 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=98", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "YOSJQ35BRWQ6GO6GWKB23OUQXFNAI6EL", "length": "10292", "offset": "2926328", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00214.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=982&lvl=bulletin_display 20240718141243 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=982", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5WYV2AU7F3JEVRRL3GVML44AEN6XDKNI", "length": "9541", "offset": "109699565", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00013.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9823&lvl=notice_display 20240721141018 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9823", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3JNBVEOBRR2IRYF7NZYF6O3VEFQDRKE5", "length": "4944", "offset": "4087916", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00156.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9848&lvl=notice_display 20240719095701 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9848", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PRV7WILTPOE2SJC77D5UOX2LQKBMNIH4", "length": "5200", "offset": "103826450", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00154.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=9854&lvl=author_see 20240719100540 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9854", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "TBL6RBGWNQJGP6HDHFOZBFGNIDBCZHR7", "length": "6659", "offset": "113870598", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/warc/CC-MAIN-20240719074314-20240719104314-00181.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=9860&lvl=notice_display 20240716150204 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9860", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "QQRGXKB3VLGKSB3FWXSG34VQ73W4JXJM", "length": "5174", "offset": "111471177", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00208.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=9864&lvl=author_see 20240715055943 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9864", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "OZTK5CFONUFD52O4PUZ6Z7UBVKBWIO6H", "length": "6899", "offset": "115256346", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00212.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9867&lvl=author_see 20240725185337 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9867", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "PJOVH2UH4WZONNVCL6AD6CWZ6JVLQTIH", "length": "7230", "offset": "113797707", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00215.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=987&lvl=publisher_see 20240718142052 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=987", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "Y2UHXNGFP4E3M4KGMMAU63TLBGVQOFKH", "length": "6576", "offset": "3340641", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00545.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9876&lvl=author_see 20240725195130 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9876", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JJUWXPBM6XMJAKKSONABPPWKJLJS3H4L", "length": "7870", "offset": "98937641", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00245.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=9880&lvl=author_see 20240718210647 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9880", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CSTC6UQIKC6X6MQKCMDBUHF2RXDTTI72", "length": "6637", "offset": "4355941", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/warc/CC-MAIN-20240718191743-20240718221743-00291.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=990&lvl=publisher_see 20240718142837 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=990", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ICWBULWCQRATH7VR6OCGGDJCXQFUONID", "length": "6473", "offset": "3383048", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00569.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9912&lvl=author_see 20240725201028 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9912", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "3T54SYNF5EGMBBOYVUDIPSD3FRPQZ63L", "length": "7485", "offset": "2972838", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/warc/CC-MAIN-20240725175545-20240725205545-00137.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=992&lvl=author_see 20240718144113 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=992", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "R55C6LKIIGG4LUQTCJ53CJDSTQBX5AIX", "length": "6971", "offset": "112401391", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00615.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9932&lvl=notice_display 20240721003222 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9932", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "JDK7R6TTCMKRCBJXUIZNTAPBA2N3RXIW", "length": "5171", "offset": "117976823", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00178.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=994&lvl=publisher_see 20240715055443 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=publisher_see&id=994", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "DOCLYYTKLO3VGFJ3CM2QR2LGLW5V4QPM", "length": "11546", "offset": "4933350", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00573.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9948&lvl=author_see 20240715045205 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9948", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KCZ5BMCQY2TNGER4DDINDYLRDLWUAKEI", "length": "6961", "offset": "112770151", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/warc/CC-MAIN-20240715040934-20240715070934-00215.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?id=9951&lvl=author_see 20240722111642 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9951", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "XNLTD5QGJHVPZP64RYK27DNI2M4R6QGR", "length": "6816", "offset": "109375717", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/warc/CC-MAIN-20240722095039-20240722125039-00239.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9952&lvl=notice_display 20240721011222 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9952", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GHDZ2F6PTR7E3HXHNFLE62POEO6HAN3Y", "length": "5149", "offset": "119444828", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00240.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9952&lvl=notice_display 20240721135021 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9952", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GHDZ2F6PTR7E3HXHNFLE62POEO6HAN3Y", "length": "5132", "offset": "5918750", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00309.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=996&lvl=author_see 20240721125950 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=996", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "ZOUXENJBI7M67SGACWZGPJTEZDM7SNAQ", "length": "7231", "offset": "109547550", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00619.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9962&lvl=author_see 20240718130816 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=author_see&id=9962", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "SVQ3IVLH7TR5MNP62VSUPOBGO5H3ATMB", "length": "10488", "offset": "110500556", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00271.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9986&lvl=notice_display 20240721125044 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9986", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "WZR7LFJXY6XNTLVUM62Y7VIEO2URDD7B", "length": "4942", "offset": "106585653", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00337.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?id=9987&lvl=notice_display 20240721131717 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=notice_display&id=9987", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "CWXJDKB3TT6SOOG3MLDZ5WNITNAXPSVY", "length": "4829", "offset": "106385331", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00338.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,missiondefrance,bibliotheque)/index.php?location=1&lvl=section_see 20240724145239 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=section_see&location=1", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "T2R7E4YPVQOYMRGQHN3NRFOWS2COTB37", "length": "3839", "offset": "6282192", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00847.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?location=2&lvl=section_see 20240724151311 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=section_see&location=2", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "5UFNW7UXNFMIBLL7TKVC4ZJ7VJCBYHVP", "length": "3774", "offset": "3827684", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00848.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?lvl=index 20240712170635 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=index", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "X5JASAJHR32WAUW57C5WPMPQXSBAVRNL", "length": "9309", "offset": "3717231", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/warc/CC-MAIN-20240712161324-20240712191324-00677.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?lvl=index 20240721013634 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=index", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VMWOHIOXEUEMD5K3TRWDJVMTSEM6WX2Y", "length": "9318", "offset": "105264950", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/warc/CC-MAIN-20240720235600-20240721025600-00222.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?lvl=index&search_in_perio=31&search_type_asked=extended_search 20240718131846 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=index&search_type_asked=extended_search&search_in_perio=31", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "VTEJEDUHBLT3RPAPLS7RTQ56JE7BX5WK", "length": "6995", "offset": "113337507", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/warc/CC-MAIN-20240718130417-20240718160417-00386.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?lvl=infopages&pagesid=7 20240721233024 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=infopages&pagesid=7", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "LMUUDM5JSIU3TDI6NQUNJAWKMD6BQQ2J", "length": "3556", "offset": "5671966", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00020.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?lvl=more_results&mode=keyword&tags=ok&user_query=exp%c3%a9rience 20240721132718 {"url": "https://bibliotheque.missiondefrance.fr/index.php?lvl=more_results&mode=keyword&user_query=Exp%C3%A9rience&tags=ok", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GUES2HEN5MX47ZKWD5LLN676MSLERUAX", "length": "8189", "offset": "109696531", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/warc/CC-MAIN-20240721121510-20240721151510-00201.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?lvl=more_results&mode=keyword&tags=ok&user_query=syrie+jusqu'%c3%a0+333+av.+j.-c. 20240716150405 {"url": "http://bibliotheque.missiondefrance.fr/index.php?lvl=more_results&mode=keyword&user_query=Syrie+jusqu%27%C3%A0+333+av.+J.-C.&tags=ok", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "UQJR2X2QPHX32TEEORY2JWQENRTKJNCQ", "length": "6485", "offset": "3310893", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00268.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?mode_aff=aff_simple_search&search_type_asked=extended_search 20240721215228 {"url": "https://bibliotheque.missiondefrance.fr/index.php?search_type_asked=extended_search&mode_aff=aff_simple_search", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "IQ4RZ7MIMOP2PKKUAKZH2Z7DVL5Y2PBF", "length": "5687", "offset": "111907687", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/warc/CC-MAIN-20240721213034-20240722003034-00679.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/index.php?search_type_asked=simple_search 20240724145043 {"url": "http://bibliotheque.missiondefrance.fr/index.php?search_type_asked=simple_search", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "KJWZ35G3RRH33NZXMNCQXAM5W4VSXVJA", "length": "10101", "offset": "2733680", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00824.warc.gz", "charset": "UTF-8", "languages": "fra"}
-fr,missiondefrance,bibliotheque)/robots.txt 20240712161634 {"url": "https://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "765", "offset": "571443", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/robotstxt/CC-MAIN-20240712161324-20240712191324-00185.warc.gz"}
-fr,missiondefrance,bibliotheque)/robots.txt 20240712161907 {"url": "http://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "722", "offset": "48901", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514450.42/robotstxt/CC-MAIN-20240712161324-20240712191324-00890.warc.gz"}
-fr,missiondefrance,bibliotheque)/robots.txt 20240715041153 {"url": "http://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "722", "offset": "39529", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/robotstxt/CC-MAIN-20240715040934-20240715070934-00890.warc.gz"}
-fr,missiondefrance,bibliotheque)/robots.txt 20240715042232 {"url": "https://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "767", "offset": "712678", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514659.22/robotstxt/CC-MAIN-20240715040934-20240715070934-00185.warc.gz"}
-fr,missiondefrance,bibliotheque)/robots.txt 20240716142519 {"url": "https://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "765", "offset": "556987", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/robotstxt/CC-MAIN-20240716142214-20240716172214-00185.warc.gz"}
-fr,missiondefrance,bibliotheque)/robots.txt 20240716142846 {"url": "http://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "721", "offset": "36790", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/robotstxt/CC-MAIN-20240716142214-20240716172214-00890.warc.gz"}
-fr,missiondefrance,bibliotheque)/robots.txt 20240718130815 {"url": "https://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "758", "offset": "620127", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/robotstxt/CC-MAIN-20240718130417-20240718160417-00185.warc.gz"}
-fr,missiondefrance,bibliotheque)/robots.txt 20240718131103 {"url": "http://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "722", "offset": "35421", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514831.13/robotstxt/CC-MAIN-20240718130417-20240718160417-00890.warc.gz"}
-fr,missiondefrance,bibliotheque)/robots.txt 20240718191949 {"url": "http://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "724", "offset": "52522", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/robotstxt/CC-MAIN-20240718191743-20240718221743-00890.warc.gz"}
-fr,missiondefrance,bibliotheque)/robots.txt 20240718192520 {"url": "https://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "757", "offset": "491992", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514859.56/robotstxt/CC-MAIN-20240718191743-20240718221743-00185.warc.gz"}
-fr,missiondefrance,bibliotheque)/robots.txt 20240719074558 {"url": "https://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "756", "offset": "486032", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/robotstxt/CC-MAIN-20240719074314-20240719104314-00185.warc.gz"}
-fr,missiondefrance,bibliotheque)/robots.txt 20240719075211 {"url": "http://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "724", "offset": "48990", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514900.59/robotstxt/CC-MAIN-20240719074314-20240719104314-00890.warc.gz"}
-fr,missiondefrance,bibliotheque)/robots.txt 20240719170546 {"url": "http://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "723", "offset": "60002", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/robotstxt/CC-MAIN-20240719170235-20240719200235-00890.warc.gz"}
-fr,missiondefrance,bibliotheque)/robots.txt 20240719171238 {"url": "https://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "752", "offset": "490181", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514917.3/robotstxt/CC-MAIN-20240719170235-20240719200235-00185.warc.gz"}
-fr,missiondefrance,bibliotheque)/robots.txt 20240720235924 {"url": "https://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "757", "offset": "762089", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/robotstxt/CC-MAIN-20240720235600-20240721025600-00185.warc.gz"}
-fr,missiondefrance,bibliotheque)/robots.txt 20240721001506 {"url": "http://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "723", "offset": "33797", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517544.48/robotstxt/CC-MAIN-20240720235600-20240721025600-00890.warc.gz"}
-fr,missiondefrance,bibliotheque)/robots.txt 20240721121807 {"url": "http://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "723", "offset": "51177", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/robotstxt/CC-MAIN-20240721121510-20240721151510-00890.warc.gz"}
-fr,missiondefrance,bibliotheque)/robots.txt 20240721122125 {"url": "https://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "756", "offset": "555138", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517701.96/robotstxt/CC-MAIN-20240721121510-20240721151510-00185.warc.gz"}
-fr,missiondefrance,bibliotheque)/robots.txt 20240721213217 {"url": "http://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "724", "offset": "49742", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/robotstxt/CC-MAIN-20240721213034-20240722003034-00890.warc.gz"}
-fr,missiondefrance,bibliotheque)/robots.txt 20240721213731 {"url": "https://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "757", "offset": "561307", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517796.21/robotstxt/CC-MAIN-20240721213034-20240722003034-00185.warc.gz"}
-fr,missiondefrance,bibliotheque)/robots.txt 20240722095224 {"url": "http://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "724", "offset": "38634", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/robotstxt/CC-MAIN-20240722095039-20240722125039-00890.warc.gz"}
-fr,missiondefrance,bibliotheque)/robots.txt 20240722100047 {"url": "https://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "758", "offset": "611179", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763517846.73/robotstxt/CC-MAIN-20240722095039-20240722125039-00185.warc.gz"}
-fr,missiondefrance,bibliotheque)/robots.txt 20240724141215 {"url": "http://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "723", "offset": "37142", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/robotstxt/CC-MAIN-20240724140819-20240724170819-00890.warc.gz"}
-fr,missiondefrance,bibliotheque)/robots.txt 20240724141602 {"url": "https://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "756", "offset": "564386", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/robotstxt/CC-MAIN-20240724140819-20240724170819-00185.warc.gz"}
-fr,missiondefrance,bibliotheque)/robots.txt 20240725175732 {"url": "http://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "721", "offset": "36834", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/robotstxt/CC-MAIN-20240725175545-20240725205545-00890.warc.gz"}
-fr,missiondefrance,bibliotheque)/robots.txt 20240725180355 {"url": "https://bibliotheque.missiondefrance.fr/robots.txt", "mime": "text/html", "mime-detected": "text/html", "status": "404", "digest": "VAQZB7CTBQTFVJAKAROCC5YNSZ7UOZ5Y", "length": "755", "offset": "627917", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763861452.88/robotstxt/CC-MAIN-20240725175545-20240725205545-00185.warc.gz"}
-fr,missiondefrance,bibliotheque)/select.php?auto_submit=no&caller=form_values&date_anterieure=yes&date_caller=&param1=bull_date_start&param2=date_deb_btn&what=calendrier 20240724151114 {"url": "https://bibliotheque.missiondefrance.fr/select.php?what=calendrier&caller=form_values&date_caller=&param1=bull_date_start&param2=date_deb_btn&auto_submit=NO&date_anterieure=YES", "mime": "text/html", "mime-detected": "application/xhtml+xml", "status": "200", "digest": "GWACPCVL6E6S2IZ2NCJMQVXA3X4E2ZMZ", "length": "3324", "offset": "111935641", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518304.14/warc/CC-MAIN-20240724140819-20240724170819-00413.warc.gz", "charset": "UTF-8", "languages": "eng"}
-fr,mnhn,biodiv)/fr/taxonomy/term/1017 20240719210808 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/1017", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "6PWC6QZLKGZ4C7GBJ6PG7XFIUFOF473I", "length": "8730", "offset": "108450574", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00876.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,mnhn,biodiv)/fr/taxonomy/term/1023 20240719204155 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/1023", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "XDSO3L2DMI35PPGCKTQKEDMB2F3V4MRP", "length": "8797", "offset": "116676062", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00003.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,mnhn,biodiv)/fr/taxonomy/term/1025 20240719221032 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/1025", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "4UP33YIXFFRZDQDS6DYKHQVJSG6KZJ62", "length": "8801", "offset": "112460055", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00005.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,mnhn,biodiv)/fr/taxonomy/term/103 20240719212230 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/103", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "4UZFS4HFOEFXLD6IL4DBOK2AWBOS7CHP", "length": "8938", "offset": "110435689", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00053.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,mnhn,biodiv)/fr/taxonomy/term/120 20240723092605 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/120", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "WBM6SZL2DX3RWI2K44QLSJODESS6A6FB", "length": "8862", "offset": "107100378", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518029.81/warc/CC-MAIN-20240723072353-20240723102353-00112.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,mnhn,biodiv)/fr/taxonomy/term/136 20240719204102 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/136", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "7NP5WWF7BVPJ5NUPDJZLR54HDPE6ULDL", "length": "9139", "offset": "114748215", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00149.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,mnhn,biodiv)/fr/taxonomy/term/142 20240719215813 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/142", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "4CKVR6ZATYKTYEPBJVET5YVBQ5H6EV67", "length": "8904", "offset": "109719400", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00176.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,mnhn,biodiv)/fr/taxonomy/term/182 20240723092214 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/182", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "PEXQMEW2WCIQWYYIRAUHLVKHVJGR7H2O", "length": "8907", "offset": "105425196", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518029.81/warc/CC-MAIN-20240723072353-20240723102353-00300.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,mnhn,biodiv)/fr/taxonomy/term/190 20240719224448 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/190", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "NNCUPPD54EHOGDBX6XSW2IRJARNB3HOU", "length": "8957", "offset": "111963925", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00329.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,mnhn,biodiv)/fr/taxonomy/term/247 20240723180128 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/247", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "5JJ5265Y6BKJ3EFHNNDO5PIT6JW75XGO", "length": "8850", "offset": "116773154", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518059.67/warc/CC-MAIN-20240723163815-20240723193815-00242.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,mnhn,biodiv)/fr/taxonomy/term/25/feed 20240719221158 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/25/feed", "mime": "application/rss+xml", "mime-detected": "application/rss+xml", "status": "200", "digest": "5BJF37C3M7RMB4H5PB6TGUX5UU23UZYY", "length": "1089", "offset": "113330648", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00347.warc.gz"}
-fr,mnhn,biodiv)/fr/taxonomy/term/258/feed 20240719210308 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/258/feed", "mime": "application/rss+xml", "mime-detected": "application/rss+xml", "status": "200", "digest": "BHQ645JWFI5MY3TU5MGHUTF6PJGK4KLR", "length": "1049", "offset": "119385775", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00059.warc.gz"}
-fr,mnhn,biodiv)/fr/taxonomy/term/29 20240719220806 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/29", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "6F74DIIJDPXADX3NPLLJGGCJWN33B2JU", "length": "8663", "offset": "111332665", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00298.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,mnhn,biodiv)/fr/taxonomy/term/295 20240719224813 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/295", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "SISPFF2OZDZSBZYJ4DJJLW4HQQ7PALGT", "length": "8937", "offset": "113487891", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00395.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,mnhn,biodiv)/fr/taxonomy/term/372 20240719222307 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/372", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "J5FSMMHHGHBE4Z72OXIEXSZQUP2MJ7PG", "length": "8538", "offset": "112935403", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00391.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,mnhn,biodiv)/fr/taxonomy/term/377 20240719210017 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/377", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "VXDJ35C7SIUWENPXTG5LRHN24E6LUT5B", "length": "8749", "offset": "113454441", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00396.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,mnhn,biodiv)/fr/taxonomy/term/382 20240723093403 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/382", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "TWUAWHFPAW2FMGHZ4T3V4OAODEIHGJT2", "length": "8658", "offset": "108141805", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518029.81/warc/CC-MAIN-20240723072353-20240723102353-00422.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,mnhn,biodiv)/fr/taxonomy/term/430 20240712114115 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/430", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "6FBQEWWZPSQ6YI2LAROTUIK7PTOKKUI4", "length": "8560", "offset": "90166484", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514387.30/warc/CC-MAIN-20240712094214-20240712124214-00326.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,mnhn,biodiv)/fr/taxonomy/term/448 20240723180031 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/448", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "COULGLSXTX7IJFCAGQKP5S4Z7AL5A3OM", "length": "8544", "offset": "116564582", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518059.67/warc/CC-MAIN-20240723163815-20240723193815-00365.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,mnhn,biodiv)/fr/taxonomy/term/492 20240723172943 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/492", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "WFUYM6SMJL3JQZZODYIC5EJ7HERPYEFS", "length": "9014", "offset": "110092666", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518059.67/warc/CC-MAIN-20240723163815-20240723193815-00514.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,mnhn,biodiv)/fr/taxonomy/term/547 20240723171240 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/547", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "FAH4AWWSLQLZDAPBXC32SXM5LQVZ6RNP", "length": "8531", "offset": "111634062", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518059.67/warc/CC-MAIN-20240723163815-20240723193815-00425.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,mnhn,biodiv)/fr/taxonomy/term/548 20240712101216 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/548", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "RTE4QU5YDNZCLYOLZKA3FMUDZONQTITS", "length": "8573", "offset": "88514768", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514387.30/warc/CC-MAIN-20240712094214-20240712124214-00426.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,mnhn,biodiv)/fr/taxonomy/term/557/feed 20240719201257 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/557/feed", "mime": "application/rss+xml", "mime-detected": "application/rss+xml", "status": "200", "digest": "RIEJIECICB7XS2J5MDTMFXDJTDPJFMF4", "length": "1055", "offset": "109941332", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00717.warc.gz"}
-fr,mnhn,biodiv)/fr/taxonomy/term/566 20240719213116 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/566", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "OPGIVQ5Q5ZSQDCLAJJBOOZTUKF6ZQTDN", "length": "8590", "offset": "110959283", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00486.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,mnhn,biodiv)/fr/taxonomy/term/664 20240719204905 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/664", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "PLSFUPZXHOKGOPFOZMUVC6TG5QFIMWUH", "length": "8749", "offset": "113989689", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00545.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,mnhn,biodiv)/fr/taxonomy/term/69 20240719223102 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/69", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "QYEGFD4NRZVR6ILHHRCJ64JEVZRRO7J7", "length": "8778", "offset": "119181746", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00422.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,mnhn,biodiv)/fr/taxonomy/term/731/feed 20240719221243 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/731/feed", "mime": "application/rss+xml", "mime-detected": "application/rss+xml", "status": "200", "digest": "US523WAQAOABYKOO6UONEFQUV2KDEP3S", "length": "3416", "offset": "117494461", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00271.warc.gz"}
-fr,mnhn,biodiv)/fr/taxonomy/term/742 20240723184133 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/742", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "HY5URRLP2KH7RZCSJIAUDTOGJVWGFMPT", "length": "8751", "offset": "102351348", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518059.67/warc/CC-MAIN-20240723163815-20240723193815-00542.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,mnhn,biodiv)/fr/taxonomy/term/753 20240723183300 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/753", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "HKU7SXS5E7RYOSCJEDHNPPMAB33PCJEJ", "length": "8756", "offset": "114241930", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763518059.67/warc/CC-MAIN-20240723163815-20240723193815-00574.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,mnhn,biodiv)/fr/taxonomy/term/759 20240719204536 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/759", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "5YWVB7NFAVL4JC4VHICQIDYGSLAYAFIX", "length": "8764", "offset": "109343145", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00580.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}
-fr,mnhn,biodiv)/fr/taxonomy/term/768 20240719211110 {"url": "https://biodiv.mnhn.fr/fr/taxonomy/term/768", "mime": "text/html", "mime-detected": "text/html", "status": "200", "digest": "RPBB6KTJUDYWEY767YQZN3IGX7JG4BBI", "length": "8763", "offset": "104917490", "filename": "crawl-data/CC-MAIN-2024-30/segments/1720763514928.31/warc/CC-MAIN-20240719200730-20240719230730-00610.warc.gz", "charset": "UTF-8", "languages": "fra,eng"}

From eeb3fbb925a9d80841f5e62c83553db46291a7fb Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Mon, 25 Aug 2025 15:04:41 +0000
Subject: [PATCH 09/74] minor fix

---
 cdx_toolkit/filter_cdx/__init__.py | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/cdx_toolkit/filter_cdx/__init__.py b/cdx_toolkit/filter_cdx/__init__.py
index 9cdc2f4..9811ddc 100644
--- a/cdx_toolkit/filter_cdx/__init__.py
+++ b/cdx_toolkit/filter_cdx/__init__.py
@@ -72,12 +72,14 @@ def run_filter_cdx(args, cmdline: str):
     )
 
     # Process files in parallel or sequentially
+    n_parallel = args.parallel
     total_lines_n = 0
     total_included_n = 0
     
-    if getattr(args, 'parallel', 1) > 1:
+    if n_parallel > 1:
         # Parallel processing
-        with ProcessPoolExecutor(max_workers=args.parallel) as executor:
+        logger.info("Parallel processes: %i", n_parallel)
+        with ProcessPoolExecutor(max_workers=n_parallel) as executor:
             # Create partial function with common arguments
             process_file_partial = partial(
                 _process_single_file,
@@ -104,7 +106,8 @@ def run_filter_cdx(args, cmdline: str):
                 except Exception as exc:
                     logger.error(f"File {input_path} generated an exception: {exc}")
     else:
-        # Sequential processing (original behavior)
+        # Sequential processing
+        logger.info("Sequential processing")
         for input_path, output_path in zip(input_paths, output_paths):
             lines_n, included_n = _process_single_file(
                 input_path, output_path, matcher, args.limit if hasattr(args, 'limit') else 0

From 016c5861da59f73b111551443a95d2821eb7c71a Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Mon, 25 Aug 2025 20:48:37 +0000
Subject: [PATCH 10/74] bug fix

---
 cdx_toolkit/filter_cdx/__init__.py | 35 +++++++++++++++++++++---------
 1 file changed, 25 insertions(+), 10 deletions(-)

diff --git a/cdx_toolkit/filter_cdx/__init__.py b/cdx_toolkit/filter_cdx/__init__.py
index 9811ddc..6aa0999 100644
--- a/cdx_toolkit/filter_cdx/__init__.py
+++ b/cdx_toolkit/filter_cdx/__init__.py
@@ -73,8 +73,10 @@ def run_filter_cdx(args, cmdline: str):
 
     # Process files in parallel or sequentially
     n_parallel = args.parallel
+    limit = 0 if args.limit is None else args.limit
     total_lines_n = 0
     total_included_n = 0
+    total_errors_n = 0
     
     if n_parallel > 1:
         # Parallel processing
@@ -84,7 +86,7 @@ def run_filter_cdx(args, cmdline: str):
             process_file_partial = partial(
                 _process_single_file,
                 matcher=matcher,
-                limit=args.limit if hasattr(args, 'limit') else 0
+                limit=limit
             )
             
             # Submit all jobs
@@ -103,24 +105,32 @@ def run_filter_cdx(args, cmdline: str):
                     )
                     total_lines_n += lines_n
                     total_included_n += included_n
+
                 except Exception as exc:
                     logger.error(f"File {input_path} generated an exception: {exc}")
+                    total_errors_n += 1
     else:
         # Sequential processing
         logger.info("Sequential processing")
         for input_path, output_path in zip(input_paths, output_paths):
-            lines_n, included_n = _process_single_file(
-                input_path, output_path, matcher, args.limit if hasattr(args, 'limit') else 0
-            )
-            logger.info(
-                f"File statistics for {input_path}: included_n={included_n}; lines_n={lines_n}; ratio={included_n/lines_n:.4f}"
-            )
-            total_lines_n += lines_n
-            total_included_n += included_n
+            try:
+                lines_n, included_n = _process_single_file(
+                    input_path, output_path, matcher, limit
+                )
+                logger.info(
+                    f"File statistics for {input_path}: included_n={included_n}; lines_n={lines_n}; ratio={included_n/lines_n:.4f}"
+                )
+                total_lines_n += lines_n
+                total_included_n += included_n
 
+            except Exception as exc:
+                logger.error(f"File {input_path} generated an exception: {exc}")
+                total_errors_n += 1
     logger.info(
         f"Total statistics: included_n={total_included_n}; lines_n={total_lines_n}; ratio={total_included_n/total_lines_n:.4f}"
     )
+    if total_errors_n > 0:
+        logger.error("Processing errors: %i", total_errors_n)
 
     # End timing and log execution time
     end_time = time.time()
@@ -181,7 +191,7 @@ def _process_single_file(input_path, output_path, matcher, limit: int = 0, log_e
                 record_surt = line[:surt_length]
                 lines_n += 1
                 
-                # Use matcher
+                # Use SURT matcher
                 include_record = matcher.matches(record_surt)
                 
                 if include_record:
@@ -195,6 +205,11 @@ def _process_single_file(input_path, output_path, matcher, limit: int = 0, log_e
                 if (i % log_every_n) == 0:
                     logger.info(f"Lines completed: {i:,} (matched: {included_n:,}) from {input_path}")
     
+    # Delete file if empty
+    if included_n == 0:
+        logger.warning("Output file is empty, removing it: %s", output_fs_path)
+        output_fs.rm(output_fs_path)
+
     return lines_n, included_n
 
 

From 44f3b09fae38ac418d9d4080bb94ada5dd659d95 Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Wed, 27 Aug 2025 11:22:34 +0000
Subject: [PATCH 11/74] Adding S3 writter and reader support for WARCs

---
 cdx_toolkit/cli.py                    |   1 +
 cdx_toolkit/utils.py                  |   1 +
 cdx_toolkit/warc.py                   |  48 +++++++---
 cdx_toolkit/warcer_by_cdx/__init__.py |  57 +++++++++---
 cdx_toolkit/warcer_by_cdx/args.py     |   2 -
 examples/iter-and-warc.py             |   2 +
 requirements.txt                      |   1 +
 scripts/cdx_iter                      |   2 +
 setup.py                              |   2 +-
 tests/test_warc_by_cdx.py             |  13 ++-
 tests/test_warc_writer.py             | 125 ++++++++++++++++++++++++++
 tests/unit/test_warc.py               |  34 ++++++-
 12 files changed, 258 insertions(+), 30 deletions(-)
 create mode 100644 tests/test_warc_writer.py

diff --git a/cdx_toolkit/cli.py b/cdx_toolkit/cli.py
index 0ca89db..2c3fa60 100644
--- a/cdx_toolkit/cli.py
+++ b/cdx_toolkit/cli.py
@@ -187,6 +187,7 @@ def warcer(cmd, cmdline):
             LOGGER.warning('revisit record being resolved for url %s %s', url, timestamp)
         writer.write_record(record)
 
+    writer.close()
 
 
 def sizer(cmd, cmdline):
diff --git a/cdx_toolkit/utils.py b/cdx_toolkit/utils.py
index f175d76..55f0d20 100644
--- a/cdx_toolkit/utils.py
+++ b/cdx_toolkit/utils.py
@@ -5,6 +5,7 @@
 
 LOGGER = logging.getLogger(__name__)
 
+
 def get_version():
     return cdx_toolkit.__version__
 
diff --git a/cdx_toolkit/warc.py b/cdx_toolkit/warc.py
index ac8435e..391e755 100644
--- a/cdx_toolkit/warc.py
+++ b/cdx_toolkit/warc.py
@@ -5,6 +5,7 @@
 import logging
 import sys
 
+import fsspec
 from warcio import WARCWriter
 from warcio.recordloader import ArcWarcRecordLoader
 from warcio.bufferedreaders import DecompressingBufferedReader
@@ -131,10 +132,19 @@ def fetch_warc_record(capture, warc_download_prefix):
     length = int(capture['length'])
 
     warc_url = warc_download_prefix + '/' + filename
-    headers = {'Range': 'bytes={}-{}'.format(offset, offset+length-1)}
 
-    resp = myrequests_get(warc_url, headers=headers)
-    record_bytes = resp.content
+    if warc_url.startswith("s3:"):
+        # fetch from S3
+        with fsspec.open(warc_url, 'rb') as f:
+            f.seek(offset)
+            record_bytes = f.read(length)
+    else:
+        # fetch over HTTP
+        headers = {'Range': 'bytes={}-{}'.format(offset, offset+length-1)}
+
+        resp = myrequests_get(warc_url, headers=headers)
+        record_bytes = resp.content
+
     stream = DecompressingBufferedReader(BytesIO(record_bytes))
     record = ArcWarcRecordLoader().parse_record_stream(stream)
 
@@ -152,6 +162,9 @@ def fetch_warc_record(capture, warc_download_prefix):
 
 
 class CDXToolkitWARCWriter:
+    """Writer for WARC files. 
+    
+    The fsspec package is used for writting to local or remote file system, e.g., S3."""
     def __init__(self, prefix, subprefix, info, size=1000000000, gzip=True, warc_version=None):
         self.prefix = prefix
         self.subprefix = subprefix
@@ -161,6 +174,9 @@ def __init__(self, prefix, subprefix, info, size=1000000000, gzip=True, warc_ver
         self.warc_version = warc_version
         self.segment = 0
         self.writer = None
+        self.file_handler = None
+        self.file_system, self.file_system_prefix = fsspec.url_to_fs(self.prefix)
+        self._file_context = None
 
     def write_record(self, *args, **kwargs):
         if self.writer is None:
@@ -175,21 +191,21 @@ def write_record(self, *args, **kwargs):
 
         self.writer.write_record(*args, **kwargs)
 
-        fsize = os.fstat(self.fd.fileno()).st_size
-        if fsize > self.size:
-            self.fd.close()
+        # Compare file size of current segment with max. file size
+        if self.file_handler and self.file_handler.tell() > self.size:
+            self._close_current_file()
             self.writer = None
             self.segment += 1
 
     def _unique_warc_filename(self):
         while True:
-            name = self.prefix + '-'
+            name = self.file_system_prefix + '-'
             if self.subprefix is not None:
                 name += self.subprefix + '-'
             name += '{:06d}'.format(self.segment) + '.extracted.warc'
             if self.gzip:
                 name += '.gz'
-            if os.path.exists(name):
+            if self.file_system.exists(name):
                 self.segment += 1
             else:
                 break
@@ -197,12 +213,24 @@ def _unique_warc_filename(self):
 
     def _start_new_warc(self):
         self.filename = self._unique_warc_filename()
-        self.fd = open(self.filename, 'wb')
+        self._file_context = self.file_system.open(self.filename, 'wb')
+        self.file_handler = self._file_context.__enter__()
         LOGGER.info('opening new warc file %s', self.filename)
-        self.writer = WARCWriter(self.fd, gzip=self.gzip, warc_version=self.warc_version)
+        self.writer = WARCWriter(self.file_handler, gzip=self.gzip, warc_version=self.warc_version)
         warcinfo = self.writer.create_warcinfo_record(self.filename, self.info)
         self.writer.write_record(warcinfo)
 
+    def _close_current_file(self):
+        # Close the handler of the current file (needed for fsspec abstraction)
+        if self._file_context is not None:
+            self._file_context.__exit__(None, None, None)
+            self._file_context = None
+            self.file_handler = None
+
+    def close(self):
+        # Close the WARC writer (this must be called at the end)
+        self._close_current_file()
+
 
 def get_writer(prefix, subprefix, info, **kwargs):
     return CDXToolkitWARCWriter(prefix, subprefix, info, **kwargs)
diff --git a/cdx_toolkit/warcer_by_cdx/__init__.py b/cdx_toolkit/warcer_by_cdx/__init__.py
index dc20273..99ca870 100644
--- a/cdx_toolkit/warcer_by_cdx/__init__.py
+++ b/cdx_toolkit/warcer_by_cdx/__init__.py
@@ -1,6 +1,7 @@
 from io import BytesIO
 import json
 import logging
+import os
 from pathlib import Path
 import sys
 from typing import Iterable
@@ -8,6 +9,7 @@
 import fsspec
 
 
+from tqdm import tqdm
 from warcio import WARCWriter
 from warcio.recordloader import ArcWarcRecord
 
@@ -51,18 +53,30 @@ def run_warcer_by_cdx(args, cmdline):
         kwargs_writer["size"] = kwargs["size"]
         del kwargs["size"]
 
+    log_every_n = 10_000
+    limit = 0 if args.limit is None else args.limit
+    prefix_path = Path(args.prefix)
+
+    # make sure the base dir exists
+    os.makedirs(prefix_path.parent, exist_ok=True)
+
     writer = cdx_toolkit.warc.get_writer(
-        args.prefix, args.subprefix, info, **kwargs_writer
+        str(prefix_path), args.subprefix, info, **kwargs_writer
     )
 
     # Prepare index paths
+    index_fs, index_fs_path = fsspec.url_to_fs(args.index_path)
+
     if args.index_glob is None:
         # Read from a single index
         index_paths = [args.index_path]
     else:
         # Fetch multiple indicies via glob
-        index_fs, index_fs_path = fsspec.url_to_fs(args.index_path)
-        index_paths = sorted(index_fs.glob(args.index_glob))
+        full_glob = index_fs_path + args.index_glob
+
+        logger.info("glob pattern from %s (%s)", full_glob, index_fs.protocol)
+
+        index_paths = sorted(index_fs.glob(full_glob))
 
         logger.info(
             "glob pattern found %i index files in %s", len(index_paths), index_fs_path
@@ -75,15 +89,21 @@ def run_warcer_by_cdx(args, cmdline):
     # Iterate over index files
     records_n = 0
     for index_path in index_paths:
-        logger.info("filtering based on index from %s", index_path)
+        logger.info("filtering based on index from %s (%s)", index_path, index_fs.protocol)
 
         # Read index completely (for the WARC resource record)
-        index = get_index_from_path(index_path)
+        index = get_index_from_path(index_path, index_fs=index_fs)
+
+        if not index:
+            # skip empty indicies
+            continue
 
         # Write index as record to WARC
         # TODO at what position should the resource records be written?
         writer.write_record(get_index_record(index, index_path))
 
+        logger.info("index resource recorded added")
+
         # The index file holds all the information to download specific objects (file, offset, length etc.)
         for obj in generate_caputure_objects_from_index(
             index=index, warc_download_prefix=cdx.warc_download_prefix
@@ -105,22 +125,30 @@ def run_warcer_by_cdx(args, cmdline):
             writer.write_record(record)
             records_n += 1
 
-            if args.limit > 0 and records_n >= args.limit:
-                logger.info("Limit reached at %i", args.limit)
+            if (records_n % log_every_n) == 0:
+                logger.info(f"Records completed: {records_n:,} from {index_path}")
+
+            if limit > 0 and records_n >= limit:
+                logger.info("Limit reached at %i", limit)
                 break
 
-        if args.limit > 0 and records_n >= args.limit:
+        if limit > 0 and records_n >= limit:
             # stop index loop
             break
 
         logger.info("Filtering completed (index file: %s)", index_path)
 
+    writer.close()
+
     logger.info("WARC records extracted: %i", records_n)
 
 
-def get_index_from_path(index_path: str | Path) -> str:
+def get_index_from_path(index_path: str | Path, index_fs: None | fsspec.AbstractFileSystem = None) -> str:
     """Fetch (and decompress) index content as string from local or remote path."""
-    index_fs, index_fs_path = fsspec.url_to_fs(index_path)
+    if index_fs is None:
+        index_fs, index_fs_path = fsspec.url_to_fs(index_path)
+    else:
+        index_fs_path = index_path
 
     compression = "gzip" if index_fs_path.endswith(".gz") else None
 
@@ -143,10 +171,15 @@ def get_index_record(
 
 
 def generate_caputure_objects_from_index(
-    index: str, warc_download_prefix=None, limit: int = 0
+    index: str, warc_download_prefix=None, limit: int = 0, progress_bar: bool = True
 ) -> Iterable[cdx_toolkit.CaptureObject]:
     """Read CDX index and generate CaptureObject objects."""
-    for i, line in enumerate(index.splitlines(), 1):
+    index_lines = index.splitlines()
+
+    # if progress_bar:
+    #     index_lines = tqdm(index_lines, desc="Extracting from WARC", total=len(index_lines))
+
+    for i, line in enumerate(tqdm(index_lines, desc="Extracting from WARC", total=len(index_lines)), 1):
         cols = line.split(" ", maxsplit=2)
 
         if len(cols) == 3:
diff --git a/cdx_toolkit/warcer_by_cdx/args.py b/cdx_toolkit/warcer_by_cdx/args.py
index 3c9368f..5534a07 100644
--- a/cdx_toolkit/warcer_by_cdx/args.py
+++ b/cdx_toolkit/warcer_by_cdx/args.py
@@ -1,5 +1,3 @@
-import os
-import sys
 import logging
 import argparse
 
diff --git a/examples/iter-and-warc.py b/examples/iter-and-warc.py
index 73ea3dd..b346d3f 100755
--- a/examples/iter-and-warc.py
+++ b/examples/iter-and-warc.py
@@ -32,3 +32,5 @@
     writer.write_record(record)
 
     print(' wrote', url)
+
+writer.close()
\ No newline at end of file
diff --git a/requirements.txt b/requirements.txt
index f958c0d..e6d8a91 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -5,6 +5,7 @@ requests==2.25.1
 warcio==1.7.4
 fsspec[s3]
 surt>=0.3.1
+tqdm>=4.67.1
 
 # used by Makefile
 pytest==6.2.4
diff --git a/scripts/cdx_iter b/scripts/cdx_iter
index 8b0c5a3..99445c0 100644
--- a/scripts/cdx_iter
+++ b/scripts/cdx_iter
@@ -143,6 +143,8 @@ elif args.warc:
         if obj.is_revisit():
             LOGGER.warning('revisit record being resolved for url %s %s', url, timestamp)
         writer.write_record(record)
+
+    writer.close()
 else:
     for obj in cdx.iter(args.url, **kwargs):
         printme = winnow_fields(obj)
diff --git a/setup.py b/setup.py
index 38d5c61..3eab3d2 100755
--- a/setup.py
+++ b/setup.py
@@ -8,7 +8,7 @@
 packages = find_packages(include=['cdx_toolkit*'])
 
 # remember: keep requires synchronized with requirements.txt
-requires = ['requests', 'warcio', 'fsspec[s3]', 'surt']
+requires = ['requests', 'warcio', 'fsspec[s3]', 'surt', 'tqdm']
 
 test_requirements = ['pytest', 'pytest-cov', 'boto3']
 
diff --git a/tests/test_warc_by_cdx.py b/tests/test_warc_by_cdx.py
index b405809..db00920 100644
--- a/tests/test_warc_by_cdx.py
+++ b/tests/test_warc_by_cdx.py
@@ -12,12 +12,12 @@
 fixture_path = Path(__file__).parent / "data/warc_by_cdx"
 
 
-def test_cli_warc_by_cdx(tmpdir, caplog):
+def assert_cli_warc_by_cdx(warc_download_prefix, tmpdir, caplog):
     # test cli and check output
     index_path = fixture_path / "filtered_CC-MAIN-2024-30_cdx-00187.gz"
 
     main(
-        args=f"""-v --cc --cc-mirror https://index.commoncrawl.org/ --limit 10  warc_by_cdx {str(index_path)} --prefix {str(tmpdir)}/TEST_warc_by_index --creator foo --operator bob""".split()
+        args=f"""-v --cc --limit 10  warc_by_cdx {str(index_path)} --prefix {str(tmpdir)}/TEST_warc_by_index --creator foo --operator bob --warc-download-prefix {warc_download_prefix}""".split()
     )
 
     # Check log
@@ -48,6 +48,15 @@ def test_cli_warc_by_cdx(tmpdir, caplog):
     assert "operator: bob" in info_record
 
 
+def test_cli_warc_by_cdx_over_http(tmpdir, caplog):
+    assert_cli_warc_by_cdx("https://data.commoncrawl.org", tmpdir, caplog)
+
+
+def test_cli_warc_by_cdx_over_s3(tmpdir, caplog):
+    assert_cli_warc_by_cdx("s3://commoncrawl", tmpdir, caplog)
+
+
+
 def test_get_caputure_objects_from_index():
     index_path = fixture_path / "filtered_CC-MAIN-2024-30_cdx-00187.gz"
 
diff --git a/tests/test_warc_writer.py b/tests/test_warc_writer.py
new file mode 100644
index 0000000..78cbaee
--- /dev/null
+++ b/tests/test_warc_writer.py
@@ -0,0 +1,125 @@
+from io import BytesIO
+import os
+import fsspec
+import pytest
+import cdx_toolkit
+
+from conftest import requires_aws_s3
+
+from warcio import WARCWriter
+from warcio.recordloader import ArcWarcRecord
+from warcio.archiveiterator import ArchiveIterator
+
+@pytest.mark.parametrize(
+    "prefix,gzip",
+    [
+        pytest.param("test-prefix", False, id="File name prefix on local"),
+        pytest.param("test-prefix", True, id="File name prefix on local with gzip"),
+        
+        # pytest.param("test-prefix-folder/file-prefix", None, id="Folder as prefix"),  # raised FileNotFound error (parent dir does not exist)
+    ],
+)
+def test_write_to_local(prefix, gzip, tmpdir):
+    info = {
+        'software': 'pypi_cdx_toolkit/test',
+        'description': 'test',
+        'format': 'WARC file version 1.0', 
+    }
+    encoding = "utf-8"
+    full_prefix = str(tmpdir) + "/" + prefix
+    fs, fs_prefix_path = fsspec.url_to_fs(full_prefix)
+
+    writer = cdx_toolkit.warc.get_writer(full_prefix, None, info, gzip=gzip)
+
+    # single record
+    input_resource_record_text = "foo bar text"
+    writer.write_record(WARCWriter(None).create_warc_record(
+            uri="foo/bar", 
+            record_type="resource",
+            payload=BytesIO(input_resource_record_text.encode(encoding)),
+            warc_content_type="text/plain",
+        )
+    )
+    writer.close()
+
+    # Check that WARC file was created
+    warc_path = fs_prefix_path + "-000000.extracted.warc"
+    if gzip:
+        warc_path += ".gz"
+    
+    assert fs.exists(warc_path)
+
+    # Validate that creator/operator are not in warcinfo record
+    info_record = None
+    resource_record = None
+    with open(warc_path, 'rb') as stream:
+        for record in ArchiveIterator(stream):
+            if record.rec_type == 'warcinfo':
+                info_record = record.content_stream().read().decode(encoding)
+                
+            if record.rec_type == 'resource':
+                resource_record = record.content_stream().read().decode(encoding)
+                break
+
+    assert resource_record is not None
+    assert info_record is not None
+
+    assert "description: test" in info_record
+    assert resource_record == input_resource_record_text
+
+
+@requires_aws_s3
+@pytest.mark.parametrize(
+    "prefix",
+    [
+        pytest.param("s3://commoncrawl-dev/cdx_toolkit/ci/test-outputs", id="S3 prefix"),
+    ],
+)
+def test_write_to_s3(prefix, tmpdir):
+    info = {
+        'software': 'pypi_cdx_toolkit/test',
+        'description': 'test',
+        'format': 'WARC file version 1.0', 
+    }
+    encoding = "utf-8"
+    full_prefix = prefix + str(tmpdir)  # append tmp dir on S3
+    fs, fs_prefix_path = fsspec.url_to_fs(full_prefix)
+
+    # remove all existing paths from S3 dir
+    if fs.exists(prefix):
+        fs.rm(prefix, recursive=True)
+
+    writer = cdx_toolkit.warc.get_writer(full_prefix, None, info)
+
+    # single record
+    input_resource_record_text = "foo bar text"
+    writer.write_record(WARCWriter(None).create_warc_record(
+            uri="foo/bar", 
+            record_type="resource",
+            payload=BytesIO(input_resource_record_text.encode(encoding)),
+            warc_content_type="text/plain",
+        )
+    )
+    writer.close()
+
+    # Check that WARC file was created
+    warc_path = fs_prefix_path + "-000000.extracted.warc.gz"
+    assert fs.exists(warc_path)
+
+    # Validate that creator/operator are not in warcinfo record
+    info_record = None
+    resource_record = None
+    with fs.open(warc_path, 'rb') as stream:
+        for record in ArchiveIterator(stream):
+            if record.rec_type == 'warcinfo':
+                info_record = record.content_stream().read().decode(encoding)
+                
+            if record.rec_type == 'resource':
+                resource_record = record.content_stream().read().decode(encoding)
+                break
+
+    assert resource_record is not None
+    assert info_record is not None
+
+    assert "description: test" in info_record
+    assert resource_record == input_resource_record_text
diff --git a/tests/unit/test_warc.py b/tests/unit/test_warc.py
index e5df43f..0c52614 100644
--- a/tests/unit/test_warc.py
+++ b/tests/unit/test_warc.py
@@ -1,7 +1,35 @@
-import cdx_toolkit.warc
-
+from conftest import requires_aws_s3
+from cdx_toolkit.warc import wb_redir_to_original, fetch_warc_record
 
 def test_wb_redir_to_original():
     location = 'https://web.archive.org/web/20110209062054id_/http://commoncrawl.org/'
     ret = 'http://commoncrawl.org/'
-    assert cdx_toolkit.warc.wb_redir_to_original(location) == ret
+    assert wb_redir_to_original(location) == ret
+
+
+def test_fetch_warc_record_from_http():
+    encoding = "utf-8"
+    capture = {'url': 'https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=319', 'mime': 'text/html', 'mime-detected': 'application/xhtml+xml', 'status': '200', 'digest': 'D5K3FUWDRAOMMTJC2CTWV7L2ABFIJ5BP', 'length': '9754', 'offset': '111440525', 'filename': 'crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00337.warc.gz', 'charset': 'UTF-8', 'languages': 'fra', 'timestamp': '20240716153155'}
+    warc_download_prefix = 'https://data.commoncrawl.org'
+
+    record = fetch_warc_record(capture, warc_download_prefix)
+    record_content = record.content_stream().read().decode(encoding, errors="ignore")
+
+    assert record.rec_type == "response"
+    assert record.length == 75825
+    assert "<title>Catalogue en ligne Mission de France</title>" in record_content
+
+
+@requires_aws_s3
+def test_fetch_warc_record_from_s3():
+    encoding = "utf-8"
+    capture = {'url': 'https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=319', 'mime': 'text/html', 'mime-detected': 'application/xhtml+xml', 'status': '200', 'digest': 'D5K3FUWDRAOMMTJC2CTWV7L2ABFIJ5BP', 'length': '9754', 'offset': '111440525', 'filename': 'crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00337.warc.gz', 'charset': 'UTF-8', 'languages': 'fra', 'timestamp': '20240716153155'}
+    warc_download_prefix = 's3://commoncrawl'
+
+    record = fetch_warc_record(capture, warc_download_prefix)
+    record_content = record.content_stream().read().decode(encoding, errors="ignore")
+
+    assert record.rec_type == "response"
+    assert record.length == 75825
+    assert "<title>Catalogue en ligne Mission de France</title>" in record_content
+

From 5f8d9e0c358b088c12e84e1f001d10af99d57d92 Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Wed, 27 Aug 2025 11:29:46 +0000
Subject: [PATCH 12/74] added comment on CDX format

---
 cdx_toolkit/warcer_by_cdx/__init__.py | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/cdx_toolkit/warcer_by_cdx/__init__.py b/cdx_toolkit/warcer_by_cdx/__init__.py
index 99ca870..756ec0a 100644
--- a/cdx_toolkit/warcer_by_cdx/__init__.py
+++ b/cdx_toolkit/warcer_by_cdx/__init__.py
@@ -185,6 +185,10 @@ def generate_caputure_objects_from_index(
         if len(cols) == 3:
             # TODO can there be a different format?
             # surt, timestamp, json_data = cols
+            # 
+            # CC seems to not follow the specification from https://iipc.github.io/warc-specifications/specifications/cdx-format/cdx-2015/
+            # > The default first line of a CDX file is:
+            # > CDX A b e a m s c k r V v D d g M n
             data = json.loads(cols[2])
             data["timestamp"] = cols[1]
         else:

From c53562f8779ca34e08352733d158e88d629d6953 Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Wed, 27 Aug 2025 12:22:38 +0000
Subject: [PATCH 13/74] Making index record optional, fixing prefix S3 handling

---
 cdx_toolkit/warcer_by_cdx/__init__.py | 17 +++++++++++------
 cdx_toolkit/warcer_by_cdx/args.py     |  5 +++++
 tests/test_warc_by_cdx.py             | 23 ++++++++++++++++-------
 3 files changed, 32 insertions(+), 13 deletions(-)

diff --git a/cdx_toolkit/warcer_by_cdx/__init__.py b/cdx_toolkit/warcer_by_cdx/__init__.py
index 756ec0a..b340bb9 100644
--- a/cdx_toolkit/warcer_by_cdx/__init__.py
+++ b/cdx_toolkit/warcer_by_cdx/__init__.py
@@ -33,6 +33,7 @@ def run_warcer_by_cdx(args, cmdline):
     """
     cdx, kwargs = setup(args)
 
+    write_index_as_record = args.write_index_as_record
     ispartof = args.prefix
     if args.subprefix:
         ispartof += "-" + args.subprefix
@@ -55,10 +56,11 @@ def run_warcer_by_cdx(args, cmdline):
 
     log_every_n = 10_000
     limit = 0 if args.limit is None else args.limit
-    prefix_path = Path(args.prefix)
-
+    prefix_path = str(args.prefix)
+    prefix_fs, prefix_fs_path =  fsspec.url_to_fs(prefix_path)
+    
     # make sure the base dir exists
-    os.makedirs(prefix_path.parent, exist_ok=True)
+    prefix_fs.makedirs(prefix_fs._parent(prefix_fs_path), exist_ok=True)
 
     writer = cdx_toolkit.warc.get_writer(
         str(prefix_path), args.subprefix, info, **kwargs_writer
@@ -89,7 +91,7 @@ def run_warcer_by_cdx(args, cmdline):
     # Iterate over index files
     records_n = 0
     for index_path in index_paths:
-        logger.info("filtering based on index from %s (%s)", index_path, index_fs.protocol)
+        logger.info("filtering based on CDX from %s (%s)", index_path, index_fs.protocol)
 
         # Read index completely (for the WARC resource record)
         index = get_index_from_path(index_path, index_fs=index_fs)
@@ -100,9 +102,11 @@ def run_warcer_by_cdx(args, cmdline):
 
         # Write index as record to WARC
         # TODO at what position should the resource records be written?
-        writer.write_record(get_index_record(index, index_path))
+        if write_index_as_record:
+            logger.info("Writing CDX as resource record to WARC ... ")
+            writer.write_record(get_index_record(index, index_path))
 
-        logger.info("index resource recorded added")
+            logger.info("CDX resource recorded added")
 
         # The index file holds all the information to download specific objects (file, offset, length etc.)
         for obj in generate_caputure_objects_from_index(
@@ -145,6 +149,7 @@ def run_warcer_by_cdx(args, cmdline):
 
 def get_index_from_path(index_path: str | Path, index_fs: None | fsspec.AbstractFileSystem = None) -> str:
     """Fetch (and decompress) index content as string from local or remote path."""
+    logger.info("Fetching index from %s ...", index_path)
     if index_fs is None:
         index_fs, index_fs_path = fsspec.url_to_fs(index_path)
     else:
diff --git a/cdx_toolkit/warcer_by_cdx/args.py b/cdx_toolkit/warcer_by_cdx/args.py
index 5534a07..6d33543 100644
--- a/cdx_toolkit/warcer_by_cdx/args.py
+++ b/cdx_toolkit/warcer_by_cdx/args.py
@@ -41,5 +41,10 @@ def add_warcer_by_cdx_args(parser: argparse.ArgumentParser):
         action="store",
         help="prefix for downloading content, automatically set for CC",
     )
+    parser.add_argument(
+        "--write-index-as-record",
+        action="store_true",
+        help="If enable, the CDX index is written as resource record to the WARC file",
+    )
 
     return parser
diff --git a/tests/test_warc_by_cdx.py b/tests/test_warc_by_cdx.py
index db00920..795b7ad 100644
--- a/tests/test_warc_by_cdx.py
+++ b/tests/test_warc_by_cdx.py
@@ -1,5 +1,7 @@
 import os
 from pathlib import Path
+
+import fsspec
 from cdx_toolkit.cli import main
 from cdx_toolkit.warcer_by_cdx import (
     generate_caputure_objects_from_index,
@@ -8,28 +10,31 @@
 import pytest
 from warcio.archiveiterator import ArchiveIterator
 
+from conftest import requires_aws_s3
+
 
 fixture_path = Path(__file__).parent / "data/warc_by_cdx"
 
 
-def assert_cli_warc_by_cdx(warc_download_prefix, tmpdir, caplog):
+def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog):
     # test cli and check output
     index_path = fixture_path / "filtered_CC-MAIN-2024-30_cdx-00187.gz"
 
     main(
-        args=f"""-v --cc --limit 10  warc_by_cdx {str(index_path)} --prefix {str(tmpdir)}/TEST_warc_by_index --creator foo --operator bob --warc-download-prefix {warc_download_prefix}""".split()
+        args=f"""-v --cc --limit 10  warc_by_cdx {str(index_path)} --write-index-as-record --prefix {str(base_prefix)}/TEST_warc_by_index --creator foo --operator bob --warc-download-prefix {warc_download_prefix}""".split()
     )
 
     # Check log
     assert "Limit reached" in caplog.text
 
     # Validate extracted WARC
-    warc_path = os.path.join(tmpdir, "TEST_warc_by_index-000000.extracted.warc.gz")
+    warc_filename = "TEST_warc_by_index-000000.extracted.warc.gz"
+    warc_path = base_prefix + "/" + warc_filename
     resource_record = None
     info_record = None
     response_records = []
 
-    with open(warc_path, 'rb') as stream:
+    with fsspec.open(warc_path, 'rb') as stream:
         for record in ArchiveIterator(stream):
             if record.rec_type == 'warcinfo':
                 info_record = record.content_stream().read().decode("utf-8")
@@ -49,11 +54,15 @@ def assert_cli_warc_by_cdx(warc_download_prefix, tmpdir, caplog):
 
 
 def test_cli_warc_by_cdx_over_http(tmpdir, caplog):
-    assert_cli_warc_by_cdx("https://data.commoncrawl.org", tmpdir, caplog)
-
+    assert_cli_warc_by_cdx("https://data.commoncrawl.org", base_prefix=tmpdir, caplog=caplog)
 
+@requires_aws_s3
 def test_cli_warc_by_cdx_over_s3(tmpdir, caplog):
-    assert_cli_warc_by_cdx("s3://commoncrawl", tmpdir, caplog)
+    assert_cli_warc_by_cdx("s3://commoncrawl", base_prefix=tmpdir, caplog=caplog)
+
+@requires_aws_s3
+def test_cli_warc_by_cdx_over_s3_to_s3(tmpdir, caplog):
+    assert_cli_warc_by_cdx("s3://commoncrawl", base_prefix="s3://commoncrawl-dev/cdx_toolkit/ci/test-outputs" + str(tmpdir), caplog=caplog)
 
 
 

From b48b191b6076179da151df42836e9b30e384aa58 Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Wed, 27 Aug 2025 13:19:34 +0000
Subject: [PATCH 14/74] adding --parallel for warc by cdx command

---
 cdx_toolkit/warcer_by_cdx/__init__.py | 89 ++++++++++++++++++---------
 cdx_toolkit/warcer_by_cdx/args.py     |  7 ++-
 tests/test_warc_by_cdx.py             |  9 ++-
 3 files changed, 73 insertions(+), 32 deletions(-)

diff --git a/cdx_toolkit/warcer_by_cdx/__init__.py b/cdx_toolkit/warcer_by_cdx/__init__.py
index b340bb9..ccccad1 100644
--- a/cdx_toolkit/warcer_by_cdx/__init__.py
+++ b/cdx_toolkit/warcer_by_cdx/__init__.py
@@ -7,6 +7,8 @@
 from typing import Iterable
 
 import fsspec
+from concurrent.futures import ThreadPoolExecutor, as_completed
+    
 
 
 from tqdm import tqdm
@@ -54,6 +56,7 @@ def run_warcer_by_cdx(args, cmdline):
         kwargs_writer["size"] = kwargs["size"]
         del kwargs["size"]
 
+    n_parallel = args.parallel
     log_every_n = 10_000
     limit = 0 if args.limit is None else args.limit
     prefix_path = str(args.prefix)
@@ -109,35 +112,18 @@ def run_warcer_by_cdx(args, cmdline):
             logger.info("CDX resource recorded added")
 
         # The index file holds all the information to download specific objects (file, offset, length etc.)
-        for obj in generate_caputure_objects_from_index(
-            index=index, warc_download_prefix=cdx.warc_download_prefix
+        for record in fetch_records_from_index(
+            index=index, warc_download_prefix=cdx.warc_download_prefix, n_parallel=n_parallel, limit=limit - records_n,
         ):
-            url = obj["url"]
-            timestamp = obj["timestamp"]
-
-            try:
-                record = obj.fetch_warc_record()
-            except RuntimeError:  # pragma: no cover
-                logger.warning(
-                    "skipping capture for RuntimeError 404: %s %s", url, timestamp
-                )
-                continue
-            if obj.is_revisit():
-                logger.warning(
-                    "revisit record being resolved for url %s %s", url, timestamp
-                )
             writer.write_record(record)
             records_n += 1
 
             if (records_n % log_every_n) == 0:
-                logger.info(f"Records completed: {records_n:,} from {index_path}")
-
-            if limit > 0 and records_n >= limit:
-                logger.info("Limit reached at %i", limit)
-                break
+                logger.info(f"Record progress: {records_n:,} from {index_path}")
 
         if limit > 0 and records_n >= limit:
             # stop index loop
+            logger.info("Limit reached")
             break
 
         logger.info("Filtering completed (index file: %s)", index_path)
@@ -174,17 +160,67 @@ def get_index_record(
         warc_headers_dict=None,  # TODO should we add some other metadata headers?
     )
 
+def fetch_single_record(obj):
+    """Fetch a single WARC record with error handling."""
+    url = obj["url"]
+    timestamp = obj["timestamp"]
+
+    try:
+        record = obj.fetch_warc_record()
+        if obj.is_revisit():
+            logger.warning(
+                "revisit record being resolved for url %s %s", url, timestamp
+            )
+        return record
+    except RuntimeError:  # pragma: no cover
+        logger.warning(
+            "skipping capture for RuntimeError 404: %s %s", url, timestamp
+        )
+        return None
+    
+def fetch_records_from_index(
+    index: str, warc_download_prefix=None, limit: int = 0, n_parallel: int = 1
+) -> Iterable[ArcWarcRecord]:
+    """Fetch WARC records based on CDX index."""
+    
+    if n_parallel <= 1:
+        # Sequential processing
+        for obj in generate_caputure_objects_from_index(
+            index=index, warc_download_prefix=warc_download_prefix, limit=limit,
+        ):
+            record = fetch_single_record(obj)
+            if record is not None:
+                yield record
+    else:
+        # Parallel processing
+        logger.info(f"Fetch records in parallel with {n_parallel=}")
+        objects = list(generate_caputure_objects_from_index(
+            index=index, warc_download_prefix=warc_download_prefix, limit=limit,
+        ))
+        
+        with ThreadPoolExecutor(max_workers=n_parallel) as executor:
+            # Submit all tasks
+            future_to_obj = {executor.submit(fetch_single_record, obj): obj for obj in objects}
+            
+            # Yield results as they complete
+            for future in as_completed(future_to_obj):
+                record = future.result()
+                if record is not None:
+                    yield record
 
 def generate_caputure_objects_from_index(
-    index: str, warc_download_prefix=None, limit: int = 0, progress_bar: bool = True
+    index: str, warc_download_prefix=None, limit: int = 0, progress_bar: bool = False
 ) -> Iterable[cdx_toolkit.CaptureObject]:
     """Read CDX index and generate CaptureObject objects."""
     index_lines = index.splitlines()
 
-    # if progress_bar:
-    #     index_lines = tqdm(index_lines, desc="Extracting from WARC", total=len(index_lines))
+    if limit > 0:
+        index_lines = index_lines[:limit]
 
-    for i, line in enumerate(tqdm(index_lines, desc="Extracting from WARC", total=len(index_lines)), 1):
+    if progress_bar:
+        index_lines = tqdm(index_lines, desc="Extracting from WARC", total=len(index_lines))
+
+    for i, line in enumerate(index_lines, 1):
         cols = line.split(" ", maxsplit=2)
 
         if len(cols) == 3:
@@ -202,6 +238,3 @@ def generate_caputure_objects_from_index(
         yield cdx_toolkit.CaptureObject(
             data=data, wb=None, warc_download_prefix=warc_download_prefix
         )
-
-        if limit > 0 and i >= limit:
-            break
diff --git a/cdx_toolkit/warcer_by_cdx/args.py b/cdx_toolkit/warcer_by_cdx/args.py
index 6d33543..e64d157 100644
--- a/cdx_toolkit/warcer_by_cdx/args.py
+++ b/cdx_toolkit/warcer_by_cdx/args.py
@@ -46,5 +46,10 @@ def add_warcer_by_cdx_args(parser: argparse.ArgumentParser):
         action="store_true",
         help="If enable, the CDX index is written as resource record to the WARC file",
     )
-
+    parser.add_argument(
+        "--parallel",
+        type=int,
+        default=1,
+        help="Number of parallel workers for fetchin WARC records (default: 1, sequential processing)",
+    )
     return parser
diff --git a/tests/test_warc_by_cdx.py b/tests/test_warc_by_cdx.py
index 795b7ad..7a1efe4 100644
--- a/tests/test_warc_by_cdx.py
+++ b/tests/test_warc_by_cdx.py
@@ -16,12 +16,12 @@
 fixture_path = Path(__file__).parent / "data/warc_by_cdx"
 
 
-def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog):
+def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog, extra_args=""):
     # test cli and check output
     index_path = fixture_path / "filtered_CC-MAIN-2024-30_cdx-00187.gz"
 
     main(
-        args=f"""-v --cc --limit 10  warc_by_cdx {str(index_path)} --write-index-as-record --prefix {str(base_prefix)}/TEST_warc_by_index --creator foo --operator bob --warc-download-prefix {warc_download_prefix}""".split()
+        args=f"""-v --cc --limit 10  warc_by_cdx {str(index_path)} --write-index-as-record --prefix {str(base_prefix)}/TEST_warc_by_index --creator foo --operator bob --warc-download-prefix {warc_download_prefix} {extra_args}""".split()
     )
 
     # Check log
@@ -29,7 +29,7 @@ def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog):
 
     # Validate extracted WARC
     warc_filename = "TEST_warc_by_index-000000.extracted.warc.gz"
-    warc_path = base_prefix + "/" + warc_filename
+    warc_path = str(base_prefix) + "/" + warc_filename
     resource_record = None
     info_record = None
     response_records = []
@@ -56,6 +56,9 @@ def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog):
 def test_cli_warc_by_cdx_over_http(tmpdir, caplog):
     assert_cli_warc_by_cdx("https://data.commoncrawl.org", base_prefix=tmpdir, caplog=caplog)
 
+def test_cli_warc_by_cdx_over_http_in_parallel(tmpdir, caplog):
+    assert_cli_warc_by_cdx("https://data.commoncrawl.org", base_prefix=tmpdir, caplog=caplog, extra_args=" --parallel 2")
+
 @requires_aws_s3
 def test_cli_warc_by_cdx_over_s3(tmpdir, caplog):
     assert_cli_warc_by_cdx("s3://commoncrawl", base_prefix=tmpdir, caplog=caplog)

From c58c883ff6ec8ba1c4f772567a5f39c3ff0f57d4 Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Wed, 27 Aug 2025 13:29:57 +0000
Subject: [PATCH 15/74] fixed progress bar

---
 cdx_toolkit/warcer_by_cdx/__init__.py | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/cdx_toolkit/warcer_by_cdx/__init__.py b/cdx_toolkit/warcer_by_cdx/__init__.py
index ccccad1..c829180 100644
--- a/cdx_toolkit/warcer_by_cdx/__init__.py
+++ b/cdx_toolkit/warcer_by_cdx/__init__.py
@@ -112,9 +112,15 @@ def run_warcer_by_cdx(args, cmdline):
             logger.info("CDX resource recorded added")
 
         # The index file holds all the information to download specific objects (file, offset, length etc.)
-        for record in fetch_records_from_index(
-            index=index, warc_download_prefix=cdx.warc_download_prefix, n_parallel=n_parallel, limit=limit - records_n,
-        ):
+        index_lines = index.splitlines()
+        index_limit = limit - records_n
+
+        if index_limit > 0:
+            index_lines = index_lines[:index_limit]
+
+        for record in tqdm(fetch_records_from_index(
+            index_lines=index_lines, warc_download_prefix=cdx.warc_download_prefix, n_parallel=n_parallel
+        ), desc="Fetch and write WARC", total=len(index_lines)):
             writer.write_record(record)
             records_n += 1
 
@@ -179,14 +185,14 @@ def fetch_single_record(obj):
         return None
     
 def fetch_records_from_index(
-    index: str, warc_download_prefix=None, limit: int = 0, n_parallel: int = 1
+    index_lines: list[str], warc_download_prefix=None, limit: int = 0, n_parallel: int = 1
 ) -> Iterable[ArcWarcRecord]:
     """Fetch WARC records based on CDX index."""
     
     if n_parallel <= 1:
         # Sequential processing
         for obj in generate_caputure_objects_from_index(
-            index=index, warc_download_prefix=warc_download_prefix, limit=limit,
+            index_lines=index_lines, warc_download_prefix=warc_download_prefix, limit=limit,
         ):
             record = fetch_single_record(obj)
             if record is not None:
@@ -195,7 +201,7 @@ def fetch_records_from_index(
         # Parallel processing
         logger.info(f"Fetch records in parallel with {n_parallel=}")
         objects = list(generate_caputure_objects_from_index(
-            index=index, warc_download_prefix=warc_download_prefix, limit=limit,
+            index_lines=index_lines, warc_download_prefix=warc_download_prefix, limit=limit,
         ))
         
         with ThreadPoolExecutor(max_workers=n_parallel) as executor:
@@ -209,10 +215,9 @@ def fetch_records_from_index(
                     yield record
 
 def generate_caputure_objects_from_index(
-    index: str, warc_download_prefix=None, limit: int = 0, progress_bar: bool = False
+    index_lines: list[str], warc_download_prefix=None, limit: int = 0, progress_bar: bool = False
 ) -> Iterable[cdx_toolkit.CaptureObject]:
     """Read CDX index and generate CaptureObject objects."""
-    index_lines = index.splitlines()
 
     if limit > 0:
         index_lines = index_lines[:limit]

From d1d2c76dac7b3659314e31a79aa635a59b4ba03c Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Wed, 27 Aug 2025 13:41:25 +0000
Subject: [PATCH 16/74] disable progress bar

---
 cdx_toolkit/warcer_by_cdx/__init__.py | 11 ++++++++---
 tests/test_warc_by_cdx.py             |  5 ++++-
 2 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/cdx_toolkit/warcer_by_cdx/__init__.py b/cdx_toolkit/warcer_by_cdx/__init__.py
index c829180..2e69335 100644
--- a/cdx_toolkit/warcer_by_cdx/__init__.py
+++ b/cdx_toolkit/warcer_by_cdx/__init__.py
@@ -57,7 +57,7 @@ def run_warcer_by_cdx(args, cmdline):
         del kwargs["size"]
 
     n_parallel = args.parallel
-    log_every_n = 10_000
+    log_every_n = 5
     limit = 0 if args.limit is None else args.limit
     prefix_path = str(args.prefix)
     prefix_fs, prefix_fs_path =  fsspec.url_to_fs(prefix_path)
@@ -118,9 +118,14 @@ def run_warcer_by_cdx(args, cmdline):
         if index_limit > 0:
             index_lines = index_lines[:index_limit]
 
-        for record in tqdm(fetch_records_from_index(
+        records_gen = fetch_records_from_index(
             index_lines=index_lines, warc_download_prefix=cdx.warc_download_prefix, n_parallel=n_parallel
-        ), desc="Fetch and write WARC", total=len(index_lines)):
+        )
+        # records_gen = tqdm(fetch_records_from_index(
+        #     index_lines=index_lines, warc_download_prefix=cdx.warc_download_prefix, n_parallel=n_parallel
+        # ), desc="Fetch and write WARC", total=len(index_lines))
+
+        for record in records_gen:
             writer.write_record(record)
             records_n += 1
 
diff --git a/tests/test_warc_by_cdx.py b/tests/test_warc_by_cdx.py
index 7a1efe4..baffba5 100644
--- a/tests/test_warc_by_cdx.py
+++ b/tests/test_warc_by_cdx.py
@@ -57,7 +57,7 @@ def test_cli_warc_by_cdx_over_http(tmpdir, caplog):
     assert_cli_warc_by_cdx("https://data.commoncrawl.org", base_prefix=tmpdir, caplog=caplog)
 
 def test_cli_warc_by_cdx_over_http_in_parallel(tmpdir, caplog):
-    assert_cli_warc_by_cdx("https://data.commoncrawl.org", base_prefix=tmpdir, caplog=caplog, extra_args=" --parallel 2")
+    assert_cli_warc_by_cdx("https://data.commoncrawl.org", base_prefix=tmpdir, caplog=caplog, extra_args=" --parallel 3")
 
 @requires_aws_s3
 def test_cli_warc_by_cdx_over_s3(tmpdir, caplog):
@@ -67,6 +67,9 @@ def test_cli_warc_by_cdx_over_s3(tmpdir, caplog):
 def test_cli_warc_by_cdx_over_s3_to_s3(tmpdir, caplog):
     assert_cli_warc_by_cdx("s3://commoncrawl", base_prefix="s3://commoncrawl-dev/cdx_toolkit/ci/test-outputs" + str(tmpdir), caplog=caplog)
 
+@requires_aws_s3
+def test_cli_warc_by_cdx_over_s3_to_s3_in_parallel(tmpdir, caplog):
+    assert_cli_warc_by_cdx("s3://commoncrawl", base_prefix="s3://commoncrawl-dev/cdx_toolkit/ci/test-outputs" + str(tmpdir), caplog=caplog, extra_args=" --parallel 3")
 
 
 def test_get_caputure_objects_from_index():

From 5154e70e59caaa2b922a95ea29a02974a4ed9109 Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Mon, 1 Sep 2025 15:35:21 +0000
Subject: [PATCH 17/74] Added aioboto3 implementation for warcer

---
 cdx_toolkit/warcer_by_cdx/__init__.py        | 240 +++--------
 cdx_toolkit/warcer_by_cdx/aioboto3_utils.py  | 206 ++++++++++
 cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py | 400 +++++++++++++++++++
 cdx_toolkit/warcer_by_cdx/aioboto3_writer.py | 106 +++++
 cdx_toolkit/warcer_by_cdx/args.py            |   3 +
 cdx_toolkit/warcer_by_cdx/cdx_utils.py       |  91 +++++
 cdx_toolkit/warcer_by_cdx/fsspec_warcer.py   | 162 ++++++++
 setup.py                                     |   2 +-
 tests/test_warc_by_cdx.py                    |  12 +-
 tests/test_warc_by_cdx_aioboto3.py           |  93 +++++
 10 files changed, 1130 insertions(+), 185 deletions(-)
 create mode 100644 cdx_toolkit/warcer_by_cdx/aioboto3_utils.py
 create mode 100644 cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py
 create mode 100644 cdx_toolkit/warcer_by_cdx/aioboto3_writer.py
 create mode 100644 cdx_toolkit/warcer_by_cdx/cdx_utils.py
 create mode 100644 cdx_toolkit/warcer_by_cdx/fsspec_warcer.py
 create mode 100644 tests/test_warc_by_cdx_aioboto3.py

diff --git a/cdx_toolkit/warcer_by_cdx/__init__.py b/cdx_toolkit/warcer_by_cdx/__init__.py
index 2e69335..e98a07c 100644
--- a/cdx_toolkit/warcer_by_cdx/__init__.py
+++ b/cdx_toolkit/warcer_by_cdx/__init__.py
@@ -1,22 +1,14 @@
-from io import BytesIO
-import json
 import logging
-import os
-from pathlib import Path
 import sys
-from typing import Iterable
+import time
+from typing import Literal
 
 import fsspec
-from concurrent.futures import ThreadPoolExecutor, as_completed
-    
-
 
-from tqdm import tqdm
-from warcio import WARCWriter
-from warcio.recordloader import ArcWarcRecord
 
-import cdx_toolkit
 from cdx_toolkit.utils import get_version, setup
+from cdx_toolkit.warcer_by_cdx.aioboto3_warcer import filter_warc_by_cdx_via_aioboto3
+from cdx_toolkit.warcer_by_cdx.fsspec_warcer import filter_warc_by_cdx_via_fsspec
 
 
 logger = logging.getLogger(__name__)
@@ -33,8 +25,15 @@ def run_warcer_by_cdx(args, cmdline):
     - Write to new WARC file with metadata including resource record with index.
     - The CDX resource record is written to the WARC directly before for response records that matches to the CDX.
     """
+    logger.info("Filtering WARC files based on CDX")
+
     cdx, kwargs = setup(args)
 
+    # Start timing
+    start_time = time.time()
+
+    implementation = args.implementation
+
     write_index_as_record = args.write_index_as_record
     ispartof = args.prefix
     if args.subprefix:
@@ -51,9 +50,9 @@ def run_warcer_by_cdx(args, cmdline):
     if args.operator:
         info["operator"] = args.operator
 
-    kwargs_writer = {}
+    writer_kwargs = {}
     if "size" in kwargs:
-        kwargs_writer["size"] = kwargs["size"]
+        writer_kwargs["size"] = kwargs["size"]
         del kwargs["size"]
 
     n_parallel = args.parallel
@@ -65,19 +64,58 @@ def run_warcer_by_cdx(args, cmdline):
     # make sure the base dir exists
     prefix_fs.makedirs(prefix_fs._parent(prefix_fs_path), exist_ok=True)
 
-    writer = cdx_toolkit.warc.get_writer(
-        str(prefix_path), args.subprefix, info, **kwargs_writer
+    index_paths = get_index_paths(
+        args.index_path,
+        args.index_glob,
     )
 
-    # Prepare index paths
-    index_fs, index_fs_path = fsspec.url_to_fs(args.index_path)
+    if implementation == "fsspec":
+        records_n = filter_warc_by_cdx_via_fsspec(
+            index_paths=index_paths,
+            prefix_path=prefix_path,
+            writer_info=info,
+            writer_subprefix=args.subprefix,
+            write_index_as_record=write_index_as_record,
+            limit = limit,
+            log_every_n = log_every_n,
+            warc_download_prefix = cdx.warc_download_prefix,
+            n_parallel=n_parallel,
+            writer_kwargs=writer_kwargs,
+        )
+    elif implementation == "aioboto3":
+        records_n = filter_warc_by_cdx_via_aioboto3(
+            index_paths=index_paths,
+            prefix_path=prefix_path,
+            writer_info=info,
+            writer_subprefix=args.subprefix,
+            write_index_as_record=write_index_as_record,
+            limit = limit,
+            log_every_n = log_every_n,
+            warc_download_prefix = cdx.warc_download_prefix,
+            n_parallel=n_parallel,
+            writer_kwargs=writer_kwargs,
+        )
+    else:
+        raise ValueError("Invalid implementation")
+
+    logger.info("WARC records extracted: %i", records_n)
+
+    # End timing and log execution time
+    end_time = time.time()
+    execution_time = end_time - start_time
 
-    if args.index_glob is None:
+    logger.info(f"Script execution time: {execution_time:.3f} seconds")
+
+def get_index_paths(index_path: str, index_glob: str | None = None) -> list[str]:
+    if index_glob is None:
         # Read from a single index
-        index_paths = [args.index_path]
+        index_paths = [index_path]
     else:
+        # Prepare index paths
+        index_fs, index_fs_path = fsspec.url_to_fs(index_path)
+
         # Fetch multiple indicies via glob
-        full_glob = index_fs_path + args.index_glob
+        full_glob = index_fs_path + index_glob
 
         logger.info("glob pattern from %s (%s)", full_glob, index_fs.protocol)
 
@@ -88,163 +126,7 @@ def run_warcer_by_cdx(args, cmdline):
         )
 
         if not index_paths:
-            logger.error("no index files found")
+            logger.error("no index files found via glob")
             sys.exit(1)
 
-    # Iterate over index files
-    records_n = 0
-    for index_path in index_paths:
-        logger.info("filtering based on CDX from %s (%s)", index_path, index_fs.protocol)
-
-        # Read index completely (for the WARC resource record)
-        index = get_index_from_path(index_path, index_fs=index_fs)
-
-        if not index:
-            # skip empty indicies
-            continue
-
-        # Write index as record to WARC
-        # TODO at what position should the resource records be written?
-        if write_index_as_record:
-            logger.info("Writing CDX as resource record to WARC ... ")
-            writer.write_record(get_index_record(index, index_path))
-
-            logger.info("CDX resource recorded added")
-
-        # The index file holds all the information to download specific objects (file, offset, length etc.)
-        index_lines = index.splitlines()
-        index_limit = limit - records_n
-
-        if index_limit > 0:
-            index_lines = index_lines[:index_limit]
-
-        records_gen = fetch_records_from_index(
-            index_lines=index_lines, warc_download_prefix=cdx.warc_download_prefix, n_parallel=n_parallel
-        )
-        # records_gen = tqdm(fetch_records_from_index(
-        #     index_lines=index_lines, warc_download_prefix=cdx.warc_download_prefix, n_parallel=n_parallel
-        # ), desc="Fetch and write WARC", total=len(index_lines))
-
-        for record in records_gen:
-            writer.write_record(record)
-            records_n += 1
-
-            if (records_n % log_every_n) == 0:
-                logger.info(f"Record progress: {records_n:,} from {index_path}")
-
-        if limit > 0 and records_n >= limit:
-            # stop index loop
-            logger.info("Limit reached")
-            break
-
-        logger.info("Filtering completed (index file: %s)", index_path)
-
-    writer.close()
-
-    logger.info("WARC records extracted: %i", records_n)
-
-
-def get_index_from_path(index_path: str | Path, index_fs: None | fsspec.AbstractFileSystem = None) -> str:
-    """Fetch (and decompress) index content as string from local or remote path."""
-    logger.info("Fetching index from %s ...", index_path)
-    if index_fs is None:
-        index_fs, index_fs_path = fsspec.url_to_fs(index_path)
-    else:
-        index_fs_path = index_path
-
-    compression = "gzip" if index_fs_path.endswith(".gz") else None
-
-    with index_fs.open(index_fs_path, "rt", compression=compression) as f:
-        return f.read()
-
-
-def get_index_record(
-    index: str, index_path: str, encoding: str = "utf-8"
-) -> ArcWarcRecord:
-    """Build WARC resource record for index."""
-    return WARCWriter(None).create_warc_record(
-        uri=index_path,  # TODO this could be a local / internal path
-        record_type="resource",
-        payload=BytesIO(index.encode(encoding)),
-        http_headers=None,
-        warc_content_type="application/cdx",
-        warc_headers_dict=None,  # TODO should we add some other metadata headers?
-    )
-
-def fetch_single_record(obj):
-    """Fetch a single WARC record with error handling."""
-    url = obj["url"]
-    timestamp = obj["timestamp"]
-
-    try:
-        record = obj.fetch_warc_record()
-        if obj.is_revisit():
-            logger.warning(
-                "revisit record being resolved for url %s %s", url, timestamp
-            )
-        return record
-    except RuntimeError:  # pragma: no cover
-        logger.warning(
-            "skipping capture for RuntimeError 404: %s %s", url, timestamp
-        )
-        return None
-    
-def fetch_records_from_index(
-    index_lines: list[str], warc_download_prefix=None, limit: int = 0, n_parallel: int = 1
-) -> Iterable[ArcWarcRecord]:
-    """Fetch WARC records based on CDX index."""
-    
-    if n_parallel <= 1:
-        # Sequential processing
-        for obj in generate_caputure_objects_from_index(
-            index_lines=index_lines, warc_download_prefix=warc_download_prefix, limit=limit,
-        ):
-            record = fetch_single_record(obj)
-            if record is not None:
-                yield record
-    else:
-        # Parallel processing
-        logger.info(f"Fetch records in parallel with {n_parallel=}")
-        objects = list(generate_caputure_objects_from_index(
-            index_lines=index_lines, warc_download_prefix=warc_download_prefix, limit=limit,
-        ))
-        
-        with ThreadPoolExecutor(max_workers=n_parallel) as executor:
-            # Submit all tasks
-            future_to_obj = {executor.submit(fetch_single_record, obj): obj for obj in objects}
-            
-            # Yield results as they complete
-            for future in as_completed(future_to_obj):
-                record = future.result()
-                if record is not None:
-                    yield record
-
-def generate_caputure_objects_from_index(
-    index_lines: list[str], warc_download_prefix=None, limit: int = 0, progress_bar: bool = False
-) -> Iterable[cdx_toolkit.CaptureObject]:
-    """Read CDX index and generate CaptureObject objects."""
-
-    if limit > 0:
-        index_lines = index_lines[:limit]
-
-    if progress_bar:
-        index_lines = tqdm(index_lines, desc="Extracting from WARC", total=len(index_lines))
-
-    for i, line in enumerate(index_lines, 1):
-        cols = line.split(" ", maxsplit=2)
-
-        if len(cols) == 3:
-            # TODO can there be a different format?
-            # surt, timestamp, json_data = cols
-            # 
-            # CC seems to not follow the specification from https://iipc.github.io/warc-specifications/specifications/cdx-format/cdx-2015/
-            # > The default first line of a CDX file is:
-            # > CDX A b e a m s c k r V v D d g M n
-            data = json.loads(cols[2])
-            data["timestamp"] = cols[1]
-        else:
-            raise ValueError(f"Cannot parse line: {line}")
-
-        yield cdx_toolkit.CaptureObject(
-            data=data, wb=None, warc_download_prefix=warc_download_prefix
-        )
+    return index_paths
diff --git a/cdx_toolkit/warcer_by_cdx/aioboto3_utils.py b/cdx_toolkit/warcer_by_cdx/aioboto3_utils.py
new file mode 100644
index 0000000..ebc6762
--- /dev/null
+++ b/cdx_toolkit/warcer_by_cdx/aioboto3_utils.py
@@ -0,0 +1,206 @@
+import asyncio
+import logging
+import time
+from dataclasses import dataclass
+
+import logging
+
+from botocore.exceptions import ClientError, EndpointConnectionError
+
+_STOP = object()
+
+logger = logging.getLogger(__name__)
+
+
+@dataclass
+class ThroughputTracker:
+    """Track throughput metrics for fetchers and consumers."""
+
+    start_time: float = 0.0
+    total_bytes: int = 0
+    total_requests: int = 0
+
+    def start(self):
+        self.start_time = time.time()
+
+    def add_bytes(self, bytes_count: int):
+        self.total_bytes += bytes_count
+        self.total_requests += 1
+
+    def get_stats(self) -> dict:
+        elapsed = time.time() - self.start_time
+        if elapsed <= 0:
+            return {
+                "elapsed": 0,
+                "bytes_per_sec": 0,
+                "mb_per_sec": 0,
+                "requests_per_sec": 0,
+            }
+
+        return {
+            "elapsed": elapsed,
+            "total_bytes": self.total_bytes,
+            "total_requests": self.total_requests,
+            "bytes_per_sec": self.total_bytes / elapsed,
+            "mb_per_sec": (self.total_bytes / elapsed) / (1024 * 1024),
+            "requests_per_sec": self.total_requests / elapsed,
+        }
+
+
+@dataclass(frozen=True)
+class RangeJob:
+    bucket: str
+    key: str
+    offset: int
+    length: int
+
+
+@dataclass(frozen=True)
+class RangePayload:
+    job: RangeJob
+    data: bytes
+
+
+def _backoff(attempt: int, base_backoff_seconds: float) -> float:
+    base = base_backoff_seconds * (2 ** (attempt - 1))
+    # jitter ±20%
+    import os as _os
+
+    return max(0.05, base * (0.8 + 0.4 * _os.urandom(1)[0] / 255))
+
+
+def parse_s3_uri(uri: str) -> tuple[str, str]:
+    if not uri.startswith("s3://"):
+        raise ValueError(f"Not an S3 URI: {uri}")
+    rest = uri[5:]
+    i = rest.find("/")
+    if i <= 0 or i == len(rest) - 1:
+        raise ValueError(f"Malformed S3 URI: {uri}")
+    return rest[:i], rest[i + 1 :]
+
+
+async def with_retries(
+    coro_factory, *, op_name: str, max_attempts: int, base_backoff_seconds: float
+):
+    last_exc = None
+    for attempt in range(1, max_attempts + 1):
+        try:
+            return await coro_factory()
+        except (TimeoutError, ClientError, EndpointConnectionError) as exc:
+            last_exc = exc
+            if attempt >= max_attempts:
+                logger.error("%s failed after %d attempts: %r", op_name, attempt, exc)
+                break
+            sleep_s = _backoff(attempt, base_backoff_seconds)
+            logger.warning(
+                "%s failed (attempt %d/%d) – retrying in %.2fs",
+                op_name,
+                attempt,
+                max_attempts,
+                sleep_s,
+            )
+            await asyncio.sleep(sleep_s)
+    raise last_exc
+
+
+async def get_object_stream(
+    s3, bucket: str, key: str, max_attempts: int, base_backoff_seconds: float
+):
+    resp = await with_retries(
+        lambda: s3.get_object(Bucket=bucket, Key=key),
+        op_name=f"get_object {bucket}/{key}",
+        max_attempts=max_attempts,
+        base_backoff_seconds=base_backoff_seconds,
+    )
+    return resp["Body"]
+
+
+async def ranged_get_bytes(
+    s3,
+    bucket: str,
+    key: str,
+    offset: int,
+    length: int,
+    max_attempts: int,
+    base_backoff_seconds: float,
+) -> bytes:
+    end = offset + length - 1  # inclusive
+    resp = await with_retries(
+        lambda: s3.get_object(Bucket=bucket, Key=key, Range=f"bytes={offset}-{end}"),
+        op_name=f"ranged_get {bucket}/{key}[{offset}:{end}]",
+        max_attempts=max_attempts,
+        base_backoff_seconds=base_backoff_seconds,
+    )
+    return await resp["Body"].read()
+
+
+async def mpu_create(
+    s3,
+    bucket: str,
+    key: str,
+    *,
+    content_type: str | None,
+    max_attempts: int,
+    base_backoff_seconds: float,
+):
+    kwargs = {"Bucket": bucket, "Key": key}
+    if content_type:
+        kwargs["ContentType"] = content_type
+    resp = await with_retries(
+        lambda: s3.create_multipart_upload(**kwargs),
+        op_name=f"create_multipart_upload {bucket}/{key}",
+        max_attempts=max_attempts,
+        base_backoff_seconds=base_backoff_seconds,
+    )
+    return resp["UploadId"]
+
+
+async def mpu_upload_part(
+    s3,
+    bucket: str,
+    key: str,
+    upload_id: str,
+    part_number: int,
+    body: bytes,
+    max_attempts: int,
+    base_backoff_seconds: float,
+) -> str:
+    resp = await with_retries(
+        lambda: s3.upload_part(
+            Bucket=bucket,
+            Key=key,
+            UploadId=upload_id,
+            PartNumber=part_number,
+            Body=body,
+        ),
+        op_name=f"upload_part {bucket}/{key}#{part_number}",
+        max_attempts=max_attempts,
+        base_backoff_seconds=base_backoff_seconds,
+    )
+    return resp["ETag"]
+
+
+async def mpu_complete(
+    s3,
+    bucket: str,
+    key: str,
+    upload_id: str,
+    parts: list[dict],
+    max_attempts: int,
+    base_backoff_seconds: float,
+):
+    await with_retries(
+        lambda: s3.complete_multipart_upload(
+            Bucket=bucket, Key=key, UploadId=upload_id, MultipartUpload={"Parts": parts}
+        ),
+        op_name=f"complete_multipart_upload {bucket}/{key}",
+        max_attempts=max_attempts,
+        base_backoff_seconds=base_backoff_seconds,
+    )
+
+
+async def mpu_abort(s3, bucket: str, key: str, upload_id: str):
+    try:
+        await s3.abort_multipart_upload(Bucket=bucket, Key=key, UploadId=upload_id)
+    except Exception:
+        logger.exception("Failed to abort MPU %s on %s/%s", upload_id, bucket, key)
diff --git a/cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py b/cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py
new file mode 100644
index 0000000..f2f21b7
--- /dev/null
+++ b/cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py
@@ -0,0 +1,400 @@
+import asyncio
+from io import BytesIO
+import logging
+
+import asyncio
+import logging
+
+import aioboto3
+from botocore.config import Config
+from warcio import WARCWriter
+
+from cdx_toolkit.warcer_by_cdx.aioboto3_utils import (
+    _STOP,
+    RangeJob,
+    RangePayload,
+    ThroughputTracker,
+    parse_s3_uri,
+    ranged_get_bytes,
+)
+from cdx_toolkit.warcer_by_cdx.aioboto3_writer import ShardWriter
+from cdx_toolkit.warcer_by_cdx.cdx_utils import (
+    read_cdx_index_from_s3,
+)
+
+
+logger = logging.getLogger(__name__)
+
+
+def filter_warc_by_cdx_via_aioboto3(
+    index_paths: list[str],
+    prefix_path: str,
+    writer_info: dict,
+    writer_subprefix: str | None = None,
+    write_index_as_record: bool = False,
+    limit: int = 0,
+    log_every_n: int = 1000,
+    warc_download_prefix: str | None = None,
+    n_parallel: int = 1,
+    writer_kwargs: dict | None = None,
+) -> int:
+
+    try:
+        return asyncio.run(
+            filter_warc_by_cdx_via_aioboto3_async(
+                index_paths=index_paths,
+                prefix_path=prefix_path,
+                writer_info=writer_info,
+                writer_subprefix=writer_subprefix,
+                write_index_as_record=write_index_as_record,
+                limit=limit,
+                log_every_n=log_every_n,
+                warc_download_prefix=warc_download_prefix,
+                writer_kwargs=writer_kwargs,
+                n_parallel=n_parallel,
+            )
+        )
+    except KeyboardInterrupt:
+        logger.warning("Interrupted by user.")
+
+    return -1
+
+
+async def filter_warc_by_cdx_via_aioboto3_async(
+    index_paths: list[str],
+    prefix_path: str,
+    writer_info: dict,
+    writer_subprefix: str | None = None,
+    write_index_as_record: bool = False,
+    limit: int = 0,
+    log_every_n: int = 1000,
+    warc_download_prefix: str | None = None,
+    n_parallel: int = 1,
+    writer_kwargs: dict | None = None,
+    max_attempts: int = 5,
+    key_queue_size: int = 1000,
+    item_queue_size: int = 200,
+    base_backoff_seconds=0.5,
+) -> int:
+    n_records = 0
+    fetcher_to_consumer_ratio = 6
+    num_fetchers = n_parallel
+    num_consumers = max(int(num_fetchers / fetcher_to_consumer_ratio), 1)
+
+    key_queue: asyncio.Queue = asyncio.Queue(maxsize=key_queue_size)
+    item_queue: asyncio.Queue = asyncio.Queue(maxsize=item_queue_size)
+
+    boto_cfg = Config(
+        region_name="us-east-1",
+        retries={"max_attempts": max(2, max_attempts), "mode": "standard"},
+        connect_timeout=10,
+        read_timeout=120,
+    )
+
+    if write_index_as_record:
+        raise NotImplementedError
+
+    session = aioboto3.Session()
+
+    async with session.client("s3", config=boto_cfg) as s3:
+        # Stage 1
+        logger.info(
+            "Starting lister, %d fetchers, %d consumers", num_fetchers, num_consumers
+        )
+        lister_task = asyncio.create_task(
+            lister_from_index(
+                key_queue=key_queue,
+                index_paths=index_paths,
+                warc_download_prefix=warc_download_prefix,
+                num_fetchers=num_fetchers,
+                limit=limit,
+            )
+        )
+
+        # Stage 2
+        fetchers = [
+            asyncio.create_task(
+                fetcher(
+                    fetcher_id=i,
+                    key_queue=key_queue,
+                    item_queue=item_queue,
+                    s3=s3,
+                    max_attempts=max_attempts,
+                    base_backoff_seconds=base_backoff_seconds,
+                    log_every_n=log_every_n,
+                )
+            )
+            for i in range(num_fetchers)
+        ]
+
+        # Stage 3
+        consumers = [
+            asyncio.create_task(
+                consumer(
+                    consumer_id=i,
+                    item_queue=item_queue,
+                    s3=s3,
+                    # shard_name_prefix=shard_name_prefix,
+                    # args.shard_extension,
+                    # args.dest_prefix,
+                    # args.dest_bucket,
+                    # args.content_type,
+                    # min_part_size=,
+                    prefix_path=prefix_path,
+                    max_attempts=max_attempts,
+                    base_backoff_seconds=base_backoff_seconds,
+                    write_index_as_record=write_index_as_record,
+                    writer_info=writer_info,
+                    writer_subprefix=writer_subprefix,
+                    writer_kwargs=writer_kwargs,
+                    log_every_n=log_every_n,
+                    gzip=index_paths[0].endswith(".gz") if index_paths else False,
+                )
+            )
+            for i in range(num_consumers)
+        ]
+
+        await lister_task
+        logger.info("Lister completed, waiting for fetchers to finish")
+
+        await asyncio.gather(*fetchers)
+        logger.info("All fetchers completed")
+
+        # Send stop signals to consumers
+        for _ in range(num_consumers):
+            await item_queue.put(_STOP)
+
+        consumer_results = await asyncio.gather(*consumers)
+        n_records = sum([result["stats"]["total_requests"] for result in consumer_results])
+
+        logger.info("All consumers completed")
+
+    return n_records
+
+
+async def lister_from_index(
+    key_queue: asyncio.Queue,
+    index_paths: list[str],
+    warc_download_prefix: str,
+    num_fetchers: int,
+    limit: int = 0,
+):
+    """Stage 1: stream the index, parse lines -> RangeJob -> key_queue."""
+
+    logger.info("Range index limit: %i", limit)
+    count = 0
+
+    if not index_paths:
+        logger.error("No index paths provided!")
+
+    else:
+
+        # Iterate over index files
+        for index_path in index_paths:
+            # Fetch range queries from index
+            try:
+                for warc_url, offset, length in read_cdx_index_from_s3(
+                    index_path, warc_download_prefix=warc_download_prefix
+                ):
+                    # Convert the CDX record back to a RangeJob
+                    bucket, key = parse_s3_uri(warc_url)
+                    job = RangeJob(bucket=bucket, key=key, offset=offset, length=length)
+                    await key_queue.put(job)
+                    count += 1
+
+                    if limit > 0 and count >= limit:
+                        logger.warning("Index limit reached at %i", count)
+                        break
+
+            except Exception as e:
+                logger.error("Failed to read CDX index from %s: %s", index_path, e)
+
+            if limit > 0 and count >= limit:
+                logger.warning("Limit reached at %i", count)
+                break
+
+    # signal fetchers to stop
+    for _ in range(num_fetchers):
+        await key_queue.put(_STOP)
+
+    logger.info("Lister enqueued %d jobs from %s", count, index_path)
+
+
+async def fetcher(
+    fetcher_id: int,
+    key_queue: asyncio.Queue,
+    item_queue: asyncio.Queue,
+    s3,
+    max_attempts: int,
+    base_backoff_seconds: float,
+    log_every_n: int = 1000,
+):
+    """Stage 2: ranged GET per job -> enqueue RangePayload."""
+    tracker = ThroughputTracker()
+    tracker.start()
+    counter = 0
+
+    while True:
+        job = await key_queue.get()
+        try:
+            if job is _STOP:
+                stats = tracker.get_stats()
+                logger.info(
+                    "Fetcher %d stopping. Stats: %.1fs, %d requests, %.1f MB, "
+                    "%.2f MB/s, %.2f req/s",
+                    fetcher_id,
+                    stats["elapsed"],
+                    stats["total_requests"],
+                    stats["total_bytes"] / (1024 * 1024),
+                    stats["mb_per_sec"],
+                    stats["requests_per_sec"],
+                )
+                break  # Exit loop, but still execute finally block
+            assert isinstance(job, RangeJob)
+            data = await ranged_get_bytes(
+                s3,
+                job.bucket,
+                job.key,
+                job.offset,
+                job.length,
+                max_attempts,
+                base_backoff_seconds,
+            )
+            tracker.add_bytes(len(data))
+            counter += 1
+
+            # Log progress every 10 items
+            if counter % log_every_n == 0:
+                stats = tracker.get_stats()
+                logger.info(
+                    "Fetcher %d: %d items, %.1f MB, %.2f MB/s, %.2f req/s",
+                    fetcher_id,
+                    counter,
+                    stats["total_bytes"] / (1024 * 1024),
+                    stats["mb_per_sec"],
+                    stats["requests_per_sec"],
+                )
+
+            await item_queue.put(RangePayload(job=job, data=data))
+        except Exception:
+            logger.exception(
+                "Fetcher %d failed on %s/%s [%d,%d]",
+                fetcher_id,
+                getattr(job, "bucket", "?"),
+                getattr(job, "key", "?"),
+                getattr(job, "offset", -1),
+                getattr(job, "length", -1),
+            )
+        finally:
+            key_queue.task_done()
+
+
+async def consumer(
+    consumer_id: int,
+    item_queue: asyncio.Queue,
+    s3,
+    # shard_name_prefix: str,
+    # shard_extension: str,
+    # dest_prefix: str,
+    # dest_bucket: str,
+    # content_type: str | None,
+    # min_part_size: int,
+    max_attempts: int,
+    base_backoff_seconds: float,
+    prefix_path: str,
+    writer_info: dict,
+    writer_subprefix: str | None = None,
+    write_index_as_record: bool = False,
+    writer_kwargs: dict | None = None,
+    warc_version: str = "1.0",
+    log_every_n: int = 1000,
+    gzip: bool = False,
+):
+    """Stage 3: each consumer owns ONE shard MPU and appends ranges to it."""
+
+    dest_bucket, dest_prefix = parse_s3_uri(prefix_path)
+
+    min_part_size = 5 * 1024 * 1024  # 5 MiB
+    content_type = None
+
+    file_name = dest_prefix + '-'
+    if writer_subprefix is not None:
+        file_name += writer_subprefix + '-'
+    file_name += '{:06d}'.format(consumer_id) + '.extracted.warc'
+    
+    if gzip:
+        file_name += '.gz'
+        
+    writer = ShardWriter(
+        file_name,
+        dest_bucket,
+        content_type,
+        min_part_size,
+        max_attempts,
+        base_backoff_seconds,
+    )
+    tracker = ThroughputTracker()
+    tracker.start()
+    counter = 0
+
+    # Initialize writer
+    await writer.start(s3)
+
+    # Write WARC header
+    buffer = BytesIO()
+    warc_writer = WARCWriter(buffer, gzip=gzip, warc_version=warc_version)
+    warcinfo = warc_writer.create_warcinfo_record(file_name, writer_info)
+    warc_writer.write_record(warcinfo)
+
+    await writer.write(s3, buffer.getvalue())
+
+    try:
+        while True:
+            item = await item_queue.get()
+            counter += 1
+            try:
+                if item is _STOP:
+                    stats = tracker.get_stats()
+                    logger.info(
+                        "Consumer %d stopping. Stats: %.1fs, %d items, %.1f MB written, "
+                        "%.2f MB/s write speed",
+                        consumer_id,
+                        stats["elapsed"],
+                        stats["total_requests"],
+                        stats["total_bytes"] / (1024 * 1024),
+                        stats["mb_per_sec"],
+                    )
+                    should_stop = True
+                else:
+                    should_stop = False
+                    assert isinstance(item, RangePayload)
+                    await writer.write(s3, item.data)
+                    tracker.add_bytes(len(item.data))
+
+                    # Log progress every 10 items
+                    if counter % log_every_n == 0:
+                        stats = tracker.get_stats()
+                        logger.info(
+                            "Consumer %d: %d items, %.1f MB written, %.2f MB/s",
+                            consumer_id,
+                            counter,
+                            stats["total_bytes"] / (1024 * 1024),
+                            stats["mb_per_sec"],
+                        )
+            except Exception:
+                logger.exception(
+                    "Consumer %d failed on %s", consumer_id, getattr(item, "job", None)
+                )
+                should_stop = False
+            finally:
+                item_queue.task_done()
+
+            if should_stop:
+                break
+    finally:
+        await writer.close(s3)
+
+    return {
+        'consumer_id': consumer_id,
+        'stats': tracker.get_stats()
+    }
diff --git a/cdx_toolkit/warcer_by_cdx/aioboto3_writer.py b/cdx_toolkit/warcer_by_cdx/aioboto3_writer.py
new file mode 100644
index 0000000..1599174
--- /dev/null
+++ b/cdx_toolkit/warcer_by_cdx/aioboto3_writer.py
@@ -0,0 +1,106 @@
+import logging
+
+from cdx_toolkit.warcer_by_cdx.aioboto3_utils import (
+    mpu_abort,
+    mpu_complete,
+    mpu_create,
+    mpu_upload_part,
+)
+
+logger = logging.getLogger(__name__)
+
+
+class ShardWriter:
+    """Manages one MPU: buffers bytes, uploads >=5 MiB parts, completes on close."""
+
+    def __init__(
+        self,
+        shard_key: str,
+        dest_bucket: str,
+        content_type: str | None,
+        min_part_size: int,
+        max_attempts: int,
+        base_backoff_seconds: float,
+    ):
+        self.shard_key = shard_key
+        self.dest_bucket = dest_bucket
+        self.content_type = content_type
+        self.min_part_size = min_part_size
+        self.max_attempts = max_attempts
+        self.base_backoff_seconds = base_backoff_seconds
+        self.upload_id: str | None = None
+        self.part_number = 1
+        self.parts: list[dict] = []
+        self.buffer = bytearray()
+
+    async def start(self, s3):
+        self.upload_id = await mpu_create(
+            s3,
+            self.dest_bucket,
+            self.shard_key,
+            content_type=self.content_type,
+            max_attempts=self.max_attempts,
+            base_backoff_seconds=self.base_backoff_seconds,
+        )
+        logger.info("Started MPU for %s (UploadId=%s)", self.shard_key, self.upload_id)
+
+    async def _flush_full_parts(self, s3):
+        while len(self.buffer) >= self.min_part_size:
+            chunk = self.buffer[: self.min_part_size]
+            del self.buffer[: self.min_part_size]
+            etag = await mpu_upload_part(
+                s3,
+                self.dest_bucket,
+                self.shard_key,
+                self.upload_id,
+                self.part_number,
+                bytes(chunk),
+                self.max_attempts,
+                self.base_backoff_seconds,
+            )
+            self.parts.append({"PartNumber": self.part_number, "ETag": etag})
+            self.part_number += 1
+
+    async def write(self, s3, data: bytes):
+        # self.buffer.extend(transform(data))
+        # TODO write proper WARC record?
+        self.buffer.extend(data)
+        await self._flush_full_parts(s3)
+
+    async def close(self, s3):
+        try:
+            if self.buffer:
+                etag = await mpu_upload_part(
+                    s3,
+                    self.dest_bucket,
+                    self.shard_key,
+                    self.upload_id,
+                    self.part_number,
+                    bytes(self.buffer),
+                    self.max_attempts,
+                    self.base_backoff_seconds,
+                )
+                self.parts.append({"PartNumber": self.part_number, "ETag": etag})
+                self.part_number += 1
+                self.buffer.clear()
+
+            if self.parts:
+                await mpu_complete(
+                    s3,
+                    self.dest_bucket,
+                    self.shard_key,
+                    self.upload_id,
+                    self.parts,
+                    self.max_attempts,
+                    self.base_backoff_seconds,
+                )
+            logger.info(
+                "Completed MPU for %s with %d parts.", self.shard_key, len(self.parts)
+            )
+        except Exception:
+            logger.exception(
+                "Completing MPU failed for %s; attempting abort.", self.shard_key
+            )
+            if self.upload_id:
+                await mpu_abort(s3, self.dest_bucket, self.shard_key, self.upload_id)
+            raise
diff --git a/cdx_toolkit/warcer_by_cdx/args.py b/cdx_toolkit/warcer_by_cdx/args.py
index e64d157..d81b3c1 100644
--- a/cdx_toolkit/warcer_by_cdx/args.py
+++ b/cdx_toolkit/warcer_by_cdx/args.py
@@ -52,4 +52,7 @@ def add_warcer_by_cdx_args(parser: argparse.ArgumentParser):
         default=1,
         help="Number of parallel workers for fetchin WARC records (default: 1, sequential processing)",
     )
+    parser.add_argument(
+        "--implementation", type=str, default="fsspec", help="implementation (fsspec, aioboto3)"
+    )
     return parser
diff --git a/cdx_toolkit/warcer_by_cdx/cdx_utils.py b/cdx_toolkit/warcer_by_cdx/cdx_utils.py
new file mode 100644
index 0000000..869fbe3
--- /dev/null
+++ b/cdx_toolkit/warcer_by_cdx/cdx_utils.py
@@ -0,0 +1,91 @@
+import json
+from pathlib import Path
+
+from io import BytesIO
+from typing import Iterable
+
+import fsspec
+import logging
+
+from warcio import WARCWriter
+from warcio.recordloader import ArcWarcRecord
+
+
+logger = logging.getLogger(__name__)
+
+
+def get_index_as_string_from_path(index_path: str | Path, index_fs: None | fsspec.AbstractFileSystem = None) -> str:
+    """Fetch (and decompress) index content as string from local or remote path."""
+    logger.info("Fetching index from %s ...", index_path)
+    if index_fs is None:
+        index_fs, index_fs_path = fsspec.url_to_fs(index_path)
+    else:
+        index_fs_path = index_path
+
+    compression = "gzip" if index_fs_path.endswith(".gz") else None
+
+    with index_fs.open(index_fs_path, "rt", compression=compression) as f:
+        return f.read()
+
+
+def get_index_record(
+    index: str, index_path: str, encoding: str = "utf-8"
+) -> ArcWarcRecord:
+    """Build WARC resource record for index."""
+    return WARCWriter(None).create_warc_record(
+        uri=index_path,  # TODO this could be a local / internal path
+        record_type="resource",
+        payload=BytesIO(index.encode(encoding)),
+        http_headers=None,
+        warc_content_type="application/cdx",
+        warc_headers_dict=None,  # TODO should we add some other metadata headers?
+    )
+
+
+
+
+def read_cdx_line(line: str, warc_download_prefix: str) -> tuple[str, int, int]:
+    cols = line.split(" ", maxsplit=2)
+
+    if len(cols) == 3:
+        # TODO can there be a different format?
+        # surt, timestamp, json_data = cols
+        #
+        # CC seems to not follow the specification from https://iipc.github.io/warc-specifications/specifications/cdx-format/cdx-2015/
+        # > The default first line of a CDX file is:
+        # > CDX A b e a m s c k r V v D d g M n
+        data = json.loads(cols[2])
+        data["timestamp"] = cols[1]
+    else:
+        raise ValueError(f"Cannot parse line: {line}")
+
+    filename = data["filename"]
+    offset = int(data["offset"])
+    length = int(data["length"])
+
+    warc_url = warc_download_prefix + "/" + filename
+
+    return (warc_url, offset, length)
+
+
+
+def read_cdx_index_from_s3(s3_path: str, warc_download_prefix: str) -> Iterable[tuple[str, int, int]]:
+    """
+    Read CDX records from a gzipped S3 file.
+    """
+    # if not s3_path.startswith("s3://"):
+    #     raise ValueError(f"Invalid S3 path: {s3_path}")
+     
+    logger.info("Reading CDX from %s", s3_path)
+
+    with fsspec.open(s3_path, "rt", compression="gzip" if s3_path.endswith(".gz") else None) as f:
+        for line in f:
+            try:
+                yield read_cdx_line(line, warc_download_prefix)
+            except Exception:
+                # Skip malformed lines
+                logger.error("Invalid CDX line: %s", line)
+                continue
+
+    logger.info(f"CDX completed from %s", s3_path)
+    
\ No newline at end of file
diff --git a/cdx_toolkit/warcer_by_cdx/fsspec_warcer.py b/cdx_toolkit/warcer_by_cdx/fsspec_warcer.py
new file mode 100644
index 0000000..dc3eec1
--- /dev/null
+++ b/cdx_toolkit/warcer_by_cdx/fsspec_warcer.py
@@ -0,0 +1,162 @@
+
+import json
+import logging
+from typing import Iterable
+
+import cdx_toolkit
+from concurrent.futures import ThreadPoolExecutor, as_completed
+
+from warcio.recordloader import ArcWarcRecord
+
+from cdx_toolkit.warcer_by_cdx.cdx_utils import get_index_as_string_from_path, get_index_record
+    
+
+logger = logging.getLogger(__name__)
+
+def filter_warc_by_cdx_via_fsspec(
+        index_paths: list[str],
+        prefix_path: str,
+        writer_info: dict,
+        writer_subprefix: str | None = None,
+        write_index_as_record: bool = False,
+        limit: int = 0,
+        log_every_n: int = 1000,
+        warc_download_prefix: str | None = None,
+        n_parallel: int = 1,
+        writer_kwargs: dict | None = None,
+    ) -> int:
+    
+    writer = cdx_toolkit.warc.get_writer(
+        prefix_path, writer_subprefix, writer_info, **(writer_kwargs if writer_kwargs else {}),
+    )
+
+    # Iterate over index files
+    records_n = 0
+    for index_path in index_paths:
+        logger.info("filtering based on CDX from %s", index_path)
+
+        # Read index completely (for the WARC resource record)
+        index = get_index_as_string_from_path(index_path)
+
+        if not index:
+            # skip empty indicies
+            continue
+
+        # Write index as record to WARC
+        # TODO at what position should the resource records be written?
+        if write_index_as_record:
+            logger.info("Writing CDX as resource record to WARC ... ")
+            writer.write_record(get_index_record(index, index_path))
+
+            logger.info("CDX resource recorded added")
+
+        # The index file holds all the information to download specific objects (file, offset, length etc.)
+        index_lines = index.splitlines()
+        index_limit = limit - records_n
+
+        if index_limit > 0:
+            index_lines = index_lines[:index_limit]
+
+        records_gen = fetch_records_from_index(
+            index_lines=index_lines, warc_download_prefix=warc_download_prefix, n_parallel=n_parallel
+        )
+        # records_gen = tqdm(fetch_records_from_index(
+        #     index_lines=index_lines, warc_download_prefix=cdx.warc_download_prefix, n_parallel=n_parallel
+        # ), desc="Fetch and write WARC", total=len(index_lines))
+
+        for record in records_gen:
+            writer.write_record(record)
+            records_n += 1
+
+            if (records_n % log_every_n) == 0:
+                logger.info(f"Record progress: {records_n:,} from {index_path}")
+
+        if limit > 0 and records_n >= limit:
+            # stop index loop
+            logger.info("Limit reached")
+            break
+
+        logger.info("Filtering completed (index file: %s)", index_path)
+
+    writer.close()
+
+    return records_n
+
+
+def fetch_single_record(obj):
+    """Fetch a single WARC record with error handling."""
+    url = obj["url"]
+    timestamp = obj["timestamp"]
+
+    try:
+        record = obj.fetch_warc_record()
+        if obj.is_revisit():
+            logger.warning(
+                "revisit record being resolved for url %s %s", url, timestamp
+            )
+        return record
+    except RuntimeError:  # pragma: no cover
+        logger.warning(
+            "skipping capture for RuntimeError 404: %s %s", url, timestamp
+        )
+        return None
+    
+def fetch_records_from_index(
+    index_lines: list[str], warc_download_prefix=None, limit: int = 0, n_parallel: int = 1
+) -> Iterable[ArcWarcRecord]:
+    """Fetch WARC records based on CDX index."""
+    
+    if n_parallel <= 1:
+        # Sequential processing
+        for obj in generate_caputure_objects_from_index(
+            index_lines=index_lines, warc_download_prefix=warc_download_prefix, limit=limit,
+        ):
+            record = fetch_single_record(obj)
+            if record is not None:
+                yield record
+    else:
+        # Parallel processing
+        logger.info(f"Fetch records in parallel with {n_parallel=}")
+        objects = list(generate_caputure_objects_from_index(
+            index_lines=index_lines, warc_download_prefix=warc_download_prefix, limit=limit,
+        ))
+        
+        with ThreadPoolExecutor(max_workers=n_parallel) as executor:
+            # Submit all tasks
+            future_to_obj = {executor.submit(fetch_single_record, obj): obj for obj in objects}
+            
+            # Yield results as they complete
+            for future in as_completed(future_to_obj):
+                record = future.result()
+                if record is not None:
+                    yield record
+
+def generate_caputure_objects_from_index(
+    index_lines: list[str], warc_download_prefix=None, limit: int = 0, progress_bar: bool = False
+) -> Iterable[cdx_toolkit.CaptureObject]:
+    """Read CDX index and generate CaptureObject objects."""
+
+    if limit > 0:
+        index_lines = index_lines[:limit]
+
+    # if progress_bar:
+    #     index_lines = tqdm(index_lines, desc="Extracting from WARC", total=len(index_lines))
+
+    for i, line in enumerate(index_lines, 1):
+        cols = line.split(" ", maxsplit=2)
+
+        if len(cols) == 3:
+            # TODO can there be a different format?
+            # surt, timestamp, json_data = cols
+            # 
+            # CC seems to not follow the specification from https://iipc.github.io/warc-specifications/specifications/cdx-format/cdx-2015/
+            # > The default first line of a CDX file is:
+            # > CDX A b e a m s c k r V v D d g M n
+            data = json.loads(cols[2])
+            data["timestamp"] = cols[1]
+        else:
+            raise ValueError(f"Cannot parse line: {line}")
+
+        yield cdx_toolkit.CaptureObject(
+            data=data, wb=None, warc_download_prefix=warc_download_prefix
+        )
diff --git a/setup.py b/setup.py
index 3eab3d2..7d5c205 100755
--- a/setup.py
+++ b/setup.py
@@ -8,7 +8,7 @@
 packages = find_packages(include=['cdx_toolkit*'])
 
 # remember: keep requires synchronized with requirements.txt
-requires = ['requests', 'warcio', 'fsspec[s3]', 'surt', 'tqdm']
+requires = ['requests', 'warcio', 'fsspec[s3]', 'aioboto3', 'surt', 'tqdm']
 
 test_requirements = ['pytest', 'pytest-cov', 'boto3']
 
diff --git a/tests/test_warc_by_cdx.py b/tests/test_warc_by_cdx.py
index baffba5..3ed7b64 100644
--- a/tests/test_warc_by_cdx.py
+++ b/tests/test_warc_by_cdx.py
@@ -3,9 +3,11 @@
 
 import fsspec
 from cdx_toolkit.cli import main
-from cdx_toolkit.warcer_by_cdx import (
+from cdx_toolkit.warcer_by_cdx.cdx_utils import (
+    get_index_as_string_from_path,
+)
+from cdx_toolkit.warcer_by_cdx.fsspec_warcer import (
     generate_caputure_objects_from_index,
-    get_index_from_path,
 )
 import pytest
 from warcio.archiveiterator import ArchiveIterator
@@ -75,7 +77,7 @@ def test_cli_warc_by_cdx_over_s3_to_s3_in_parallel(tmpdir, caplog):
 def test_get_caputure_objects_from_index():
     index_path = fixture_path / "filtered_CC-MAIN-2024-30_cdx-00187.gz"
 
-    for obj in generate_caputure_objects_from_index(get_index_from_path(index_path)):
+    for obj in generate_caputure_objects_from_index(get_index_as_string_from_path(index_path).splitlines()):
         break
 
     assert obj.data["length"] == "9754"
@@ -101,10 +103,10 @@ def test_generate_caputure_objects_invalid_cdx_line():
 def test_generate_caputure_objects_with_limit():
     # Test limit functionality in get_caputure_objects_from_index
     index_path = fixture_path / "filtered_CC-MAIN-2024-30_cdx-00187.gz"
-    index_content = get_index_from_path(index_path)
+    index_content = get_index_as_string_from_path(index_path)
     
     # Count objects with limit=2
-    objects = list(generate_caputure_objects_from_index(index_content, limit=2))
+    objects = list(generate_caputure_objects_from_index(index_content.splitlines(), limit=2))
     
     # Should stop after 2 objects
     assert len(objects) == 2
diff --git a/tests/test_warc_by_cdx_aioboto3.py b/tests/test_warc_by_cdx_aioboto3.py
new file mode 100644
index 0000000..abb678b
--- /dev/null
+++ b/tests/test_warc_by_cdx_aioboto3.py
@@ -0,0 +1,93 @@
+from io import BytesIO
+import os
+from pathlib import Path
+
+import fsspec
+from cdx_toolkit.cli import main
+from cdx_toolkit.warcer_by_cdx.cdx_utils import (
+    get_index_as_string_from_path,
+)
+from cdx_toolkit.warcer_by_cdx.fsspec_warcer import (
+    generate_caputure_objects_from_index,
+)
+import pytest
+from warcio.archiveiterator import ArchiveIterator
+
+from conftest import requires_aws_s3
+
+from warcio import WARCWriter
+
+fixture_path = Path(__file__).parent / "data/warc_by_cdx"
+
+
+def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog, extra_args=""):
+    # test cli and check output
+    index_path = fixture_path / "filtered_CC-MAIN-2024-30_cdx-00187.gz"
+
+    # --write-index-as-record
+
+    main(
+        args=f"""-v --cc --limit 10  warc_by_cdx {str(index_path)} --prefix {str(base_prefix)}/TEST_warc_by_index --creator foo --operator bob --warc-download-prefix {warc_download_prefix} {extra_args}""".split()
+    )
+
+    # Check log
+    assert "Limit reached" in caplog.text
+
+    # Validate extracted WARC
+    warc_filename = "TEST_warc_by_index-000000.extracted.warc.gz"
+    warc_path = str(base_prefix) + "/" + warc_filename
+    resource_record = None
+    info_record = None
+    response_records = []
+    response_contents = []
+
+    with fsspec.open(warc_path, 'rb') as stream:
+        for record in ArchiveIterator(stream):
+            if record.rec_type == 'warcinfo':
+                info_record = record.content_stream().read().decode("utf-8")
+        
+            if record.rec_type == 'response':
+                response_records.append(record)
+                response_contents.append(record.content_stream().read().decode("utf-8", errors="ignore"))
+
+            # if record.rec_type == 'resource':
+            #     resource_record = record
+
+    assert len(response_records) == 10, "Invalid record count"
+    # assert resource_record is not None
+    # assert resource_record.length == 568010
+
+    assert "Catalogue en ligne Mission de France" in response_contents[0], "Invalid response content"
+    assert "dojo/dijit/themes/tundra/tundra" in response_contents[9], "Invalid response content"
+    assert info_record is not None
+    assert "operator: bob" in info_record, "Invalid WARC info"
+    
+
+
+@requires_aws_s3
+def test_cli_warc_by_cdx_over_s3_to_s3_in_parallel_aioboto3(tmpdir, caplog):
+    assert_cli_warc_by_cdx("s3://commoncrawl", base_prefix="s3://commoncrawl-dev/cdx_toolkit/ci/test-outputs" + str(tmpdir), caplog=caplog, extra_args=" --parallel 3 --implementation aioboto3")
+
+
+
+def test_warc_info():
+    warc_version = "1.0"
+    gzip = False
+    file_handler = BytesIO()
+    filename = "foo.warc"
+
+    info = {
+        "software": "pypi_cdx_toolkit/123",
+        "isPartOf": "bar",
+        "description": "warc extraction based on CDX generated with: xx",
+        "format": "WARC file version 1.0",
+    }
+
+    writer = WARCWriter(file_handler, gzip=gzip, warc_version=warc_version)
+    warcinfo = writer.create_warcinfo_record(filename, info)
+    
+    writer.write_record(warcinfo)
+
+    file_value = file_handler.getvalue().decode("utf-8")
+
+    assert "pypi_cdx_toolkit/123" in file_value

From d13f1a867d5cd0a83c5f0fe2f0b0cdf3a03ae88a Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Wed, 10 Sep 2025 15:50:38 +0000
Subject: [PATCH 18/74] Small clean up

---
 cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py b/cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py
index f2f21b7..aa958d1 100644
--- a/cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py
+++ b/cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py
@@ -97,7 +97,7 @@ async def filter_warc_by_cdx_via_aioboto3_async(
     session = aioboto3.Session()
 
     async with session.client("s3", config=boto_cfg) as s3:
-        # Stage 1
+        # Fetch file paths and ranges (offset, length) from index files
         logger.info(
             "Starting lister, %d fetchers, %d consumers", num_fetchers, num_consumers
         )
@@ -111,7 +111,7 @@ async def filter_warc_by_cdx_via_aioboto3_async(
             )
         )
 
-        # Stage 2
+        # Read WARC records based on file paths and ranges
         fetchers = [
             asyncio.create_task(
                 fetcher(
@@ -127,19 +127,13 @@ async def filter_warc_by_cdx_via_aioboto3_async(
             for i in range(num_fetchers)
         ]
 
-        # Stage 3
+        # Write WARC records
         consumers = [
             asyncio.create_task(
                 consumer(
                     consumer_id=i,
                     item_queue=item_queue,
                     s3=s3,
-                    # shard_name_prefix=shard_name_prefix,
-                    # args.shard_extension,
-                    # args.dest_prefix,
-                    # args.dest_bucket,
-                    # args.content_type,
-                    # min_part_size=,
                     prefix_path=prefix_path,
                     max_attempts=max_attempts,
                     base_backoff_seconds=base_backoff_seconds,

From aa69c54fc5d3bcd4dee9f0b47757671daba58abd Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Wed, 17 Sep 2025 09:55:09 +0000
Subject: [PATCH 19/74] updated format and feat CI

---
 .github/workflows/ci-feat-warc-by-cdx.yaml    |  56 +++++
 .github/workflows/ci.yaml                     |  18 +-
 cdx_toolkit/filter_cdx/__init__.py            | 105 +++++-----
 cdx_toolkit/filter_cdx/args.py                |  38 ++--
 cdx_toolkit/filter_cdx/matcher.py             |  26 +--
 cdx_toolkit/warcer_by_cdx/__init__.py         |  65 +++---
 cdx_toolkit/warcer_by_cdx/aioboto3_utils.py   |  68 +++---
 cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py  | 109 +++++-----
 cdx_toolkit/warcer_by_cdx/aioboto3_writer.py  |  17 +-
 cdx_toolkit/warcer_by_cdx/args.py             |  48 ++---
 cdx_toolkit/warcer_by_cdx/cdx_utils.py        |  42 ++--
 cdx_toolkit/warcer_by_cdx/fsspec_warcer.py    | 100 ++++-----
 tests/__init__.py                             |   0
 tests/test_filter_cdx.py                      | 154 --------------
 tests/test_warc_by_cdx_aioboto3.py            |  93 ---------
 tests/unit/test_warc.py                       |  33 +--
 tests/warc_by_cdx/__init__.py                 |   0
 tests/warc_by_cdx/test_filter_cdx.py          | 165 +++++++++++++++
 tests/{ => warc_by_cdx}/test_matcher.py       | 194 +++++++++---------
 tests/{ => warc_by_cdx}/test_warc_by_cdx.py   | 134 ++++++++----
 .../warc_by_cdx/test_warc_by_cdx_aioboto3.py  | 105 ++++++++++
 tests/warc_by_cdx/test_warc_from_fs.py        |  53 +++++
 tests/{ => warc_by_cdx}/test_warc_writer.py   |  67 +++---
 23 files changed, 905 insertions(+), 785 deletions(-)
 create mode 100644 .github/workflows/ci-feat-warc-by-cdx.yaml
 create mode 100644 tests/__init__.py
 delete mode 100644 tests/test_filter_cdx.py
 delete mode 100644 tests/test_warc_by_cdx_aioboto3.py
 create mode 100644 tests/warc_by_cdx/__init__.py
 create mode 100644 tests/warc_by_cdx/test_filter_cdx.py
 rename tests/{ => warc_by_cdx}/test_matcher.py (58%)
 rename tests/{ => warc_by_cdx}/test_warc_by_cdx.py (51%)
 create mode 100644 tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
 create mode 100644 tests/warc_by_cdx/test_warc_from_fs.py
 rename tests/{ => warc_by_cdx}/test_warc_writer.py (66%)

diff --git a/.github/workflows/ci-feat-warc-by-cdx.yaml b/.github/workflows/ci-feat-warc-by-cdx.yaml
new file mode 100644
index 0000000..80bb1bc
--- /dev/null
+++ b/.github/workflows/ci-feat-warc-by-cdx.yaml
@@ -0,0 +1,56 @@
+name: CI (only feature)
+
+on:
+  push:
+    branches:
+    - main
+  pull_request:
+    branches:
+    - main
+
+jobs:
+  unit-tests:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      max-parallel: 1  # avoids ever triggering a rate limit
+      matrix:
+        python-version: ['3.8', '3.9', '3.10', '3.11', '3.12']
+        os: [ubuntu-latest]
+        EXTRA: [false]  # used to force includes to get included
+        include:
+          - python-version: '3.12'
+            os: ubuntu-latest
+            EXTRA: true
+            env:
+              LOGLEVEL=DEBUG
+          - python-version: '3.8'
+            os: ubuntu-22.04  # oldest version on github actions
+            EXTRA: true
+
+    steps:
+      - name: checkout
+        uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install setuptools on python 3.12+
+        if: ${{ matrix.python-version >= '3.12' }}
+        run: |
+          pip install setuptools
+
+      - name: Install cdx_toolkit
+        run: pip install .[test]
+
+      - name: Run tests (feature only)
+        run: |
+          PYTHONPATH=. py.test -rA -s --doctest-modules --cov-report=xml --cov-append --cov cdx_toolkit tests/warc_by_cdx tests/unit -v -v
+          coverage report
+
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v4
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
index c43c4ca..7f471c7 100644
--- a/.github/workflows/ci.yaml
+++ b/.github/workflows/ci.yaml
@@ -1,13 +1,15 @@
 name: CI
 
-on:
-  # runtime is erratic and up to an hour
-  push:
-    branches:
-    - main
-  pull_request:
-    branches:
-    - main
+on: workflow_dispatch
+# Disabled for this feature
+# on:
+#   # runtime is erratic and up to an hour
+#   push:
+#     branches:
+#     - main
+#   pull_request:
+#     branches:
+#     - main
 
 jobs:
   unit-tests:
diff --git a/cdx_toolkit/filter_cdx/__init__.py b/cdx_toolkit/filter_cdx/__init__.py
index 6aa0999..75c9de0 100644
--- a/cdx_toolkit/filter_cdx/__init__.py
+++ b/cdx_toolkit/filter_cdx/__init__.py
@@ -22,7 +22,7 @@ def run_filter_cdx(args, cmdline: str):
     - All other index entries are discarded.
     - All input/output paths can be local or remote paths (S3, ...) and compressed (*.gz).
     """
-    logger.info("Filtering CDX files based on whitelist")
+    logger.info('Filtering CDX files based on whitelist')
 
     # Start timing
     start_time = time.time()
@@ -36,24 +36,22 @@ def run_filter_cdx(args, cmdline: str):
     )
     validate_resolved_paths(output_paths, args.overwrite)
 
-    logger.info(
-        f"Found {len(input_paths)} files matching pattern: {args.input_base_path}/{args.input_glob}"
-    )
+    logger.info(f'Found {len(input_paths)} files matching pattern: {args.input_base_path}/{args.input_glob}')
 
     # Load URL or SURT prefixes from file (each line is a surt)
     filter_fs, filter_fs_path = fsspec.url_to_fs(args.filter_file)
-    logger.info("Loading whitelist from %s", filter_fs_path)
+    logger.info('Loading whitelist from %s', filter_fs_path)
 
     if not filter_fs.exists(filter_fs_path):  # Check that surts file exists
-        logger.error(f"Filter file not found: {filter_fs_path}")
+        logger.error(f'Filter file not found: {filter_fs_path}')
         sys.exit(1)
 
-    with filter_fs.open(filter_fs_path, "rt") as input_f:
+    with filter_fs.open(filter_fs_path, 'rt') as input_f:
         include_prefixes = [line.strip() for line in input_f.readlines()]
 
-    # Convert to SURT if filter file contains URLs 
-    if args.filter_type == "url":
-        logger.info("Converting urls to surts ...")
+    # Convert to SURT if filter file contains URLs
+    if args.filter_type == 'url':
+        logger.info('Converting urls to surts ...')
         include_surt_prefixes = [surt(url) for url in include_prefixes]
     else:
         # Filter is already given as surts
@@ -61,15 +59,13 @@ def run_filter_cdx(args, cmdline: str):
 
     # Create matcher based on selected approach
     matcher_classes = {
-        "trie": TrieMatcher,
-        "tuple": TupleMatcher,
+        'trie': TrieMatcher,
+        'tuple': TupleMatcher,
     }
 
     matcher = matcher_classes[args.matching_approach](include_surt_prefixes)
 
-    logger.info(
-        f"Loaded {len(include_surt_prefixes):,} filter entries using {args.matching_approach} approach"
-    )
+    logger.info(f'Loaded {len(include_surt_prefixes):,} filter entries using {args.matching_approach} approach')
 
     # Process files in parallel or sequentially
     n_parallel = args.parallel
@@ -77,66 +73,60 @@ def run_filter_cdx(args, cmdline: str):
     total_lines_n = 0
     total_included_n = 0
     total_errors_n = 0
-    
+
     if n_parallel > 1:
         # Parallel processing
-        logger.info("Parallel processes: %i", n_parallel)
+        logger.info('Parallel processes: %i', n_parallel)
         with ProcessPoolExecutor(max_workers=n_parallel) as executor:
             # Create partial function with common arguments
-            process_file_partial = partial(
-                _process_single_file,
-                matcher=matcher,
-                limit=limit
-            )
-            
+            process_file_partial = partial(_process_single_file, matcher=matcher, limit=limit)
+
             # Submit all jobs
             future_to_paths = {
                 executor.submit(process_file_partial, input_path, output_path): (input_path, output_path)
                 for input_path, output_path in zip(input_paths, output_paths)
             }
-            
+
             # Collect results
             for future in as_completed(future_to_paths):
                 input_path, output_path = future_to_paths[future]
                 try:
                     lines_n, included_n = future.result()
                     logger.info(
-                        f"File statistics for {input_path}: included_n={included_n}; lines_n={lines_n}; ratio={included_n/lines_n:.4f}"
+                        f'File statistics for {input_path}: included_n={included_n}; lines_n={lines_n}; ratio={included_n / lines_n:.4f}'
                     )
                     total_lines_n += lines_n
                     total_included_n += included_n
 
                 except Exception as exc:
-                    logger.error(f"File {input_path} generated an exception: {exc}")
+                    logger.error(f'File {input_path} generated an exception: {exc}')
                     total_errors_n += 1
     else:
         # Sequential processing
-        logger.info("Sequential processing")
+        logger.info('Sequential processing')
         for input_path, output_path in zip(input_paths, output_paths):
             try:
-                lines_n, included_n = _process_single_file(
-                    input_path, output_path, matcher, limit
-                )
+                lines_n, included_n = _process_single_file(input_path, output_path, matcher, limit)
                 logger.info(
-                    f"File statistics for {input_path}: included_n={included_n}; lines_n={lines_n}; ratio={included_n/lines_n:.4f}"
+                    f'File statistics for {input_path}: included_n={included_n}; lines_n={lines_n}; ratio={included_n / lines_n:.4f}'
                 )
                 total_lines_n += lines_n
                 total_included_n += included_n
 
             except Exception as exc:
-                logger.error(f"File {input_path} generated an exception: {exc}")
+                logger.error(f'File {input_path} generated an exception: {exc}')
                 total_errors_n += 1
     logger.info(
-        f"Total statistics: included_n={total_included_n}; lines_n={total_lines_n}; ratio={total_included_n/total_lines_n:.4f}"
+        f'Total statistics: included_n={total_included_n}; lines_n={total_lines_n}; ratio={total_included_n / total_lines_n:.4f}'
     )
     if total_errors_n > 0:
-        logger.error("Processing errors: %i", total_errors_n)
+        logger.error('Processing errors: %i', total_errors_n)
 
     # End timing and log execution time
     end_time = time.time()
     execution_time = end_time - start_time
 
-    logger.info(f"Script execution time: {execution_time:.3f} seconds")
+    logger.info(f'Script execution time: {execution_time:.3f} seconds')
 
 
 def resolve_paths(input_base_path: str, input_glob: str, output_base_path: str):
@@ -148,7 +138,7 @@ def resolve_paths(input_base_path: str, input_glob: str, output_base_path: str):
     # Get input files from glob pattern
     input_fs_file_paths = sorted(input_fs.glob(input_full_glob))
     if not input_fs_file_paths:
-        logger.error(f"No files found matching glob pattern: {input_full_glob}")
+        logger.error(f'No files found matching glob pattern: {input_full_glob}')
         sys.exit(1)
 
     # Generate corresponding output paths
@@ -169,45 +159,45 @@ def _process_single_file(input_path, output_path, matcher, limit: int = 0, log_e
     """Process a single input/output file pair. Returns (lines_n, included_n)."""
     lines_n = 0
     included_n = 0
-    
-    logger.info("Reading index from %s", input_path)
-    logger.info("Writing filter output to %s", output_path)
-    
+
+    logger.info('Reading index from %s', input_path)
+    logger.info('Writing filter output to %s', output_path)
+
     # Input/output from local or remote file system
     input_fs, input_fs_path = fsspec.url_to_fs(input_path)
     output_fs, output_fs_path = fsspec.url_to_fs(output_path)
-    
+
     # Make sure output directory exists
     output_fs.makedirs(output_fs._parent(output_fs_path), exist_ok=True)
-    
+
     # Read and write compressed file if needed
-    compression = "gzip" if input_fs_path.endswith(".gz") else None
-    
-    with output_fs.open(output_fs_path, "w", compression=compression) as output_f:
-        with input_fs.open(input_fs_path, "rt", compression=compression) as input_f:
+    compression = 'gzip' if input_fs_path.endswith('.gz') else None
+
+    with output_fs.open(output_fs_path, 'w', compression=compression) as output_f:
+        with input_fs.open(input_fs_path, 'rt', compression=compression) as input_f:
             for i, line in enumerate(input_f, 1):
                 # Read CDX line
-                surt_length = line.find(" ")  # we do not need to parse the full line
+                surt_length = line.find(' ')  # we do not need to parse the full line
                 record_surt = line[:surt_length]
                 lines_n += 1
-                
+
                 # Use SURT matcher
                 include_record = matcher.matches(record_surt)
-                
+
                 if include_record:
                     output_f.write(line)
                     included_n += 1
-                    
+
                     if limit > 0 and included_n >= limit:
-                        logger.info("Limit reached at %i from %s", limit, input_path)
+                        logger.info('Limit reached at %i from %s', limit, input_path)
                         break
-                
+
                 if (i % log_every_n) == 0:
-                    logger.info(f"Lines completed: {i:,} (matched: {included_n:,}) from {input_path}")
-    
+                    logger.info(f'Lines completed: {i:,} (matched: {included_n:,}) from {input_path}')
+
     # Delete file if empty
     if included_n == 0:
-        logger.warning("Output file is empty, removing it: %s", output_fs_path)
+        logger.warning('Output file is empty, removing it: %s', output_fs_path)
         output_fs.rm(output_fs_path)
 
     return lines_n, included_n
@@ -220,10 +210,7 @@ def validate_resolved_paths(output_paths, overwrite):
         output_fs, _ = fsspec.url_to_fs(output_paths[0])
         for output_path in output_paths:
             if output_fs.exists(output_path):
-                logger.error(
-                    f"Output file already exists: {output_path}. "
-                    "Use --overwrite to overwrite existing files."
-                )
+                logger.error(f'Output file already exists: {output_path}. Use --overwrite to overwrite existing files.')
                 sys.exit(1)
 
             # Make sure directory exists
diff --git a/cdx_toolkit/filter_cdx/args.py b/cdx_toolkit/filter_cdx/args.py
index 818412b..5e72553 100644
--- a/cdx_toolkit/filter_cdx/args.py
+++ b/cdx_toolkit/filter_cdx/args.py
@@ -4,43 +4,43 @@
 def add_filter_cdx_args(parser: argparse.ArgumentParser):
     """Add command line arguments."""
     parser.add_argument(
-        "input_base_path",
-        help="Base directory path on the local file system or remote URL for one or multiple CDX files (e.g., URL to S3 bucket)",
+        'input_base_path',
+        help='Base directory path on the local file system or remote URL for one or multiple CDX files (e.g., URL to S3 bucket)',
     )
     parser.add_argument(
-        "filter_file",
-        help="Path to file containing URL or SURT prefixes to filter for (one per line)",
+        'filter_file',
+        help='Path to file containing URL or SURT prefixes to filter for (one per line)',
     )
     parser.add_argument(
-        "output_base_path",
-        help="Base directory path for output files (directory structure will be replicated from input_base_path)",
+        'output_base_path',
+        help='Base directory path for output files (directory structure will be replicated from input_base_path)',
     )
     parser.add_argument(
-        "--filter-type",
+        '--filter-type',
         type=str,
-        default="url",
-        help="Type of filter entries (options: `url` or `surt`, defaults to `url`)",
+        default='url',
+        help='Type of filter entries (options: `url` or `surt`, defaults to `url`)',
     )
     parser.add_argument(
-        "--input-glob",
+        '--input-glob',
         help="Glob pattern relative to input_base_path (e.g., '**/*.cdx.gz' or 'collections/*/indexes/*.gz')",
     )
     parser.add_argument(
-        "--matching-approach",
-        choices=["trie", "tuple"],
-        default="trie",
-        help="Matching approach to use (default: trie)",
+        '--matching-approach',
+        choices=['trie', 'tuple'],
+        default='trie',
+        help='Matching approach to use (default: trie)',
     )
     parser.add_argument(
-        "--overwrite",
-        action="store_true",
-        help="Allow overwriting existing output files",
+        '--overwrite',
+        action='store_true',
+        help='Allow overwriting existing output files',
     )
     parser.add_argument(
-        "--parallel",
+        '--parallel',
         type=int,
         default=1,
-        help="Number of parallel workers for processing multiple input files (default: 1, sequential processing)",
+        help='Number of parallel workers for processing multiple input files (default: 1, sequential processing)',
     )
 
     return parser
diff --git a/cdx_toolkit/filter_cdx/matcher.py b/cdx_toolkit/filter_cdx/matcher.py
index 64899d1..c10400a 100644
--- a/cdx_toolkit/filter_cdx/matcher.py
+++ b/cdx_toolkit/filter_cdx/matcher.py
@@ -1,3 +1,4 @@
+from typing import List, Tuple
 import logging
 from abc import ABC, abstractmethod
 
@@ -8,7 +9,7 @@ class Matcher(ABC):
     """Base class for all matching approaches."""
 
     @abstractmethod
-    def __init__(self, prefixes: tuple[str] | list[str]):
+    def __init__(self, prefixes: Tuple[str] | List[str]):
         """Initialize the matcher with a list of prefixes."""
         pass
 
@@ -18,23 +19,24 @@ def matches(self, text: str) -> bool:
         pass
 
     @staticmethod
-    def validate_prefixes(prefixes: tuple[str] | list[str]) -> tuple[str]:
+    def validate_prefixes(prefixes: Tuple[str] | List[str]) -> Tuple[str]:
         valid_prefixes = []
 
         for prefix in prefixes:
             if prefix is None or not isinstance(prefix, str):
-                raise ValueError("Prefix must be a string and not none.")
+                raise ValueError('Prefix must be a string and not none.')
 
             # remove white spaces
             prefix = prefix.strip()
 
             if len(prefix) == 0:
-                raise ValueError("Empty prefixes are not allowed")
+                raise ValueError('Empty prefixes are not allowed')
 
             valid_prefixes.append(prefix)
 
         return tuple(valid_prefixes)
 
+
 class TrieNode:
     def __init__(self):
         self.children = {}
@@ -44,11 +46,11 @@ def __init__(self):
 class TrieMatcher(Matcher):
     """Trie-based matching approach."""
 
-    def __init__(self, prefixes: tuple[str] | list[str]):
-        logger.info(f"Building trie matcher based on {len(prefixes):,} inputs")
+    def __init__(self, prefixes: Tuple[str] | List[str]):
+        logger.info(f'Building trie matcher based on {len(prefixes):,} inputs')
         self.root = self._build_trie(self.validate_prefixes(prefixes))
 
-    def _build_trie(self, prefixes: tuple[str]):
+    def _build_trie(self, prefixes: Tuple[str]):
         """Build a trie from a collection of prefixes."""
         root = TrieNode()
         for prefix in prefixes:
@@ -75,10 +77,10 @@ def matches(self, text: str) -> bool:
 class TupleMatcher(Matcher):
     """Tuple-based matching approach using the built-in method `str.startswith`."""
 
-    def __init__(self, prefixes: tuple[str] | list[str]):
-        logger.info(f"Building tuple matcher based on {len(prefixes):,} inputs")
-        self.prefixes_tuple = self.validate_prefixes(prefixes)
+    def __init__(self, prefixes: Tuple[str] | List[str]):
+        logger.info(f'Building Tuple matcher based on {len(prefixes):,} inputs')
+        self.prefixes_Tuple = self.validate_prefixes(prefixes)
 
     def matches(self, text: str) -> bool:
-        """Check if text starts with any prefix in the tuple."""
-        return text.startswith(self.prefixes_tuple)
+        """Check if text starts with any prefix in the Tuple."""
+        return text.startswith(self.prefixes_Tuple)
diff --git a/cdx_toolkit/warcer_by_cdx/__init__.py b/cdx_toolkit/warcer_by_cdx/__init__.py
index e98a07c..ee5e932 100644
--- a/cdx_toolkit/warcer_by_cdx/__init__.py
+++ b/cdx_toolkit/warcer_by_cdx/__init__.py
@@ -1,7 +1,7 @@
 import logging
 import sys
 import time
-from typing import Literal
+from typing import List, Literal
 
 import fsspec
 
@@ -13,6 +13,8 @@
 
 logger = logging.getLogger(__name__)
 
+ImplementationType = Literal['fsspec', 'aioboto3']
+
 
 def run_warcer_by_cdx(args, cmdline):
     """Like warcer but fetches WARC records based on one or more CDX index files.
@@ -25,42 +27,42 @@ def run_warcer_by_cdx(args, cmdline):
     - Write to new WARC file with metadata including resource record with index.
     - The CDX resource record is written to the WARC directly before for response records that matches to the CDX.
     """
-    logger.info("Filtering WARC files based on CDX")
+    logger.info('Filtering WARC files based on CDX')
 
     cdx, kwargs = setup(args)
 
     # Start timing
     start_time = time.time()
 
-    implementation = args.implementation
+    implementation: ImplementationType = args.implementation
 
     write_index_as_record = args.write_index_as_record
     ispartof = args.prefix
     if args.subprefix:
-        ispartof += "-" + args.subprefix
+        ispartof += '-' + args.subprefix
 
     info = {
-        "software": "pypi_cdx_toolkit/" + get_version(),
-        "isPartOf": ispartof,
-        "description": "warc extraction based on CDX generated with: " + cmdline,
-        "format": "WARC file version 1.0",
+        'software': 'pypi_cdx_toolkit/' + get_version(),
+        'isPartOf': ispartof,
+        'description': 'warc extraction based on CDX generated with: ' + cmdline,
+        'format': 'WARC file version 1.0',
     }
     if args.creator:
-        info["creator"] = args.creator
+        info['creator'] = args.creator
     if args.operator:
-        info["operator"] = args.operator
+        info['operator'] = args.operator
 
     writer_kwargs = {}
-    if "size" in kwargs:
-        writer_kwargs["size"] = kwargs["size"]
-        del kwargs["size"]
+    if 'size' in kwargs:
+        writer_kwargs['size'] = kwargs['size']
+        del kwargs['size']
 
     n_parallel = args.parallel
     log_every_n = 5
     limit = 0 if args.limit is None else args.limit
     prefix_path = str(args.prefix)
-    prefix_fs, prefix_fs_path =  fsspec.url_to_fs(prefix_path)
-    
+    prefix_fs, prefix_fs_path = fsspec.url_to_fs(prefix_path)
+
     # make sure the base dir exists
     prefix_fs.makedirs(prefix_fs._parent(prefix_fs_path), exist_ok=True)
 
@@ -69,44 +71,45 @@ def run_warcer_by_cdx(args, cmdline):
         args.index_glob,
     )
 
-    if implementation == "fsspec":
+    if implementation == 'fsspec':
         records_n = filter_warc_by_cdx_via_fsspec(
             index_paths=index_paths,
             prefix_path=prefix_path,
             writer_info=info,
             writer_subprefix=args.subprefix,
             write_index_as_record=write_index_as_record,
-            limit = limit,
-            log_every_n = log_every_n,
-            warc_download_prefix = cdx.warc_download_prefix,
+            limit=limit,
+            log_every_n=log_every_n,
+            warc_download_prefix=cdx.warc_download_prefix,
             n_parallel=n_parallel,
             writer_kwargs=writer_kwargs,
         )
-    elif implementation == "aioboto3":
+    elif implementation == 'aioboto3':
         records_n = filter_warc_by_cdx_via_aioboto3(
             index_paths=index_paths,
             prefix_path=prefix_path,
             writer_info=info,
             writer_subprefix=args.subprefix,
             write_index_as_record=write_index_as_record,
-            limit = limit,
-            log_every_n = log_every_n,
-            warc_download_prefix = cdx.warc_download_prefix,
+            limit=limit,
+            log_every_n=log_every_n,
+            warc_download_prefix=cdx.warc_download_prefix,
             n_parallel=n_parallel,
             writer_kwargs=writer_kwargs,
         )
     else:
-        raise ValueError("Invalid implementation")
+        raise ValueError(f'Invalid implementation: {implementation}')
 
-    logger.info("WARC records extracted: %i", records_n)
+    logger.info('WARC records extracted: %i', records_n)
 
     # End timing and log execution time
     end_time = time.time()
     execution_time = end_time - start_time
 
-    logger.info(f"Script execution time: {execution_time:.3f} seconds")
+    logger.info(f'Script execution time: {execution_time:.3f} seconds')
 
-def get_index_paths(index_path: str, index_glob: str | None = None) -> list[str]:
+
+def get_index_paths(index_path: str, index_glob: str | None = None) -> List[str]:
     if index_glob is None:
         # Read from a single index
         index_paths = [index_path]
@@ -117,16 +120,14 @@ def get_index_paths(index_path: str, index_glob: str | None = None) -> list[str]
         # Fetch multiple indicies via glob
         full_glob = index_fs_path + index_glob
 
-        logger.info("glob pattern from %s (%s)", full_glob, index_fs.protocol)
+        logger.info('glob pattern from %s (%s)', full_glob, index_fs.protocol)
 
         index_paths = sorted(index_fs.glob(full_glob))
 
-        logger.info(
-            "glob pattern found %i index files in %s", len(index_paths), index_fs_path
-        )
+        logger.info('glob pattern found %i index files in %s', len(index_paths), index_fs_path)
 
         if not index_paths:
-            logger.error("no index files found via glob")
+            logger.error('no index files found via glob')
             sys.exit(1)
 
     return index_paths
diff --git a/cdx_toolkit/warcer_by_cdx/aioboto3_utils.py b/cdx_toolkit/warcer_by_cdx/aioboto3_utils.py
index ebc6762..3c5350d 100644
--- a/cdx_toolkit/warcer_by_cdx/aioboto3_utils.py
+++ b/cdx_toolkit/warcer_by_cdx/aioboto3_utils.py
@@ -31,19 +31,19 @@ def get_stats(self) -> dict:
         elapsed = time.time() - self.start_time
         if elapsed <= 0:
             return {
-                "elapsed": 0,
-                "bytes_per_sec": 0,
-                "mb_per_sec": 0,
-                "requests_per_sec": 0,
+                'elapsed': 0,
+                'bytes_per_sec': 0,
+                'mb_per_sec': 0,
+                'requests_per_sec': 0,
             }
 
         return {
-            "elapsed": elapsed,
-            "total_bytes": self.total_bytes,
-            "total_requests": self.total_requests,
-            "bytes_per_sec": self.total_bytes / elapsed,
-            "mb_per_sec": (self.total_bytes / elapsed) / (1024 * 1024),
-            "requests_per_sec": self.total_requests / elapsed,
+            'elapsed': elapsed,
+            'total_bytes': self.total_bytes,
+            'total_requests': self.total_requests,
+            'bytes_per_sec': self.total_bytes / elapsed,
+            'mb_per_sec': (self.total_bytes / elapsed) / (1024 * 1024),
+            'requests_per_sec': self.total_requests / elapsed,
         }
 
 
@@ -70,18 +70,16 @@ def _backoff(attempt: int, base_backoff_seconds: float) -> float:
 
 
 def parse_s3_uri(uri: str) -> tuple[str, str]:
-    if not uri.startswith("s3://"):
-        raise ValueError(f"Not an S3 URI: {uri}")
+    if not uri.startswith('s3://'):
+        raise ValueError(f'Not an S3 URI: {uri}')
     rest = uri[5:]
-    i = rest.find("/")
+    i = rest.find('/')
     if i <= 0 or i == len(rest) - 1:
-        raise ValueError(f"Malformed S3 URI: {uri}")
+        raise ValueError(f'Malformed S3 URI: {uri}')
     return rest[:i], rest[i + 1 :]
 
 
-async def with_retries(
-    coro_factory, *, op_name: str, max_attempts: int, base_backoff_seconds: float
-):
+async def with_retries(coro_factory, *, op_name: str, max_attempts: int, base_backoff_seconds: float):
     last_exc = None
     for attempt in range(1, max_attempts + 1):
         try:
@@ -89,11 +87,11 @@ async def with_retries(
         except (TimeoutError, ClientError, EndpointConnectionError) as exc:
             last_exc = exc
             if attempt >= max_attempts:
-                logger.error("%s failed after %d attempts: %r", op_name, attempt, exc)
+                logger.error('%s failed after %d attempts: %r', op_name, attempt, exc)
                 break
             sleep_s = _backoff(attempt, base_backoff_seconds)
             logger.warning(
-                "%s failed (attempt %d/%d) – retrying in %.2fs",
+                '%s failed (attempt %d/%d) – retrying in %.2fs',
                 op_name,
                 attempt,
                 max_attempts,
@@ -103,16 +101,14 @@ async def with_retries(
     raise last_exc
 
 
-async def get_object_stream(
-    s3, bucket: str, key: str, max_attempts: int, base_backoff_seconds: float
-):
+async def get_object_stream(s3, bucket: str, key: str, max_attempts: int, base_backoff_seconds: float):
     resp = await with_retries(
         lambda: s3.get_object(Bucket=bucket, Key=key),
-        op_name=f"get_object {bucket}/{key}",
+        op_name=f'get_object {bucket}/{key}',
         max_attempts=max_attempts,
         base_backoff_seconds=base_backoff_seconds,
     )
-    return resp["Body"]
+    return resp['Body']
 
 
 async def ranged_get_bytes(
@@ -126,12 +122,12 @@ async def ranged_get_bytes(
 ) -> bytes:
     end = offset + length - 1  # inclusive
     resp = await with_retries(
-        lambda: s3.get_object(Bucket=bucket, Key=key, Range=f"bytes={offset}-{end}"),
-        op_name=f"ranged_get {bucket}/{key}[{offset}:{end}]",
+        lambda: s3.get_object(Bucket=bucket, Key=key, Range=f'bytes={offset}-{end}'),
+        op_name=f'ranged_get {bucket}/{key}[{offset}:{end}]',
         max_attempts=max_attempts,
         base_backoff_seconds=base_backoff_seconds,
     )
-    return await resp["Body"].read()
+    return await resp['Body'].read()
 
 
 async def mpu_create(
@@ -143,16 +139,16 @@ async def mpu_create(
     max_attempts: int,
     base_backoff_seconds: float,
 ):
-    kwargs = {"Bucket": bucket, "Key": key}
+    kwargs = {'Bucket': bucket, 'Key': key}
     if content_type:
-        kwargs["ContentType"] = content_type
+        kwargs['ContentType'] = content_type
     resp = await with_retries(
         lambda: s3.create_multipart_upload(**kwargs),
-        op_name=f"create_multipart_upload {bucket}/{key}",
+        op_name=f'create_multipart_upload {bucket}/{key}',
         max_attempts=max_attempts,
         base_backoff_seconds=base_backoff_seconds,
     )
-    return resp["UploadId"]
+    return resp['UploadId']
 
 
 async def mpu_upload_part(
@@ -173,11 +169,11 @@ async def mpu_upload_part(
             PartNumber=part_number,
             Body=body,
         ),
-        op_name=f"upload_part {bucket}/{key}#{part_number}",
+        op_name=f'upload_part {bucket}/{key}#{part_number}',
         max_attempts=max_attempts,
         base_backoff_seconds=base_backoff_seconds,
     )
-    return resp["ETag"]
+    return resp['ETag']
 
 
 async def mpu_complete(
@@ -191,9 +187,9 @@ async def mpu_complete(
 ):
     await with_retries(
         lambda: s3.complete_multipart_upload(
-            Bucket=bucket, Key=key, UploadId=upload_id, MultipartUpload={"Parts": parts}
+            Bucket=bucket, Key=key, UploadId=upload_id, MultipartUpload={'Parts': parts}
         ),
-        op_name=f"complete_multipart_upload {bucket}/{key}",
+        op_name=f'complete_multipart_upload {bucket}/{key}',
         max_attempts=max_attempts,
         base_backoff_seconds=base_backoff_seconds,
     )
@@ -203,4 +199,4 @@ async def mpu_abort(s3, bucket: str, key: str, upload_id: str):
     try:
         await s3.abort_multipart_upload(Bucket=bucket, Key=key, UploadId=upload_id)
     except Exception:
-        logger.exception("Failed to abort MPU %s on %s/%s", upload_id, bucket, key)
+        logger.exception('Failed to abort MPU %s on %s/%s', upload_id, bucket, key)
diff --git a/cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py b/cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py
index aa958d1..9e25bd0 100644
--- a/cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py
+++ b/cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py
@@ -1,9 +1,7 @@
 import asyncio
 from io import BytesIO
 import logging
-
-import asyncio
-import logging
+from typing import List
 
 import aioboto3
 from botocore.config import Config
@@ -27,7 +25,7 @@
 
 
 def filter_warc_by_cdx_via_aioboto3(
-    index_paths: list[str],
+    index_paths: List[str],
     prefix_path: str,
     writer_info: dict,
     writer_subprefix: str | None = None,
@@ -38,7 +36,6 @@ def filter_warc_by_cdx_via_aioboto3(
     n_parallel: int = 1,
     writer_kwargs: dict | None = None,
 ) -> int:
-
     try:
         return asyncio.run(
             filter_warc_by_cdx_via_aioboto3_async(
@@ -55,13 +52,13 @@ def filter_warc_by_cdx_via_aioboto3(
             )
         )
     except KeyboardInterrupt:
-        logger.warning("Interrupted by user.")
+        logger.warning('Interrupted by user.')
 
     return -1
 
 
 async def filter_warc_by_cdx_via_aioboto3_async(
-    index_paths: list[str],
+    index_paths: List[str],
     prefix_path: str,
     writer_info: dict,
     writer_subprefix: str | None = None,
@@ -85,8 +82,8 @@ async def filter_warc_by_cdx_via_aioboto3_async(
     item_queue: asyncio.Queue = asyncio.Queue(maxsize=item_queue_size)
 
     boto_cfg = Config(
-        region_name="us-east-1",
-        retries={"max_attempts": max(2, max_attempts), "mode": "standard"},
+        region_name='us-east-1',
+        retries={'max_attempts': max(2, max_attempts), 'mode': 'standard'},
         connect_timeout=10,
         read_timeout=120,
     )
@@ -96,11 +93,9 @@ async def filter_warc_by_cdx_via_aioboto3_async(
 
     session = aioboto3.Session()
 
-    async with session.client("s3", config=boto_cfg) as s3:
+    async with session.client('s3', config=boto_cfg) as s3:
         # Fetch file paths and ranges (offset, length) from index files
-        logger.info(
-            "Starting lister, %d fetchers, %d consumers", num_fetchers, num_consumers
-        )
+        logger.info('Starting lister, %d fetchers, %d consumers', num_fetchers, num_consumers)
         lister_task = asyncio.create_task(
             lister_from_index(
                 key_queue=key_queue,
@@ -142,47 +137,46 @@ async def filter_warc_by_cdx_via_aioboto3_async(
                     writer_subprefix=writer_subprefix,
                     writer_kwargs=writer_kwargs,
                     log_every_n=log_every_n,
-                    gzip=index_paths[0].endswith(".gz") if index_paths else False,
+                    gzip=index_paths[0].endswith('.gz') if index_paths else False,
                 )
             )
             for i in range(num_consumers)
         ]
 
         await lister_task
-        logger.info("Lister completed, waiting for fetchers to finish")
+        logger.info('Lister completed, waiting for fetchers to finish')
 
         await asyncio.gather(*fetchers)
-        logger.info("All fetchers completed")
+        logger.info('All fetchers completed')
 
         # Send stop signals to consumers
         for _ in range(num_consumers):
             await item_queue.put(_STOP)
 
         consumer_results = await asyncio.gather(*consumers)
-        n_records = sum([result["stats"]["total_requests"] for result in consumer_results])
+        n_records = sum([result['stats']['total_requests'] for result in consumer_results])
 
-        logger.info("All consumers completed")
+        logger.info('All consumers completed')
 
     return n_records
 
 
 async def lister_from_index(
     key_queue: asyncio.Queue,
-    index_paths: list[str],
+    index_paths: List[str],
     warc_download_prefix: str,
     num_fetchers: int,
     limit: int = 0,
 ):
     """Stage 1: stream the index, parse lines -> RangeJob -> key_queue."""
 
-    logger.info("Range index limit: %i", limit)
+    logger.info('Range index limit: %i', limit)
     count = 0
 
     if not index_paths:
-        logger.error("No index paths provided!")
+        logger.error('No index paths provided!')
 
     else:
-
         # Iterate over index files
         for index_path in index_paths:
             # Fetch range queries from index
@@ -197,21 +191,21 @@ async def lister_from_index(
                     count += 1
 
                     if limit > 0 and count >= limit:
-                        logger.warning("Index limit reached at %i", count)
+                        logger.warning('Index limit reached at %i', count)
                         break
 
             except Exception as e:
-                logger.error("Failed to read CDX index from %s: %s", index_path, e)
+                logger.error('Failed to read CDX index from %s: %s', index_path, e)
 
             if limit > 0 and count >= limit:
-                logger.warning("Limit reached at %i", count)
+                logger.warning('Limit reached at %i', count)
                 break
 
     # signal fetchers to stop
     for _ in range(num_fetchers):
         await key_queue.put(_STOP)
 
-    logger.info("Lister enqueued %d jobs from %s", count, index_path)
+    logger.info('Lister enqueued %d jobs from %s', count, index_path)
 
 
 async def fetcher(
@@ -234,14 +228,13 @@ async def fetcher(
             if job is _STOP:
                 stats = tracker.get_stats()
                 logger.info(
-                    "Fetcher %d stopping. Stats: %.1fs, %d requests, %.1f MB, "
-                    "%.2f MB/s, %.2f req/s",
+                    'Fetcher %d stopping. Stats: %.1fs, %d requests, %.1f MB, %.2f MB/s, %.2f req/s',
                     fetcher_id,
-                    stats["elapsed"],
-                    stats["total_requests"],
-                    stats["total_bytes"] / (1024 * 1024),
-                    stats["mb_per_sec"],
-                    stats["requests_per_sec"],
+                    stats['elapsed'],
+                    stats['total_requests'],
+                    stats['total_bytes'] / (1024 * 1024),
+                    stats['mb_per_sec'],
+                    stats['requests_per_sec'],
                 )
                 break  # Exit loop, but still execute finally block
             assert isinstance(job, RangeJob)
@@ -261,23 +254,23 @@ async def fetcher(
             if counter % log_every_n == 0:
                 stats = tracker.get_stats()
                 logger.info(
-                    "Fetcher %d: %d items, %.1f MB, %.2f MB/s, %.2f req/s",
+                    'Fetcher %d: %d items, %.1f MB, %.2f MB/s, %.2f req/s',
                     fetcher_id,
                     counter,
-                    stats["total_bytes"] / (1024 * 1024),
-                    stats["mb_per_sec"],
-                    stats["requests_per_sec"],
+                    stats['total_bytes'] / (1024 * 1024),
+                    stats['mb_per_sec'],
+                    stats['requests_per_sec'],
                 )
 
             await item_queue.put(RangePayload(job=job, data=data))
         except Exception:
             logger.exception(
-                "Fetcher %d failed on %s/%s [%d,%d]",
+                'Fetcher %d failed on %s/%s [%d,%d]',
                 fetcher_id,
-                getattr(job, "bucket", "?"),
-                getattr(job, "key", "?"),
-                getattr(job, "offset", -1),
-                getattr(job, "length", -1),
+                getattr(job, 'bucket', '?'),
+                getattr(job, 'key', '?'),
+                getattr(job, 'offset', -1),
+                getattr(job, 'length', -1),
             )
         finally:
             key_queue.task_done()
@@ -300,7 +293,7 @@ async def consumer(
     writer_subprefix: str | None = None,
     write_index_as_record: bool = False,
     writer_kwargs: dict | None = None,
-    warc_version: str = "1.0",
+    warc_version: str = '1.0',
     log_every_n: int = 1000,
     gzip: bool = False,
 ):
@@ -315,10 +308,10 @@ async def consumer(
     if writer_subprefix is not None:
         file_name += writer_subprefix + '-'
     file_name += '{:06d}'.format(consumer_id) + '.extracted.warc'
-    
+
     if gzip:
         file_name += '.gz'
-        
+
     writer = ShardWriter(
         file_name,
         dest_bucket,
@@ -350,13 +343,12 @@ async def consumer(
                 if item is _STOP:
                     stats = tracker.get_stats()
                     logger.info(
-                        "Consumer %d stopping. Stats: %.1fs, %d items, %.1f MB written, "
-                        "%.2f MB/s write speed",
+                        'Consumer %d stopping. Stats: %.1fs, %d items, %.1f MB written, %.2f MB/s write speed',
                         consumer_id,
-                        stats["elapsed"],
-                        stats["total_requests"],
-                        stats["total_bytes"] / (1024 * 1024),
-                        stats["mb_per_sec"],
+                        stats['elapsed'],
+                        stats['total_requests'],
+                        stats['total_bytes'] / (1024 * 1024),
+                        stats['mb_per_sec'],
                     )
                     should_stop = True
                 else:
@@ -369,16 +361,14 @@ async def consumer(
                     if counter % log_every_n == 0:
                         stats = tracker.get_stats()
                         logger.info(
-                            "Consumer %d: %d items, %.1f MB written, %.2f MB/s",
+                            'Consumer %d: %d items, %.1f MB written, %.2f MB/s',
                             consumer_id,
                             counter,
-                            stats["total_bytes"] / (1024 * 1024),
-                            stats["mb_per_sec"],
+                            stats['total_bytes'] / (1024 * 1024),
+                            stats['mb_per_sec'],
                         )
             except Exception:
-                logger.exception(
-                    "Consumer %d failed on %s", consumer_id, getattr(item, "job", None)
-                )
+                logger.exception('Consumer %d failed on %s', consumer_id, getattr(item, 'job', None))
                 should_stop = False
             finally:
                 item_queue.task_done()
@@ -388,7 +378,4 @@ async def consumer(
     finally:
         await writer.close(s3)
 
-    return {
-        'consumer_id': consumer_id,
-        'stats': tracker.get_stats()
-    }
+    return {'consumer_id': consumer_id, 'stats': tracker.get_stats()}
diff --git a/cdx_toolkit/warcer_by_cdx/aioboto3_writer.py b/cdx_toolkit/warcer_by_cdx/aioboto3_writer.py
index 1599174..b38135d 100644
--- a/cdx_toolkit/warcer_by_cdx/aioboto3_writer.py
+++ b/cdx_toolkit/warcer_by_cdx/aioboto3_writer.py
@@ -1,4 +1,5 @@
 import logging
+from typing import List, Dict
 
 from cdx_toolkit.warcer_by_cdx.aioboto3_utils import (
     mpu_abort,
@@ -30,7 +31,7 @@ def __init__(
         self.base_backoff_seconds = base_backoff_seconds
         self.upload_id: str | None = None
         self.part_number = 1
-        self.parts: list[dict] = []
+        self.parts: List[Dict] = []
         self.buffer = bytearray()
 
     async def start(self, s3):
@@ -42,7 +43,7 @@ async def start(self, s3):
             max_attempts=self.max_attempts,
             base_backoff_seconds=self.base_backoff_seconds,
         )
-        logger.info("Started MPU for %s (UploadId=%s)", self.shard_key, self.upload_id)
+        logger.info('Started MPU for %s (UploadId=%s)', self.shard_key, self.upload_id)
 
     async def _flush_full_parts(self, s3):
         while len(self.buffer) >= self.min_part_size:
@@ -58,7 +59,7 @@ async def _flush_full_parts(self, s3):
                 self.max_attempts,
                 self.base_backoff_seconds,
             )
-            self.parts.append({"PartNumber": self.part_number, "ETag": etag})
+            self.parts.append({'PartNumber': self.part_number, 'ETag': etag})
             self.part_number += 1
 
     async def write(self, s3, data: bytes):
@@ -80,7 +81,7 @@ async def close(self, s3):
                     self.max_attempts,
                     self.base_backoff_seconds,
                 )
-                self.parts.append({"PartNumber": self.part_number, "ETag": etag})
+                self.parts.append({'PartNumber': self.part_number, 'ETag': etag})
                 self.part_number += 1
                 self.buffer.clear()
 
@@ -94,13 +95,9 @@ async def close(self, s3):
                     self.max_attempts,
                     self.base_backoff_seconds,
                 )
-            logger.info(
-                "Completed MPU for %s with %d parts.", self.shard_key, len(self.parts)
-            )
+            logger.info('Completed MPU for %s with %d parts.', self.shard_key, len(self.parts))
         except Exception:
-            logger.exception(
-                "Completing MPU failed for %s; attempting abort.", self.shard_key
-            )
+            logger.exception('Completing MPU failed for %s; attempting abort.', self.shard_key)
             if self.upload_id:
                 await mpu_abort(s3, self.dest_bucket, self.shard_key, self.upload_id)
             raise
diff --git a/cdx_toolkit/warcer_by_cdx/args.py b/cdx_toolkit/warcer_by_cdx/args.py
index d81b3c1..3555ad7 100644
--- a/cdx_toolkit/warcer_by_cdx/args.py
+++ b/cdx_toolkit/warcer_by_cdx/args.py
@@ -6,53 +6,47 @@
 
 
 def add_warcer_by_cdx_args(parser: argparse.ArgumentParser):
+    parser.add_argument('index_path', help='Path to CDX index file (local or remote, e.g. S3)')
     parser.add_argument(
-        "index_path", help="Path to CDX index file (local or remote, e.g. S3)"
-    )
-    parser.add_argument(
-        "--index-glob",
+        '--index-glob',
         type=str,
         default=None,
-        help="a glob pattern for read from multiple indices",
+        help='a glob pattern for read from multiple indices',
     )
-    parser.add_argument("--prefix", default="TEST", help="prefix for the warc filename")
+    parser.add_argument('--prefix', default='TEST', help='prefix for the warc filename')
     parser.add_argument(
-        "--subprefix",
+        '--subprefix',
         type=str,
         default=None,
-        help="subprefix for the warc filename, default None",
+        help='subprefix for the warc filename, default None',
     )
     parser.add_argument(
-        "--size",
+        '--size',
         type=int,
         default=1000000000,
-        help="target for the warc filesize in bytes",
-    )
-    parser.add_argument(
-        "--creator",
-        action="store",
-        help="creator of the warc: person, organization, service",
+        help='target for the warc filesize in bytes',
     )
     parser.add_argument(
-        "--operator", action="store", help="a person, if the creator is an organization"
+        '--creator',
+        action='store',
+        help='creator of the warc: person, organization, service',
     )
+    parser.add_argument('--operator', action='store', help='a person, if the creator is an organization')
     parser.add_argument(
-        "--warc-download-prefix",
-        action="store",
-        help="prefix for downloading content, automatically set for CC",
+        '--warc-download-prefix',
+        action='store',
+        help='prefix for downloading content, automatically set for CC',
     )
     parser.add_argument(
-        "--write-index-as-record",
-        action="store_true",
-        help="If enable, the CDX index is written as resource record to the WARC file",
+        '--write-index-as-record',
+        action='store_true',
+        help='If enable, the CDX index is written as resource record to the WARC file',
     )
     parser.add_argument(
-        "--parallel",
+        '--parallel',
         type=int,
         default=1,
-        help="Number of parallel workers for fetchin WARC records (default: 1, sequential processing)",
-    )
-    parser.add_argument(
-        "--implementation", type=str, default="fsspec", help="implementation (fsspec, aioboto3)"
+        help='Number of parallel workers for fetchin WARC records (default: 1, sequential processing)',
     )
+    parser.add_argument('--implementation', type=str, default='fsspec', help='implementation (fsspec, aioboto3)')
     return parser
diff --git a/cdx_toolkit/warcer_by_cdx/cdx_utils.py b/cdx_toolkit/warcer_by_cdx/cdx_utils.py
index 869fbe3..822f6fd 100644
--- a/cdx_toolkit/warcer_by_cdx/cdx_utils.py
+++ b/cdx_toolkit/warcer_by_cdx/cdx_utils.py
@@ -16,36 +16,32 @@
 
 def get_index_as_string_from_path(index_path: str | Path, index_fs: None | fsspec.AbstractFileSystem = None) -> str:
     """Fetch (and decompress) index content as string from local or remote path."""
-    logger.info("Fetching index from %s ...", index_path)
+    logger.info('Fetching index from %s ...', index_path)
     if index_fs is None:
         index_fs, index_fs_path = fsspec.url_to_fs(index_path)
     else:
         index_fs_path = index_path
 
-    compression = "gzip" if index_fs_path.endswith(".gz") else None
+    compression = 'gzip' if index_fs_path.endswith('.gz') else None
 
-    with index_fs.open(index_fs_path, "rt", compression=compression) as f:
+    with index_fs.open(index_fs_path, 'rt', compression=compression) as f:
         return f.read()
 
 
-def get_index_record(
-    index: str, index_path: str, encoding: str = "utf-8"
-) -> ArcWarcRecord:
+def get_index_record(index: str, index_path: str, encoding: str = 'utf-8') -> ArcWarcRecord:
     """Build WARC resource record for index."""
     return WARCWriter(None).create_warc_record(
         uri=index_path,  # TODO this could be a local / internal path
-        record_type="resource",
+        record_type='resource',
         payload=BytesIO(index.encode(encoding)),
         http_headers=None,
-        warc_content_type="application/cdx",
+        warc_content_type='application/cdx',
         warc_headers_dict=None,  # TODO should we add some other metadata headers?
     )
 
 
-
-
 def read_cdx_line(line: str, warc_download_prefix: str) -> tuple[str, int, int]:
-    cols = line.split(" ", maxsplit=2)
+    cols = line.split(' ', maxsplit=2)
 
     if len(cols) == 3:
         # TODO can there be a different format?
@@ -55,37 +51,35 @@ def read_cdx_line(line: str, warc_download_prefix: str) -> tuple[str, int, int]:
         # > The default first line of a CDX file is:
         # > CDX A b e a m s c k r V v D d g M n
         data = json.loads(cols[2])
-        data["timestamp"] = cols[1]
+        data['timestamp'] = cols[1]
     else:
-        raise ValueError(f"Cannot parse line: {line}")
+        raise ValueError(f'Cannot parse line: {line}')
 
-    filename = data["filename"]
-    offset = int(data["offset"])
-    length = int(data["length"])
+    filename = data['filename']
+    offset = int(data['offset'])
+    length = int(data['length'])
 
-    warc_url = warc_download_prefix + "/" + filename
+    warc_url = warc_download_prefix + '/' + filename
 
     return (warc_url, offset, length)
 
 
-
 def read_cdx_index_from_s3(s3_path: str, warc_download_prefix: str) -> Iterable[tuple[str, int, int]]:
     """
     Read CDX records from a gzipped S3 file.
     """
     # if not s3_path.startswith("s3://"):
     #     raise ValueError(f"Invalid S3 path: {s3_path}")
-     
-    logger.info("Reading CDX from %s", s3_path)
 
-    with fsspec.open(s3_path, "rt", compression="gzip" if s3_path.endswith(".gz") else None) as f:
+    logger.info('Reading CDX from %s', s3_path)
+
+    with fsspec.open(s3_path, 'rt', compression='gzip' if s3_path.endswith('.gz') else None) as f:
         for line in f:
             try:
                 yield read_cdx_line(line, warc_download_prefix)
             except Exception:
                 # Skip malformed lines
-                logger.error("Invalid CDX line: %s", line)
+                logger.error('Invalid CDX line: %s', line)
                 continue
 
-    logger.info(f"CDX completed from %s", s3_path)
-    
\ No newline at end of file
+    logger.info(f'CDX completed from {s3_path}')
diff --git a/cdx_toolkit/warcer_by_cdx/fsspec_warcer.py b/cdx_toolkit/warcer_by_cdx/fsspec_warcer.py
index dc3eec1..1cc5442 100644
--- a/cdx_toolkit/warcer_by_cdx/fsspec_warcer.py
+++ b/cdx_toolkit/warcer_by_cdx/fsspec_warcer.py
@@ -1,7 +1,6 @@
-
 import json
 import logging
-from typing import Iterable
+from typing import Dict, Iterable, List
 
 import cdx_toolkit
 from concurrent.futures import ThreadPoolExecutor, as_completed
@@ -9,31 +8,34 @@
 from warcio.recordloader import ArcWarcRecord
 
 from cdx_toolkit.warcer_by_cdx.cdx_utils import get_index_as_string_from_path, get_index_record
-    
+
 
 logger = logging.getLogger(__name__)
 
+
 def filter_warc_by_cdx_via_fsspec(
-        index_paths: list[str],
-        prefix_path: str,
-        writer_info: dict,
-        writer_subprefix: str | None = None,
-        write_index_as_record: bool = False,
-        limit: int = 0,
-        log_every_n: int = 1000,
-        warc_download_prefix: str | None = None,
-        n_parallel: int = 1,
-        writer_kwargs: dict | None = None,
-    ) -> int:
-    
+    index_paths: List[str],
+    prefix_path: str,
+    writer_info: Dict,
+    writer_subprefix: str | None = None,
+    write_index_as_record: bool = False,
+    limit: int = 0,
+    log_every_n: int = 1000,
+    warc_download_prefix: str | None = None,
+    n_parallel: int = 1,
+    writer_kwargs: Dict | None = None,
+) -> int:
     writer = cdx_toolkit.warc.get_writer(
-        prefix_path, writer_subprefix, writer_info, **(writer_kwargs if writer_kwargs else {}),
+        prefix_path,
+        writer_subprefix,
+        writer_info,
+        **(writer_kwargs if writer_kwargs else {}),
     )
 
     # Iterate over index files
     records_n = 0
     for index_path in index_paths:
-        logger.info("filtering based on CDX from %s", index_path)
+        logger.info('filtering based on CDX from %s', index_path)
 
         # Read index completely (for the WARC resource record)
         index = get_index_as_string_from_path(index_path)
@@ -45,10 +47,10 @@ def filter_warc_by_cdx_via_fsspec(
         # Write index as record to WARC
         # TODO at what position should the resource records be written?
         if write_index_as_record:
-            logger.info("Writing CDX as resource record to WARC ... ")
+            logger.info('Writing CDX as resource record to WARC ... ')
             writer.write_record(get_index_record(index, index_path))
 
-            logger.info("CDX resource recorded added")
+            logger.info('CDX resource recorded added')
 
         # The index file holds all the information to download specific objects (file, offset, length etc.)
         index_lines = index.splitlines()
@@ -69,14 +71,14 @@ def filter_warc_by_cdx_via_fsspec(
             records_n += 1
 
             if (records_n % log_every_n) == 0:
-                logger.info(f"Record progress: {records_n:,} from {index_path}")
+                logger.info(f'Record progress: {records_n:,} from {index_path}')
 
         if limit > 0 and records_n >= limit:
             # stop index loop
-            logger.info("Limit reached")
+            logger.info('Limit reached')
             break
 
-        logger.info("Filtering completed (index file: %s)", index_path)
+        logger.info('Filtering completed (index file: %s)', index_path)
 
     writer.close()
 
@@ -85,54 +87,58 @@ def filter_warc_by_cdx_via_fsspec(
 
 def fetch_single_record(obj):
     """Fetch a single WARC record with error handling."""
-    url = obj["url"]
-    timestamp = obj["timestamp"]
+    url = obj['url']
+    timestamp = obj['timestamp']
 
     try:
         record = obj.fetch_warc_record()
         if obj.is_revisit():
-            logger.warning(
-                "revisit record being resolved for url %s %s", url, timestamp
-            )
+            logger.warning('revisit record being resolved for url %s %s', url, timestamp)
         return record
     except RuntimeError:  # pragma: no cover
-        logger.warning(
-            "skipping capture for RuntimeError 404: %s %s", url, timestamp
-        )
+        logger.warning('skipping capture for RuntimeError 404: %s %s', url, timestamp)
         return None
-    
+
+
 def fetch_records_from_index(
-    index_lines: list[str], warc_download_prefix=None, limit: int = 0, n_parallel: int = 1
+    index_lines: List[str], warc_download_prefix=None, limit: int = 0, n_parallel: int = 1
 ) -> Iterable[ArcWarcRecord]:
     """Fetch WARC records based on CDX index."""
-    
+
     if n_parallel <= 1:
         # Sequential processing
         for obj in generate_caputure_objects_from_index(
-            index_lines=index_lines, warc_download_prefix=warc_download_prefix, limit=limit,
+            index_lines=index_lines,
+            warc_download_prefix=warc_download_prefix,
+            limit=limit,
         ):
             record = fetch_single_record(obj)
             if record is not None:
                 yield record
     else:
         # Parallel processing
-        logger.info(f"Fetch records in parallel with {n_parallel=}")
-        objects = list(generate_caputure_objects_from_index(
-            index_lines=index_lines, warc_download_prefix=warc_download_prefix, limit=limit,
-        ))
-        
+        logger.info(f'Fetch records in parallel with {n_parallel=}')
+        objects = list(
+            generate_caputure_objects_from_index(
+                index_lines=index_lines,
+                warc_download_prefix=warc_download_prefix,
+                limit=limit,
+            )
+        )
+
         with ThreadPoolExecutor(max_workers=n_parallel) as executor:
             # Submit all tasks
             future_to_obj = {executor.submit(fetch_single_record, obj): obj for obj in objects}
-            
+
             # Yield results as they complete
             for future in as_completed(future_to_obj):
                 record = future.result()
                 if record is not None:
                     yield record
 
+
 def generate_caputure_objects_from_index(
-    index_lines: list[str], warc_download_prefix=None, limit: int = 0, progress_bar: bool = False
+    index_lines: List[str], warc_download_prefix=None, limit: int = 0, progress_bar: bool = False
 ) -> Iterable[cdx_toolkit.CaptureObject]:
     """Read CDX index and generate CaptureObject objects."""
 
@@ -143,20 +149,18 @@ def generate_caputure_objects_from_index(
     #     index_lines = tqdm(index_lines, desc="Extracting from WARC", total=len(index_lines))
 
     for i, line in enumerate(index_lines, 1):
-        cols = line.split(" ", maxsplit=2)
+        cols = line.split(' ', maxsplit=2)
 
         if len(cols) == 3:
             # TODO can there be a different format?
             # surt, timestamp, json_data = cols
-            # 
+            #
             # CC seems to not follow the specification from https://iipc.github.io/warc-specifications/specifications/cdx-format/cdx-2015/
             # > The default first line of a CDX file is:
             # > CDX A b e a m s c k r V v D d g M n
             data = json.loads(cols[2])
-            data["timestamp"] = cols[1]
+            data['timestamp'] = cols[1]
         else:
-            raise ValueError(f"Cannot parse line: {line}")
+            raise ValueError(f'Cannot parse line: {line}')
 
-        yield cdx_toolkit.CaptureObject(
-            data=data, wb=None, warc_download_prefix=warc_download_prefix
-        )
+        yield cdx_toolkit.CaptureObject(data=data, wb=None, warc_download_prefix=warc_download_prefix)
diff --git a/tests/__init__.py b/tests/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/tests/test_filter_cdx.py b/tests/test_filter_cdx.py
deleted file mode 100644
index 7d864f9..0000000
--- a/tests/test_filter_cdx.py
+++ /dev/null
@@ -1,154 +0,0 @@
-import pytest
-from pathlib import Path
-
-from cdx_toolkit.cli import main
-from cdx_toolkit.filter_cdx import resolve_paths, validate_resolved_paths
-from conftest import requires_aws_s3
-
-fixture_path = Path(__file__).parent / "data/filter_cdx"
-
-
-@requires_aws_s3
-def test_cli_filter_cdx_with_surts(tmpdir, caplog):
-    # check if expected number is reached
-    index_path = "s3://commoncrawl/cc-index/collections"
-    index_glob = "/CC-MAIN-2024-30/indexes/cdx-00187.gz"
-    whitelist_path = (
-        fixture_path / "whitelist_10_surts.txt"
-    )  # matches on first domain and after 100k and 200k lines
-
-    main(
-        args=f"-v --limit 1140 filter_cdx {index_path} {str(whitelist_path)} {tmpdir} --filter-type surt --input-glob {index_glob}".split()
-    )
-
-    assert "Limit reached" in caplog.text
-
-
-@requires_aws_s3
-def test_cli_filter_cdx_with_urls(tmpdir, caplog):
-    # check if expected number is reached
-    index_path = "s3://commoncrawl/cc-index/collections"
-    index_glob = "/CC-MAIN-2024-30/indexes/cdx-00187.gz"
-    whitelist_path = (
-        fixture_path / "whitelist_10_urls.txt"
-    )  # matches on first domain and after 100k and 200k lines
-
-    main(
-        args=f"-v --limit 1140 filter_cdx {index_path} {str(whitelist_path)} {tmpdir} --filter-type url --input-glob {index_glob}".split()
-    )
-
-    assert "Limit reached" in caplog.text
-    
-
-@requires_aws_s3
-def test_resolve_cdx_paths_from_cc_s3_to_local(tmpdir):
-    tmpdir = str(tmpdir)
-    base_path = "s3://commoncrawl/cc-index/collections"
-    glob_pattern = "/CC-MAIN-2016-30/indexes/*.gz"
-
-    input_files, output_files = resolve_paths(
-        base_path, glob_pattern, output_base_path=tmpdir
-    )
-
-    assert len(input_files) == len(
-        output_files
-    ), "Input and output count must be the same"
-    assert len(input_files) == 300, "Invalid input count"
-    assert (
-        input_files[0] == base_path + "/CC-MAIN-2016-30/indexes/cdx-00000.gz"
-    ), "Invalid input file"
-    assert (
-        output_files[0] == tmpdir + "/CC-MAIN-2016-30/indexes/cdx-00000.gz"
-    ), "Invalid output file"
-    assert input_files[-1] == base_path + "/CC-MAIN-2016-30/indexes/cdx-00299.gz"
-
-
-@requires_aws_s3
-def test_resolve_cdx_paths_from_cc_s3_to_another_s3():
-    output_base_path = "s3://some-other-bucket/filter-cdx"
-    base_path = "s3://commoncrawl/cc-index/collections"
-    glob_pattern = "/CC-MAIN-2016-30/indexes/cdx-000*.gz"
-
-    input_files, output_files = resolve_paths(
-        base_path, glob_pattern, output_base_path=output_base_path
-    )
-
-    assert len(input_files) == len(
-        output_files
-    ), "Input and output count must be the same"
-    assert len(input_files) == 100, "Invalid input count"
-    assert (
-        input_files[0] == base_path + "/CC-MAIN-2016-30/indexes/cdx-00000.gz"
-    ), "Invalid input file"
-    assert (
-        output_files[0] == output_base_path + "/CC-MAIN-2016-30/indexes/cdx-00000.gz"
-    ), "Invalid output file"
-    assert input_files[-1] == base_path + "/CC-MAIN-2016-30/indexes/cdx-00099.gz"
-
-
-@requires_aws_s3
-def test_filter_cdx_nonexistent_surt_file_exits(tmpdir, caplog):
-    index_path = "s3://commoncrawl/cc-index/collections"
-    index_glob = "/CC-MAIN-2024-30/indexes/cdx-00187.gz"
-    nonexistent_surt_file = str(tmpdir / "nonexistent_surts.txt")
-    
-    # Test that the command exits when SURT file doesn't exist
-    with pytest.raises(SystemExit) as exc_info:
-        main(
-            args=f"-v --limit 1140 filter_cdx {index_path} {nonexistent_surt_file} {tmpdir} --input-glob {index_glob}".split()
-        )
-    
-    assert exc_info.value.code == 1
-    assert f"Filter file not found: {nonexistent_surt_file}" in caplog.text
-
-
-def test_resolve_paths_no_files_found_exits(tmpdir, caplog):
-    # Test that resolve_paths exits when no files match the glob pattern
-    with pytest.raises(SystemExit) as exc_info:
-        resolve_paths(
-            input_base_path=str(tmpdir),
-            input_glob="/nonexistent-pattern-*.gz",
-            output_base_path=str(tmpdir)
-        )
-    
-    assert exc_info.value.code == 1
-    assert "No files found matching glob pattern:" in caplog.text
-
-
-def test_validate_resolved_paths_existing_file_exits(tmpdir, caplog):
-    # Create an existing output file
-    existing_file = tmpdir / "existing_output.txt"
-    existing_file.write_text("existing content", encoding="utf-8")
-    
-    output_paths = [str(existing_file)]
-    
-    # Test that validate_resolved_paths exits when output file exists and overwrite=False
-    with pytest.raises(SystemExit) as exc_info:
-        validate_resolved_paths(output_paths, overwrite=False)
-    
-    assert exc_info.value.code == 1
-    assert f"Output file already exists: {str(existing_file)}" in caplog.text
-    assert "Use --overwrite to overwrite existing files" in caplog.text
-
-
-@requires_aws_s3
-def test_cli_filter_cdx_with_parallel_processing(tmpdir, caplog):
-    """Test that parallel processing works correctly and processes multiple files."""
-    index_path = "s3://commoncrawl/cc-index/collections"
-    index_glob = "/CC-MAIN-2024-30/indexes/cdx-0018[78].gz"  # Multiple files pattern
-    whitelist_path = fixture_path / "whitelist_11_surts.txt"  # Additonal entry for cdx-00188.gz
-
-    # Run with parallel processing (2 workers)
-    main(
-        args=f"-v --limit 10 filter_cdx {index_path} {str(whitelist_path)} {tmpdir} --filter-type surt --input-glob {index_glob} --parallel 2".split()
-    )
-
-    # Check that multiple files were processed in parallel
-    assert "Found" in caplog.text and "files matching pattern" in caplog.text
-    assert "File statistics for" in caplog.text
-    assert "Total statistics:" in caplog.text
-    
-    # Should have processed multiple files (pattern matches 2 files: cdx-00187.gz and cdx-00188.gz)
-    file_stats_count = caplog.text.count("File statistics for")
-    assert file_stats_count == 2, "Should process exactly 2 files with the glob pattern"
-
diff --git a/tests/test_warc_by_cdx_aioboto3.py b/tests/test_warc_by_cdx_aioboto3.py
deleted file mode 100644
index abb678b..0000000
--- a/tests/test_warc_by_cdx_aioboto3.py
+++ /dev/null
@@ -1,93 +0,0 @@
-from io import BytesIO
-import os
-from pathlib import Path
-
-import fsspec
-from cdx_toolkit.cli import main
-from cdx_toolkit.warcer_by_cdx.cdx_utils import (
-    get_index_as_string_from_path,
-)
-from cdx_toolkit.warcer_by_cdx.fsspec_warcer import (
-    generate_caputure_objects_from_index,
-)
-import pytest
-from warcio.archiveiterator import ArchiveIterator
-
-from conftest import requires_aws_s3
-
-from warcio import WARCWriter
-
-fixture_path = Path(__file__).parent / "data/warc_by_cdx"
-
-
-def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog, extra_args=""):
-    # test cli and check output
-    index_path = fixture_path / "filtered_CC-MAIN-2024-30_cdx-00187.gz"
-
-    # --write-index-as-record
-
-    main(
-        args=f"""-v --cc --limit 10  warc_by_cdx {str(index_path)} --prefix {str(base_prefix)}/TEST_warc_by_index --creator foo --operator bob --warc-download-prefix {warc_download_prefix} {extra_args}""".split()
-    )
-
-    # Check log
-    assert "Limit reached" in caplog.text
-
-    # Validate extracted WARC
-    warc_filename = "TEST_warc_by_index-000000.extracted.warc.gz"
-    warc_path = str(base_prefix) + "/" + warc_filename
-    resource_record = None
-    info_record = None
-    response_records = []
-    response_contents = []
-
-    with fsspec.open(warc_path, 'rb') as stream:
-        for record in ArchiveIterator(stream):
-            if record.rec_type == 'warcinfo':
-                info_record = record.content_stream().read().decode("utf-8")
-        
-            if record.rec_type == 'response':
-                response_records.append(record)
-                response_contents.append(record.content_stream().read().decode("utf-8", errors="ignore"))
-
-            # if record.rec_type == 'resource':
-            #     resource_record = record
-
-    assert len(response_records) == 10, "Invalid record count"
-    # assert resource_record is not None
-    # assert resource_record.length == 568010
-
-    assert "Catalogue en ligne Mission de France" in response_contents[0], "Invalid response content"
-    assert "dojo/dijit/themes/tundra/tundra" in response_contents[9], "Invalid response content"
-    assert info_record is not None
-    assert "operator: bob" in info_record, "Invalid WARC info"
-    
-
-
-@requires_aws_s3
-def test_cli_warc_by_cdx_over_s3_to_s3_in_parallel_aioboto3(tmpdir, caplog):
-    assert_cli_warc_by_cdx("s3://commoncrawl", base_prefix="s3://commoncrawl-dev/cdx_toolkit/ci/test-outputs" + str(tmpdir), caplog=caplog, extra_args=" --parallel 3 --implementation aioboto3")
-
-
-
-def test_warc_info():
-    warc_version = "1.0"
-    gzip = False
-    file_handler = BytesIO()
-    filename = "foo.warc"
-
-    info = {
-        "software": "pypi_cdx_toolkit/123",
-        "isPartOf": "bar",
-        "description": "warc extraction based on CDX generated with: xx",
-        "format": "WARC file version 1.0",
-    }
-
-    writer = WARCWriter(file_handler, gzip=gzip, warc_version=warc_version)
-    warcinfo = writer.create_warcinfo_record(filename, info)
-    
-    writer.write_record(warcinfo)
-
-    file_value = file_handler.getvalue().decode("utf-8")
-
-    assert "pypi_cdx_toolkit/123" in file_value
diff --git a/tests/unit/test_warc.py b/tests/unit/test_warc.py
index 0c52614..e2474ff 100644
--- a/tests/unit/test_warc.py
+++ b/tests/unit/test_warc.py
@@ -1,35 +1,6 @@
-from conftest import requires_aws_s3
-from cdx_toolkit.warc import wb_redir_to_original, fetch_warc_record
+import cdx_toolkit.warc
 
 def test_wb_redir_to_original():
     location = 'https://web.archive.org/web/20110209062054id_/http://commoncrawl.org/'
     ret = 'http://commoncrawl.org/'
-    assert wb_redir_to_original(location) == ret
-
-
-def test_fetch_warc_record_from_http():
-    encoding = "utf-8"
-    capture = {'url': 'https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=319', 'mime': 'text/html', 'mime-detected': 'application/xhtml+xml', 'status': '200', 'digest': 'D5K3FUWDRAOMMTJC2CTWV7L2ABFIJ5BP', 'length': '9754', 'offset': '111440525', 'filename': 'crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00337.warc.gz', 'charset': 'UTF-8', 'languages': 'fra', 'timestamp': '20240716153155'}
-    warc_download_prefix = 'https://data.commoncrawl.org'
-
-    record = fetch_warc_record(capture, warc_download_prefix)
-    record_content = record.content_stream().read().decode(encoding, errors="ignore")
-
-    assert record.rec_type == "response"
-    assert record.length == 75825
-    assert "<title>Catalogue en ligne Mission de France</title>" in record_content
-
-
-@requires_aws_s3
-def test_fetch_warc_record_from_s3():
-    encoding = "utf-8"
-    capture = {'url': 'https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=319', 'mime': 'text/html', 'mime-detected': 'application/xhtml+xml', 'status': '200', 'digest': 'D5K3FUWDRAOMMTJC2CTWV7L2ABFIJ5BP', 'length': '9754', 'offset': '111440525', 'filename': 'crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00337.warc.gz', 'charset': 'UTF-8', 'languages': 'fra', 'timestamp': '20240716153155'}
-    warc_download_prefix = 's3://commoncrawl'
-
-    record = fetch_warc_record(capture, warc_download_prefix)
-    record_content = record.content_stream().read().decode(encoding, errors="ignore")
-
-    assert record.rec_type == "response"
-    assert record.length == 75825
-    assert "<title>Catalogue en ligne Mission de France</title>" in record_content
-
+    assert cdx_toolkit.warc.wb_redir_to_original(location) == ret
diff --git a/tests/warc_by_cdx/__init__.py b/tests/warc_by_cdx/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/tests/warc_by_cdx/test_filter_cdx.py b/tests/warc_by_cdx/test_filter_cdx.py
new file mode 100644
index 0000000..988f523
--- /dev/null
+++ b/tests/warc_by_cdx/test_filter_cdx.py
@@ -0,0 +1,165 @@
+import pytest
+from pathlib import Path
+
+from cdx_toolkit.cli import main
+from cdx_toolkit.filter_cdx import resolve_paths, validate_resolved_paths
+from tests.conftest import requires_aws_s3
+
+fixture_path = Path(__file__).parent.parent / 'data/filter_cdx'
+
+
+@requires_aws_s3
+def test_cli_filter_cdx_with_surts(tmpdir, caplog):
+    # check if expected number is reached
+    index_path = 's3://commoncrawl/cc-index/collections'
+    index_glob = '/CC-MAIN-2024-30/indexes/cdx-00187.gz'
+    whitelist_path = fixture_path / 'whitelist_10_surts.txt'  # matches on first domain and after 100k and 200k lines
+
+    main(
+        args=[
+            '-v',
+            '--limit=1140',
+            'filter_cdx',
+            f'{index_path}',
+            f'{str(whitelist_path)}',
+            f'{tmpdir}',
+            '--filter-type=surt',
+            f'--input-glob={index_glob}'
+        ]
+    )
+
+    assert 'Limit reached' in caplog.text
+
+
+@requires_aws_s3
+def test_cli_filter_cdx_with_urls(tmpdir, caplog):
+    # check if expected number is reached
+    index_path = 's3://commoncrawl/cc-index/collections'
+    index_glob = '/CC-MAIN-2024-30/indexes/cdx-00187.gz'
+    whitelist_path = fixture_path / 'whitelist_10_urls.txt'  # matches on first domain and after 100k and 200k lines
+
+    main(
+        args=[
+            '-v',
+            '--limit=1140',
+            'filter_cdx',
+            f'{index_path}',
+            f'{str(whitelist_path)}',
+            f'{tmpdir}',
+            '--filter-type=url',
+            f'--input-glob={index_glob}'
+        ]
+    )
+
+    assert 'Limit reached' in caplog.text
+
+
+@requires_aws_s3
+def test_resolve_cdx_paths_from_cc_s3_to_local(tmpdir):
+    tmpdir = str(tmpdir)
+    base_path = 's3://commoncrawl/cc-index/collections'
+    glob_pattern = '/CC-MAIN-2016-30/indexes/*.gz'
+
+    input_files, output_files = resolve_paths(base_path, glob_pattern, output_base_path=tmpdir)
+
+    assert len(input_files) == len(output_files), 'Input and output count must be the same'
+    assert len(input_files) == 300, 'Invalid input count'
+    assert input_files[0] == base_path + '/CC-MAIN-2016-30/indexes/cdx-00000.gz', 'Invalid input file'
+    assert output_files[0] == tmpdir + '/CC-MAIN-2016-30/indexes/cdx-00000.gz', 'Invalid output file'
+    assert input_files[-1] == base_path + '/CC-MAIN-2016-30/indexes/cdx-00299.gz'
+
+
+@requires_aws_s3
+def test_resolve_cdx_paths_from_cc_s3_to_another_s3():
+    output_base_path = 's3://some-other-bucket/filter-cdx'
+    base_path = 's3://commoncrawl/cc-index/collections'
+    glob_pattern = '/CC-MAIN-2016-30/indexes/cdx-000*.gz'
+
+    input_files, output_files = resolve_paths(base_path, glob_pattern, output_base_path=output_base_path)
+
+    assert len(input_files) == len(output_files), 'Input and output count must be the same'
+    assert len(input_files) == 100, 'Invalid input count'
+    assert input_files[0] == base_path + '/CC-MAIN-2016-30/indexes/cdx-00000.gz', 'Invalid input file'
+    assert output_files[0] == output_base_path + '/CC-MAIN-2016-30/indexes/cdx-00000.gz', 'Invalid output file'
+    assert input_files[-1] == base_path + '/CC-MAIN-2016-30/indexes/cdx-00099.gz'
+
+
+@requires_aws_s3
+def test_filter_cdx_nonexistent_surt_file_exits(tmpdir, caplog):
+    index_path = 's3://commoncrawl/cc-index/collections'
+    index_glob = '/CC-MAIN-2024-30/indexes/cdx-00187.gz'
+    nonexistent_surt_file = str(tmpdir / 'nonexistent_surts.txt')
+
+    # Test that the command exits when SURT file doesn't exist
+    with pytest.raises(SystemExit) as exc_info:
+        main(
+            args=[
+                '-v',
+                '--limit=1140',
+                'filter_cdx',
+                f'{index_path}',
+                f'{nonexistent_surt_file}',
+                f'{tmpdir}',
+                f'--input-glob={index_glob}'
+            ]
+        )
+
+    assert exc_info.value.code == 1
+    assert f'Filter file not found: {nonexistent_surt_file}' in caplog.text
+
+
+def test_resolve_paths_no_files_found_exits(tmpdir, caplog):
+    # Test that resolve_paths exits when no files match the glob pattern
+    with pytest.raises(SystemExit) as exc_info:
+        resolve_paths(input_base_path=str(tmpdir), input_glob='/nonexistent-pattern-*.gz', output_base_path=str(tmpdir))
+
+    assert exc_info.value.code == 1
+    assert 'No files found matching glob pattern:' in caplog.text
+
+
+def test_validate_resolved_paths_existing_file_exits(tmpdir, caplog):
+    # Create an existing output file
+    existing_file = tmpdir / 'existing_output.txt'
+    existing_file.write_text('existing content', encoding='utf-8')
+
+    output_paths = [str(existing_file)]
+
+    # Test that validate_resolved_paths exits when output file exists and overwrite=False
+    with pytest.raises(SystemExit) as exc_info:
+        validate_resolved_paths(output_paths, overwrite=False)
+
+    assert exc_info.value.code == 1
+    assert f'Output file already exists: {str(existing_file)}' in caplog.text
+    assert 'Use --overwrite to overwrite existing files' in caplog.text
+
+
+@requires_aws_s3
+def test_cli_filter_cdx_with_parallel_processing(tmpdir, caplog):
+    """Test that parallel processing works correctly and processes multiple files."""
+    index_path = 's3://commoncrawl/cc-index/collections'
+    index_glob = '/CC-MAIN-2024-30/indexes/cdx-0018[78].gz'  # Multiple files pattern
+    whitelist_path = fixture_path / 'whitelist_11_surts.txt'  # Additonal entry for cdx-00188.gz
+
+    # Run with parallel processing (2 workers)
+    main(
+        args=[
+            '-v',
+            '--limit=10',
+            'filter_cdx',
+            f'{index_path}',
+            f'{str(whitelist_path)}',
+            f'{tmpdir}',
+            '--filter-type=surt',
+            f'--input-glob={index_glob}',
+            '--parallel=2'
+        ]
+    )
+
+    # Check that multiple files were processed in parallel
+    assert 'Found' in caplog.text and 'files matching pattern' in caplog.text
+    assert 'File statistics for' in caplog.text
+    assert 'Total statistics:' in caplog.text
+
+    # Should have processed multiple files (pattern matches 2 files: cdx-00187.gz and cdx-00188.gz)
+    file_stats_count = caplog.text.count('File statistics for')
+    assert file_stats_count == 2, 'Should process exactly 2 files with the glob pattern'
diff --git a/tests/test_matcher.py b/tests/warc_by_cdx/test_matcher.py
similarity index 58%
rename from tests/test_matcher.py
rename to tests/warc_by_cdx/test_matcher.py
index 527467c..b449fc9 100644
--- a/tests/test_matcher.py
+++ b/tests/warc_by_cdx/test_matcher.py
@@ -3,74 +3,74 @@
 
 
 @pytest.mark.parametrize(
-    "prefixes,test_strings,expected_results",
+    'prefixes,test_strings,expected_results',
     [
         # Basic functionality
         (
-            ["http://", "https://"],
-            ["http://example.com", "https://example.com", "ftp://example.com"],
+            ['http://', 'https://'],
+            ['http://example.com', 'https://example.com', 'ftp://example.com'],
             [True, True, False],
         ),
         # Empty prefix list
-        ([], ["any string", "", "test"], [False, False, False]),
+        ([], ['any string', '', 'test'], [False, False, False]),
         # Single character prefixes
         (
-            ["a", "b", "c"],
-            ["apple", "banana", "cherry", "dog", ""],
+            ['a', 'b', 'c'],
+            ['apple', 'banana', 'cherry', 'dog', ''],
             [True, True, True, False, False],
         ),
         # Overlapping prefixes
         (
-            ["test", "testing", "te"],
-            ["test", "testing", "tea", "other"],
+            ['test', 'testing', 'te'],
+            ['test', 'testing', 'tea', 'other'],
             [True, True, True, False],
         ),
         # Unicode characters
         (
-            ["café", "naïve", "résumé"],
-            ["café au lait", "naïve person", "résumé.pdf", "regular text"],
+            ['café', 'naïve', 'résumé'],
+            ['café au lait', 'naïve person', 'résumé.pdf', 'regular text'],
             [True, True, True, False],
         ),
         # Special characters
         (
-            ["[test]", ".*", "\\n"],
-            ["[test] case", ".*regex", "\\newline", "normal"],
+            ['[test]', '.*', '\\n'],
+            ['[test] case', '.*regex', '\\newline', 'normal'],
             [True, True, True, False],
         ),
         # Case sensitivity
         (
-            ["HTTP", "Https"],
-            ["HTTP://example.com", "https://example.com", "HTTPS://EXAMPLE.COM"],
+            ['HTTP', 'Https'],
+            ['HTTP://example.com', 'https://example.com', 'HTTPS://EXAMPLE.COM'],
             [True, False, True],
         ),
         # Very long prefixes
         (
-            ["a" * 1000],
-            ["a" * 1000 + "suffix", "a" * 999, "b" * 1000],
+            ['a' * 1000],
+            ['a' * 1000 + 'suffix', 'a' * 999, 'b' * 1000],
             [True, False, False],
         ),
         # Duplicate prefixes
         (
-            ["test", "test", "demo"],
-            ["testing", "demo version", "other"],
+            ['test', 'test', 'demo'],
+            ['testing', 'demo version', 'other'],
             [True, True, False],
         ),
         # Prefixes that are substrings of each other
         (
-            ["ab", "abc", "abcd"],
-            ["ab", "abc", "abcd", "abcde", "a"],
+            ['ab', 'abc', 'abcd'],
+            ['ab', 'abc', 'abcd', 'abcde', 'a'],
             [True, True, True, True, False],
         ),
         # Numbers and mixed content
         (
-            ["123", "4.56"],
-            ["123test", "4.56789", "789", "test123"],
+            ['123', '4.56'],
+            ['123test', '4.56789', '789', 'test123'],
             [True, True, False, False],
         ),
         # Whitespace handling (note: whitespace is stripped from prefixes, so " test" becomes "test")
         (
-            [" test", "\tindent", "\nline"],
-            ["test case", "indented", "line break", " test case", "nowhitespace"],
+            [' test', '\tindent', '\nline'],
+            ['test case', 'indented', 'line break', ' test case', 'nowhitespace'],
             [True, True, True, False, False],
         ),
     ],
@@ -86,32 +86,31 @@ def test_matcher_approaches(prefixes, test_strings, expected_results):
 
         # Both matchers should agree with each other
         assert tuple_result == trie_result, (
-            f"TupleMatcher({tuple_result}) != TrieMatcher({trie_result}) "
+            f'TupleMatcher({tuple_result}) != TrieMatcher({trie_result}) '
             f"for prefixes {prefixes} and string '{test_string}'"
         )
 
         # Both should match the expected result
         assert tuple_result == expected_result, (
-            f"Expected {expected_result}, got {tuple_result} "
-            f"for prefixes {prefixes} and string '{test_string}'"
+            f"Expected {expected_result}, got {tuple_result} for prefixes {prefixes} and string '{test_string}'"
         )
 
 
 @pytest.mark.parametrize(
-    "invalid_prefixes,expected_error",
+    'invalid_prefixes,expected_error',
     [
         # Empty string prefixes
-        ([""], "Empty prefixes are not allowed"),
+        ([''], 'Empty prefixes are not allowed'),
         # Whitespace-only prefixes (should be stripped to empty and raise error)
-        (["   "], "Empty prefixes are not allowed"),
-        (["\t\n "], "Empty prefixes are not allowed"),
+        (['   '], 'Empty prefixes are not allowed'),
+        (['\t\n '], 'Empty prefixes are not allowed'),
         # None values
-        ([None], "Prefix must be a string and not none"),
-        (["test", None, "demo"], "Prefix must be a string and not none"),
+        ([None], 'Prefix must be a string and not none'),
+        (['test', None, 'demo'], 'Prefix must be a string and not none'),
         # Non-string types
-        ([123], "Prefix must be a string and not none"),
-        (["test", 456, "demo"], "Prefix must be a string and not none"),
-        ([[], {}, set()], "Prefix must be a string and not none"),
+        ([123], 'Prefix must be a string and not none'),
+        (['test', 456, 'demo'], 'Prefix must be a string and not none'),
+        ([[], {}, set()], 'Prefix must be a string and not none'),
     ],
 )
 def test_prefix_validation_errors(invalid_prefixes, expected_error):
@@ -125,23 +124,23 @@ def test_prefix_validation_errors(invalid_prefixes, expected_error):
 
 
 @pytest.mark.parametrize(
-    "test_string,expected",
+    'test_string,expected',
     [
-        ("test", True),
-        ("testing", True),
-        ("demo", True),
-        ("demonstration", True),
-        ("example", True),
-        ("examples", True),
-        ("  test", False),  # Leading whitespace in test string shouldn't match
-        ("other", False),
+        ('test', True),
+        ('testing', True),
+        ('demo', True),
+        ('demonstration', True),
+        ('example', True),
+        ('examples', True),
+        ('  test', False),  # Leading whitespace in test string shouldn't match
+        ('other', False),
     ],
 )
 def test_whitespace_stripping(test_string, expected):
     """Test that whitespace is properly stripped from prefixes."""
 
     # Prefixes with leading/trailing whitespace should be stripped
-    prefixes_with_whitespace = ["  test  ", "\tdemo\n", " example "]
+    prefixes_with_whitespace = ['  test  ', '\tdemo\n', ' example ']
 
     tuple_matcher = TupleMatcher(prefixes_with_whitespace)
     trie_matcher = TrieMatcher(prefixes_with_whitespace)
@@ -151,11 +150,11 @@ def test_whitespace_stripping(test_string, expected):
 
     assert tuple_result == trie_result == expected, (
         f"Whitespace stripping test failed for '{test_string}': "
-        f"expected {expected}, got Tuple({tuple_result}), Trie({trie_result})"
+        f'expected {expected}, got Tuple({tuple_result}), Trie({trie_result})'
     )
 
 
-@pytest.mark.parametrize("test_string", ["anything", "", "test", "a", "123"])
+@pytest.mark.parametrize('test_string', ['anything', '', 'test', 'a', '123'])
 def test_empty_prefix_list(test_string):
     """Test with empty prefix list - should never match anything."""
     empty_prefixes = []
@@ -167,16 +166,16 @@ def test_empty_prefix_list(test_string):
     trie_result = trie_matcher.matches(test_string)
 
     # Both should return False for empty prefix list
-    assert tuple_result == trie_result == False, (
+    assert not tuple_result and not trie_result, (
         f"Both matchers should return False for '{test_string}' with empty prefixes, "
-        f"got Tuple({tuple_result}), Trie({trie_result})"
+        f'got Tuple({tuple_result}), Trie({trie_result})'
     )
 
 
 def test_empty_string_against_prefixes():
     """Test matching empty strings against non-empty prefixes."""
-    non_empty_prefixes = ["test", "demo", "example"]
-    empty_test_string = ""
+    non_empty_prefixes = ['test', 'demo', 'example']
+    empty_test_string = ''
 
     tuple_matcher = TupleMatcher(non_empty_prefixes)
     trie_matcher = TrieMatcher(non_empty_prefixes)
@@ -185,28 +184,28 @@ def test_empty_string_against_prefixes():
     trie_result = trie_matcher.matches(empty_test_string)
 
     # Both should return False when testing empty string against non-empty prefixes
-    assert tuple_result == trie_result == False, (
-        f"Both matchers should return False for empty string with non-empty prefixes, "
-        f"got Tuple({tuple_result}), Trie({trie_result})"
+    assert not tuple_result and not trie_result, (
+        f'Both matchers should return False for empty string with non-empty prefixes, '
+        f'got Tuple({tuple_result}), Trie({trie_result})'
     )
 
 
 @pytest.mark.parametrize(
-    "test_string,expected",
+    'test_string,expected',
     [
-        ("a", True),
-        ("1", True),
-        ("!", True),
-        ("ab", True),
-        ("12", True),
-        ("!@", True),
-        ("other", False),
-        ("", False),
+        ('a', True),
+        ('1', True),
+        ('!', True),
+        ('ab', True),
+        ('12', True),
+        ('!@', True),
+        ('other', False),
+        ('', False),
     ],
 )
 def test_single_character_edge_cases(test_string, expected):
     """Test single character prefixes and strings (without empty prefixes)."""
-    prefixes = ["a", "1", "!"]
+    prefixes = ['a', '1', '!']
 
     tuple_matcher = TupleMatcher(prefixes)
     trie_matcher = TrieMatcher(prefixes)
@@ -214,16 +213,16 @@ def test_single_character_edge_cases(test_string, expected):
     tuple_result = tuple_matcher.matches(test_string)
     trie_result = trie_matcher.matches(test_string)
 
-    assert (
-        tuple_result == trie_result == expected
-    ), f"Mismatch for '{test_string}': Tuple({tuple_result}), Trie({trie_result}), Expected({expected})"
+    assert tuple_result == trie_result == expected, (
+        f"Mismatch for '{test_string}': Tuple({tuple_result}), Trie({trie_result}), Expected({expected})"
+    )
 
 
 def test_performance_with_many_prefixes():
     """Test with a large number of prefixes to ensure both matchers handle it."""
     # Create many prefixes
-    prefixes = [f"prefix_{i}" for i in range(1000)]
-    test_strings = ["prefix_500test", "prefix_999", "nomatch", "prefix_1000"]
+    prefixes = [f'prefix_{i}' for i in range(1000)]
+    test_strings = ['prefix_500test', 'prefix_999', 'nomatch', 'prefix_1000']
 
     tuple_matcher = TupleMatcher(prefixes)
     trie_matcher = TrieMatcher(prefixes)
@@ -235,22 +234,22 @@ def test_performance_with_many_prefixes():
 
 
 @pytest.mark.parametrize(
-    "test_string,expected",
+    'test_string,expected',
     [
-        ("", False),
-        ("a", True),
-        ("ab", True),
-        ("abc", True),
-        ("abcd", True),
-        ("abcde", True),
-        ("abcdef", True),
-        ("b", False),
-        ("ac", True),
+        ('', False),
+        ('a', True),
+        ('ab', True),
+        ('abc', True),
+        ('abcd', True),
+        ('abcde', True),
+        ('abcdef', True),
+        ('b', False),
+        ('ac', True),
     ],
 )
 def test_nested_prefixes(test_string, expected):
     """Test with prefixes that are nested within each other."""
-    prefixes = ["a", "ab", "abc", "abcd", "abcde"]
+    prefixes = ['a', 'ab', 'abc', 'abcd', 'abcde']
 
     tuple_matcher = TupleMatcher(prefixes)
     trie_matcher = TrieMatcher(prefixes)
@@ -260,23 +259,23 @@ def test_nested_prefixes(test_string, expected):
 
     assert tuple_result == trie_result == expected, (
         f"Nested prefix test failed for '{test_string}': "
-        f"expected {expected}, got Tuple({tuple_result}), Trie({trie_result})"
+        f'expected {expected}, got Tuple({tuple_result}), Trie({trie_result})'
     )
 
 
 @pytest.mark.parametrize(
-    "test_string,expected",
+    'test_string,expected',
     [
-        ("🌟test", True),
-        ("café au lait", True),
-        ("𝓤𝓷𝓲𝓬𝓸𝓭𝓮 text", True),
-        ("regular", False),
-        ("", False),
+        ('🌟test', True),
+        ('café au lait', True),
+        ('𝓤𝓷𝓲𝓬𝓸𝓭𝓮 text', True),
+        ('regular', False),
+        ('', False),
     ],
 )
 def test_unicode_edge_cases(test_string, expected):
     """Test Unicode handling edge cases (without empty prefixes)."""
-    prefixes = ["🌟", "café", "𝓤𝓷𝓲𝓬𝓸𝓭𝓮"]
+    prefixes = ['🌟', 'café', '𝓤𝓷𝓲𝓬𝓸𝓭𝓮']
 
     tuple_matcher = TupleMatcher(prefixes)
     trie_matcher = TrieMatcher(prefixes)
@@ -284,16 +283,16 @@ def test_unicode_edge_cases(test_string, expected):
     tuple_result = tuple_matcher.matches(test_string)
     trie_result = trie_matcher.matches(test_string)
 
-    assert (
-        tuple_result == trie_result == expected
-    ), f"Unicode mismatch for '{test_string}': Tuple({tuple_result}), Trie({trie_result}), Expected({expected})"
+    assert tuple_result == trie_result == expected, (
+        f"Unicode mismatch for '{test_string}': Tuple({tuple_result}), Trie({trie_result}), Expected({expected})"
+    )
 
 
 def test_with_list_and_tuple_inputs():
     """Test that both list and tuple inputs work identically."""
-    prefixes_list = ["test", "demo", "example"]
-    prefixes_tuple = ("test", "demo", "example")
-    test_strings = ["testing", "demo version", "example.com", "other"]
+    prefixes_list = ['test', 'demo', 'example']
+    prefixes_tuple = ('test', 'demo', 'example')
+    test_strings = ['testing', 'demo version', 'example.com', 'other']
 
     # Test with list input
     tuple_matcher_list = TupleMatcher(prefixes_list)
@@ -312,7 +311,4 @@ def test_with_list_and_tuple_inputs():
             trie_matcher_tuple.matches(test_string),
         ]
 
-        assert all(
-            r == results[0] for r in results
-        ), f"Inconsistent results for '{test_string}': {results}"
-
+        assert all(r == results[0] for r in results), f"Inconsistent results for '{test_string}': {results}"
diff --git a/tests/test_warc_by_cdx.py b/tests/warc_by_cdx/test_warc_by_cdx.py
similarity index 51%
rename from tests/test_warc_by_cdx.py
rename to tests/warc_by_cdx/test_warc_by_cdx.py
index 3ed7b64..791cfe0 100644
--- a/tests/test_warc_by_cdx.py
+++ b/tests/warc_by_cdx/test_warc_by_cdx.py
@@ -1,5 +1,6 @@
 import os
 from pathlib import Path
+from typing import List
 
 import fsspec
 from cdx_toolkit.cli import main
@@ -12,26 +13,41 @@
 import pytest
 from warcio.archiveiterator import ArchiveIterator
 
-from conftest import requires_aws_s3
+from tests.conftest import requires_aws_s3
 
 
-fixture_path = Path(__file__).parent / "data/warc_by_cdx"
+fixture_path = Path(__file__).parent.parent / 'data/warc_by_cdx'
 
 
-def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog, extra_args=""):
+def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog, extra_args: None | List[str] = None):
     # test cli and check output
-    index_path = fixture_path / "filtered_CC-MAIN-2024-30_cdx-00187.gz"
+    index_path = fixture_path / 'filtered_CC-MAIN-2024-30_cdx-00187.gz'
+
+    if extra_args is None:
+        extra_args = []
 
     main(
-        args=f"""-v --cc --limit 10  warc_by_cdx {str(index_path)} --write-index-as-record --prefix {str(base_prefix)}/TEST_warc_by_index --creator foo --operator bob --warc-download-prefix {warc_download_prefix} {extra_args}""".split()
+        args=[
+            '-v',
+            '--cc',
+            '--limit=10',
+            'warc_by_cdx',
+            f'{str(index_path)}',
+            '--write-index-as-record',
+            f'--prefix={str(base_prefix)}/TEST_warc_by_index',
+            '--creator=foo',
+            '--operator=bob',
+            f'--warc-download-prefix={warc_download_prefix}',
+        ]
+        + extra_args
     )
 
     # Check log
-    assert "Limit reached" in caplog.text
+    assert 'Limit reached' in caplog.text
 
     # Validate extracted WARC
-    warc_filename = "TEST_warc_by_index-000000.extracted.warc.gz"
-    warc_path = str(base_prefix) + "/" + warc_filename
+    warc_filename = 'TEST_warc_by_index-000000.extracted.warc.gz'
+    warc_path = str(base_prefix) + '/' + warc_filename
     resource_record = None
     info_record = None
     response_records = []
@@ -39,11 +55,11 @@ def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog, extra_args
     with fsspec.open(warc_path, 'rb') as stream:
         for record in ArchiveIterator(stream):
             if record.rec_type == 'warcinfo':
-                info_record = record.content_stream().read().decode("utf-8")
-        
+                info_record = record.content_stream().read().decode('utf-8')
+
             if record.rec_type == 'response':
                 response_records.append(record)
-                
+
             if record.rec_type == 'resource':
                 resource_record = record
 
@@ -52,76 +68,108 @@ def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog, extra_args
     assert resource_record.length == 568010
 
     assert info_record is not None
-    assert "operator: bob" in info_record
+    assert 'operator: bob' in info_record
 
 
 def test_cli_warc_by_cdx_over_http(tmpdir, caplog):
-    assert_cli_warc_by_cdx("https://data.commoncrawl.org", base_prefix=tmpdir, caplog=caplog)
+    assert_cli_warc_by_cdx('https://data.commoncrawl.org', base_prefix=tmpdir, caplog=caplog)
+
 
 def test_cli_warc_by_cdx_over_http_in_parallel(tmpdir, caplog):
-    assert_cli_warc_by_cdx("https://data.commoncrawl.org", base_prefix=tmpdir, caplog=caplog, extra_args=" --parallel 3")
+    assert_cli_warc_by_cdx(
+        'https://data.commoncrawl.org', base_prefix=tmpdir, caplog=caplog, extra_args=['--parallel=3']
+    )
+
 
 @requires_aws_s3
 def test_cli_warc_by_cdx_over_s3(tmpdir, caplog):
-    assert_cli_warc_by_cdx("s3://commoncrawl", base_prefix=tmpdir, caplog=caplog)
+    assert_cli_warc_by_cdx('s3://commoncrawl', base_prefix=tmpdir, caplog=caplog)
+
 
 @requires_aws_s3
 def test_cli_warc_by_cdx_over_s3_to_s3(tmpdir, caplog):
-    assert_cli_warc_by_cdx("s3://commoncrawl", base_prefix="s3://commoncrawl-dev/cdx_toolkit/ci/test-outputs" + str(tmpdir), caplog=caplog)
+    assert_cli_warc_by_cdx(
+        's3://commoncrawl', base_prefix='s3://commoncrawl-dev/cdx_toolkit/ci/test-outputs' + str(tmpdir), caplog=caplog
+    )
+
 
 @requires_aws_s3
 def test_cli_warc_by_cdx_over_s3_to_s3_in_parallel(tmpdir, caplog):
-    assert_cli_warc_by_cdx("s3://commoncrawl", base_prefix="s3://commoncrawl-dev/cdx_toolkit/ci/test-outputs" + str(tmpdir), caplog=caplog, extra_args=" --parallel 3")
+    assert_cli_warc_by_cdx(
+        's3://commoncrawl',
+        base_prefix='s3://commoncrawl-dev/cdx_toolkit/ci/test-outputs' + str(tmpdir),
+        caplog=caplog,
+        extra_args=['--parallel=3'],
+    )
 
 
 def test_get_caputure_objects_from_index():
-    index_path = fixture_path / "filtered_CC-MAIN-2024-30_cdx-00187.gz"
+    index_path = fixture_path / 'filtered_CC-MAIN-2024-30_cdx-00187.gz'
 
     for obj in generate_caputure_objects_from_index(get_index_as_string_from_path(index_path).splitlines()):
         break
 
-    assert obj.data["length"] == "9754"
+    assert obj.data['length'] == '9754'
 
 
 def test_warc_by_cdx_no_index_files_found_exits(tmpdir, caplog):
     # Test that warc_by_cdx exits when no index files match the glob pattern
     with pytest.raises(SystemExit) as exc_info:
         main(
-            args=f"""-v --cc --cc-mirror https://index.commoncrawl.org/ warc_by_cdx {str(tmpdir)} --prefix {str(tmpdir)}/TEST --index-glob "/nonexistent-pattern-*.gz" """.split()
+            args=[
+                '-v',
+                '--cc',
+                '--cc-mirror=https://index.commoncrawl.org/',
+                'warc_by_cdx',
+                f'{str(tmpdir)}',
+                f'--prefix={str(tmpdir)}/TEST',
+                '--index-glob=/nonexistent-pattern-*.gz',
+            ]
         )
-    
+
     assert exc_info.value.code == 1
-    assert "no index files found" in caplog.text
+    assert 'no index files found' in caplog.text
 
 
-def test_generate_caputure_objects_invalid_cdx_line():    
+def test_generate_caputure_objects_invalid_cdx_line():
     # Test invalid CDX line parsing (line with wrong number of columns)
     with pytest.raises(ValueError):
-        list(generate_caputure_objects_from_index("invalid-format"))
+        list(generate_caputure_objects_from_index('invalid-format'))
 
 
 def test_generate_caputure_objects_with_limit():
     # Test limit functionality in get_caputure_objects_from_index
-    index_path = fixture_path / "filtered_CC-MAIN-2024-30_cdx-00187.gz"
+    index_path = fixture_path / 'filtered_CC-MAIN-2024-30_cdx-00187.gz'
     index_content = get_index_as_string_from_path(index_path)
-    
+
     # Count objects with limit=2
     objects = list(generate_caputure_objects_from_index(index_content.splitlines(), limit=2))
-    
+
     # Should stop after 2 objects
     assert len(objects) == 2
 
 
 def test_warc_by_cdx_subprefix_and_metadata(tmpdir):
     # Test subprefix functionality and creator/operator metadata
-    index_path = fixture_path / "filtered_CC-MAIN-2024-30_cdx-00187.gz"
+    index_path = fixture_path / 'filtered_CC-MAIN-2024-30_cdx-00187.gz'
 
     main(
-        args=f"""-v --cc --cc-mirror https://index.commoncrawl.org/ --limit 1 warc_by_cdx {str(index_path)} --prefix {str(tmpdir)}/TEST --subprefix SUB --creator test_creator --operator test_operator""".split()
+        args=[
+            '-v',
+            '--cc',
+            '--cc-mirror=https://index.commoncrawl.org/',
+            '--limit=1',
+            'warc_by_cdx',
+            f'{str(index_path)}',
+            f'--prefix={str(tmpdir)}/TEST',
+            '--subprefix=SUB',
+            '--creator=test_creator',
+            '--operator=test_operator',
+        ]
     )
 
     # Check that WARC file was created with subprefix
-    warc_path = os.path.join(tmpdir, "TEST-SUB-000000.extracted.warc.gz")
+    warc_path = os.path.join(tmpdir, 'TEST-SUB-000000.extracted.warc.gz')
     assert os.path.exists(warc_path)
 
     # Validate metadata in warcinfo record
@@ -129,24 +177,32 @@ def test_warc_by_cdx_subprefix_and_metadata(tmpdir):
     with open(warc_path, 'rb') as stream:
         for record in ArchiveIterator(stream):
             if record.rec_type == 'warcinfo':
-                info_record = record.content_stream().read().decode("utf-8")
+                info_record = record.content_stream().read().decode('utf-8')
                 break
 
     assert info_record is not None
-    assert "creator: test_creator" in info_record
-    assert "operator: test_operator" in info_record
+    assert 'creator: test_creator' in info_record
+    assert 'operator: test_operator' in info_record
 
 
 def test_warc_by_cdx_without_creator_operator(tmpdir):
     # Test that creator and operator are optional (lines 44-47)
-    index_path = fixture_path / "filtered_CC-MAIN-2024-30_cdx-00187.gz"
+    index_path = fixture_path / 'filtered_CC-MAIN-2024-30_cdx-00187.gz'
 
     main(
-        args=f"""-v --cc --cc-mirror https://index.commoncrawl.org/ --limit 1 warc_by_cdx {str(index_path)} --prefix {str(tmpdir)}/TEST_NO_META""".split()
+        args=[
+            '-v',
+            '--cc',
+            '--cc-mirror=https://index.commoncrawl.org/',
+            '--limit=1',
+            'warc_by_cdx',
+            f'{str(index_path)}',
+            f'--prefix={str(tmpdir)}/TEST_NO_META',
+        ]
     )
 
     # Check that WARC file was created
-    warc_path = os.path.join(tmpdir, "TEST_NO_META-000000.extracted.warc.gz")
+    warc_path = os.path.join(tmpdir, 'TEST_NO_META-000000.extracted.warc.gz')
     assert os.path.exists(warc_path)
 
     # Validate that creator/operator are not in warcinfo record
@@ -154,9 +210,9 @@ def test_warc_by_cdx_without_creator_operator(tmpdir):
     with open(warc_path, 'rb') as stream:
         for record in ArchiveIterator(stream):
             if record.rec_type == 'warcinfo':
-                info_record = record.content_stream().read().decode("utf-8")
+                info_record = record.content_stream().read().decode('utf-8')
                 break
 
     assert info_record is not None
-    assert "creator:" not in info_record
-    assert "operator:" not in info_record
+    assert 'creator:' not in info_record
+    assert 'operator:' not in info_record
diff --git a/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py b/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
new file mode 100644
index 0000000..69a50ab
--- /dev/null
+++ b/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
@@ -0,0 +1,105 @@
+from io import BytesIO
+from pathlib import Path
+from typing import List
+
+import fsspec
+from cdx_toolkit.cli import main
+from warcio.archiveiterator import ArchiveIterator
+
+from tests.conftest import requires_aws_s3
+
+from warcio import WARCWriter
+
+fixture_path = Path(__file__).parent.parent / 'data/warc_by_cdx'
+
+
+def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog, extra_args: None | List[str] = None):
+    # test cli and check output
+    index_path = fixture_path / 'filtered_CC-MAIN-2024-30_cdx-00187.gz'
+    if extra_args is None:
+        extra_args = []
+
+    # --write-index-as-record
+
+    main(
+        args=[
+            '-v',
+            '--cc',
+            '--limit=10',
+            'warc_by_cdx',
+            str(index_path),
+            f'--prefix={str(base_prefix)}/TEST_warc_by_index',
+            '--creator=foo',
+            '--operator=bob',
+            f'--warc-download-prefix={warc_download_prefix}',
+        ]
+        + extra_args,
+    )
+
+    # Check log
+    assert 'Limit reached' in caplog.text
+
+    # Validate extracted WARC
+    warc_filename = 'TEST_warc_by_index-000000.extracted.warc.gz'
+    warc_path = str(base_prefix) + '/' + warc_filename
+    resource_record = None
+    info_record = None
+    response_records = []
+    response_contents = []
+
+    with fsspec.open(warc_path, 'rb') as stream:
+        for record in ArchiveIterator(stream):
+            if record.rec_type == 'warcinfo':
+                info_record = record.content_stream().read().decode('utf-8')
+
+            if record.rec_type == 'response':
+                response_records.append(record)
+                response_contents.append(record.content_stream().read().decode('utf-8', errors='ignore'))
+
+            # if record.rec_type == 'resource':
+            #     resource_record = record
+
+    assert len(response_records) == 10, 'Invalid record count'
+    # assert resource_record is not None
+    # assert resource_record.length == 568010
+
+    assert 'Catalogue en ligne Mission de France' in response_contents[0], 'Invalid response content'
+    assert 'dojo/dijit/themes/tundra/tundra' in response_contents[9], 'Invalid response content'
+    assert info_record is not None
+    assert 'operator: bob' in info_record, 'Invalid WARC info'
+
+
+@requires_aws_s3
+def test_cli_warc_by_cdx_over_s3_to_s3_in_parallel_aioboto3(tmpdir, caplog):
+    assert_cli_warc_by_cdx(
+        's3://commoncrawl',
+        base_prefix='s3://commoncrawl-dev/cdx_toolkit/ci/test-outputs' + str(tmpdir),
+        caplog=caplog,
+        extra_args=[
+            '--parallel=3',
+            '--implementation=aioboto3',
+        ],
+    )
+
+
+def test_warc_info():
+    warc_version = '1.0'
+    gzip = False
+    file_handler = BytesIO()
+    filename = 'foo.warc'
+
+    info = {
+        'software': 'pypi_cdx_toolkit/123',
+        'isPartOf': 'bar',
+        'description': 'warc extraction based on CDX generated with: xx',
+        'format': 'WARC file version 1.0',
+    }
+
+    writer = WARCWriter(file_handler, gzip=gzip, warc_version=warc_version)
+    warcinfo = writer.create_warcinfo_record(filename, info)
+
+    writer.write_record(warcinfo)
+
+    file_value = file_handler.getvalue().decode('utf-8')
+
+    assert 'pypi_cdx_toolkit/123' in file_value
diff --git a/tests/warc_by_cdx/test_warc_from_fs.py b/tests/warc_by_cdx/test_warc_from_fs.py
new file mode 100644
index 0000000..ccceaf0
--- /dev/null
+++ b/tests/warc_by_cdx/test_warc_from_fs.py
@@ -0,0 +1,53 @@
+from tests.conftest import requires_aws_s3
+from cdx_toolkit.warc import fetch_warc_record
+
+
+def test_fetch_warc_record_from_http():
+    encoding = 'utf-8'
+    capture = {
+        'url': 'https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=319',
+        'mime': 'text/html',
+        'mime-detected': 'application/xhtml+xml',
+        'status': '200',
+        'digest': 'D5K3FUWDRAOMMTJC2CTWV7L2ABFIJ5BP',
+        'length': '9754',
+        'offset': '111440525',
+        'filename': 'crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00337.warc.gz',
+        'charset': 'UTF-8',
+        'languages': 'fra',
+        'timestamp': '20240716153155',
+    }
+    warc_download_prefix = 'https://data.commoncrawl.org'
+
+    record = fetch_warc_record(capture, warc_download_prefix)
+    record_content = record.content_stream().read().decode(encoding, errors='ignore')
+
+    assert record.rec_type == 'response'
+    assert record.length == 75825
+    assert '<title>Catalogue en ligne Mission de France</title>' in record_content
+
+
+@requires_aws_s3
+def test_fetch_warc_record_from_s3():
+    encoding = 'utf-8'
+    capture = {
+        'url': 'https://bibliotheque.missiondefrance.fr/index.php?lvl=bulletin_display&id=319',
+        'mime': 'text/html',
+        'mime-detected': 'application/xhtml+xml',
+        'status': '200',
+        'digest': 'D5K3FUWDRAOMMTJC2CTWV7L2ABFIJ5BP',
+        'length': '9754',
+        'offset': '111440525',
+        'filename': 'crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00337.warc.gz',
+        'charset': 'UTF-8',
+        'languages': 'fra',
+        'timestamp': '20240716153155',
+    }
+    warc_download_prefix = 's3://commoncrawl'
+
+    record = fetch_warc_record(capture, warc_download_prefix)
+    record_content = record.content_stream().read().decode(encoding, errors='ignore')
+
+    assert record.rec_type == 'response'
+    assert record.length == 75825
+    assert '<title>Catalogue en ligne Mission de France</title>' in record_content
diff --git a/tests/test_warc_writer.py b/tests/warc_by_cdx/test_warc_writer.py
similarity index 66%
rename from tests/test_warc_writer.py
rename to tests/warc_by_cdx/test_warc_writer.py
index 78cbaee..70ca45b 100644
--- a/tests/test_warc_writer.py
+++ b/tests/warc_by_cdx/test_warc_writer.py
@@ -1,52 +1,52 @@
 from io import BytesIO
-import os
 import fsspec
 import pytest
 import cdx_toolkit
 
-from conftest import requires_aws_s3
+from tests.conftest import requires_aws_s3
 
 from warcio import WARCWriter
-from warcio.recordloader import ArcWarcRecord
 from warcio.archiveiterator import ArchiveIterator
 
+
 @pytest.mark.parametrize(
-    "prefix,gzip",
+    'prefix,gzip',
     [
-        pytest.param("test-prefix", False, id="File name prefix on local"),
-        pytest.param("test-prefix", True, id="File name prefix on local with gzip"),
-        
-        # pytest.param("test-prefix-folder/file-prefix", None, id="Folder as prefix"),  # raised FileNotFound error (parent dir does not exist)
+        pytest.param('test-prefix', False, id='File name prefix on local'),
+        pytest.param('test-prefix', True, id='File name prefix on local with gzip'),
+        # raised FileNotFound error (parent dir does not exist)
+        # pytest.param("test-prefix-folder/file-prefix", None, id="Folder as prefix"),  
     ],
 )
 def test_write_to_local(prefix, gzip, tmpdir):
     info = {
         'software': 'pypi_cdx_toolkit/test',
         'description': 'test',
-        'format': 'WARC file version 1.0', 
+        'format': 'WARC file version 1.0',
     }
-    encoding = "utf-8"
-    full_prefix = str(tmpdir) + "/" + prefix
+    encoding = 'utf-8'
+    full_prefix = str(tmpdir) + '/' + prefix
     fs, fs_prefix_path = fsspec.url_to_fs(full_prefix)
 
     writer = cdx_toolkit.warc.get_writer(full_prefix, None, info, gzip=gzip)
 
     # single record
-    input_resource_record_text = "foo bar text"
-    writer.write_record(WARCWriter(None).create_warc_record(
-            uri="foo/bar", 
-            record_type="resource",
+    input_resource_record_text = 'foo bar text'
+    writer.write_record(
+        WARCWriter(None).create_warc_record(
+            uri='foo/bar',
+            record_type='resource',
             payload=BytesIO(input_resource_record_text.encode(encoding)),
-            warc_content_type="text/plain",
+            warc_content_type='text/plain',
         )
     )
     writer.close()
 
     # Check that WARC file was created
-    warc_path = fs_prefix_path + "-000000.extracted.warc"
+    warc_path = fs_prefix_path + '-000000.extracted.warc'
     if gzip:
-        warc_path += ".gz"
-    
+        warc_path += '.gz'
+
     assert fs.exists(warc_path)
 
     # Validate that creator/operator are not in warcinfo record
@@ -56,7 +56,7 @@ def test_write_to_local(prefix, gzip, tmpdir):
         for record in ArchiveIterator(stream):
             if record.rec_type == 'warcinfo':
                 info_record = record.content_stream().read().decode(encoding)
-                
+
             if record.rec_type == 'resource':
                 resource_record = record.content_stream().read().decode(encoding)
                 break
@@ -64,24 +64,24 @@ def test_write_to_local(prefix, gzip, tmpdir):
     assert resource_record is not None
     assert info_record is not None
 
-    assert "description: test" in info_record
+    assert 'description: test' in info_record
     assert resource_record == input_resource_record_text
 
 
 @requires_aws_s3
 @pytest.mark.parametrize(
-    "prefix",
+    'prefix',
     [
-        pytest.param("s3://commoncrawl-dev/cdx_toolkit/ci/test-outputs", id="S3 prefix"),
+        pytest.param('s3://commoncrawl-dev/cdx_toolkit/ci/test-outputs', id='S3 prefix'),
     ],
 )
 def test_write_to_s3(prefix, tmpdir):
     info = {
         'software': 'pypi_cdx_toolkit/test',
         'description': 'test',
-        'format': 'WARC file version 1.0', 
+        'format': 'WARC file version 1.0',
     }
-    encoding = "utf-8"
+    encoding = 'utf-8'
     full_prefix = prefix + str(tmpdir)  # append tmp dir on S3
     fs, fs_prefix_path = fsspec.url_to_fs(full_prefix)
 
@@ -92,18 +92,19 @@ def test_write_to_s3(prefix, tmpdir):
     writer = cdx_toolkit.warc.get_writer(full_prefix, None, info)
 
     # single record
-    input_resource_record_text = "foo bar text"
-    writer.write_record(WARCWriter(None).create_warc_record(
-            uri="foo/bar", 
-            record_type="resource",
+    input_resource_record_text = 'foo bar text'
+    writer.write_record(
+        WARCWriter(None).create_warc_record(
+            uri='foo/bar',
+            record_type='resource',
             payload=BytesIO(input_resource_record_text.encode(encoding)),
-            warc_content_type="text/plain",
+            warc_content_type='text/plain',
         )
     )
     writer.close()
 
     # Check that WARC file was created
-    warc_path = fs_prefix_path + "-000000.extracted.warc.gz"
+    warc_path = fs_prefix_path + '-000000.extracted.warc.gz'
     assert fs.exists(warc_path)
 
     # Validate that creator/operator are not in warcinfo record
@@ -113,7 +114,7 @@ def test_write_to_s3(prefix, tmpdir):
         for record in ArchiveIterator(stream):
             if record.rec_type == 'warcinfo':
                 info_record = record.content_stream().read().decode(encoding)
-                
+
             if record.rec_type == 'resource':
                 resource_record = record.content_stream().read().decode(encoding)
                 break
@@ -121,5 +122,5 @@ def test_write_to_s3(prefix, tmpdir):
     assert resource_record is not None
     assert info_record is not None
 
-    assert "description: test" in info_record
+    assert 'description: test' in info_record
     assert resource_record == input_resource_record_text

From d45a3da5c1a1a66675dd0dedba800fe488f143cb Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Wed, 17 Sep 2025 11:03:45 +0000
Subject: [PATCH 20/74] fixing type hints for py38

---
 cdx_toolkit/filter_cdx/matcher.py             | 10 +++----
 cdx_toolkit/warcer_by_cdx/__init__.py         |  4 +--
 cdx_toolkit/warcer_by_cdx/aioboto3_utils.py   |  7 ++---
 cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py  | 30 ++++++++-----------
 cdx_toolkit/warcer_by_cdx/aioboto3_writer.py  |  8 ++---
 cdx_toolkit/warcer_by_cdx/cdx_utils.py        |  7 +++--
 cdx_toolkit/warcer_by_cdx/fsspec_warcer.py    |  8 ++---
 tests/warc_by_cdx/test_warc_by_cdx.py         |  4 +--
 .../warc_by_cdx/test_warc_by_cdx_aioboto3.py  |  4 +--
 9 files changed, 38 insertions(+), 44 deletions(-)

diff --git a/cdx_toolkit/filter_cdx/matcher.py b/cdx_toolkit/filter_cdx/matcher.py
index c10400a..d6da16d 100644
--- a/cdx_toolkit/filter_cdx/matcher.py
+++ b/cdx_toolkit/filter_cdx/matcher.py
@@ -1,4 +1,4 @@
-from typing import List, Tuple
+from typing import List, Tuple, Union
 import logging
 from abc import ABC, abstractmethod
 
@@ -9,7 +9,7 @@ class Matcher(ABC):
     """Base class for all matching approaches."""
 
     @abstractmethod
-    def __init__(self, prefixes: Tuple[str] | List[str]):
+    def __init__(self, prefixes: Union[Tuple[str], List[str]]):
         """Initialize the matcher with a list of prefixes."""
         pass
 
@@ -19,7 +19,7 @@ def matches(self, text: str) -> bool:
         pass
 
     @staticmethod
-    def validate_prefixes(prefixes: Tuple[str] | List[str]) -> Tuple[str]:
+    def validate_prefixes(prefixes: Union[Tuple[str], List[str]]) -> Tuple[str]:
         valid_prefixes = []
 
         for prefix in prefixes:
@@ -46,7 +46,7 @@ def __init__(self):
 class TrieMatcher(Matcher):
     """Trie-based matching approach."""
 
-    def __init__(self, prefixes: Tuple[str] | List[str]):
+    def __init__(self, prefixes: Union[Tuple[str], List[str]]):
         logger.info(f'Building trie matcher based on {len(prefixes):,} inputs')
         self.root = self._build_trie(self.validate_prefixes(prefixes))
 
@@ -77,7 +77,7 @@ def matches(self, text: str) -> bool:
 class TupleMatcher(Matcher):
     """Tuple-based matching approach using the built-in method `str.startswith`."""
 
-    def __init__(self, prefixes: Tuple[str] | List[str]):
+    def __init__(self, prefixes: Union[Tuple[str], List[str]]):
         logger.info(f'Building Tuple matcher based on {len(prefixes):,} inputs')
         self.prefixes_Tuple = self.validate_prefixes(prefixes)
 
diff --git a/cdx_toolkit/warcer_by_cdx/__init__.py b/cdx_toolkit/warcer_by_cdx/__init__.py
index ee5e932..ca6f36b 100644
--- a/cdx_toolkit/warcer_by_cdx/__init__.py
+++ b/cdx_toolkit/warcer_by_cdx/__init__.py
@@ -1,7 +1,7 @@
 import logging
 import sys
 import time
-from typing import List, Literal
+from typing import List, Literal, Optional
 
 import fsspec
 
@@ -109,7 +109,7 @@ def run_warcer_by_cdx(args, cmdline):
     logger.info(f'Script execution time: {execution_time:.3f} seconds')
 
 
-def get_index_paths(index_path: str, index_glob: str | None = None) -> List[str]:
+def get_index_paths(index_path: str, index_glob: Optional[str] = None) -> List[str]:
     if index_glob is None:
         # Read from a single index
         index_paths = [index_path]
diff --git a/cdx_toolkit/warcer_by_cdx/aioboto3_utils.py b/cdx_toolkit/warcer_by_cdx/aioboto3_utils.py
index 3c5350d..40f5457 100644
--- a/cdx_toolkit/warcer_by_cdx/aioboto3_utils.py
+++ b/cdx_toolkit/warcer_by_cdx/aioboto3_utils.py
@@ -2,8 +2,7 @@
 import logging
 import time
 from dataclasses import dataclass
-
-import logging
+from typing import Dict, List, Optional
 
 from botocore.exceptions import ClientError, EndpointConnectionError
 
@@ -135,7 +134,7 @@ async def mpu_create(
     bucket: str,
     key: str,
     *,
-    content_type: str | None,
+    content_type: Optional[str],
     max_attempts: int,
     base_backoff_seconds: float,
 ):
@@ -181,7 +180,7 @@ async def mpu_complete(
     bucket: str,
     key: str,
     upload_id: str,
-    parts: list[dict],
+    parts: List[Dict],
     max_attempts: int,
     base_backoff_seconds: float,
 ):
diff --git a/cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py b/cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py
index 9e25bd0..f19e44d 100644
--- a/cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py
+++ b/cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py
@@ -1,7 +1,7 @@
 import asyncio
 from io import BytesIO
 import logging
-from typing import List
+from typing import List, Optional, Dict
 
 import aioboto3
 from botocore.config import Config
@@ -27,14 +27,14 @@
 def filter_warc_by_cdx_via_aioboto3(
     index_paths: List[str],
     prefix_path: str,
-    writer_info: dict,
-    writer_subprefix: str | None = None,
+    writer_info: Dict,
+    writer_subprefix: Optional[str] = None,
     write_index_as_record: bool = False,
     limit: int = 0,
     log_every_n: int = 1000,
-    warc_download_prefix: str | None = None,
+    warc_download_prefix: Optional[str] = None,
     n_parallel: int = 1,
-    writer_kwargs: dict | None = None,
+    writer_kwargs: Optional[Dict] = None,
 ) -> int:
     try:
         return asyncio.run(
@@ -60,14 +60,14 @@ def filter_warc_by_cdx_via_aioboto3(
 async def filter_warc_by_cdx_via_aioboto3_async(
     index_paths: List[str],
     prefix_path: str,
-    writer_info: dict,
-    writer_subprefix: str | None = None,
+    writer_info: Dict,
+    writer_subprefix: Optional[str] = None,
     write_index_as_record: bool = False,
     limit: int = 0,
     log_every_n: int = 1000,
-    warc_download_prefix: str | None = None,
+    warc_download_prefix: Optional[str] = None,
     n_parallel: int = 1,
-    writer_kwargs: dict | None = None,
+    writer_kwargs: Optional[Dict] = None,
     max_attempts: int = 5,
     key_queue_size: int = 1000,
     item_queue_size: int = 200,
@@ -280,19 +280,13 @@ async def consumer(
     consumer_id: int,
     item_queue: asyncio.Queue,
     s3,
-    # shard_name_prefix: str,
-    # shard_extension: str,
-    # dest_prefix: str,
-    # dest_bucket: str,
-    # content_type: str | None,
-    # min_part_size: int,
     max_attempts: int,
     base_backoff_seconds: float,
     prefix_path: str,
-    writer_info: dict,
-    writer_subprefix: str | None = None,
+    writer_info: Dict,
+    writer_subprefix: Optional[str] = None,
     write_index_as_record: bool = False,
-    writer_kwargs: dict | None = None,
+    writer_kwargs: Optional[Dict] = None,
     warc_version: str = '1.0',
     log_every_n: int = 1000,
     gzip: bool = False,
diff --git a/cdx_toolkit/warcer_by_cdx/aioboto3_writer.py b/cdx_toolkit/warcer_by_cdx/aioboto3_writer.py
index b38135d..f262a88 100644
--- a/cdx_toolkit/warcer_by_cdx/aioboto3_writer.py
+++ b/cdx_toolkit/warcer_by_cdx/aioboto3_writer.py
@@ -1,5 +1,5 @@
 import logging
-from typing import List, Dict
+from typing import List, Dict, Optional
 
 from cdx_toolkit.warcer_by_cdx.aioboto3_utils import (
     mpu_abort,
@@ -18,7 +18,7 @@ def __init__(
         self,
         shard_key: str,
         dest_bucket: str,
-        content_type: str | None,
+        content_type: Optional[str],
         min_part_size: int,
         max_attempts: int,
         base_backoff_seconds: float,
@@ -29,7 +29,7 @@ def __init__(
         self.min_part_size = min_part_size
         self.max_attempts = max_attempts
         self.base_backoff_seconds = base_backoff_seconds
-        self.upload_id: str | None = None
+        self.upload_id: Optional[str] = None
         self.part_number = 1
         self.parts: List[Dict] = []
         self.buffer = bytearray()
@@ -63,8 +63,6 @@ async def _flush_full_parts(self, s3):
             self.part_number += 1
 
     async def write(self, s3, data: bytes):
-        # self.buffer.extend(transform(data))
-        # TODO write proper WARC record?
         self.buffer.extend(data)
         await self._flush_full_parts(s3)
 
diff --git a/cdx_toolkit/warcer_by_cdx/cdx_utils.py b/cdx_toolkit/warcer_by_cdx/cdx_utils.py
index 822f6fd..93179a5 100644
--- a/cdx_toolkit/warcer_by_cdx/cdx_utils.py
+++ b/cdx_toolkit/warcer_by_cdx/cdx_utils.py
@@ -2,7 +2,7 @@
 from pathlib import Path
 
 from io import BytesIO
-from typing import Iterable
+from typing import Iterable, Optional, Union
 
 import fsspec
 import logging
@@ -14,7 +14,10 @@
 logger = logging.getLogger(__name__)
 
 
-def get_index_as_string_from_path(index_path: str | Path, index_fs: None | fsspec.AbstractFileSystem = None) -> str:
+def get_index_as_string_from_path(
+        index_path: Union[str, Path], 
+        index_fs: Optional[fsspec.AbstractFileSystem] = None
+    ) -> str:
     """Fetch (and decompress) index content as string from local or remote path."""
     logger.info('Fetching index from %s ...', index_path)
     if index_fs is None:
diff --git a/cdx_toolkit/warcer_by_cdx/fsspec_warcer.py b/cdx_toolkit/warcer_by_cdx/fsspec_warcer.py
index 1cc5442..f170279 100644
--- a/cdx_toolkit/warcer_by_cdx/fsspec_warcer.py
+++ b/cdx_toolkit/warcer_by_cdx/fsspec_warcer.py
@@ -1,6 +1,6 @@
 import json
 import logging
-from typing import Dict, Iterable, List
+from typing import Dict, Iterable, List, Optional
 
 import cdx_toolkit
 from concurrent.futures import ThreadPoolExecutor, as_completed
@@ -17,13 +17,13 @@ def filter_warc_by_cdx_via_fsspec(
     index_paths: List[str],
     prefix_path: str,
     writer_info: Dict,
-    writer_subprefix: str | None = None,
+    writer_subprefix: Optional[str] = None,
     write_index_as_record: bool = False,
     limit: int = 0,
     log_every_n: int = 1000,
-    warc_download_prefix: str | None = None,
+    warc_download_prefix: Optional[str] = None,
     n_parallel: int = 1,
-    writer_kwargs: Dict | None = None,
+    writer_kwargs: Optional[Dict] = None,
 ) -> int:
     writer = cdx_toolkit.warc.get_writer(
         prefix_path,
diff --git a/tests/warc_by_cdx/test_warc_by_cdx.py b/tests/warc_by_cdx/test_warc_by_cdx.py
index 791cfe0..fc80ae2 100644
--- a/tests/warc_by_cdx/test_warc_by_cdx.py
+++ b/tests/warc_by_cdx/test_warc_by_cdx.py
@@ -1,6 +1,6 @@
 import os
 from pathlib import Path
-from typing import List
+from typing import List, Optional
 
 import fsspec
 from cdx_toolkit.cli import main
@@ -19,7 +19,7 @@
 fixture_path = Path(__file__).parent.parent / 'data/warc_by_cdx'
 
 
-def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog, extra_args: None | List[str] = None):
+def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog, extra_args: Optional[List[str]] = None):
     # test cli and check output
     index_path = fixture_path / 'filtered_CC-MAIN-2024-30_cdx-00187.gz'
 
diff --git a/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py b/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
index 69a50ab..10dd118 100644
--- a/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
+++ b/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
@@ -1,6 +1,6 @@
 from io import BytesIO
 from pathlib import Path
-from typing import List
+from typing import List, Optional
 
 import fsspec
 from cdx_toolkit.cli import main
@@ -13,7 +13,7 @@
 fixture_path = Path(__file__).parent.parent / 'data/warc_by_cdx'
 
 
-def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog, extra_args: None | List[str] = None):
+def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog, extra_args: Optional[List[str]] = None):
     # test cli and check output
     index_path = fixture_path / 'filtered_CC-MAIN-2024-30_cdx-00187.gz'
     if extra_args is None:

From a81a2b4ca536196d2140904a0c39cedd50f79785 Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Wed, 17 Sep 2025 11:10:13 +0000
Subject: [PATCH 21/74] fixed types and fail fast

---
 .github/workflows/ci-feat-warc-by-cdx.yaml  | 2 +-
 cdx_toolkit/warcer_by_cdx/aioboto3_utils.py | 7 ++++---
 cdx_toolkit/warcer_by_cdx/cdx_utils.py      | 6 +++---
 3 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/.github/workflows/ci-feat-warc-by-cdx.yaml b/.github/workflows/ci-feat-warc-by-cdx.yaml
index 80bb1bc..8688e8c 100644
--- a/.github/workflows/ci-feat-warc-by-cdx.yaml
+++ b/.github/workflows/ci-feat-warc-by-cdx.yaml
@@ -12,7 +12,7 @@ jobs:
   unit-tests:
     runs-on: ${{ matrix.os }}
     strategy:
-      fail-fast: false
+      fail-fast: true
       max-parallel: 1  # avoids ever triggering a rate limit
       matrix:
         python-version: ['3.8', '3.9', '3.10', '3.11', '3.12']
diff --git a/cdx_toolkit/warcer_by_cdx/aioboto3_utils.py b/cdx_toolkit/warcer_by_cdx/aioboto3_utils.py
index 40f5457..adbfd05 100644
--- a/cdx_toolkit/warcer_by_cdx/aioboto3_utils.py
+++ b/cdx_toolkit/warcer_by_cdx/aioboto3_utils.py
@@ -3,6 +3,7 @@
 import time
 from dataclasses import dataclass
 from typing import Dict, List, Optional
+from os import urandom
 
 from botocore.exceptions import ClientError, EndpointConnectionError
 
@@ -61,11 +62,11 @@ class RangePayload:
 
 
 def _backoff(attempt: int, base_backoff_seconds: float) -> float:
+    """Time to sleep based on number of attempts"""
     base = base_backoff_seconds * (2 ** (attempt - 1))
-    # jitter ±20%
-    import os as _os
 
-    return max(0.05, base * (0.8 + 0.4 * _os.urandom(1)[0] / 255))
+    # Add random jitter between 80-120% of base delay
+    return max(0.05, base * (0.8 + 0.4 * urandom(1)[0] / 255))
 
 
 def parse_s3_uri(uri: str) -> tuple[str, str]:
diff --git a/cdx_toolkit/warcer_by_cdx/cdx_utils.py b/cdx_toolkit/warcer_by_cdx/cdx_utils.py
index 93179a5..4611478 100644
--- a/cdx_toolkit/warcer_by_cdx/cdx_utils.py
+++ b/cdx_toolkit/warcer_by_cdx/cdx_utils.py
@@ -2,7 +2,7 @@
 from pathlib import Path
 
 from io import BytesIO
-from typing import Iterable, Optional, Union
+from typing import Iterable, Optional, Tuple, Union
 
 import fsspec
 import logging
@@ -43,7 +43,7 @@ def get_index_record(index: str, index_path: str, encoding: str = 'utf-8') -> Ar
     )
 
 
-def read_cdx_line(line: str, warc_download_prefix: str) -> tuple[str, int, int]:
+def read_cdx_line(line: str, warc_download_prefix: str) -> Tuple[str, int, int]:
     cols = line.split(' ', maxsplit=2)
 
     if len(cols) == 3:
@@ -67,7 +67,7 @@ def read_cdx_line(line: str, warc_download_prefix: str) -> tuple[str, int, int]:
     return (warc_url, offset, length)
 
 
-def read_cdx_index_from_s3(s3_path: str, warc_download_prefix: str) -> Iterable[tuple[str, int, int]]:
+def read_cdx_index_from_s3(s3_path: str, warc_download_prefix: str) -> Iterable[Tuple[str, int, int]]:
     """
     Read CDX records from a gzipped S3 file.
     """

From 72c3201260fe3928fa8a1bab4cda203aa3f6600e Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Wed, 17 Sep 2025 11:12:39 +0000
Subject: [PATCH 22/74] fixed types and fail fast

---
 cdx_toolkit/warcer_by_cdx/aioboto3_utils.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/cdx_toolkit/warcer_by_cdx/aioboto3_utils.py b/cdx_toolkit/warcer_by_cdx/aioboto3_utils.py
index adbfd05..16851ea 100644
--- a/cdx_toolkit/warcer_by_cdx/aioboto3_utils.py
+++ b/cdx_toolkit/warcer_by_cdx/aioboto3_utils.py
@@ -2,7 +2,7 @@
 import logging
 import time
 from dataclasses import dataclass
-from typing import Dict, List, Optional
+from typing import Dict, List, Optional, Tuple
 from os import urandom
 
 from botocore.exceptions import ClientError, EndpointConnectionError
@@ -69,7 +69,7 @@ def _backoff(attempt: int, base_backoff_seconds: float) -> float:
     return max(0.05, base * (0.8 + 0.4 * urandom(1)[0] / 255))
 
 
-def parse_s3_uri(uri: str) -> tuple[str, str]:
+def parse_s3_uri(uri: str) -> Tuple[str, str]:
     if not uri.startswith('s3://'):
         raise ValueError(f'Not an S3 URI: {uri}')
     rest = uri[5:]

From d9adf0352abf42d3f3cbcfcd4f44e8c813ed3aa5 Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Wed, 17 Sep 2025 15:07:03 +0000
Subject: [PATCH 23/74] adding max file size to aioboto3 implementation;
 improving test coverage

---
 cdx_toolkit/warcer_by_cdx/__init__.py         |  17 +-
 cdx_toolkit/warcer_by_cdx/aioboto3_utils.py   |  13 +-
 cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py  | 200 ++++++++++++++----
 cdx_toolkit/warcer_by_cdx/args.py             |  11 +-
 cdx_toolkit/warcer_by_cdx/cdx_utils.py        |  10 +-
 cdx_toolkit/warcer_by_cdx/fsspec_warcer.py    |  33 ++-
 cdx_toolkit/warcer_by_cdx/warc_utils.py       |  78 +++++++
 tests/conftest.py                             |   3 +
 ...ed_CC-MAIN-2024-30_cdx-00187.metadata.json |   4 +
 tests/warc_by_cdx/test_cdx_utils.py           |  28 +++
 tests/warc_by_cdx/test_filter_cdx.py          |   5 +-
 tests/warc_by_cdx/test_warc_by_cdx.py         |  52 ++++-
 .../warc_by_cdx/test_warc_by_cdx_aioboto3.py  | 146 ++++++++++++-
 tests/warc_by_cdx/test_warc_utils.py          |  31 +++
 14 files changed, 532 insertions(+), 99 deletions(-)
 create mode 100644 cdx_toolkit/warcer_by_cdx/warc_utils.py
 create mode 100644 tests/data/warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.metadata.json
 create mode 100644 tests/warc_by_cdx/test_cdx_utils.py
 create mode 100644 tests/warc_by_cdx/test_warc_utils.py

diff --git a/cdx_toolkit/warcer_by_cdx/__init__.py b/cdx_toolkit/warcer_by_cdx/__init__.py
index ca6f36b..d12ac45 100644
--- a/cdx_toolkit/warcer_by_cdx/__init__.py
+++ b/cdx_toolkit/warcer_by_cdx/__init__.py
@@ -36,7 +36,16 @@ def run_warcer_by_cdx(args, cmdline):
 
     implementation: ImplementationType = args.implementation
 
-    write_index_as_record = args.write_index_as_record
+    write_paths_as_resource_records = args.write_paths_as_resource_records
+    write_paths_as_resource_records_metadata = args.write_paths_as_resource_records_metadata
+
+    if write_paths_as_resource_records and write_paths_as_resource_records_metadata:
+        if len(write_paths_as_resource_records) != len(write_paths_as_resource_records_metadata):
+            raise ValueError("Number of paths to resource records must be equal to metadata paths.")
+
+    if not write_paths_as_resource_records and write_paths_as_resource_records_metadata:
+        raise ValueError("Metadata paths are set but resource records paths are missing.")
+
     ispartof = args.prefix
     if args.subprefix:
         ispartof += '-' + args.subprefix
@@ -77,7 +86,8 @@ def run_warcer_by_cdx(args, cmdline):
             prefix_path=prefix_path,
             writer_info=info,
             writer_subprefix=args.subprefix,
-            write_index_as_record=write_index_as_record,
+            write_paths_as_resource_records=write_paths_as_resource_records,
+            write_paths_as_resource_records_metadata=write_paths_as_resource_records_metadata,
             limit=limit,
             log_every_n=log_every_n,
             warc_download_prefix=cdx.warc_download_prefix,
@@ -90,7 +100,8 @@ def run_warcer_by_cdx(args, cmdline):
             prefix_path=prefix_path,
             writer_info=info,
             writer_subprefix=args.subprefix,
-            write_index_as_record=write_index_as_record,
+            write_paths_as_resource_records=write_paths_as_resource_records,
+            write_paths_as_resource_records_metadata=write_paths_as_resource_records_metadata,
             limit=limit,
             log_every_n=log_every_n,
             warc_download_prefix=cdx.warc_download_prefix,
diff --git a/cdx_toolkit/warcer_by_cdx/aioboto3_utils.py b/cdx_toolkit/warcer_by_cdx/aioboto3_utils.py
index 16851ea..1ea64e8 100644
--- a/cdx_toolkit/warcer_by_cdx/aioboto3_utils.py
+++ b/cdx_toolkit/warcer_by_cdx/aioboto3_utils.py
@@ -29,21 +29,14 @@ def add_bytes(self, bytes_count: int):
 
     def get_stats(self) -> dict:
         elapsed = time.time() - self.start_time
-        if elapsed <= 0:
-            return {
-                'elapsed': 0,
-                'bytes_per_sec': 0,
-                'mb_per_sec': 0,
-                'requests_per_sec': 0,
-            }
 
         return {
             'elapsed': elapsed,
             'total_bytes': self.total_bytes,
             'total_requests': self.total_requests,
-            'bytes_per_sec': self.total_bytes / elapsed,
-            'mb_per_sec': (self.total_bytes / elapsed) / (1024 * 1024),
-            'requests_per_sec': self.total_requests / elapsed,
+            'bytes_per_sec': self.total_bytes / elapsed if elapsed > 0 else 0,
+            'mb_per_sec': (self.total_bytes / elapsed) / (1024 * 1024) if elapsed > 0 else 0,
+            'requests_per_sec': self.total_requests / elapsed if elapsed > 0 else 0,
         }
 
 
diff --git a/cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py b/cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py
index f19e44d..511e3e6 100644
--- a/cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py
+++ b/cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py
@@ -17,8 +17,9 @@
 )
 from cdx_toolkit.warcer_by_cdx.aioboto3_writer import ShardWriter
 from cdx_toolkit.warcer_by_cdx.cdx_utils import (
-    read_cdx_index_from_s3,
+    iter_cdx_index_from_path,
 )
+from cdx_toolkit.warcer_by_cdx.warc_utils import get_bytes_from_warc_record, get_resource_record_from_path
 
 
 logger = logging.getLogger(__name__)
@@ -29,7 +30,8 @@ def filter_warc_by_cdx_via_aioboto3(
     prefix_path: str,
     writer_info: Dict,
     writer_subprefix: Optional[str] = None,
-    write_index_as_record: bool = False,
+    write_paths_as_resource_records: Optional[List[str]] = None,
+    write_paths_as_resource_records_metadata: Optional[List[str]] = None,
     limit: int = 0,
     log_every_n: int = 1000,
     warc_download_prefix: Optional[str] = None,
@@ -43,7 +45,8 @@ def filter_warc_by_cdx_via_aioboto3(
                 prefix_path=prefix_path,
                 writer_info=writer_info,
                 writer_subprefix=writer_subprefix,
-                write_index_as_record=write_index_as_record,
+                write_paths_as_resource_records=write_paths_as_resource_records,
+                write_paths_as_resource_records_metadata=write_paths_as_resource_records_metadata,
                 limit=limit,
                 log_every_n=log_every_n,
                 warc_download_prefix=warc_download_prefix,
@@ -62,7 +65,8 @@ async def filter_warc_by_cdx_via_aioboto3_async(
     prefix_path: str,
     writer_info: Dict,
     writer_subprefix: Optional[str] = None,
-    write_index_as_record: bool = False,
+    write_paths_as_resource_records: Optional[List[str]] = None,
+    write_paths_as_resource_records_metadata: Optional[List[str]] = None,
     limit: int = 0,
     log_every_n: int = 1000,
     warc_download_prefix: Optional[str] = None,
@@ -72,6 +76,7 @@ async def filter_warc_by_cdx_via_aioboto3_async(
     key_queue_size: int = 1000,
     item_queue_size: int = 200,
     base_backoff_seconds=0.5,
+    s3_region_name: str = 'us-east-1',
 ) -> int:
     n_records = 0
     fetcher_to_consumer_ratio = 6
@@ -82,22 +87,19 @@ async def filter_warc_by_cdx_via_aioboto3_async(
     item_queue: asyncio.Queue = asyncio.Queue(maxsize=item_queue_size)
 
     boto_cfg = Config(
-        region_name='us-east-1',
+        region_name=s3_region_name,
         retries={'max_attempts': max(2, max_attempts), 'mode': 'standard'},
         connect_timeout=10,
         read_timeout=120,
     )
 
-    if write_index_as_record:
-        raise NotImplementedError
-
     session = aioboto3.Session()
 
     async with session.client('s3', config=boto_cfg) as s3:
         # Fetch file paths and ranges (offset, length) from index files
         logger.info('Starting lister, %d fetchers, %d consumers', num_fetchers, num_consumers)
         lister_task = asyncio.create_task(
-            lister_from_index(
+            get_range_jobs_from_index_paths(
                 key_queue=key_queue,
                 index_paths=index_paths,
                 warc_download_prefix=warc_download_prefix,
@@ -109,7 +111,7 @@ async def filter_warc_by_cdx_via_aioboto3_async(
         # Read WARC records based on file paths and ranges
         fetchers = [
             asyncio.create_task(
-                fetcher(
+                fetch_warc_ranges(
                     fetcher_id=i,
                     key_queue=key_queue,
                     item_queue=item_queue,
@@ -125,14 +127,15 @@ async def filter_warc_by_cdx_via_aioboto3_async(
         # Write WARC records
         consumers = [
             asyncio.create_task(
-                consumer(
+                write_warc(
                     consumer_id=i,
                     item_queue=item_queue,
                     s3=s3,
                     prefix_path=prefix_path,
                     max_attempts=max_attempts,
                     base_backoff_seconds=base_backoff_seconds,
-                    write_index_as_record=write_index_as_record,
+                    write_paths_as_resource_records=write_paths_as_resource_records,
+                    write_paths_as_resource_records_metadata=write_paths_as_resource_records_metadata,
                     writer_info=writer_info,
                     writer_subprefix=writer_subprefix,
                     writer_kwargs=writer_kwargs,
@@ -161,14 +164,14 @@ async def filter_warc_by_cdx_via_aioboto3_async(
     return n_records
 
 
-async def lister_from_index(
+async def get_range_jobs_from_index_paths(
     key_queue: asyncio.Queue,
     index_paths: List[str],
     warc_download_prefix: str,
     num_fetchers: int,
     limit: int = 0,
 ):
-    """Stage 1: stream the index, parse lines -> RangeJob -> key_queue."""
+    """Stage 1: stream the CDX paths, parse lines -> RangeJob (WARC files and offets) -> key_queue."""
 
     logger.info('Range index limit: %i', limit)
     count = 0
@@ -181,7 +184,7 @@ async def lister_from_index(
         for index_path in index_paths:
             # Fetch range queries from index
             try:
-                for warc_url, offset, length in read_cdx_index_from_s3(
+                for warc_url, offset, length in iter_cdx_index_from_path(
                     index_path, warc_download_prefix=warc_download_prefix
                 ):
                     # Convert the CDX record back to a RangeJob
@@ -208,7 +211,7 @@ async def lister_from_index(
     logger.info('Lister enqueued %d jobs from %s', count, index_path)
 
 
-async def fetcher(
+async def fetch_warc_ranges(
     fetcher_id: int,
     key_queue: asyncio.Queue,
     item_queue: asyncio.Queue,
@@ -276,58 +279,139 @@ async def fetcher(
             key_queue.task_done()
 
 
-async def consumer(
+def generate_warc_filename(
+    dest_prefix: str,
     consumer_id: int,
-    item_queue: asyncio.Queue,
-    s3,
-    max_attempts: int,
-    base_backoff_seconds: float,
-    prefix_path: str,
-    writer_info: Dict,
+    sequence: int,
     writer_subprefix: Optional[str] = None,
-    write_index_as_record: bool = False,
-    writer_kwargs: Optional[Dict] = None,
-    warc_version: str = '1.0',
-    log_every_n: int = 1000,
     gzip: bool = False,
-):
-    """Stage 3: each consumer owns ONE shard MPU and appends ranges to it."""
-
-    dest_bucket, dest_prefix = parse_s3_uri(prefix_path)
-
-    min_part_size = 5 * 1024 * 1024  # 5 MiB
-    content_type = None
-
+) -> str:
     file_name = dest_prefix + '-'
     if writer_subprefix is not None:
         file_name += writer_subprefix + '-'
-    file_name += '{:06d}'.format(consumer_id) + '.extracted.warc'
-
+    file_name += '{:06d}-{:03d}'.format(consumer_id, sequence) + '.extracted.warc'
     if gzip:
         file_name += '.gz'
 
-    writer = ShardWriter(
-        file_name,
+    return file_name
+
+
+async def create_new_writer_with_header(
+    s3,
+    consumer_id: int,
+    sequence: int,
+    dest_bucket: str,
+    dest_prefix: str,
+    max_attempts: int,
+    base_backoff_seconds: float,
+    min_part_size: int,
+    writer_info: Dict,
+    warc_version: str = '1.0',
+    writer_subprefix: Optional[str] = None,
+    gzip: bool = False,
+    content_type: Optional[str] = None,
+):
+    filename = generate_warc_filename(
+        dest_prefix=dest_prefix,
+        consumer_id=consumer_id,
+        sequence=sequence,
+        writer_subprefix=writer_subprefix,
+        gzip=gzip,
+    )
+
+    new_writer = ShardWriter(
+        filename,
         dest_bucket,
         content_type,
         min_part_size,
         max_attempts,
         base_backoff_seconds,
     )
-    tracker = ThroughputTracker()
-    tracker.start()
-    counter = 0
 
     # Initialize writer
-    await writer.start(s3)
+    await new_writer.start(s3)
 
     # Write WARC header
     buffer = BytesIO()
     warc_writer = WARCWriter(buffer, gzip=gzip, warc_version=warc_version)
-    warcinfo = warc_writer.create_warcinfo_record(file_name, writer_info)
+    warcinfo = warc_writer.create_warcinfo_record(filename, writer_info)
     warc_writer.write_record(warcinfo)
+    header_data = buffer.getvalue()
+    await new_writer.write(s3, header_data)
 
-    await writer.write(s3, buffer.getvalue())
+    return new_writer, len(header_data)
+
+
+async def write_warc(
+    consumer_id: int,
+    item_queue: asyncio.Queue,
+    s3,
+    max_attempts: int,
+    base_backoff_seconds: float,
+    prefix_path: str,
+    writer_info: Dict,
+    writer_subprefix: Optional[str] = None,
+    write_paths_as_resource_records: Optional[List[str]] = None,
+    write_paths_as_resource_records_metadata: Optional[List[str]] = None,
+    writer_kwargs: Optional[Dict] = None,
+    warc_version: str = '1.0',
+    log_every_n: int = 1000,
+    gzip: bool = False,
+    content_type=None,
+    min_part_size: int = 5 * 1024 * 1024,  # 5 MiB (for upload)
+    max_file_size: Optional[int] = 1 * 1024 * 1024 * 1024,  # 1 GiB (for WARC outputs)
+):
+    """Stage 3: Write WARC. Each consumer owns ONE shard MPU and appends ranges to it."""
+
+    dest_bucket, dest_prefix = parse_s3_uri(prefix_path)
+
+    # File rotation tracking
+    current_file_sequence = 1
+    current_file_size = 0
+
+    # Initialize first writer with header
+    writer, header_size = await create_new_writer_with_header(
+        s3,
+        consumer_id=consumer_id,
+        sequence=current_file_sequence,
+        dest_bucket=dest_bucket,
+        dest_prefix=dest_prefix,
+        max_attempts=max_attempts,
+        base_backoff_seconds=base_backoff_seconds,
+        writer_info=writer_info,
+        warc_version=warc_version,
+        writer_subprefix=writer_subprefix,
+        gzip=gzip,
+        content_type=content_type,
+        min_part_size=min_part_size,
+    )
+    current_file_size = header_size
+
+    tracker = ThroughputTracker()
+    tracker.start()
+    counter = 0
+
+    # Write WARC resource records
+    if write_paths_as_resource_records:
+        logger.info(f'Writing {len(write_paths_as_resource_records)} resource records to WARC ... ')
+
+        # Resource records are written at the beginning the WARC file.
+        for i, resource_record_path in enumerate(write_paths_as_resource_records):
+            logger.info(f'Writing resource record from {resource_record_path} ...')
+            resource_record = get_resource_record_from_path(
+                file_path=resource_record_path,
+                metadata_path=(
+                    write_paths_as_resource_records_metadata[i] if write_paths_as_resource_records_metadata else None
+                ),
+            )
+            record_data = get_bytes_from_warc_record(resource_record, warc_version=warc_version, gzip=gzip)
+
+            await writer.write(s3, record_data)
+
+            # Keep track but do not rotate resource records
+            current_file_size += len(record_data)
+
+        logger.info(f'Resource records added: {len(write_paths_as_resource_records)}')
 
     try:
         while True:
@@ -348,7 +432,33 @@ async def consumer(
                 else:
                     should_stop = False
                     assert isinstance(item, RangePayload)
+
+                    # Check if we need to rotate files due to size limit
+                    if max_file_size and current_file_size + len(item.data) > max_file_size:
+                        await writer.close(s3)
+                        current_file_sequence += 1
+
+                        writer, header_size = await create_new_writer_with_header(
+                            s3,
+                            consumer_id=consumer_id,
+                            sequence=current_file_sequence,
+                            dest_bucket=dest_bucket,
+                            dest_prefix=dest_prefix,
+                            max_attempts=max_attempts,
+                            base_backoff_seconds=base_backoff_seconds,
+                            writer_info=writer_info,
+                            warc_version=warc_version,
+                            writer_subprefix=writer_subprefix,
+                            gzip=gzip,
+                            content_type=content_type,
+                            min_part_size=min_part_size,
+                        )
+
+                        current_file_size = header_size
+                        logger.info(f'Rotated to new WARC file sequence {current_file_sequence} due to size limit')
+
                     await writer.write(s3, item.data)
+                    current_file_size += len(item.data)
                     tracker.add_bytes(len(item.data))
 
                     # Log progress every 10 items
diff --git a/cdx_toolkit/warcer_by_cdx/args.py b/cdx_toolkit/warcer_by_cdx/args.py
index 3555ad7..c54496d 100644
--- a/cdx_toolkit/warcer_by_cdx/args.py
+++ b/cdx_toolkit/warcer_by_cdx/args.py
@@ -38,9 +38,14 @@ def add_warcer_by_cdx_args(parser: argparse.ArgumentParser):
         help='prefix for downloading content, automatically set for CC',
     )
     parser.add_argument(
-        '--write-index-as-record',
-        action='store_true',
-        help='If enable, the CDX index is written as resource record to the WARC file',
+        '--write-paths-as-resource-records',  # --write-index-as-record
+        nargs="*",
+        help='Paths to multiple files. File content is written to as a resource record to each the WARC file',
+    )
+    parser.add_argument(
+        '--write-paths-as-resource-records-metadata',
+        nargs="*",
+        help='Paths to multiple metadata files (JSON) for resource records from `--write-paths-as-resource-records`',
     )
     parser.add_argument(
         '--parallel',
diff --git a/cdx_toolkit/warcer_by_cdx/cdx_utils.py b/cdx_toolkit/warcer_by_cdx/cdx_utils.py
index 4611478..0f2bc30 100644
--- a/cdx_toolkit/warcer_by_cdx/cdx_utils.py
+++ b/cdx_toolkit/warcer_by_cdx/cdx_utils.py
@@ -67,16 +67,16 @@ def read_cdx_line(line: str, warc_download_prefix: str) -> Tuple[str, int, int]:
     return (warc_url, offset, length)
 
 
-def read_cdx_index_from_s3(s3_path: str, warc_download_prefix: str) -> Iterable[Tuple[str, int, int]]:
+def iter_cdx_index_from_path(index_path: str, warc_download_prefix: str) -> Iterable[Tuple[str, int, int]]:
     """
-    Read CDX records from a gzipped S3 file.
+    Iterate CDX records from a file path (gzipped; local or remote).
     """
     # if not s3_path.startswith("s3://"):
     #     raise ValueError(f"Invalid S3 path: {s3_path}")
 
-    logger.info('Reading CDX from %s', s3_path)
+    logger.info('Reading CDX from %s', index_path)
 
-    with fsspec.open(s3_path, 'rt', compression='gzip' if s3_path.endswith('.gz') else None) as f:
+    with fsspec.open(index_path, 'rt', compression='gzip' if index_path.endswith('.gz') else None) as f:
         for line in f:
             try:
                 yield read_cdx_line(line, warc_download_prefix)
@@ -85,4 +85,4 @@ def read_cdx_index_from_s3(s3_path: str, warc_download_prefix: str) -> Iterable[
                 logger.error('Invalid CDX line: %s', line)
                 continue
 
-    logger.info(f'CDX completed from {s3_path}')
+    logger.info(f'CDX completed from {index_path}')
diff --git a/cdx_toolkit/warcer_by_cdx/fsspec_warcer.py b/cdx_toolkit/warcer_by_cdx/fsspec_warcer.py
index f170279..7e0fefe 100644
--- a/cdx_toolkit/warcer_by_cdx/fsspec_warcer.py
+++ b/cdx_toolkit/warcer_by_cdx/fsspec_warcer.py
@@ -7,7 +7,8 @@
 
 from warcio.recordloader import ArcWarcRecord
 
-from cdx_toolkit.warcer_by_cdx.cdx_utils import get_index_as_string_from_path, get_index_record
+from cdx_toolkit.warcer_by_cdx.cdx_utils import get_index_as_string_from_path
+from cdx_toolkit.warcer_by_cdx.warc_utils import get_resource_record_from_path
 
 
 logger = logging.getLogger(__name__)
@@ -18,7 +19,8 @@ def filter_warc_by_cdx_via_fsspec(
     prefix_path: str,
     writer_info: Dict,
     writer_subprefix: Optional[str] = None,
-    write_index_as_record: bool = False,
+    write_paths_as_resource_records: Optional[List[str]] = None,
+    write_paths_as_resource_records_metadata: Optional[List[str]] = None,
     limit: int = 0,
     log_every_n: int = 1000,
     warc_download_prefix: Optional[str] = None,
@@ -35,7 +37,7 @@ def filter_warc_by_cdx_via_fsspec(
     # Iterate over index files
     records_n = 0
     for index_path in index_paths:
-        logger.info('filtering based on CDX from %s', index_path)
+        logger.info('Filtering WARC based on CDX from %s', index_path)
 
         # Read index completely (for the WARC resource record)
         index = get_index_as_string_from_path(index_path)
@@ -44,13 +46,24 @@ def filter_warc_by_cdx_via_fsspec(
             # skip empty indicies
             continue
 
-        # Write index as record to WARC
-        # TODO at what position should the resource records be written?
-        if write_index_as_record:
-            logger.info('Writing CDX as resource record to WARC ... ')
-            writer.write_record(get_index_record(index, index_path))
-
-            logger.info('CDX resource recorded added')
+        # Write file content from paths as resource records to WARC
+        if write_paths_as_resource_records:
+            logger.info('Writing resource records to WARC ... ')
+
+            # Resource records are written at the beginning the WARC file.
+            for i, resource_record_path in enumerate(write_paths_as_resource_records):
+                logger.info(f'Writing resource record from {resource_record_path} ...')
+                resource_record = get_resource_record_from_path(
+                    file_path=resource_record_path,
+                    metadata_path=(
+                        write_paths_as_resource_records_metadata[i]
+                        if write_paths_as_resource_records_metadata
+                        else None
+                    ),
+                )
+                writer.write_record(resource_record)
+            
+            logger.info(f'Resource records added: {len(write_paths_as_resource_records)}')
 
         # The index file holds all the information to download specific objects (file, offset, length etc.)
         index_lines = index.splitlines()
diff --git a/cdx_toolkit/warcer_by_cdx/warc_utils.py b/cdx_toolkit/warcer_by_cdx/warc_utils.py
new file mode 100644
index 0000000..0eb5b71
--- /dev/null
+++ b/cdx_toolkit/warcer_by_cdx/warc_utils.py
@@ -0,0 +1,78 @@
+from io import BytesIO
+import json
+from pathlib import Path
+import fsspec
+from warcio.recordloader import ArcWarcRecord
+from warcio import WARCWriter
+
+from typing import Optional, Union
+
+import mimetypes
+
+def get_bytes_from_warc_record(
+    record, 
+    warc_version: str = '1.0',
+    gzip: bool = False,
+    ):
+    buffer = BytesIO()
+    warc_writer = WARCWriter(buffer, gzip=gzip, warc_version=warc_version)
+    warc_writer.write_record(record)
+
+    return buffer.getvalue()
+
+def get_resource_record_from_path(
+    file_path: Union[str, Path],
+    metadata_path: Optional[Union[str, Path]] = None,
+    ) -> ArcWarcRecord:
+    """Build WARC resource record for file path and metdata path.
+    
+    The metadata file must be a valid JSON and can have the following fields:
+    - warc_content_type
+    - uri
+    - http_headers
+    - warc_headers_dict
+
+    If uri is not provided as metadata, the file_path is used.
+    If warc_content_type is not provided as metadata, the type is guessed.
+    """
+    # Cast to string
+    file_path = str(file_path)
+    
+    with fsspec.open(file_path, "rb") as f:
+        file_bytes = BytesIO(f.read())
+
+    if metadata_path:
+        # Load metadata from path
+        metadata_path = str(metadata_path)
+
+        if not metadata_path.endswith(".json"):
+            raise ValueError("Metadata must be provided JSON (file path ends with *.json)")
+        
+        with fsspec.open(metadata_path) as f:
+            metadata = json.load(f)
+
+            warc_content_type = metadata.get("warc_content_type", None)
+            uri = metadata.get("uri", None)
+            http_headers = metadata.get("http_headers", None)
+            warc_headers_dict = metadata.get("warc_headers_dict", None)
+    else:
+        # Without metdata
+        warc_content_type = None
+        uri = None
+        http_headers = None
+        warc_headers_dict = None
+
+    if warc_content_type is None:
+        warc_content_type = mimetypes.guess_type(file_path)[0]
+
+    if uri is None:
+        uri = file_path
+
+    return WARCWriter(None).create_warc_record(
+        uri=uri,
+        record_type='resource',
+        payload=file_bytes,
+        http_headers=http_headers,
+        warc_content_type=warc_content_type,
+        warc_headers_dict=warc_headers_dict,
+    )
\ No newline at end of file
diff --git a/tests/conftest.py b/tests/conftest.py
index 7a5dbd4..b662111 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -1,7 +1,10 @@
+from pathlib import Path
 import pytest
 import boto3
 from botocore.exceptions import NoCredentialsError, ClientError
 
+TEST_DATA_PATH = Path(__file__).parent / "data"
+
 
 def check_aws_s3_access():
     """Check if AWS S3 access is available."""
diff --git a/tests/data/warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.metadata.json b/tests/data/warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.metadata.json
new file mode 100644
index 0000000..6a4103f
--- /dev/null
+++ b/tests/data/warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.metadata.json
@@ -0,0 +1,4 @@
+{
+    "uri": "filter_cdx.cdx.gz",
+    "warc_content_type": "application/cdx"
+}
\ No newline at end of file
diff --git a/tests/warc_by_cdx/test_cdx_utils.py b/tests/warc_by_cdx/test_cdx_utils.py
new file mode 100644
index 0000000..414a867
--- /dev/null
+++ b/tests/warc_by_cdx/test_cdx_utils.py
@@ -0,0 +1,28 @@
+import fsspec
+import pytest
+from cdx_toolkit.warcer_by_cdx.cdx_utils import get_index_as_string_from_path, read_cdx_line
+from tests.conftest import TEST_DATA_PATH
+
+
+def test_get_index_as_string_from_path():
+    cdx_path = TEST_DATA_PATH / "warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.gz"
+
+    index = get_index_as_string_from_path(cdx_path)
+
+    assert len(index) == 568010
+
+
+def test_get_index_as_string_from_path_with_fs():
+    fs, cdx_path = fsspec.url_to_fs(TEST_DATA_PATH / "warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.gz")
+
+    index = get_index_as_string_from_path(cdx_path, fs)
+
+    assert len(index) == 568010
+
+get_index_as_string_from_path
+
+def test_read_cdx_line_error():
+    with pytest.raises(ValueError) as ec_info:
+        read_cdx_line("this_is_a_bad_CDX-line", warc_download_prefix="http://")
+
+    assert ec_info.match("Cannot parse line")
\ No newline at end of file
diff --git a/tests/warc_by_cdx/test_filter_cdx.py b/tests/warc_by_cdx/test_filter_cdx.py
index 988f523..8eb8980 100644
--- a/tests/warc_by_cdx/test_filter_cdx.py
+++ b/tests/warc_by_cdx/test_filter_cdx.py
@@ -1,11 +1,10 @@
 import pytest
-from pathlib import Path
 
 from cdx_toolkit.cli import main
 from cdx_toolkit.filter_cdx import resolve_paths, validate_resolved_paths
-from tests.conftest import requires_aws_s3
+from tests.conftest import requires_aws_s3, TEST_DATA_PATH
 
-fixture_path = Path(__file__).parent.parent / 'data/filter_cdx'
+fixture_path = TEST_DATA_PATH / 'filter_cdx'
 
 
 @requires_aws_s3
diff --git a/tests/warc_by_cdx/test_warc_by_cdx.py b/tests/warc_by_cdx/test_warc_by_cdx.py
index fc80ae2..b9b1724 100644
--- a/tests/warc_by_cdx/test_warc_by_cdx.py
+++ b/tests/warc_by_cdx/test_warc_by_cdx.py
@@ -1,5 +1,4 @@
 import os
-from pathlib import Path
 from typing import List, Optional
 
 import fsspec
@@ -13,15 +12,16 @@
 import pytest
 from warcio.archiveiterator import ArchiveIterator
 
-from tests.conftest import requires_aws_s3
+from tests.conftest import requires_aws_s3, TEST_DATA_PATH
 
 
-fixture_path = Path(__file__).parent.parent / 'data/warc_by_cdx'
+fixture_path = TEST_DATA_PATH / 'warc_by_cdx'
 
 
 def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog, extra_args: Optional[List[str]] = None):
     # test cli and check output
     index_path = fixture_path / 'filtered_CC-MAIN-2024-30_cdx-00187.gz'
+    resource_record_path = TEST_DATA_PATH / 'filter_cdx/whitelist_10_urls.txt'
 
     if extra_args is None:
         extra_args = []
@@ -32,8 +32,9 @@ def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog, extra_args
             '--cc',
             '--limit=10',
             'warc_by_cdx',
-            f'{str(index_path)}',
-            '--write-index-as-record',
+            str(index_path),
+            '--write-paths-as-resource-records',
+            str(resource_record_path),
             f'--prefix={str(base_prefix)}/TEST_warc_by_index',
             '--creator=foo',
             '--operator=bob',
@@ -48,10 +49,13 @@ def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog, extra_args
     # Validate extracted WARC
     warc_filename = 'TEST_warc_by_index-000000.extracted.warc.gz'
     warc_path = str(base_prefix) + '/' + warc_filename
-    resource_record = None
+
     info_record = None
     response_records = []
 
+    resource_record = None
+    resource_record_content = None
+
     with fsspec.open(warc_path, 'rb') as stream:
         for record in ArchiveIterator(stream):
             if record.rec_type == 'warcinfo':
@@ -62,13 +66,17 @@ def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog, extra_args
 
             if record.rec_type == 'resource':
                 resource_record = record
+                resource_record_content = record.content_stream().read().decode('utf-8')
 
     assert len(response_records) == 10
+
     assert resource_record is not None
-    assert resource_record.length == 568010
+    assert resource_record.length == 294, 'Invalid resource record'
+    assert resource_record_content[:10] == 'example.co', 'Invalid resource record'
+    assert resource_record_content[-20:-1] == 'hr.fr/produit/t-837', 'Invalid resource record'
 
-    assert info_record is not None
-    assert 'operator: bob' in info_record
+    assert info_record is not None, 'Invalid info record'
+    assert 'operator: bob' in info_record, 'Invalid info record'
 
 
 def test_cli_warc_by_cdx_over_http(tmpdir, caplog):
@@ -216,3 +224,29 @@ def test_warc_by_cdx_without_creator_operator(tmpdir):
     assert info_record is not None
     assert 'creator:' not in info_record
     assert 'operator:' not in info_record
+
+
+def test_resource_records_paths_mismatch():
+    # Test if mismatch of number of paths for resource records and their metdata is raised.
+    with pytest.raises(ValueError) as exc_info:
+        main(
+            args=[
+                '-v',
+                '--cc',
+                'warc_by_cdx',
+                'foo/bar',
+                '--write-paths-as-resource-records',
+                'resource1',
+                'resource2',
+                '--write-paths-as-resource-records-metadata',
+                'metadata2',
+            ]
+        )
+    assert exc_info.match('Number of paths to resource records')
+
+
+def test_metadata_paths_without_resource_records_paths():
+    # Test if error of missing resource records paths is raised.
+    with pytest.raises(ValueError) as exc_info:
+        main(args=['-v', '--cc', 'warc_by_cdx', 'foo/bar', '--write-paths-as-resource-records-metadata', 'metadata2'])
+    assert exc_info.match('Metadata paths are set but')
diff --git a/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py b/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
index 10dd118..5cceead 100644
--- a/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
+++ b/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
@@ -1,26 +1,29 @@
+import asyncio
 from io import BytesIO
-from pathlib import Path
 from typing import List, Optional
 
+import aioboto3
 import fsspec
 from cdx_toolkit.cli import main
 from warcio.archiveiterator import ArchiveIterator
 
-from tests.conftest import requires_aws_s3
+from tests.conftest import requires_aws_s3, TEST_DATA_PATH
 
 from warcio import WARCWriter
+from cdx_toolkit.warcer_by_cdx.aioboto3_warcer import get_range_jobs_from_index_paths, write_warc
+from cdx_toolkit.warcer_by_cdx.aioboto3_utils import RangePayload, _STOP
 
-fixture_path = Path(__file__).parent.parent / 'data/warc_by_cdx'
+fixture_path = TEST_DATA_PATH / 'warc_by_cdx'
 
 
 def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog, extra_args: Optional[List[str]] = None):
     # test cli and check output
     index_path = fixture_path / 'filtered_CC-MAIN-2024-30_cdx-00187.gz'
+    resource_record_path = TEST_DATA_PATH / 'filter_cdx/whitelist_10_urls.txt'
+
     if extra_args is None:
         extra_args = []
 
-    # --write-index-as-record
-
     main(
         args=[
             '-v',
@@ -28,6 +31,8 @@ def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog, extra_args
             '--limit=10',
             'warc_by_cdx',
             str(index_path),
+            '--write-paths-as-resource-records',
+            str(resource_record_path),
             f'--prefix={str(base_prefix)}/TEST_warc_by_index',
             '--creator=foo',
             '--operator=bob',
@@ -40,13 +45,16 @@ def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog, extra_args
     assert 'Limit reached' in caplog.text
 
     # Validate extracted WARC
-    warc_filename = 'TEST_warc_by_index-000000.extracted.warc.gz'
+    warc_filename = 'TEST_warc_by_index-000000-001.extracted.warc.gz'
     warc_path = str(base_prefix) + '/' + warc_filename
-    resource_record = None
+
     info_record = None
     response_records = []
     response_contents = []
 
+    resource_record = None
+    resource_record_content = None
+
     with fsspec.open(warc_path, 'rb') as stream:
         for record in ArchiveIterator(stream):
             if record.rec_type == 'warcinfo':
@@ -56,8 +64,9 @@ def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog, extra_args
                 response_records.append(record)
                 response_contents.append(record.content_stream().read().decode('utf-8', errors='ignore'))
 
-            # if record.rec_type == 'resource':
-            #     resource_record = record
+            if record.rec_type == 'resource':
+                resource_record = record
+                resource_record_content = record.content_stream().read().decode('utf-8')
 
     assert len(response_records) == 10, 'Invalid record count'
     # assert resource_record is not None
@@ -65,8 +74,14 @@ def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog, extra_args
 
     assert 'Catalogue en ligne Mission de France' in response_contents[0], 'Invalid response content'
     assert 'dojo/dijit/themes/tundra/tundra' in response_contents[9], 'Invalid response content'
-    assert info_record is not None
-    assert 'operator: bob' in info_record, 'Invalid WARC info'
+
+    assert info_record is not None, 'Invalid info record'
+    assert 'operator: bob' in info_record, 'Invalid info record'
+
+    assert resource_record is not None
+    assert resource_record.length == 294, 'Invalid resource record'
+    assert resource_record_content[:10] == 'example.co', 'Invalid resource record'
+    assert resource_record_content[-20:-1] == 'hr.fr/produit/t-837', 'Invalid resource record'
 
 
 @requires_aws_s3
@@ -103,3 +118,112 @@ def test_warc_info():
     file_value = file_handler.getvalue().decode('utf-8')
 
     assert 'pypi_cdx_toolkit/123' in file_value
+
+
+@requires_aws_s3
+def test_write_warc_with_file_rotation(tmpdir):
+    """Test write_warc function with file size rotation"""
+
+    async def run_test():
+        # Setup test data
+        index_path = fixture_path / 'filtered_CC-MAIN-2024-30_cdx-00187.gz'
+        warc_download_prefix = 's3://commoncrawl'
+        prefix_path = f's3://commoncrawl-dev/cdx_toolkit/ci/test-outputs{tmpdir}/file_rotation_test'
+
+        # Use small file size to force rotation (100 KB)
+        max_file_size = 100 * 1024  # 100 KB
+
+        # Create asyncio queues
+        key_queue = asyncio.Queue()
+        item_queue = asyncio.Queue()
+
+        # Writer info for WARC header
+        writer_info = {
+            'software': 'cdx_toolkit test',
+            'operator': 'test',
+            'creator': 'test',
+            'description': 'Test WARC with file rotation',
+        }
+
+        # Setup S3 client
+        from botocore.config import Config
+
+        boto_cfg = Config(
+            region_name='us-east-1',
+            retries={'max_attempts': 3, 'mode': 'standard'},
+            connect_timeout=10,
+            read_timeout=120,
+        )
+
+        session = aioboto3.Session()
+
+        async with session.client('s3', config=boto_cfg) as s3:
+            # Generate range jobs from CDX file
+            await get_range_jobs_from_index_paths(
+                key_queue=key_queue,
+                index_paths=[str(index_path)],
+                warc_download_prefix=warc_download_prefix,
+                num_fetchers=1,
+                limit=10,  # Use 10 records to ensure we have enough data
+            )
+
+            # Collect all range jobs
+            range_jobs = []
+            while not key_queue.empty():
+                job = await key_queue.get()
+                if job is not _STOP:
+                    range_jobs.append(job)
+                key_queue.task_done()
+
+            # Create mock RangePayload objects with dummy data to simulate large content
+            # Each payload will be ~30KB to force multiple file rotations
+            dummy_data = b'A' * (30 * 1024)  # 30KB of dummy data
+
+            for job in range_jobs:
+                payload = RangePayload(job=job, data=dummy_data)
+                await item_queue.put(payload)
+
+            # Add stop signal
+            await item_queue.put(_STOP)
+
+            # Run write_warc function
+            await write_warc(
+                consumer_id=0,
+                item_queue=item_queue,
+                s3=s3,
+                max_attempts=3,
+                base_backoff_seconds=0.5,
+                prefix_path=prefix_path,
+                writer_info=writer_info,
+                max_file_size=max_file_size,
+                gzip=True,
+            )
+
+            # Verify that multiple WARC files were created
+            dest_bucket = 'commoncrawl-dev'
+            dest_prefix = f'cdx_toolkit/ci/test-outputs{tmpdir}/file_rotation_test'
+
+            # List objects to find all created WARC files
+            response = await s3.list_objects_v2(Bucket=dest_bucket, Prefix=dest_prefix)
+
+            warc_files = []
+            if 'Contents' in response:
+                for obj in response['Contents']:
+                    if obj['Key'].endswith('.extracted.warc.gz'):
+                        warc_files.append(obj['Key'])
+
+            # Assert that more than one WARC file was created
+            assert len(warc_files) == 4, f'Expected multiple WARC files, but found {len(warc_files)}: {warc_files}'
+
+            # Verify filename pattern includes sequence numbers
+            for warc_file in warc_files:
+                filename = warc_file.split('/')[-1]
+                # Should match pattern: prefix-000000-XXX.extracted.warc.gz
+                assert '-000000-' in filename, f"Filename doesn't contain expected sequence pattern: {filename}"
+
+            # Clean up created files
+            for warc_file in warc_files:
+                await s3.delete_object(Bucket=dest_bucket, Key=warc_file)
+
+    # Run the async test
+    asyncio.run(run_test())
diff --git a/tests/warc_by_cdx/test_warc_utils.py b/tests/warc_by_cdx/test_warc_utils.py
new file mode 100644
index 0000000..f95fbe5
--- /dev/null
+++ b/tests/warc_by_cdx/test_warc_utils.py
@@ -0,0 +1,31 @@
+import pytest
+from cdx_toolkit.warcer_by_cdx.warc_utils import get_resource_record_from_path
+from tests.conftest import TEST_DATA_PATH
+
+
+def test_get_resource_record_from_path():
+    resource_path = TEST_DATA_PATH / "filter_cdx/whitelist_10_urls.txt"
+    record = get_resource_record_from_path(resource_path)
+
+    assert record.content_type == "text/plain"
+
+    record_headers = dict(record.rec_headers.headers)
+    assert record_headers["WARC-Target-URI"] == str(resource_path)
+    
+
+def test_get_resource_record_from_path_with_metadata():
+    resource_path = TEST_DATA_PATH / "warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.gz"
+    metadata_path = TEST_DATA_PATH / "warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.metadata.json"
+
+    record = get_resource_record_from_path(resource_path, metadata_path)
+
+    assert record.content_type == "application/cdx"
+
+    record_headers = dict(record.rec_headers.headers)
+    assert record_headers["WARC-Target-URI"] == "filter_cdx.cdx.gz"
+    
+
+def test_get_resource_record_from_path_with_invalid_metadata_path():
+    with pytest.raises(ValueError):
+        resource_path = TEST_DATA_PATH / "filter_cdx/whitelist_10_urls.txt"
+        get_resource_record_from_path(resource_path, "invalid_metadata.xy")
\ No newline at end of file

From 24b263e3cfb2f2899d80cb7ca9f0ab520ea99f07 Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Fri, 19 Sep 2025 10:17:18 +0000
Subject: [PATCH 24/74] S3 access to CI, more unit tests

---
 .github/workflows/ci-feat-warc-by-cdx.yaml    |  12 +
 cdx_toolkit/warcer_by_cdx/aioboto3_utils.py   |  22 +-
 cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py  |   3 +-
 cdx_toolkit/warcer_by_cdx/aioboto3_writer.py  |   1 -
 cdx_toolkit/warcer_by_cdx/cdx_utils.py        |  12 -
 cdx_toolkit/warcer_by_cdx/warc_utils.py       |   8 +-
 tests/conftest.py                             |   2 +
 tests/warc_by_cdx/test_aioboto3_utils.py      | 213 +++++++++++++
 tests/warc_by_cdx/test_aioboto3_writer.py     | 290 ++++++++++++++++++
 tests/warc_by_cdx/test_warc_by_cdx.py         |   6 +-
 .../warc_by_cdx/test_warc_by_cdx_aioboto3.py  |  12 +-
 11 files changed, 540 insertions(+), 41 deletions(-)
 create mode 100644 tests/warc_by_cdx/test_aioboto3_utils.py
 create mode 100644 tests/warc_by_cdx/test_aioboto3_writer.py

diff --git a/.github/workflows/ci-feat-warc-by-cdx.yaml b/.github/workflows/ci-feat-warc-by-cdx.yaml
index 8688e8c..b532f65 100644
--- a/.github/workflows/ci-feat-warc-by-cdx.yaml
+++ b/.github/workflows/ci-feat-warc-by-cdx.yaml
@@ -8,6 +8,12 @@ on:
     branches:
     - main
 
+# These permissions are needed to interact with AWS S3 via GitHub's OIDC Token endpoint
+permissions:
+  id-token: write
+  contents: read
+  pull-requests: read
+
 jobs:
   unit-tests:
     runs-on: ${{ matrix.os }}
@@ -32,6 +38,12 @@ jobs:
       - name: checkout
         uses: actions/checkout@v4
 
+      - name: Configure AWS credentials from OIDC
+        uses: aws-actions/configure-aws-credentials@v4
+        with:
+          role-to-assume: arn:aws:iam::837454214164:role/GitHubActions-Role
+          aws-region: us-east-1
+
       - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:
diff --git a/cdx_toolkit/warcer_by_cdx/aioboto3_utils.py b/cdx_toolkit/warcer_by_cdx/aioboto3_utils.py
index 1ea64e8..ca68f1f 100644
--- a/cdx_toolkit/warcer_by_cdx/aioboto3_utils.py
+++ b/cdx_toolkit/warcer_by_cdx/aioboto3_utils.py
@@ -7,7 +7,6 @@
 
 from botocore.exceptions import ClientError, EndpointConnectionError
 
-_STOP = object()
 
 logger = logging.getLogger(__name__)
 
@@ -42,6 +41,7 @@ def get_stats(self) -> dict:
 
 @dataclass(frozen=True)
 class RangeJob:
+    """Defines a S3 range read request."""
     bucket: str
     key: str
     offset: int
@@ -50,6 +50,7 @@ class RangeJob:
 
 @dataclass(frozen=True)
 class RangePayload:
+    """Bytes output from S3 range read."""
     job: RangeJob
     data: bytes
 
@@ -63,6 +64,7 @@ def _backoff(attempt: int, base_backoff_seconds: float) -> float:
 
 
 def parse_s3_uri(uri: str) -> Tuple[str, str]:
+    """Parse a S3 URI and return bucket and prefix."""
     if not uri.startswith('s3://'):
         raise ValueError(f'Not an S3 URI: {uri}')
     rest = uri[5:]
@@ -94,16 +96,6 @@ async def with_retries(coro_factory, *, op_name: str, max_attempts: int, base_ba
     raise last_exc
 
 
-async def get_object_stream(s3, bucket: str, key: str, max_attempts: int, base_backoff_seconds: float):
-    resp = await with_retries(
-        lambda: s3.get_object(Bucket=bucket, Key=key),
-        op_name=f'get_object {bucket}/{key}',
-        max_attempts=max_attempts,
-        base_backoff_seconds=base_backoff_seconds,
-    )
-    return resp['Body']
-
-
 async def ranged_get_bytes(
     s3,
     bucket: str,
@@ -113,6 +105,7 @@ async def ranged_get_bytes(
     max_attempts: int,
     base_backoff_seconds: float,
 ) -> bytes:
+    """Ranged get request to S3 with retries and backoff."""
     end = offset + length - 1  # inclusive
     resp = await with_retries(
         lambda: s3.get_object(Bucket=bucket, Key=key, Range=f'bytes={offset}-{end}'),
@@ -128,13 +121,11 @@ async def mpu_create(
     bucket: str,
     key: str,
     *,
-    content_type: Optional[str],
     max_attempts: int,
     base_backoff_seconds: float,
 ):
+    """Create multi part upload to S3."""
     kwargs = {'Bucket': bucket, 'Key': key}
-    if content_type:
-        kwargs['ContentType'] = content_type
     resp = await with_retries(
         lambda: s3.create_multipart_upload(**kwargs),
         op_name=f'create_multipart_upload {bucket}/{key}',
@@ -154,6 +145,7 @@ async def mpu_upload_part(
     max_attempts: int,
     base_backoff_seconds: float,
 ) -> str:
+    """Upload a part of a multi-part upload to S3."""
     resp = await with_retries(
         lambda: s3.upload_part(
             Bucket=bucket,
@@ -178,6 +170,7 @@ async def mpu_complete(
     max_attempts: int,
     base_backoff_seconds: float,
 ):
+    """Send complete for multi-part upload."""
     await with_retries(
         lambda: s3.complete_multipart_upload(
             Bucket=bucket, Key=key, UploadId=upload_id, MultipartUpload={'Parts': parts}
@@ -189,6 +182,7 @@ async def mpu_complete(
 
 
 async def mpu_abort(s3, bucket: str, key: str, upload_id: str):
+    """Abort mult-part upload."""
     try:
         await s3.abort_multipart_upload(Bucket=bucket, Key=key, UploadId=upload_id)
     except Exception:
diff --git a/cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py b/cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py
index 511e3e6..cbec2c4 100644
--- a/cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py
+++ b/cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py
@@ -8,7 +8,6 @@
 from warcio import WARCWriter
 
 from cdx_toolkit.warcer_by_cdx.aioboto3_utils import (
-    _STOP,
     RangeJob,
     RangePayload,
     ThroughputTracker,
@@ -22,6 +21,8 @@
 from cdx_toolkit.warcer_by_cdx.warc_utils import get_bytes_from_warc_record, get_resource_record_from_path
 
 
+_STOP = object()
+
 logger = logging.getLogger(__name__)
 
 
diff --git a/cdx_toolkit/warcer_by_cdx/aioboto3_writer.py b/cdx_toolkit/warcer_by_cdx/aioboto3_writer.py
index f262a88..0bdf803 100644
--- a/cdx_toolkit/warcer_by_cdx/aioboto3_writer.py
+++ b/cdx_toolkit/warcer_by_cdx/aioboto3_writer.py
@@ -39,7 +39,6 @@ async def start(self, s3):
             s3,
             self.dest_bucket,
             self.shard_key,
-            content_type=self.content_type,
             max_attempts=self.max_attempts,
             base_backoff_seconds=self.base_backoff_seconds,
         )
diff --git a/cdx_toolkit/warcer_by_cdx/cdx_utils.py b/cdx_toolkit/warcer_by_cdx/cdx_utils.py
index 0f2bc30..513b02c 100644
--- a/cdx_toolkit/warcer_by_cdx/cdx_utils.py
+++ b/cdx_toolkit/warcer_by_cdx/cdx_utils.py
@@ -31,18 +31,6 @@ def get_index_as_string_from_path(
         return f.read()
 
 
-def get_index_record(index: str, index_path: str, encoding: str = 'utf-8') -> ArcWarcRecord:
-    """Build WARC resource record for index."""
-    return WARCWriter(None).create_warc_record(
-        uri=index_path,  # TODO this could be a local / internal path
-        record_type='resource',
-        payload=BytesIO(index.encode(encoding)),
-        http_headers=None,
-        warc_content_type='application/cdx',
-        warc_headers_dict=None,  # TODO should we add some other metadata headers?
-    )
-
-
 def read_cdx_line(line: str, warc_download_prefix: str) -> Tuple[str, int, int]:
     cols = line.split(' ', maxsplit=2)
 
diff --git a/cdx_toolkit/warcer_by_cdx/warc_utils.py b/cdx_toolkit/warcer_by_cdx/warc_utils.py
index 0eb5b71..0a75f2f 100644
--- a/cdx_toolkit/warcer_by_cdx/warc_utils.py
+++ b/cdx_toolkit/warcer_by_cdx/warc_utils.py
@@ -27,10 +27,10 @@ def get_resource_record_from_path(
     """Build WARC resource record for file path and metdata path.
     
     The metadata file must be a valid JSON and can have the following fields:
-    - warc_content_type
-    - uri
-    - http_headers
-    - warc_headers_dict
+    - warc_content_type: str
+    - uri: str
+    - http_headers: dict
+    - warc_headers_dict: str
 
     If uri is not provided as metadata, the file_path is used.
     If warc_content_type is not provided as metadata, the type is guessed.
diff --git a/tests/conftest.py b/tests/conftest.py
index b662111..def6312 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -1,9 +1,11 @@
+import os
 from pathlib import Path
 import pytest
 import boto3
 from botocore.exceptions import NoCredentialsError, ClientError
 
 TEST_DATA_PATH = Path(__file__).parent / "data"
+TEST_S3_BUCKET = os.environ.get("CDXT_TEST_S3_BUCKET", "commoncrawl-ci-temp")
 
 
 def check_aws_s3_access():
diff --git a/tests/warc_by_cdx/test_aioboto3_utils.py b/tests/warc_by_cdx/test_aioboto3_utils.py
new file mode 100644
index 0000000..6054495
--- /dev/null
+++ b/tests/warc_by_cdx/test_aioboto3_utils.py
@@ -0,0 +1,213 @@
+import pytest
+
+import asyncio
+from unittest.mock import AsyncMock
+
+
+from cdx_toolkit.warcer_by_cdx.aioboto3_utils import (
+    _backoff,
+    parse_s3_uri,
+    mpu_abort,
+    with_retries,
+)
+from botocore.exceptions import EndpointConnectionError
+from botocore.exceptions import ClientError
+
+
+def test_backoff():
+    """Test _backoff function with exponential backoff and jitter."""
+    base_backoff = 1.0
+
+    # Test attempt 1: should be between 0.8 and 1.2 seconds (with jitter)
+    result1 = _backoff(1, base_backoff)
+    assert 0.8 <= result1 <= 1.2
+
+    # Test attempt 2: should be between 1.6 and 2.4 seconds (2^1 * base * jitter)
+    result2 = _backoff(2, base_backoff)
+    assert 1.6 <= result2 <= 2.4
+
+    # Test attempt 3: should be between 3.2 and 4.8 seconds (2^2 * base * jitter)
+    result3 = _backoff(3, base_backoff)
+    assert 3.2 <= result3 <= 4.8
+
+    # Test with different base backoff
+    base_backoff_small = 0.1
+    result_small = _backoff(1, base_backoff_small)
+    assert 0.08 <= result_small <= 0.12
+
+    # Test minimum backoff (should never be less than 0.05)
+    very_small_base = 0.001
+    result_min = _backoff(1, very_small_base)
+    assert result_min >= 0.05
+
+    # Test that backoff increases with attempts
+    results = [_backoff(i, 0.5) for i in range(1, 6)]
+    # Generally should increase, though jitter might cause small variations
+    # Check that the trend is generally increasing
+    assert results[1] > results[0] * 0.8  # Allow for jitter variation
+    assert results[2] > results[1] * 0.8
+    assert results[3] > results[2] * 0.8
+
+
+def test_parse_s3_uri():
+    """Test parse_s3_uri function for valid and invalid S3 URIs."""
+
+    # Test valid S3 URIs
+    bucket, prefix = parse_s3_uri('s3://my-bucket/path/to/file.txt')
+    assert bucket == 'my-bucket'
+    assert prefix == 'path/to/file.txt'
+
+    bucket, prefix = parse_s3_uri('s3://test-bucket/folder/subfolder/data.json')
+    assert bucket == 'test-bucket'
+    assert prefix == 'folder/subfolder/data.json'
+
+    bucket, prefix = parse_s3_uri('s3://simple/file')
+    assert bucket == 'simple'
+    assert prefix == 'file'
+
+    # Test with deep nested paths
+    bucket, prefix = parse_s3_uri('s3://bucket/a/b/c/d/e/f/file.ext')
+    assert bucket == 'bucket'
+    assert prefix == 'a/b/c/d/e/f/file.ext'
+
+    # Test invalid URIs - should raise ValueError
+    with pytest.raises(ValueError, match='Not an S3 URI'):
+        parse_s3_uri('http://example.com/path')
+
+    with pytest.raises(ValueError, match='Not an S3 URI'):
+        parse_s3_uri('ftp://bucket/file')
+
+    with pytest.raises(ValueError, match='Not an S3 URI'):
+        parse_s3_uri('bucket/file')
+
+    # Test malformed S3 URIs
+    with pytest.raises(ValueError, match='Malformed S3 URI'):
+        parse_s3_uri('s3://')
+
+    with pytest.raises(ValueError, match='Malformed S3 URI'):
+        parse_s3_uri('s3://bucket')
+
+    with pytest.raises(ValueError, match='Malformed S3 URI'):
+        parse_s3_uri('s3://bucket/')
+
+    with pytest.raises(ValueError, match='Malformed S3 URI'):
+        parse_s3_uri('s3:///file')
+
+
+def test_mpu_abort_success():
+    """Test mpu_abort function with successful abort."""
+
+    async def run_test():
+        mock_s3 = AsyncMock()
+        bucket = 'test-bucket'
+        key = 'test-key'
+        upload_id = 'test-upload-id'
+
+        await mpu_abort(mock_s3, bucket, key, upload_id)
+
+        mock_s3.abort_multipart_upload.assert_called_once_with(Bucket=bucket, Key=key, UploadId=upload_id)
+
+    asyncio.run(run_test())
+
+
+def test_mpu_abort_with_exception():
+    """Test mpu_abort function when abort fails (should catch exception)."""
+
+    async def run_test():
+        mock_s3 = AsyncMock()
+        mock_s3.abort_multipart_upload.side_effect = Exception('S3 error')
+
+        bucket = 'test-bucket'
+        key = 'test-key'
+        upload_id = 'test-upload-id'
+
+        # Should not raise exception, should log it instead
+        await mpu_abort(mock_s3, bucket, key, upload_id)
+
+        mock_s3.abort_multipart_upload.assert_called_once_with(Bucket=bucket, Key=key, UploadId=upload_id)
+
+    asyncio.run(run_test())
+
+
+def test_with_retries_success():
+    """Test with_retries function with successful operation on first attempt."""
+
+    async def run_test():
+        call_count = 0
+
+        async def successful_coro():
+            nonlocal call_count
+            call_count += 1
+            return 'success'
+
+        result = await with_retries(successful_coro, op_name='test_op', max_attempts=3, base_backoff_seconds=0.1)
+
+        assert result == 'success'
+        assert call_count == 1
+
+    asyncio.run(run_test())
+
+
+def test_with_retries_eventual_success():
+    """Test with_retries function that succeeds after initial failures."""
+
+    async def run_test():
+        call_count = 0
+
+        async def eventually_successful_coro():
+            nonlocal call_count
+            call_count += 1
+            if call_count < 3:
+                raise ClientError({'Error': {'Code': 'Throttling'}}, 'test_op')
+            return 'success'
+
+        result = await with_retries(
+            eventually_successful_coro,
+            op_name='test_op',
+            max_attempts=3,
+            base_backoff_seconds=0.01,  # Very short for testing
+        )
+
+        assert result == 'success'
+        assert call_count == 3
+
+    asyncio.run(run_test())
+
+
+def test_with_retries_max_attempts_exceeded():
+    """Test with_retries function when max attempts are exceeded."""
+
+    async def run_test():
+        call_count = 0
+
+        async def failing_coro():
+            nonlocal call_count
+            call_count += 1
+            raise EndpointConnectionError(endpoint_url='test')
+
+        with pytest.raises(EndpointConnectionError):
+            await with_retries(failing_coro, op_name='test_op', max_attempts=2, base_backoff_seconds=0.01)
+
+        assert call_count == 2
+
+    asyncio.run(run_test())
+
+
+def test_with_retries_non_retryable_exception():
+    """Test with_retries function with non-retryable exceptions."""
+
+    async def run_test():
+        call_count = 0
+
+        async def failing_coro():
+            nonlocal call_count
+            call_count += 1
+            raise ValueError('Non-retryable error')
+
+        with pytest.raises(ValueError):
+            await with_retries(failing_coro, op_name='test_op', max_attempts=3, base_backoff_seconds=0.01)
+
+        # Should fail immediately without retries
+        assert call_count == 1
+
+    asyncio.run(run_test())
diff --git a/tests/warc_by_cdx/test_aioboto3_writer.py b/tests/warc_by_cdx/test_aioboto3_writer.py
new file mode 100644
index 0000000..22cb38b
--- /dev/null
+++ b/tests/warc_by_cdx/test_aioboto3_writer.py
@@ -0,0 +1,290 @@
+import pytest
+import asyncio
+from unittest.mock import AsyncMock, patch
+
+from cdx_toolkit.warcer_by_cdx.aioboto3_writer import ShardWriter
+
+
+def test_shard_writer_init():
+    """Test ShardWriter initialization."""
+    shard_key = 'test-shard.warc.gz'
+    dest_bucket = 'test-bucket'
+    content_type = 'application/gzip'
+    min_part_size = 5 * 1024 * 1024  # 5 MiB
+    max_attempts = 3
+    base_backoff_seconds = 0.1
+
+    writer = ShardWriter(
+        shard_key=shard_key,
+        dest_bucket=dest_bucket,
+        content_type=content_type,
+        min_part_size=min_part_size,
+        max_attempts=max_attempts,
+        base_backoff_seconds=base_backoff_seconds,
+    )
+
+    assert writer.shard_key == shard_key
+    assert writer.dest_bucket == dest_bucket
+    assert writer.content_type == content_type
+    assert writer.min_part_size == min_part_size
+    assert writer.max_attempts == max_attempts
+    assert writer.base_backoff_seconds == base_backoff_seconds
+    assert writer.upload_id is None
+    assert writer.part_number == 1
+    assert writer.parts == []
+    assert isinstance(writer.buffer, bytearray)
+    assert len(writer.buffer) == 0
+
+
+def test_shard_writer_start():
+    """Test ShardWriter start method."""
+
+    async def run_test():
+        with patch('cdx_toolkit.warcer_by_cdx.aioboto3_writer.mpu_create') as mock_mpu_create:
+            mock_mpu_create.return_value = 'test-upload-id'
+
+            writer = ShardWriter(
+                shard_key='test.warc.gz',
+                dest_bucket='test-bucket',
+                content_type='application/gzip',
+                min_part_size=1024,
+                max_attempts=3,
+                base_backoff_seconds=0.1,
+            )
+
+            mock_s3 = AsyncMock()
+            await writer.start(mock_s3)
+
+            assert writer.upload_id == 'test-upload-id'
+            mock_mpu_create.assert_called_once_with(
+                mock_s3,
+                'test-bucket',
+                'test.warc.gz',
+                max_attempts=3,
+                base_backoff_seconds=0.1,
+            )
+
+    asyncio.run(run_test())
+
+
+def test_shard_writer_write_small_data():
+    """Test ShardWriter write method with small data that stays in buffer."""
+
+    async def run_test():
+        writer = ShardWriter(
+            shard_key='test.warc.gz',
+            dest_bucket='test-bucket',
+            content_type='application/gzip',
+            min_part_size=1024,  # 1 KiB
+            max_attempts=3,
+            base_backoff_seconds=0.1,
+        )
+
+        mock_s3 = AsyncMock()
+        small_data = b'small test data'
+
+        await writer.write(mock_s3, small_data)
+
+        # Data should be in buffer, no parts uploaded yet
+        assert len(writer.buffer) == len(small_data)
+        assert bytes(writer.buffer) == small_data
+        assert writer.part_number == 1
+        assert len(writer.parts) == 0
+
+    asyncio.run(run_test())
+
+
+def test_shard_writer_write_large_data():
+    """Test ShardWriter write method with large data that triggers part uploads."""
+
+    async def run_test():
+        with patch('cdx_toolkit.warcer_by_cdx.aioboto3_writer.mpu_upload_part') as mock_upload_part:
+            mock_upload_part.return_value = 'test-etag-1'
+
+            writer = ShardWriter(
+                shard_key='test.warc.gz',
+                dest_bucket='test-bucket',
+                content_type='application/gzip',
+                min_part_size=100,  # 100 bytes
+                max_attempts=3,
+                base_backoff_seconds=0.1,
+            )
+            writer.upload_id = 'test-upload-id'
+
+            mock_s3 = AsyncMock()
+            large_data = b'x' * 250  # 250 bytes, should create 2 parts
+
+            await writer.write(mock_s3, large_data)
+
+            # Should have uploaded 2 parts (100 bytes each) with 50 bytes remaining in buffer
+            assert mock_upload_part.call_count == 2
+            assert len(writer.parts) == 2
+            assert writer.part_number == 3  # Next part would be #3
+            assert len(writer.buffer) == 50  # Remaining bytes
+            assert bytes(writer.buffer) == b'x' * 50
+
+            # Verify parts structure
+            assert writer.parts[0] == {'PartNumber': 1, 'ETag': 'test-etag-1'}
+            assert writer.parts[1] == {'PartNumber': 2, 'ETag': 'test-etag-1'}
+
+    asyncio.run(run_test())
+
+
+def test_shard_writer_flush_full_parts():
+    """Test ShardWriter _flush_full_parts private method directly."""
+
+    async def run_test():
+        with patch('cdx_toolkit.warcer_by_cdx.aioboto3_writer.mpu_upload_part') as mock_upload_part:
+            mock_upload_part.return_value = 'test-etag-flush'
+
+            writer = ShardWriter(
+                shard_key='test.warc.gz',
+                dest_bucket='test-bucket',
+                content_type='application/gzip',
+                min_part_size=50,  # 50 bytes
+                max_attempts=3,
+                base_backoff_seconds=0.1,
+            )
+            writer.upload_id = 'test-upload-id'
+
+            # Pre-fill buffer with 150 bytes (should create 3 parts of 50 bytes each)
+            writer.buffer.extend(b'a' * 150)
+
+            mock_s3 = AsyncMock()
+            await writer._flush_full_parts(mock_s3)
+
+            # Should have uploaded 3 full parts, no remainder
+            assert mock_upload_part.call_count == 3
+            assert len(writer.parts) == 3
+            assert writer.part_number == 4  # Next part would be #4
+            assert len(writer.buffer) == 0  # All data flushed
+
+            # Verify all parts were created correctly
+            for i in range(3):
+                assert writer.parts[i] == {'PartNumber': i + 1, 'ETag': 'test-etag-flush'}
+
+    asyncio.run(run_test())
+
+
+def test_shard_writer_close_with_buffer():
+    """Test ShardWriter close method with data remaining in buffer."""
+
+    async def run_test():
+        with patch('cdx_toolkit.warcer_by_cdx.aioboto3_writer.mpu_upload_part') as mock_upload_part, patch(
+            'cdx_toolkit.warcer_by_cdx.aioboto3_writer.mpu_complete'
+        ) as mock_complete:
+            mock_upload_part.return_value = 'final-etag'
+
+            writer = ShardWriter(
+                shard_key='test.warc.gz',
+                dest_bucket='test-bucket',
+                content_type='application/gzip',
+                min_part_size=1000,  # Large min size to keep data in buffer
+                max_attempts=3,
+                base_backoff_seconds=0.1,
+            )
+            writer.upload_id = 'test-upload-id'
+
+            # Add some data to buffer
+            remaining_data = b'final chunk data'
+            writer.buffer.extend(remaining_data)
+
+            mock_s3 = AsyncMock()
+            await writer.close(mock_s3)
+
+            # Should upload the final part and complete MPU
+            mock_upload_part.assert_called_once_with(
+                mock_s3,
+                'test-bucket',
+                'test.warc.gz',
+                'test-upload-id',
+                1,  # part number
+                remaining_data,
+                3,  # max attempts
+                0.1,  # base backoff
+            )
+
+            mock_complete.assert_called_once_with(
+                mock_s3,
+                'test-bucket',
+                'test.warc.gz',
+                'test-upload-id',
+                [{'PartNumber': 1, 'ETag': 'final-etag'}],
+                3,  # max attempts
+                0.1,  # base backoff
+            )
+
+            # Buffer should be cleared
+            assert len(writer.buffer) == 0
+            assert len(writer.parts) == 1
+
+    asyncio.run(run_test())
+
+
+def test_shard_writer_close_empty():
+    """Test ShardWriter close method with no data (empty buffer, no parts)."""
+
+    async def run_test():
+        with patch('cdx_toolkit.warcer_by_cdx.aioboto3_writer.mpu_upload_part') as mock_upload_part, patch(
+            'cdx_toolkit.warcer_by_cdx.aioboto3_writer.mpu_complete'
+        ) as mock_complete:
+            writer = ShardWriter(
+                shard_key='test.warc.gz',
+                dest_bucket='test-bucket',
+                content_type='application/gzip',
+                min_part_size=1000,
+                max_attempts=3,
+                base_backoff_seconds=0.1,
+            )
+            writer.upload_id = 'test-upload-id'
+
+            # No data in buffer, no parts uploaded
+            mock_s3 = AsyncMock()
+            await writer.close(mock_s3)
+
+            # Should not upload any parts or complete MPU since there's no data
+            mock_upload_part.assert_not_called()
+            mock_complete.assert_not_called()
+
+            # State should remain unchanged
+            assert len(writer.buffer) == 0
+            assert len(writer.parts) == 0
+
+    asyncio.run(run_test())
+
+
+def test_shard_writer_close_with_exception():
+    """Test ShardWriter close method with exception and abort handling."""
+
+    async def run_test():
+        with patch('cdx_toolkit.warcer_by_cdx.aioboto3_writer.mpu_upload_part') as mock_upload_part, patch(
+            'cdx_toolkit.warcer_by_cdx.aioboto3_writer.mpu_complete'
+        ) as mock_complete, patch('cdx_toolkit.warcer_by_cdx.aioboto3_writer.mpu_abort') as mock_abort:
+            mock_upload_part.return_value = 'error-etag'
+            mock_complete.side_effect = Exception('Complete failed')
+
+            writer = ShardWriter(
+                shard_key='test.warc.gz',
+                dest_bucket='test-bucket',
+                content_type='application/gzip',
+                min_part_size=1000,
+                max_attempts=3,
+                base_backoff_seconds=0.1,
+            )
+            writer.upload_id = 'test-upload-id'
+
+            # Add some data to buffer to trigger upload and complete
+            writer.buffer.extend(b'some data')
+
+            mock_s3 = AsyncMock()
+
+            # Should raise the exception after attempting abort
+            with pytest.raises(Exception, match='Complete failed'):
+                await writer.close(mock_s3)
+
+            # Should have attempted to upload part and complete, then abort on failure
+            mock_upload_part.assert_called_once()
+            mock_complete.assert_called_once()
+            mock_abort.assert_called_once_with(mock_s3, 'test-bucket', 'test.warc.gz', 'test-upload-id')
+
+    asyncio.run(run_test())
diff --git a/tests/warc_by_cdx/test_warc_by_cdx.py b/tests/warc_by_cdx/test_warc_by_cdx.py
index b9b1724..cc47447 100644
--- a/tests/warc_by_cdx/test_warc_by_cdx.py
+++ b/tests/warc_by_cdx/test_warc_by_cdx.py
@@ -12,7 +12,7 @@
 import pytest
 from warcio.archiveiterator import ArchiveIterator
 
-from tests.conftest import requires_aws_s3, TEST_DATA_PATH
+from tests.conftest import TEST_S3_BUCKET, requires_aws_s3, TEST_DATA_PATH
 
 
 fixture_path = TEST_DATA_PATH / 'warc_by_cdx'
@@ -97,7 +97,7 @@ def test_cli_warc_by_cdx_over_s3(tmpdir, caplog):
 @requires_aws_s3
 def test_cli_warc_by_cdx_over_s3_to_s3(tmpdir, caplog):
     assert_cli_warc_by_cdx(
-        's3://commoncrawl', base_prefix='s3://commoncrawl-dev/cdx_toolkit/ci/test-outputs' + str(tmpdir), caplog=caplog
+        's3://commoncrawl', base_prefix=f's3://{TEST_S3_BUCKET}/cdx_toolkit/ci/test-outputs' + str(tmpdir), caplog=caplog
     )
 
 
@@ -105,7 +105,7 @@ def test_cli_warc_by_cdx_over_s3_to_s3(tmpdir, caplog):
 def test_cli_warc_by_cdx_over_s3_to_s3_in_parallel(tmpdir, caplog):
     assert_cli_warc_by_cdx(
         's3://commoncrawl',
-        base_prefix='s3://commoncrawl-dev/cdx_toolkit/ci/test-outputs' + str(tmpdir),
+        base_prefix=f's3://{TEST_S3_BUCKET}/cdx_toolkit/ci/test-outputs' + str(tmpdir),
         caplog=caplog,
         extra_args=['--parallel=3'],
     )
diff --git a/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py b/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
index 5cceead..5d48bbf 100644
--- a/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
+++ b/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
@@ -7,11 +7,11 @@
 from cdx_toolkit.cli import main
 from warcio.archiveiterator import ArchiveIterator
 
-from tests.conftest import requires_aws_s3, TEST_DATA_PATH
+from tests.conftest import TEST_S3_BUCKET, requires_aws_s3, TEST_DATA_PATH
 
 from warcio import WARCWriter
-from cdx_toolkit.warcer_by_cdx.aioboto3_warcer import get_range_jobs_from_index_paths, write_warc
-from cdx_toolkit.warcer_by_cdx.aioboto3_utils import RangePayload, _STOP
+from cdx_toolkit.warcer_by_cdx.aioboto3_warcer import get_range_jobs_from_index_paths, write_warc, _STOP
+from cdx_toolkit.warcer_by_cdx.aioboto3_utils import RangePayload
 
 fixture_path = TEST_DATA_PATH / 'warc_by_cdx'
 
@@ -88,7 +88,7 @@ def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog, extra_args
 def test_cli_warc_by_cdx_over_s3_to_s3_in_parallel_aioboto3(tmpdir, caplog):
     assert_cli_warc_by_cdx(
         's3://commoncrawl',
-        base_prefix='s3://commoncrawl-dev/cdx_toolkit/ci/test-outputs' + str(tmpdir),
+        base_prefix=f's3://{TEST_S3_BUCKET}/cdx_toolkit/ci/test-outputs' + str(tmpdir),
         caplog=caplog,
         extra_args=[
             '--parallel=3',
@@ -128,7 +128,7 @@ async def run_test():
         # Setup test data
         index_path = fixture_path / 'filtered_CC-MAIN-2024-30_cdx-00187.gz'
         warc_download_prefix = 's3://commoncrawl'
-        prefix_path = f's3://commoncrawl-dev/cdx_toolkit/ci/test-outputs{tmpdir}/file_rotation_test'
+        prefix_path = f's3://{TEST_S3_BUCKET}/cdx_toolkit/ci/test-outputs{tmpdir}/file_rotation_test'
 
         # Use small file size to force rotation (100 KB)
         max_file_size = 100 * 1024  # 100 KB
@@ -200,7 +200,7 @@ async def run_test():
             )
 
             # Verify that multiple WARC files were created
-            dest_bucket = 'commoncrawl-dev'
+            dest_bucket = TEST_S3_BUCKET
             dest_prefix = f'cdx_toolkit/ci/test-outputs{tmpdir}/file_rotation_test'
 
             # List objects to find all created WARC files

From 5840c4c31b6bd60ae8fd07854c8cc6e343714bf5 Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Fri, 19 Sep 2025 11:55:07 +0000
Subject: [PATCH 25/74] fix s3 access in action

---
 .github/workflows/ci-feat-warc-by-cdx.yaml | 12 ++++++------
 tests/conftest.py                          |  5 +++--
 2 files changed, 9 insertions(+), 8 deletions(-)

diff --git a/.github/workflows/ci-feat-warc-by-cdx.yaml b/.github/workflows/ci-feat-warc-by-cdx.yaml
index b532f65..001a1c7 100644
--- a/.github/workflows/ci-feat-warc-by-cdx.yaml
+++ b/.github/workflows/ci-feat-warc-by-cdx.yaml
@@ -38,12 +38,6 @@ jobs:
       - name: checkout
         uses: actions/checkout@v4
 
-      - name: Configure AWS credentials from OIDC
-        uses: aws-actions/configure-aws-credentials@v4
-        with:
-          role-to-assume: arn:aws:iam::837454214164:role/GitHubActions-Role
-          aws-region: us-east-1
-
       - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:
@@ -57,6 +51,12 @@ jobs:
       - name: Install cdx_toolkit
         run: pip install .[test]
 
+      - name: Configure AWS credentials from OIDC
+        uses: aws-actions/configure-aws-credentials@v4
+        with:
+          role-to-assume: arn:aws:iam::837454214164:role/GitHubActions-Role
+          aws-region: us-east-1
+          
       - name: Run tests (feature only)
         run: |
           PYTHONPATH=. py.test -rA -s --doctest-modules --cov-report=xml --cov-append --cov cdx_toolkit tests/warc_by_cdx tests/unit -v -v
diff --git a/tests/conftest.py b/tests/conftest.py
index def6312..5191e45 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -12,8 +12,9 @@ def check_aws_s3_access():
     """Check if AWS S3 access is available."""
     try:
         s3_client = boto3.client('s3')
-        # Try to list buckets as a simple check
-        s3_client.list_buckets()
+
+        # Try list objects on test bucket
+        s3_client.list_objects_v2(Bucket=TEST_S3_BUCKET, MaxKeys=1)
         return True
     except (NoCredentialsError, ClientError):
         return False

From 841fe075415715ade7199a65c9d1c186acfbad0b Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Fri, 19 Sep 2025 12:26:11 +0000
Subject: [PATCH 26/74] disable s3 tests for py < 39

---
 .github/workflows/ci-feat-warc-by-cdx.yaml |  5 +++++
 cdx_toolkit/warcer_by_cdx/__init__.py      |  4 ++++
 tests/conftest.py                          | 14 ++++++++++----
 3 files changed, 19 insertions(+), 4 deletions(-)

diff --git a/.github/workflows/ci-feat-warc-by-cdx.yaml b/.github/workflows/ci-feat-warc-by-cdx.yaml
index 001a1c7..f86db9b 100644
--- a/.github/workflows/ci-feat-warc-by-cdx.yaml
+++ b/.github/workflows/ci-feat-warc-by-cdx.yaml
@@ -56,6 +56,11 @@ jobs:
         with:
           role-to-assume: arn:aws:iam::837454214164:role/GitHubActions-Role
           aws-region: us-east-1
+
+      - name: Disable S3 unit tests for Python < 3.9
+        run: |
+          if [[ "${{ matrix.python-version }}" < "3.9" ]]; then
+            echo "CDXT_DISABLE_S3_TESTS=1" >> $GITHUB_ENV
           
       - name: Run tests (feature only)
         run: |
diff --git a/cdx_toolkit/warcer_by_cdx/__init__.py b/cdx_toolkit/warcer_by_cdx/__init__.py
index d12ac45..9757ccc 100644
--- a/cdx_toolkit/warcer_by_cdx/__init__.py
+++ b/cdx_toolkit/warcer_by_cdx/__init__.py
@@ -95,6 +95,10 @@ def run_warcer_by_cdx(args, cmdline):
             writer_kwargs=writer_kwargs,
         )
     elif implementation == 'aioboto3':
+        if sys.version_info.major < 3 or (sys.version_info.major >= 3 and sys.version_info.minor < 9):
+            logger.error('The `aioboto3` implementation requires Python version >= 3.9')
+            sys.exit(1)
+
         records_n = filter_warc_by_cdx_via_aioboto3(
             index_paths=index_paths,
             prefix_path=prefix_path,
diff --git a/tests/conftest.py b/tests/conftest.py
index 5191e45..bfc4b40 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -6,6 +6,7 @@
 
 TEST_DATA_PATH = Path(__file__).parent / "data"
 TEST_S3_BUCKET = os.environ.get("CDXT_TEST_S3_BUCKET", "commoncrawl-ci-temp")
+DISABLE_S3_TESTS = bool(os.environ.get("CDXT_DISABLE_S3_TESTS", False))
 
 
 def check_aws_s3_access():
@@ -21,8 +22,13 @@ def check_aws_s3_access():
 
 
 def requires_aws_s3(func):
-    """Pytest decorator that skips test if AWS S3 access is not available."""
+    """Pytest decorator that skips test if AWS S3 access is not available or disabled."""
     return pytest.mark.skipif(
-        not check_aws_s3_access(),
-        reason="AWS S3 access not available (no credentials or permissions)"
-    )(func)
\ No newline at end of file
+        DISABLE_S3_TESTS,
+        reason="AWS S3 access is disabled via environment variable."
+        )(
+            pytest.mark.skipif(
+            not check_aws_s3_access(),
+            reason="AWS S3 access not available (no credentials or permissions)"
+        )(func)
+    )

From eb0a4eb176e0e6c14d903f44fc43cdcaae694708 Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Fri, 19 Sep 2025 12:30:48 +0000
Subject: [PATCH 27/74] fixed syntax

---
 .github/workflows/ci-feat-warc-by-cdx.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.github/workflows/ci-feat-warc-by-cdx.yaml b/.github/workflows/ci-feat-warc-by-cdx.yaml
index f86db9b..0d0be8b 100644
--- a/.github/workflows/ci-feat-warc-by-cdx.yaml
+++ b/.github/workflows/ci-feat-warc-by-cdx.yaml
@@ -61,6 +61,7 @@ jobs:
         run: |
           if [[ "${{ matrix.python-version }}" < "3.9" ]]; then
             echo "CDXT_DISABLE_S3_TESTS=1" >> $GITHUB_ENV
+          fi
           
       - name: Run tests (feature only)
         run: |

From 3ddf1a4a9b5396f6a72d5c161b79730818545870 Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Fri, 19 Sep 2025 12:35:28 +0000
Subject: [PATCH 28/74] fixed bad s3 bucket

---
 tests/warc_by_cdx/test_warc_writer.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tests/warc_by_cdx/test_warc_writer.py b/tests/warc_by_cdx/test_warc_writer.py
index 70ca45b..020ab3d 100644
--- a/tests/warc_by_cdx/test_warc_writer.py
+++ b/tests/warc_by_cdx/test_warc_writer.py
@@ -3,7 +3,7 @@
 import pytest
 import cdx_toolkit
 
-from tests.conftest import requires_aws_s3
+from tests.conftest import TEST_S3_BUCKET, requires_aws_s3
 
 from warcio import WARCWriter
 from warcio.archiveiterator import ArchiveIterator
@@ -72,7 +72,7 @@ def test_write_to_local(prefix, gzip, tmpdir):
 @pytest.mark.parametrize(
     'prefix',
     [
-        pytest.param('s3://commoncrawl-dev/cdx_toolkit/ci/test-outputs', id='S3 prefix'),
+        pytest.param(f's3://{TEST_S3_BUCKET}/cdx_toolkit/ci/test-outputs', id='S3 prefix'),
     ],
 )
 def test_write_to_s3(prefix, tmpdir):

From d8a627fec02d2230a31fb54485f30b5ebb010690 Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Fri, 19 Sep 2025 12:52:41 +0000
Subject: [PATCH 29/74] adding more tests

---
 cdx_toolkit/warcer_by_cdx/cdx_utils.py | 17 ++-------
 tests/warc_by_cdx/test_cdx_utils.py    | 53 +++++++++++++++++++++++---
 2 files changed, 51 insertions(+), 19 deletions(-)

diff --git a/cdx_toolkit/warcer_by_cdx/cdx_utils.py b/cdx_toolkit/warcer_by_cdx/cdx_utils.py
index 513b02c..ef8b92c 100644
--- a/cdx_toolkit/warcer_by_cdx/cdx_utils.py
+++ b/cdx_toolkit/warcer_by_cdx/cdx_utils.py
@@ -1,23 +1,18 @@
 import json
 from pathlib import Path
 
-from io import BytesIO
 from typing import Iterable, Optional, Tuple, Union
 
 import fsspec
 import logging
 
-from warcio import WARCWriter
-from warcio.recordloader import ArcWarcRecord
-
 
 logger = logging.getLogger(__name__)
 
 
 def get_index_as_string_from_path(
-        index_path: Union[str, Path], 
-        index_fs: Optional[fsspec.AbstractFileSystem] = None
-    ) -> str:
+    index_path: Union[str, Path], index_fs: Optional[fsspec.AbstractFileSystem] = None
+) -> str:
     """Fetch (and decompress) index content as string from local or remote path."""
     logger.info('Fetching index from %s ...', index_path)
     if index_fs is None:
@@ -35,10 +30,9 @@ def read_cdx_line(line: str, warc_download_prefix: str) -> Tuple[str, int, int]:
     cols = line.split(' ', maxsplit=2)
 
     if len(cols) == 3:
-        # TODO can there be a different format?
-        # surt, timestamp, json_data = cols
+        # NOTE: We assume the following format (CC-CDX format): <surt> <timestamp> <json_data>
         #
-        # CC seems to not follow the specification from https://iipc.github.io/warc-specifications/specifications/cdx-format/cdx-2015/
+        # IA follows a different CDX specification from https://iipc.github.io/warc-specifications/specifications/cdx-format/cdx-2015/
         # > The default first line of a CDX file is:
         # > CDX A b e a m s c k r V v D d g M n
         data = json.loads(cols[2])
@@ -59,9 +53,6 @@ def iter_cdx_index_from_path(index_path: str, warc_download_prefix: str) -> Iter
     """
     Iterate CDX records from a file path (gzipped; local or remote).
     """
-    # if not s3_path.startswith("s3://"):
-    #     raise ValueError(f"Invalid S3 path: {s3_path}")
-
     logger.info('Reading CDX from %s', index_path)
 
     with fsspec.open(index_path, 'rt', compression='gzip' if index_path.endswith('.gz') else None) as f:
diff --git a/tests/warc_by_cdx/test_cdx_utils.py b/tests/warc_by_cdx/test_cdx_utils.py
index 414a867..3363f5c 100644
--- a/tests/warc_by_cdx/test_cdx_utils.py
+++ b/tests/warc_by_cdx/test_cdx_utils.py
@@ -1,11 +1,15 @@
 import fsspec
 import pytest
-from cdx_toolkit.warcer_by_cdx.cdx_utils import get_index_as_string_from_path, read_cdx_line
+from cdx_toolkit.warcer_by_cdx.cdx_utils import get_index_as_string_from_path, read_cdx_line, iter_cdx_index_from_path
 from tests.conftest import TEST_DATA_PATH
 
+import tempfile
+import gzip
+from unittest.mock import patch
+
 
 def test_get_index_as_string_from_path():
-    cdx_path = TEST_DATA_PATH / "warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.gz"
+    cdx_path = TEST_DATA_PATH / 'warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.gz'
 
     index = get_index_as_string_from_path(cdx_path)
 
@@ -13,16 +17,53 @@ def test_get_index_as_string_from_path():
 
 
 def test_get_index_as_string_from_path_with_fs():
-    fs, cdx_path = fsspec.url_to_fs(TEST_DATA_PATH / "warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.gz")
+    fs, cdx_path = fsspec.url_to_fs(TEST_DATA_PATH / 'warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.gz')
 
     index = get_index_as_string_from_path(cdx_path, fs)
 
     assert len(index) == 568010
 
-get_index_as_string_from_path
 
 def test_read_cdx_line_error():
     with pytest.raises(ValueError) as ec_info:
-        read_cdx_line("this_is_a_bad_CDX-line", warc_download_prefix="http://")
+        read_cdx_line('this_is_a_bad_CDX-line', warc_download_prefix='http://')
+
+    assert ec_info.match('Cannot parse line')
+
+
+def test_iter_cdx_index_from_path_with_error():
+    """Test iter_cdx_index_from_path error handling when read_cdx_line raises exception."""
+
+    # Create a temporary CDX file with mixed valid and invalid lines
+    test_cdx_content = """
+org,example)/ 20240101120000 {"url": "http://example.org/", "filename": "test.warc.gz", "offset": "100", "length": "500"}
+invalid_line_here_that_will_cause_error
+org,test)/ 20240102130000 {"url": "http://test.org/", "filename": "test2.warc.gz", "offset": "600", "length": "300"}
+another_bad_line
+org,valid)/ 20240103140000 {"url": "http://valid.org/", "filename": "test3.warc.gz", "offset": "900", "length": "200"}
+""".strip()
+
+    with tempfile.NamedTemporaryFile(suffix='.cdx.gz') as tmp_file:
+        # Write gzipped CDX content
+        with gzip.open(tmp_file.name, 'wt') as f:
+            f.write(test_cdx_content)
+
+        # Mock read_cdx_line to raise exception for invalid lines
+        original_read_cdx_line = read_cdx_line
+
+        def mock_read_cdx_line(line, warc_download_prefix):
+            if 'invalid' in line or 'bad' in line:
+                raise ValueError(f'Mock error for line: {line}')
+            return original_read_cdx_line(line, warc_download_prefix)
+
+        with patch('cdx_toolkit.warcer_by_cdx.cdx_utils.read_cdx_line', side_effect=mock_read_cdx_line):
+            # Collect results from iterator
+            results = list(iter_cdx_index_from_path(tmp_file.name, 'http://warc-prefix'))
+
+            # Should have 3 valid results despite 2 invalid lines being skipped
+            assert len(results) == 3
 
-    assert ec_info.match("Cannot parse line")
\ No newline at end of file
+            # Verify the valid results
+            assert results[0] == ('http://warc-prefix/test.warc.gz', 100, 500)
+            assert results[1] == ('http://warc-prefix/test2.warc.gz', 600, 300)
+            assert results[2] == ('http://warc-prefix/test3.warc.gz', 900, 200)

From 155db0518df30adff08f35b7a01a13a4c8735544 Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Fri, 19 Sep 2025 14:21:16 +0000
Subject: [PATCH 30/74] more tests

---
 cdx_toolkit/filter_cdx/__init__.py           | 113 ++++++++++---------
 cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py |  50 ++++----
 tests/warc_by_cdx/test_aioboto3_warcer.py    |  73 ++++++++++++
 tests/warc_by_cdx/test_filter_cdx.py         |  77 +++++++++++--
 4 files changed, 225 insertions(+), 88 deletions(-)
 create mode 100644 tests/warc_by_cdx/test_aioboto3_warcer.py

diff --git a/cdx_toolkit/filter_cdx/__init__.py b/cdx_toolkit/filter_cdx/__init__.py
index 75c9de0..cfdee8b 100644
--- a/cdx_toolkit/filter_cdx/__init__.py
+++ b/cdx_toolkit/filter_cdx/__init__.py
@@ -4,11 +4,12 @@
 import sys
 from concurrent.futures import ProcessPoolExecutor, as_completed
 from functools import partial
+from typing import List, Tuple
 
 import fsspec
 from surt import surt
 
-from cdx_toolkit.filter_cdx.matcher import TupleMatcher, TrieMatcher
+from cdx_toolkit.filter_cdx.matcher import Matcher, TupleMatcher, TrieMatcher
 
 
 logger = logging.getLogger(__name__)
@@ -62,71 +63,77 @@ def run_filter_cdx(args, cmdline: str):
         'trie': TrieMatcher,
         'tuple': TupleMatcher,
     }
+    limit = 0 if args.limit is None else args.limit
+    logger.info(f'Loaded {len(include_surt_prefixes):,} filter entries using {args.matching_approach} approach')
 
-    matcher = matcher_classes[args.matching_approach](include_surt_prefixes)
+    # Process files in parallel
+    total_lines_n, total_included_n, total_errors_n = filter_cdx(
+        matcher=matcher_classes[args.matching_approach](include_surt_prefixes),
+        input_paths=input_paths,
+        output_paths=output_paths,
+        limit=limit,
+        n_parallel=max(1, args.parallel),
+    )
 
-    logger.info(f'Loaded {len(include_surt_prefixes):,} filter entries using {args.matching_approach} approach')
+    logger.info(
+        f'Filter statistics: {total_included_n} / {total_lines_n} lines ({total_included_n / total_lines_n:.4f})'
+    )
+    logger.info(
+        f'Errors: {total_errors_n}'
+    )
 
-    # Process files in parallel or sequentially
-    n_parallel = args.parallel
-    limit = 0 if args.limit is None else args.limit
-    total_lines_n = 0
-    total_included_n = 0
-    total_errors_n = 0
-
-    if n_parallel > 1:
-        # Parallel processing
-        logger.info('Parallel processes: %i', n_parallel)
-        with ProcessPoolExecutor(max_workers=n_parallel) as executor:
-            # Create partial function with common arguments
-            process_file_partial = partial(_process_single_file, matcher=matcher, limit=limit)
-
-            # Submit all jobs
-            future_to_paths = {
-                executor.submit(process_file_partial, input_path, output_path): (input_path, output_path)
-                for input_path, output_path in zip(input_paths, output_paths)
-            }
-
-            # Collect results
-            for future in as_completed(future_to_paths):
-                input_path, output_path = future_to_paths[future]
-                try:
-                    lines_n, included_n = future.result()
-                    logger.info(
-                        f'File statistics for {input_path}: included_n={included_n}; lines_n={lines_n}; ratio={included_n / lines_n:.4f}'
-                    )
-                    total_lines_n += lines_n
-                    total_included_n += included_n
-
-                except Exception as exc:
-                    logger.error(f'File {input_path} generated an exception: {exc}')
-                    total_errors_n += 1
-    else:
-        # Sequential processing
-        logger.info('Sequential processing')
-        for input_path, output_path in zip(input_paths, output_paths):
+    if limit > 0 and total_included_n >= 0:
+        logger.info(f"Limit reached at {limit}")
+
+    # End timing and log execution time
+    end_time = time.time()
+    execution_time = end_time - start_time
+
+    logger.info(f'Script execution time: {execution_time:.3f} seconds')
+
+
+def filter_cdx(
+    matcher: Matcher,
+    input_paths: List[str],
+    output_paths: List[str],
+    n_parallel: int = 1,
+    limit: int = 0,
+    total_lines_n: int = 0,
+    total_included_n: int = 0,
+    total_errors_n: int = 0,
+) -> Tuple[int, int, int]:
+    """Filter CDX files from input paths using a matcher to output paths."""
+
+    # Parallel processing
+    logger.info('Filtering with %i processes in parallel (limit: %i)', n_parallel, limit)
+
+    with ProcessPoolExecutor(max_workers=n_parallel) as executor:
+        # Create partial function with common arguments
+        process_file_partial = partial(_process_single_file, matcher=matcher, limit=limit)
+
+        # Submit all jobs
+        future_to_paths = {
+            executor.submit(process_file_partial, input_path, output_path): (input_path, output_path)
+            for input_path, output_path in zip(input_paths, output_paths)
+        }
+
+        # Collect results
+        for future in as_completed(future_to_paths):
+            input_path, output_path = future_to_paths[future]
             try:
-                lines_n, included_n = _process_single_file(input_path, output_path, matcher, limit)
+                lines_n, included_n = future.result()
                 logger.info(
-                    f'File statistics for {input_path}: included_n={included_n}; lines_n={lines_n}; ratio={included_n / lines_n:.4f}'
+                    f'File statistics: included {total_included_n} / {total_lines_n} lines: {input_path}'
                 )
+
                 total_lines_n += lines_n
                 total_included_n += included_n
 
             except Exception as exc:
                 logger.error(f'File {input_path} generated an exception: {exc}')
                 total_errors_n += 1
-    logger.info(
-        f'Total statistics: included_n={total_included_n}; lines_n={total_lines_n}; ratio={total_included_n / total_lines_n:.4f}'
-    )
-    if total_errors_n > 0:
-        logger.error('Processing errors: %i', total_errors_n)
-
-    # End timing and log execution time
-    end_time = time.time()
-    execution_time = end_time - start_time
 
-    logger.info(f'Script execution time: {execution_time:.3f} seconds')
+    return total_lines_n, total_included_n, total_errors_n
 
 
 def resolve_paths(input_base_path: str, input_glob: str, output_base_path: str):
diff --git a/cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py b/cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py
index cbec2c4..5fd8bc4 100644
--- a/cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py
+++ b/cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py
@@ -177,33 +177,29 @@ async def get_range_jobs_from_index_paths(
     logger.info('Range index limit: %i', limit)
     count = 0
 
-    if not index_paths:
-        logger.error('No index paths provided!')
-
-    else:
-        # Iterate over index files
-        for index_path in index_paths:
-            # Fetch range queries from index
-            try:
-                for warc_url, offset, length in iter_cdx_index_from_path(
-                    index_path, warc_download_prefix=warc_download_prefix
-                ):
-                    # Convert the CDX record back to a RangeJob
-                    bucket, key = parse_s3_uri(warc_url)
-                    job = RangeJob(bucket=bucket, key=key, offset=offset, length=length)
-                    await key_queue.put(job)
-                    count += 1
-
-                    if limit > 0 and count >= limit:
-                        logger.warning('Index limit reached at %i', count)
-                        break
-
-            except Exception as e:
-                logger.error('Failed to read CDX index from %s: %s', index_path, e)
-
-            if limit > 0 and count >= limit:
-                logger.warning('Limit reached at %i', count)
-                break
+    # Iterate over index files
+    for index_path in index_paths:
+        # Fetch range queries from index
+        try:
+            for warc_url, offset, length in iter_cdx_index_from_path(
+                index_path, warc_download_prefix=warc_download_prefix
+            ):
+                # Convert the CDX record back to a RangeJob
+                bucket, key = parse_s3_uri(warc_url)
+                job = RangeJob(bucket=bucket, key=key, offset=offset, length=length)
+                await key_queue.put(job)
+                count += 1
+
+                if limit > 0 and count >= limit:
+                    logger.warning('Index limit reached at %i', count)
+                    break
+
+        except Exception as e:
+            logger.error('Failed to read CDX index from %s: %s', index_path, e)
+
+        if limit > 0 and count >= limit:
+            logger.warning('Limit reached at %i', count)
+            break
 
     # signal fetchers to stop
     for _ in range(num_fetchers):
diff --git a/tests/warc_by_cdx/test_aioboto3_warcer.py b/tests/warc_by_cdx/test_aioboto3_warcer.py
new file mode 100644
index 0000000..ad7885c
--- /dev/null
+++ b/tests/warc_by_cdx/test_aioboto3_warcer.py
@@ -0,0 +1,73 @@
+import asyncio
+from unittest.mock import patch, AsyncMock
+
+from cdx_toolkit.warcer_by_cdx.aioboto3_warcer import filter_warc_by_cdx_via_aioboto3, get_range_jobs_from_index_paths
+
+
+def test_filter_warc_by_cdx_via_aioboto3_keyboard_interrupt(caplog):
+    """Test filter_warc_by_cdx_via_aioboto3 KeyboardInterrupt exception handling."""
+
+    # Mock the async function to raise KeyboardInterrupt
+    async def mock_async_function(*args, **kwargs):
+        raise KeyboardInterrupt('User interrupted')
+
+    with patch(
+        'cdx_toolkit.warcer_by_cdx.aioboto3_warcer.filter_warc_by_cdx_via_aioboto3_async',
+        side_effect=mock_async_function,
+    ):
+        # Call the function with minimal required parameters
+        result = filter_warc_by_cdx_via_aioboto3(
+            index_paths=['test_index.cdx'], prefix_path='s3://test-bucket/test-prefix', writer_info={'software': 'test'}
+        )
+
+        # Verify that KeyboardInterrupt was handled correctly
+        assert result == -1, 'Should return -1 when KeyboardInterrupt is caught'
+
+        # Check that the warning message was logged
+        assert 'Interrupted by user.' in caplog.text
+
+        # Verify the log level is warning
+        warning_records = [record for record in caplog.records if record.levelname == 'WARNING']
+        assert len(warning_records) == 1
+        assert warning_records[0].message == 'Interrupted by user.'
+
+
+
+def test_get_range_jobs_from_index_paths_exception_handling_with_logging(caplog):
+    """Test get_range_jobs_from_index_paths logs errors when iter_cdx_index_from_path raises."""
+
+    async def run_test():
+        # Create a mock queue
+        key_queue = AsyncMock(spec=asyncio.Queue)
+
+        # Test parameters
+        index_paths = ['failing_index.cdx']
+        warc_download_prefix = 'http://test-prefix'
+        num_fetchers = 1
+
+        # Mock iter_cdx_index_from_path to always raise exception
+        def mock_iter_cdx_index_from_path(index_path, warc_download_prefix):
+            raise ValueError('Simulated CDX parsing error')
+
+        with patch(
+            'cdx_toolkit.warcer_by_cdx.aioboto3_warcer.iter_cdx_index_from_path',
+            side_effect=mock_iter_cdx_index_from_path,
+        ):
+            # Run the function
+            await get_range_jobs_from_index_paths(
+                key_queue=key_queue,
+                index_paths=index_paths,
+                warc_download_prefix=warc_download_prefix,
+                num_fetchers=num_fetchers,
+                limit=0,
+            )
+
+            # Verify error was logged
+            assert 'Failed to read CDX index from failing_index.cdx' in caplog.text
+            assert 'Simulated CDX parsing error' in caplog.text
+
+            # Verify that only STOP signal was sent (no jobs due to exception)
+            assert key_queue.put.call_count == 1  # Only 1 STOP signal
+
+    # Run the test
+    asyncio.run(run_test())
diff --git a/tests/warc_by_cdx/test_filter_cdx.py b/tests/warc_by_cdx/test_filter_cdx.py
index 8eb8980..ef48776 100644
--- a/tests/warc_by_cdx/test_filter_cdx.py
+++ b/tests/warc_by_cdx/test_filter_cdx.py
@@ -1,7 +1,10 @@
 import pytest
 
+from unittest.mock import patch
+
 from cdx_toolkit.cli import main
-from cdx_toolkit.filter_cdx import resolve_paths, validate_resolved_paths
+from cdx_toolkit.filter_cdx import _process_single_file, resolve_paths, validate_resolved_paths, filter_cdx
+from cdx_toolkit.filter_cdx.matcher import TupleMatcher
 from tests.conftest import requires_aws_s3, TEST_DATA_PATH
 
 fixture_path = TEST_DATA_PATH / 'filter_cdx'
@@ -23,7 +26,7 @@ def test_cli_filter_cdx_with_surts(tmpdir, caplog):
             f'{str(whitelist_path)}',
             f'{tmpdir}',
             '--filter-type=surt',
-            f'--input-glob={index_glob}'
+            f'--input-glob={index_glob}',
         ]
     )
 
@@ -46,7 +49,7 @@ def test_cli_filter_cdx_with_urls(tmpdir, caplog):
             f'{str(whitelist_path)}',
             f'{tmpdir}',
             '--filter-type=url',
-            f'--input-glob={index_glob}'
+            f'--input-glob={index_glob}',
         ]
     )
 
@@ -99,7 +102,7 @@ def test_filter_cdx_nonexistent_surt_file_exits(tmpdir, caplog):
                 f'{index_path}',
                 f'{nonexistent_surt_file}',
                 f'{tmpdir}',
-                f'--input-glob={index_glob}'
+                f'--input-glob={index_glob}',
             ]
         )
 
@@ -150,15 +153,73 @@ def test_cli_filter_cdx_with_parallel_processing(tmpdir, caplog):
             f'{tmpdir}',
             '--filter-type=surt',
             f'--input-glob={index_glob}',
-            '--parallel=2'
+            '--parallel=2',
         ]
     )
 
     # Check that multiple files were processed in parallel
     assert 'Found' in caplog.text and 'files matching pattern' in caplog.text
-    assert 'File statistics for' in caplog.text
-    assert 'Total statistics:' in caplog.text
+    assert 'File statistics' in caplog.text
+    assert 'Filter statistics' in caplog.text
 
     # Should have processed multiple files (pattern matches 2 files: cdx-00187.gz and cdx-00188.gz)
-    file_stats_count = caplog.text.count('File statistics for')
+    file_stats_count = caplog.text.count('File statistics')
     assert file_stats_count == 2, 'Should process exactly 2 files with the glob pattern'
+
+
+def test_process_single_file(tmpdir):
+    input_path = TEST_DATA_PATH / 'warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.gz'
+    matcher = TupleMatcher(prefixes=['fr,'])
+
+    lines_n, included_n = _process_single_file(
+        input_path=input_path,
+        output_path=tmpdir + '/filter_cdx',
+        matcher=matcher,
+        log_every_n=10,
+        limit=100,
+    )
+
+    assert included_n == 100
+    assert lines_n == 100
+
+
+def test_process_single_file_empty(tmpdir):
+    input_path = tmpdir + '/input'
+    with open(input_path, 'w') as f:
+        f.write('')
+
+    lines_n, included_n = _process_single_file(
+        input_path=input_path,
+        output_path=tmpdir + '/output',
+        matcher=None,
+    )
+    assert lines_n == 0
+    assert included_n == 0
+
+
+def test_filter_cdx_error_handling(tmpdir, caplog):
+    """Test filter_cdx function error handling when exceptions occur during processing."""
+
+    def mock_process_single_file(*args, **kwargs):
+        raise ValueError()
+
+    # Create test input and output paths
+    input_paths = [str(tmpdir / 'input1.cdx'), str(tmpdir / 'input2.cdx')]
+    output_paths = [str(tmpdir / 'output1.cdx'), str(tmpdir / 'output2.cdx')]
+
+    # Replace the _process_single_file function with our mock
+    with patch('cdx_toolkit.filter_cdx._process_single_file', side_effect=mock_process_single_file):
+        # Test the error handling
+        total_lines, total_included, total_errors = filter_cdx(
+            matcher=None,
+            input_paths=input_paths,
+            output_paths=output_paths,
+        )
+
+        # Verify error handling results
+        assert total_errors == 2, f'Should have 1 error from the failed file, got {total_errors}'
+        assert total_lines == 0, 'Should have lines from the successful file'
+        assert total_included == 0, 'Should have included lines from the successful file'
+
+        # Check that error was logged correctly
+        assert 'generated an exception' in caplog.text

From e670d12febfe623652731dc05bb10896d7d5b041 Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Tue, 23 Sep 2025 12:58:18 +0000
Subject: [PATCH 31/74] fix CI

---
 .github/workflows/ci-feat-warc-by-cdx.yaml | 74 ----------------------
 .github/workflows/ci.yaml                  | 27 +++++++-
 2 files changed, 26 insertions(+), 75 deletions(-)
 delete mode 100644 .github/workflows/ci-feat-warc-by-cdx.yaml

diff --git a/.github/workflows/ci-feat-warc-by-cdx.yaml b/.github/workflows/ci-feat-warc-by-cdx.yaml
deleted file mode 100644
index 0d0be8b..0000000
--- a/.github/workflows/ci-feat-warc-by-cdx.yaml
+++ /dev/null
@@ -1,74 +0,0 @@
-name: CI (only feature)
-
-on:
-  push:
-    branches:
-    - main
-  pull_request:
-    branches:
-    - main
-
-# These permissions are needed to interact with AWS S3 via GitHub's OIDC Token endpoint
-permissions:
-  id-token: write
-  contents: read
-  pull-requests: read
-
-jobs:
-  unit-tests:
-    runs-on: ${{ matrix.os }}
-    strategy:
-      fail-fast: true
-      max-parallel: 1  # avoids ever triggering a rate limit
-      matrix:
-        python-version: ['3.8', '3.9', '3.10', '3.11', '3.12']
-        os: [ubuntu-latest]
-        EXTRA: [false]  # used to force includes to get included
-        include:
-          - python-version: '3.12'
-            os: ubuntu-latest
-            EXTRA: true
-            env:
-              LOGLEVEL=DEBUG
-          - python-version: '3.8'
-            os: ubuntu-22.04  # oldest version on github actions
-            EXTRA: true
-
-    steps:
-      - name: checkout
-        uses: actions/checkout@v4
-
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v5
-        with:
-          python-version: ${{ matrix.python-version }}
-
-      - name: Install setuptools on python 3.12+
-        if: ${{ matrix.python-version >= '3.12' }}
-        run: |
-          pip install setuptools
-
-      - name: Install cdx_toolkit
-        run: pip install .[test]
-
-      - name: Configure AWS credentials from OIDC
-        uses: aws-actions/configure-aws-credentials@v4
-        with:
-          role-to-assume: arn:aws:iam::837454214164:role/GitHubActions-Role
-          aws-region: us-east-1
-
-      - name: Disable S3 unit tests for Python < 3.9
-        run: |
-          if [[ "${{ matrix.python-version }}" < "3.9" ]]; then
-            echo "CDXT_DISABLE_S3_TESTS=1" >> $GITHUB_ENV
-          fi
-          
-      - name: Run tests (feature only)
-        run: |
-          PYTHONPATH=. py.test -rA -s --doctest-modules --cov-report=xml --cov-append --cov cdx_toolkit tests/warc_by_cdx tests/unit -v -v
-          coverage report
-
-      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v4
-        with:
-          token: ${{ secrets.CODECOV_TOKEN }}
diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
index 3ae063d..1ab5832 100644
--- a/.github/workflows/ci.yaml
+++ b/.github/workflows/ci.yaml
@@ -8,14 +8,26 @@ on:
     branches:
     - main
 
+# These permissions are needed to interact with AWS S3 via GitHub's OIDC Token endpoint
+permissions:
+  id-token: write
+  contents: read
+  pull-requests: read
+
 jobs:
   unit-tests:
     runs-on: ${{ matrix.os }}
     strategy:
       fail-fast: true
       matrix:
+        # The full test-suite is only run with os=ubuntu and py=3.12
         python-version: [
-          '3.8', '3.9', '3.10', '3.11', '3.12', '3.13'
+          '3.8', 
+          '3.9', 
+          '3.10', 
+          '3.11', 
+          '3.12', 
+          '3.13'
         ]
         os: [ubuntu-latest]
         EXTRA: [false]  # used to force includes to get included
@@ -57,6 +69,19 @@ jobs:
       - name: Install cdx_toolkit
         run: pip install .[test]
 
+      - name: Configure AWS credentials from OIDC (disabled for forks)
+        if: github.event.pull_request.head.repo.full_name == github.repository || github.event_name == 'push'        
+        uses: aws-actions/configure-aws-credentials@v4
+        with:
+          role-to-assume: arn:aws:iam::837454214164:role/GitHubActions-Role
+          aws-region: us-east-1
+
+      - name: Disable S3 unit tests for Python < 3.9
+        run: |
+          if [[ "${{ matrix.python-version }}" < "3.9" ]]; then
+            echo "CDXT_DISABLE_S3_TESTS=1" >> $GITHUB_ENV
+          fi
+
       - name: Run tests
         run: |
           make test_coverage

From 807a39d775f53b116ab74e5ab41a591c803588aa Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Tue, 23 Sep 2025 13:03:21 +0000
Subject: [PATCH 32/74] fix CI (2)

---
 .github/workflows/ci.yaml | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
index 1ab5832..d9ff671 100644
--- a/.github/workflows/ci.yaml
+++ b/.github/workflows/ci.yaml
@@ -76,11 +76,12 @@ jobs:
           role-to-assume: arn:aws:iam::837454214164:role/GitHubActions-Role
           aws-region: us-east-1
 
-      - name: Disable S3 unit tests for Python < 3.9
-        run: |
-          if [[ "${{ matrix.python-version }}" < "3.9" ]]; then
-            echo "CDXT_DISABLE_S3_TESTS=1" >> $GITHUB_ENV
-          fi
+      - name: Disable S3 unit tests for Python 3.8
+        if: ${{ startsWith(matrix.python-version, '3.8') }}
+        uses: actions/github-script@v7
+        with:
+          script: |
+            core.exportVariable('CDXT_DISABLE_S3_TESTS', '1')
 
       - name: Run tests
         run: |

From 5d208d68a3eaeb0f8bd14869e0c43d244cbe8878 Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Tue, 23 Sep 2025 16:09:39 +0200
Subject: [PATCH 33/74] fixing Ci for windows

---
 .github/workflows/ci.yaml                     | 32 +++++++++----------
 cdx_toolkit/filter_cdx/__init__.py            | 18 ++++++++---
 tests/warc_by_cdx/test_cdx_utils.py           | 12 +++++--
 tests/warc_by_cdx/test_filter_cdx.py          |  6 ++--
 .../warc_by_cdx/test_warc_by_cdx_aioboto3.py  |  8 ++++-
 5 files changed, 50 insertions(+), 26 deletions(-)

diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
index d9ff671..b997e2f 100644
--- a/.github/workflows/ci.yaml
+++ b/.github/workflows/ci.yaml
@@ -22,27 +22,27 @@ jobs:
       matrix:
         # The full test-suite is only run with os=ubuntu and py=3.12
         python-version: [
-          '3.8', 
-          '3.9', 
-          '3.10', 
-          '3.11', 
+          # '3.8', 
+          # '3.9', 
+          # '3.10', 
+          # '3.11', 
           '3.12', 
-          '3.13'
+          # '3.13'
         ]
         os: [ubuntu-latest]
         EXTRA: [false]  # used to force includes to get included
         include:
-          - python-version: '3.8'
-            os: ubuntu-22.04  # oldest version on github actions
-            EXTRA: true
-          - python-version: '3.13'
-            os: ubuntu-latest
-            env:
-              LOGLEVEL=DEBUG
-            EXTRA: true
-          - python-version: '3.13'
-            os: macos-latest
-            EXTRA: true
+          # - python-version: '3.8'
+          #   os: ubuntu-22.04  # oldest version on github actions
+          #   EXTRA: true
+          # - python-version: '3.13'
+          #   os: ubuntu-latest
+          #   env:
+          #     LOGLEVEL=DEBUG
+          #   EXTRA: true
+          # - python-version: '3.13'
+          #   os: macos-latest
+          #   EXTRA: true
           - python-version: '3.13'
             os: windows-latest
             EXTRA: true
diff --git a/cdx_toolkit/filter_cdx/__init__.py b/cdx_toolkit/filter_cdx/__init__.py
index cfdee8b..1be31d7 100644
--- a/cdx_toolkit/filter_cdx/__init__.py
+++ b/cdx_toolkit/filter_cdx/__init__.py
@@ -75,8 +75,10 @@ def run_filter_cdx(args, cmdline: str):
         n_parallel=max(1, args.parallel),
     )
 
+    # Calculate ratio safely to avoid division by zero
+    ratio = total_included_n / total_lines_n if total_lines_n > 0 else 0.0
     logger.info(
-        f'Filter statistics: {total_included_n} / {total_lines_n} lines ({total_included_n / total_lines_n:.4f})'
+        f'Filter statistics: {total_included_n} / {total_lines_n} lines ({ratio:.4f})'
     )
     logger.info(
         f'Errors: {total_errors_n}'
@@ -153,11 +155,19 @@ def resolve_paths(input_base_path: str, input_glob: str, output_base_path: str):
     input_file_paths = []
     for input_path in input_fs_file_paths:
         # Get relative path from input_base_path without last slash
-        rel_path = input_path[len(input_fs_base_path) + 1 :]
+        rel_path = input_path[len(input_fs_base_path)+1:]
 
         # Create corresponding full input and output path
-        output_file_paths.append(os.path.join(output_base_path, rel_path))
-        input_file_paths.append(os.path.join(input_base_path, rel_path))
+        # Use forward slashes for URL paths (S3, HTTP, etc.) to ensure cross-platform compatibility
+        if '://' in output_base_path:
+            output_file_paths.append(output_base_path + '/' + rel_path)
+        else:
+            output_file_paths.append(os.path.join(output_base_path, rel_path))
+
+        if '://' in input_base_path:
+            input_file_paths.append(input_base_path + '/' + rel_path)
+        else:
+            input_file_paths.append(os.path.join(input_base_path, rel_path))
 
     return input_file_paths, output_file_paths
 
diff --git a/tests/warc_by_cdx/test_cdx_utils.py b/tests/warc_by_cdx/test_cdx_utils.py
index 3363f5c..af46466 100644
--- a/tests/warc_by_cdx/test_cdx_utils.py
+++ b/tests/warc_by_cdx/test_cdx_utils.py
@@ -5,6 +5,7 @@
 
 import tempfile
 import gzip
+import os
 from unittest.mock import patch
 
 
@@ -43,9 +44,12 @@ def test_iter_cdx_index_from_path_with_error():
 org,valid)/ 20240103140000 {"url": "http://valid.org/", "filename": "test3.warc.gz", "offset": "900", "length": "200"}
 """.strip()
 
-    with tempfile.NamedTemporaryFile(suffix='.cdx.gz') as tmp_file:
+    fd, tmp_file_path = tempfile.mkstemp(suffix='.cdx.gz')
+    try:
+        os.close(fd)  # Close the file descriptor
+
         # Write gzipped CDX content
-        with gzip.open(tmp_file.name, 'wt') as f:
+        with gzip.open(tmp_file_path, 'wt') as f:
             f.write(test_cdx_content)
 
         # Mock read_cdx_line to raise exception for invalid lines
@@ -58,7 +62,7 @@ def mock_read_cdx_line(line, warc_download_prefix):
 
         with patch('cdx_toolkit.warcer_by_cdx.cdx_utils.read_cdx_line', side_effect=mock_read_cdx_line):
             # Collect results from iterator
-            results = list(iter_cdx_index_from_path(tmp_file.name, 'http://warc-prefix'))
+            results = list(iter_cdx_index_from_path(tmp_file_path, 'http://warc-prefix'))
 
             # Should have 3 valid results despite 2 invalid lines being skipped
             assert len(results) == 3
@@ -67,3 +71,5 @@ def mock_read_cdx_line(line, warc_download_prefix):
             assert results[0] == ('http://warc-prefix/test.warc.gz', 100, 500)
             assert results[1] == ('http://warc-prefix/test2.warc.gz', 600, 300)
             assert results[2] == ('http://warc-prefix/test3.warc.gz', 900, 200)
+    finally:
+        os.unlink(tmp_file_path)
diff --git a/tests/warc_by_cdx/test_filter_cdx.py b/tests/warc_by_cdx/test_filter_cdx.py
index ef48776..a3f214a 100644
--- a/tests/warc_by_cdx/test_filter_cdx.py
+++ b/tests/warc_by_cdx/test_filter_cdx.py
@@ -90,7 +90,8 @@ def test_resolve_cdx_paths_from_cc_s3_to_another_s3():
 def test_filter_cdx_nonexistent_surt_file_exits(tmpdir, caplog):
     index_path = 's3://commoncrawl/cc-index/collections'
     index_glob = '/CC-MAIN-2024-30/indexes/cdx-00187.gz'
-    nonexistent_surt_file = str(tmpdir / 'nonexistent_surts.txt')
+    nonexistent_surt_file_name = 'nonexistent_surts.txt'
+    nonexistent_surt_file = str(tmpdir / nonexistent_surt_file_name)
 
     # Test that the command exits when SURT file doesn't exist
     with pytest.raises(SystemExit) as exc_info:
@@ -107,7 +108,8 @@ def test_filter_cdx_nonexistent_surt_file_exits(tmpdir, caplog):
         )
 
     assert exc_info.value.code == 1
-    assert f'Filter file not found: {nonexistent_surt_file}' in caplog.text
+    assert 'Filter file not found: ' in caplog.text
+    assert nonexistent_surt_file_name in caplog.text
 
 
 def test_resolve_paths_no_files_found_exits(tmpdir, caplog):
diff --git a/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py b/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
index 5d48bbf..5f8722b 100644
--- a/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
+++ b/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
@@ -79,10 +79,16 @@ def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog, extra_args
     assert 'operator: bob' in info_record, 'Invalid info record'
 
     assert resource_record is not None
-    assert resource_record.length == 294, 'Invalid resource record'
+
     assert resource_record_content[:10] == 'example.co', 'Invalid resource record'
     assert resource_record_content[-20:-1] == 'hr.fr/produit/t-837', 'Invalid resource record'
 
+    # Length may vary due to OS-specific line endings after decoding
+    expected_length_range = (290, 300)  # Allow for CRLF vs LF differences
+    assert expected_length_range[0] <= resource_record.length <= expected_length_range[1], (
+        f'Invalid resource record length {resource_record.length}, expected {expected_length_range}'
+    )
+
 
 @requires_aws_s3
 def test_cli_warc_by_cdx_over_s3_to_s3_in_parallel_aioboto3(tmpdir, caplog):

From c8f984c1c56730682051aa0327ff9bdf31e1e004 Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Tue, 23 Sep 2025 16:19:05 +0200
Subject: [PATCH 34/74] fixing Ci for windows

---
 tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py b/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
index 5f8722b..7f28829 100644
--- a/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
+++ b/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
@@ -81,12 +81,18 @@ def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog, extra_args
     assert resource_record is not None
 
     assert resource_record_content[:10] == 'example.co', 'Invalid resource record'
-    assert resource_record_content[-20:-1] == 'hr.fr/produit/t-837', 'Invalid resource record'
 
-    # Length may vary due to OS-specific line endings after decoding
-    expected_length_range = (290, 300)  # Allow for CRLF vs LF differences
-    assert expected_length_range[0] <= resource_record.length <= expected_length_range[1], (
-        f'Invalid resource record length {resource_record.length}, expected {expected_length_range}'
+    # Disabled due to OS-specific line endings
+    # assert resource_record_content[-20:-1] == 'hr.fr/produit/t-837', 'Invalid resource record'
+
+    # Calculate expected length based on the actual source file on current OS
+    resource_record_path = TEST_DATA_PATH / 'filter_cdx/whitelist_10_urls.txt'
+    with open(resource_record_path, 'rb') as f:
+        expected_length = len(f.read())
+
+    assert resource_record.length == expected_length, (
+        f'Invalid resource record length {resource_record.length}, expected {expected_length} '
+        f'(computed from {resource_record_path} on current OS)'
     )
 
 

From 63db23ca4742c13eefa78ab42b5566e327085e07 Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Tue, 23 Sep 2025 16:27:18 +0200
Subject: [PATCH 35/74] removed duplicated code

---
 tests/warc_by_cdx/test_warc_by_cdx.py         | 40 +++++++--
 .../warc_by_cdx/test_warc_by_cdx_aioboto3.py  | 87 +------------------
 2 files changed, 35 insertions(+), 92 deletions(-)

diff --git a/tests/warc_by_cdx/test_warc_by_cdx.py b/tests/warc_by_cdx/test_warc_by_cdx.py
index cc47447..4739290 100644
--- a/tests/warc_by_cdx/test_warc_by_cdx.py
+++ b/tests/warc_by_cdx/test_warc_by_cdx.py
@@ -18,7 +18,13 @@
 fixture_path = TEST_DATA_PATH / 'warc_by_cdx'
 
 
-def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog, extra_args: Optional[List[str]] = None):
+def assert_cli_warc_by_cdx(
+    warc_download_prefix,
+    base_prefix,
+    caplog,
+    extra_args: Optional[List[str]] = None,
+    warc_filename: str = 'TEST_warc_by_index-000000.extracted.warc.gz',
+):
     # test cli and check output
     index_path = fixture_path / 'filtered_CC-MAIN-2024-30_cdx-00187.gz'
     resource_record_path = TEST_DATA_PATH / 'filter_cdx/whitelist_10_urls.txt'
@@ -52,6 +58,7 @@ def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog, extra_args
 
     info_record = None
     response_records = []
+    response_contents = []
 
     resource_record = None
     resource_record_content = None
@@ -63,21 +70,36 @@ def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog, extra_args
 
             if record.rec_type == 'response':
                 response_records.append(record)
+                response_contents.append(record.content_stream().read().decode('utf-8', errors='ignore'))
 
             if record.rec_type == 'resource':
                 resource_record = record
                 resource_record_content = record.content_stream().read().decode('utf-8')
 
-    assert len(response_records) == 10
-
-    assert resource_record is not None
-    assert resource_record.length == 294, 'Invalid resource record'
-    assert resource_record_content[:10] == 'example.co', 'Invalid resource record'
-    assert resource_record_content[-20:-1] == 'hr.fr/produit/t-837', 'Invalid resource record'
+    assert len(response_records) == 10, 'Invalid record count'
 
     assert info_record is not None, 'Invalid info record'
     assert 'operator: bob' in info_record, 'Invalid info record'
 
+    assert 'Catalogue en ligne Mission de France' in response_contents[0], 'Invalid response content'
+    assert 'dojo/dijit/themes/tundra/tundra' in response_contents[9], 'Invalid response content'
+
+    assert resource_record is not None, 'Resource record not set'
+
+    assert resource_record_content[:10] == 'example.co', 'Invalid resource record'
+
+    # Disabled due to OS-specific line endings
+    # assert resource_record_content[-20:-1] == 'hr.fr/produit/t-837', 'Invalid resource record'
+
+    # Calculate expected length based on the actual source file on current OS
+    with open(resource_record_path, 'rb') as f:
+        expected_length = len(f.read())
+
+    assert resource_record.length == expected_length, (
+        f'Invalid resource record length {resource_record.length}, expected {expected_length} '
+        f'(computed from {resource_record_path} on current OS)'
+    )
+
 
 def test_cli_warc_by_cdx_over_http(tmpdir, caplog):
     assert_cli_warc_by_cdx('https://data.commoncrawl.org', base_prefix=tmpdir, caplog=caplog)
@@ -97,7 +119,9 @@ def test_cli_warc_by_cdx_over_s3(tmpdir, caplog):
 @requires_aws_s3
 def test_cli_warc_by_cdx_over_s3_to_s3(tmpdir, caplog):
     assert_cli_warc_by_cdx(
-        's3://commoncrawl', base_prefix=f's3://{TEST_S3_BUCKET}/cdx_toolkit/ci/test-outputs' + str(tmpdir), caplog=caplog
+        's3://commoncrawl',
+        base_prefix=f's3://{TEST_S3_BUCKET}/cdx_toolkit/ci/test-outputs' + str(tmpdir),
+        caplog=caplog,
     )
 
 
diff --git a/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py b/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
index 7f28829..fdeb025 100644
--- a/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
+++ b/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
@@ -1,99 +1,17 @@
 import asyncio
 from io import BytesIO
-from typing import List, Optional
 
 import aioboto3
-import fsspec
-from cdx_toolkit.cli import main
-from warcio.archiveiterator import ArchiveIterator
 
 from tests.conftest import TEST_S3_BUCKET, requires_aws_s3, TEST_DATA_PATH
 
 from warcio import WARCWriter
 from cdx_toolkit.warcer_by_cdx.aioboto3_warcer import get_range_jobs_from_index_paths, write_warc, _STOP
 from cdx_toolkit.warcer_by_cdx.aioboto3_utils import RangePayload
+from tests.warc_by_cdx.test_warc_by_cdx import assert_cli_warc_by_cdx
 
 fixture_path = TEST_DATA_PATH / 'warc_by_cdx'
-
-
-def assert_cli_warc_by_cdx(warc_download_prefix, base_prefix, caplog, extra_args: Optional[List[str]] = None):
-    # test cli and check output
-    index_path = fixture_path / 'filtered_CC-MAIN-2024-30_cdx-00187.gz'
-    resource_record_path = TEST_DATA_PATH / 'filter_cdx/whitelist_10_urls.txt'
-
-    if extra_args is None:
-        extra_args = []
-
-    main(
-        args=[
-            '-v',
-            '--cc',
-            '--limit=10',
-            'warc_by_cdx',
-            str(index_path),
-            '--write-paths-as-resource-records',
-            str(resource_record_path),
-            f'--prefix={str(base_prefix)}/TEST_warc_by_index',
-            '--creator=foo',
-            '--operator=bob',
-            f'--warc-download-prefix={warc_download_prefix}',
-        ]
-        + extra_args,
-    )
-
-    # Check log
-    assert 'Limit reached' in caplog.text
-
-    # Validate extracted WARC
-    warc_filename = 'TEST_warc_by_index-000000-001.extracted.warc.gz'
-    warc_path = str(base_prefix) + '/' + warc_filename
-
-    info_record = None
-    response_records = []
-    response_contents = []
-
-    resource_record = None
-    resource_record_content = None
-
-    with fsspec.open(warc_path, 'rb') as stream:
-        for record in ArchiveIterator(stream):
-            if record.rec_type == 'warcinfo':
-                info_record = record.content_stream().read().decode('utf-8')
-
-            if record.rec_type == 'response':
-                response_records.append(record)
-                response_contents.append(record.content_stream().read().decode('utf-8', errors='ignore'))
-
-            if record.rec_type == 'resource':
-                resource_record = record
-                resource_record_content = record.content_stream().read().decode('utf-8')
-
-    assert len(response_records) == 10, 'Invalid record count'
-    # assert resource_record is not None
-    # assert resource_record.length == 568010
-
-    assert 'Catalogue en ligne Mission de France' in response_contents[0], 'Invalid response content'
-    assert 'dojo/dijit/themes/tundra/tundra' in response_contents[9], 'Invalid response content'
-
-    assert info_record is not None, 'Invalid info record'
-    assert 'operator: bob' in info_record, 'Invalid info record'
-
-    assert resource_record is not None
-
-    assert resource_record_content[:10] == 'example.co', 'Invalid resource record'
-
-    # Disabled due to OS-specific line endings
-    # assert resource_record_content[-20:-1] == 'hr.fr/produit/t-837', 'Invalid resource record'
-
-    # Calculate expected length based on the actual source file on current OS
-    resource_record_path = TEST_DATA_PATH / 'filter_cdx/whitelist_10_urls.txt'
-    with open(resource_record_path, 'rb') as f:
-        expected_length = len(f.read())
-
-    assert resource_record.length == expected_length, (
-        f'Invalid resource record length {resource_record.length}, expected {expected_length} '
-        f'(computed from {resource_record_path} on current OS)'
-    )
+aioboto3_warc_filename = 'TEST_warc_by_index-000000-001.extracted.warc.gz'  # due to parallel writer
 
 
 @requires_aws_s3
@@ -106,6 +24,7 @@ def test_cli_warc_by_cdx_over_s3_to_s3_in_parallel_aioboto3(tmpdir, caplog):
             '--parallel=3',
             '--implementation=aioboto3',
         ],
+        warc_filename=aioboto3_warc_filename,
     )
 
 

From e75f143c11aaa0cc1221468a8684b0123a5f104c Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Tue, 23 Sep 2025 16:38:35 +0200
Subject: [PATCH 36/74] more windows test fixes

---
 cdx_toolkit/filter_cdx/__init__.py             | 8 ++++++--
 tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py | 2 +-
 2 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/cdx_toolkit/filter_cdx/__init__.py b/cdx_toolkit/filter_cdx/__init__.py
index 1be31d7..1efebe6 100644
--- a/cdx_toolkit/filter_cdx/__init__.py
+++ b/cdx_toolkit/filter_cdx/__init__.py
@@ -162,12 +162,16 @@ def resolve_paths(input_base_path: str, input_glob: str, output_base_path: str):
         if '://' in output_base_path:
             output_file_paths.append(output_base_path + '/' + rel_path)
         else:
-            output_file_paths.append(os.path.join(output_base_path, rel_path))
+            # Normalize path separators for local filesystem
+            normalized_rel_path = rel_path.replace('/', os.sep)
+            output_file_paths.append(os.path.join(output_base_path, normalized_rel_path))
 
         if '://' in input_base_path:
             input_file_paths.append(input_base_path + '/' + rel_path)
         else:
-            input_file_paths.append(os.path.join(input_base_path, rel_path))
+            # Normalize path separators for local filesystem
+            normalized_rel_path = rel_path.replace('/', os.sep)
+            input_file_paths.append(os.path.join(input_base_path, normalized_rel_path))
 
     return input_file_paths, output_file_paths
 
diff --git a/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py b/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
index fdeb025..314e11e 100644
--- a/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
+++ b/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
@@ -18,7 +18,7 @@
 def test_cli_warc_by_cdx_over_s3_to_s3_in_parallel_aioboto3(tmpdir, caplog):
     assert_cli_warc_by_cdx(
         's3://commoncrawl',
-        base_prefix=f's3://{TEST_S3_BUCKET}/cdx_toolkit/ci/test-outputs' + str(tmpdir),
+        base_prefix=f's3://{TEST_S3_BUCKET}/cdx_toolkit/ci/test-outputs' + str(tmpdir).replace('\\', '/'),
         caplog=caplog,
         extra_args=[
             '--parallel=3',

From 578a8aec45bf71c9e698df21e8ad73902bb00563 Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Tue, 23 Sep 2025 16:52:26 +0200
Subject: [PATCH 37/74] more windows test fixes (2)

---
 tests/warc_by_cdx/test_filter_cdx.py           | 5 ++++-
 tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py | 5 ++++-
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/tests/warc_by_cdx/test_filter_cdx.py b/tests/warc_by_cdx/test_filter_cdx.py
index a3f214a..fcb7e0b 100644
--- a/tests/warc_by_cdx/test_filter_cdx.py
+++ b/tests/warc_by_cdx/test_filter_cdx.py
@@ -1,3 +1,4 @@
+import os
 import pytest
 
 from unittest.mock import patch
@@ -67,7 +68,9 @@ def test_resolve_cdx_paths_from_cc_s3_to_local(tmpdir):
     assert len(input_files) == len(output_files), 'Input and output count must be the same'
     assert len(input_files) == 300, 'Invalid input count'
     assert input_files[0] == base_path + '/CC-MAIN-2016-30/indexes/cdx-00000.gz', 'Invalid input file'
-    assert output_files[0] == tmpdir + '/CC-MAIN-2016-30/indexes/cdx-00000.gz', 'Invalid output file'
+    assert output_files[0] == tmpdir + '/CC-MAIN-2016-30/indexes/cdx-00000.gz'.replace('/', os.sep), (
+        'Invalid output file'
+    )
     assert input_files[-1] == base_path + '/CC-MAIN-2016-30/indexes/cdx-00299.gz'
 
 
diff --git a/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py b/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
index 314e11e..214842c 100644
--- a/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
+++ b/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
@@ -16,9 +16,12 @@
 
 @requires_aws_s3
 def test_cli_warc_by_cdx_over_s3_to_s3_in_parallel_aioboto3(tmpdir, caplog):
+    # Make sure s3 dir is valid even on Windows
+    s3_tmpdir = str(tmpdir).replace('\\', '/').replace(":", "")
+
     assert_cli_warc_by_cdx(
         's3://commoncrawl',
-        base_prefix=f's3://{TEST_S3_BUCKET}/cdx_toolkit/ci/test-outputs' + str(tmpdir).replace('\\', '/'),
+        base_prefix=f's3://{TEST_S3_BUCKET}/cdx_toolkit/ci/test-outputs' + s3_tmpdir,
         caplog=caplog,
         extra_args=[
             '--parallel=3',

From 4eaf366262e0826987d8f9bd9b754cbafb77a00a Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Tue, 23 Sep 2025 17:06:42 +0200
Subject: [PATCH 38/74] more windows test fixes (3)

---
 tests/warc_by_cdx/test_warc_by_cdx.py | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/tests/warc_by_cdx/test_warc_by_cdx.py b/tests/warc_by_cdx/test_warc_by_cdx.py
index 4739290..1ca5c31 100644
--- a/tests/warc_by_cdx/test_warc_by_cdx.py
+++ b/tests/warc_by_cdx/test_warc_by_cdx.py
@@ -29,6 +29,8 @@ def assert_cli_warc_by_cdx(
     index_path = fixture_path / 'filtered_CC-MAIN-2024-30_cdx-00187.gz'
     resource_record_path = TEST_DATA_PATH / 'filter_cdx/whitelist_10_urls.txt'
 
+    base_prefix = str(base_prefix)
+
     if extra_args is None:
         extra_args = []
 
@@ -41,7 +43,7 @@ def assert_cli_warc_by_cdx(
             str(index_path),
             '--write-paths-as-resource-records',
             str(resource_record_path),
-            f'--prefix={str(base_prefix)}/TEST_warc_by_index',
+            f'--prefix={base_prefix}/TEST_warc_by_index',
             '--creator=foo',
             '--operator=bob',
             f'--warc-download-prefix={warc_download_prefix}',
@@ -53,8 +55,10 @@ def assert_cli_warc_by_cdx(
     assert 'Limit reached' in caplog.text
 
     # Validate extracted WARC
-    warc_filename = 'TEST_warc_by_index-000000.extracted.warc.gz'
-    warc_path = str(base_prefix) + '/' + warc_filename
+    if 's3:' in base_prefix:
+        warc_path = base_prefix + '/' + warc_filename
+    else:
+        warc_path = os.path.join(base_prefix, warc_filename)
 
     info_record = None
     response_records = []

From ed63d2cee222ff8de5b701a12fc28dd2d02822b1 Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Tue, 23 Sep 2025 17:20:25 +0200
Subject: [PATCH 39/74] re-renable other platforms

---
 .github/workflows/ci.yaml                     | 32 +++++++++----------
 .../warc_by_cdx/test_warc_by_cdx_aioboto3.py  |  2 +-
 2 files changed, 17 insertions(+), 17 deletions(-)

diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
index b997e2f..d9ff671 100644
--- a/.github/workflows/ci.yaml
+++ b/.github/workflows/ci.yaml
@@ -22,27 +22,27 @@ jobs:
       matrix:
         # The full test-suite is only run with os=ubuntu and py=3.12
         python-version: [
-          # '3.8', 
-          # '3.9', 
-          # '3.10', 
-          # '3.11', 
+          '3.8', 
+          '3.9', 
+          '3.10', 
+          '3.11', 
           '3.12', 
-          # '3.13'
+          '3.13'
         ]
         os: [ubuntu-latest]
         EXTRA: [false]  # used to force includes to get included
         include:
-          # - python-version: '3.8'
-          #   os: ubuntu-22.04  # oldest version on github actions
-          #   EXTRA: true
-          # - python-version: '3.13'
-          #   os: ubuntu-latest
-          #   env:
-          #     LOGLEVEL=DEBUG
-          #   EXTRA: true
-          # - python-version: '3.13'
-          #   os: macos-latest
-          #   EXTRA: true
+          - python-version: '3.8'
+            os: ubuntu-22.04  # oldest version on github actions
+            EXTRA: true
+          - python-version: '3.13'
+            os: ubuntu-latest
+            env:
+              LOGLEVEL=DEBUG
+            EXTRA: true
+          - python-version: '3.13'
+            os: macos-latest
+            EXTRA: true
           - python-version: '3.13'
             os: windows-latest
             EXTRA: true
diff --git a/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py b/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
index 214842c..d9d442a 100644
--- a/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
+++ b/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
@@ -17,7 +17,7 @@
 @requires_aws_s3
 def test_cli_warc_by_cdx_over_s3_to_s3_in_parallel_aioboto3(tmpdir, caplog):
     # Make sure s3 dir is valid even on Windows
-    s3_tmpdir = str(tmpdir).replace('\\', '/').replace(":", "")
+    s3_tmpdir = str(tmpdir).replace('\\', '/').replace(':', '')
 
     assert_cli_warc_by_cdx(
         's3://commoncrawl',

From bc5ed7965c0cf5354a11b3adb22188d0256f8a03 Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Wed, 24 Sep 2025 15:33:17 +0200
Subject: [PATCH 40/74] adding s3_tmpdir fixture

---
 tests/conftest.py                             | 27 +++++++++++++++++++
 tests/warc_by_cdx/test_warc_by_cdx.py         | 10 +++----
 .../warc_by_cdx/test_warc_by_cdx_aioboto3.py  | 20 ++++++--------
 tests/warc_by_cdx/test_warc_writer.py         | 16 +++--------
 4 files changed, 43 insertions(+), 30 deletions(-)

diff --git a/tests/conftest.py b/tests/conftest.py
index 4f5460d..82afa44 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -10,6 +10,7 @@
 import requests
 import responses
 import base64
+import uuid
 
 from unittest.mock import patch
 
@@ -41,6 +42,32 @@ def requires_aws_s3(func):
     )
 
 
+@pytest.fixture
+def s3_tmpdir():
+    """S3 equivalent of tmpdir - provides a temporary S3 path and handles cleanup."""
+    bucket_name = TEST_S3_BUCKET
+
+    # Generate unique prefix using UUID to avoid collisions
+    temp_prefix = f'cdx_toolkit/ci/tmpdirs/{uuid.uuid4().hex}'
+
+    # Yield the S3 path
+    yield f's3://{bucket_name}/{temp_prefix}'
+
+    # Cleanup: delete all objects with this prefix
+    s3_client = boto3.client('s3')
+    try:
+        # List all objects with the temp prefix
+        response = s3_client.list_objects_v2(Bucket=bucket_name, Prefix=temp_prefix)
+
+        if 'Contents' in response:
+            # Delete all objects
+            objects_to_delete = [{'Key': obj['Key']} for obj in response['Contents']]
+            s3_client.delete_objects(Bucket=bucket_name, Delete={'Objects': objects_to_delete})
+    except ClientError:
+        # Ignore cleanup errors - test objects will eventually expire
+        pass
+
+
 def flexible_param_matcher(expected_params):
     """Custom matcher that ignores dynamic 'from' parameter timestamps and casts all values to strings"""
 
diff --git a/tests/warc_by_cdx/test_warc_by_cdx.py b/tests/warc_by_cdx/test_warc_by_cdx.py
index 1ca5c31..9fd7cc0 100644
--- a/tests/warc_by_cdx/test_warc_by_cdx.py
+++ b/tests/warc_by_cdx/test_warc_by_cdx.py
@@ -12,7 +12,7 @@
 import pytest
 from warcio.archiveiterator import ArchiveIterator
 
-from tests.conftest import TEST_S3_BUCKET, requires_aws_s3, TEST_DATA_PATH
+from tests.conftest import requires_aws_s3, TEST_DATA_PATH
 
 
 fixture_path = TEST_DATA_PATH / 'warc_by_cdx'
@@ -121,19 +121,19 @@ def test_cli_warc_by_cdx_over_s3(tmpdir, caplog):
 
 
 @requires_aws_s3
-def test_cli_warc_by_cdx_over_s3_to_s3(tmpdir, caplog):
+def test_cli_warc_by_cdx_over_s3_to_s3(s3_tmpdir, caplog):
     assert_cli_warc_by_cdx(
         's3://commoncrawl',
-        base_prefix=f's3://{TEST_S3_BUCKET}/cdx_toolkit/ci/test-outputs' + str(tmpdir),
+        base_prefix=s3_tmpdir,
         caplog=caplog,
     )
 
 
 @requires_aws_s3
-def test_cli_warc_by_cdx_over_s3_to_s3_in_parallel(tmpdir, caplog):
+def test_cli_warc_by_cdx_over_s3_to_s3_in_parallel(s3_tmpdir, caplog):
     assert_cli_warc_by_cdx(
         's3://commoncrawl',
-        base_prefix=f's3://{TEST_S3_BUCKET}/cdx_toolkit/ci/test-outputs' + str(tmpdir),
+        base_prefix=s3_tmpdir,
         caplog=caplog,
         extra_args=['--parallel=3'],
     )
diff --git a/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py b/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
index d9d442a..97e5b1a 100644
--- a/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
+++ b/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
@@ -3,11 +3,11 @@
 
 import aioboto3
 
-from tests.conftest import TEST_S3_BUCKET, requires_aws_s3, TEST_DATA_PATH
+from tests.conftest import requires_aws_s3, TEST_DATA_PATH
 
 from warcio import WARCWriter
 from cdx_toolkit.warcer_by_cdx.aioboto3_warcer import get_range_jobs_from_index_paths, write_warc, _STOP
-from cdx_toolkit.warcer_by_cdx.aioboto3_utils import RangePayload
+from cdx_toolkit.warcer_by_cdx.aioboto3_utils import RangePayload, parse_s3_uri
 from tests.warc_by_cdx.test_warc_by_cdx import assert_cli_warc_by_cdx
 
 fixture_path = TEST_DATA_PATH / 'warc_by_cdx'
@@ -15,13 +15,10 @@
 
 
 @requires_aws_s3
-def test_cli_warc_by_cdx_over_s3_to_s3_in_parallel_aioboto3(tmpdir, caplog):
-    # Make sure s3 dir is valid even on Windows
-    s3_tmpdir = str(tmpdir).replace('\\', '/').replace(':', '')
-
+def test_cli_warc_by_cdx_over_s3_to_s3_in_parallel_aioboto3(s3_tmpdir, caplog):
     assert_cli_warc_by_cdx(
         's3://commoncrawl',
-        base_prefix=f's3://{TEST_S3_BUCKET}/cdx_toolkit/ci/test-outputs' + s3_tmpdir,
+        base_prefix=s3_tmpdir,
         caplog=caplog,
         extra_args=[
             '--parallel=3',
@@ -55,14 +52,14 @@ def test_warc_info():
 
 
 @requires_aws_s3
-def test_write_warc_with_file_rotation(tmpdir):
+def test_write_warc_with_file_rotation(s3_tmpdir):
     """Test write_warc function with file size rotation"""
 
     async def run_test():
         # Setup test data
         index_path = fixture_path / 'filtered_CC-MAIN-2024-30_cdx-00187.gz'
         warc_download_prefix = 's3://commoncrawl'
-        prefix_path = f's3://{TEST_S3_BUCKET}/cdx_toolkit/ci/test-outputs{tmpdir}/file_rotation_test'
+        output_prefix_path = f'{s3_tmpdir}/file_rotation_test'
 
         # Use small file size to force rotation (100 KB)
         max_file_size = 100 * 1024  # 100 KB
@@ -127,15 +124,14 @@ async def run_test():
                 s3=s3,
                 max_attempts=3,
                 base_backoff_seconds=0.5,
-                prefix_path=prefix_path,
+                prefix_path=output_prefix_path,
                 writer_info=writer_info,
                 max_file_size=max_file_size,
                 gzip=True,
             )
 
             # Verify that multiple WARC files were created
-            dest_bucket = TEST_S3_BUCKET
-            dest_prefix = f'cdx_toolkit/ci/test-outputs{tmpdir}/file_rotation_test'
+            dest_bucket, dest_prefix = parse_s3_uri(output_prefix_path)
 
             # List objects to find all created WARC files
             response = await s3.list_objects_v2(Bucket=dest_bucket, Prefix=dest_prefix)
diff --git a/tests/warc_by_cdx/test_warc_writer.py b/tests/warc_by_cdx/test_warc_writer.py
index 020ab3d..b30e59a 100644
--- a/tests/warc_by_cdx/test_warc_writer.py
+++ b/tests/warc_by_cdx/test_warc_writer.py
@@ -69,27 +69,17 @@ def test_write_to_local(prefix, gzip, tmpdir):
 
 
 @requires_aws_s3
-@pytest.mark.parametrize(
-    'prefix',
-    [
-        pytest.param(f's3://{TEST_S3_BUCKET}/cdx_toolkit/ci/test-outputs', id='S3 prefix'),
-    ],
-)
-def test_write_to_s3(prefix, tmpdir):
+def test_write_to_s3(s3_tmpdir):
     info = {
         'software': 'pypi_cdx_toolkit/test',
         'description': 'test',
         'format': 'WARC file version 1.0',
     }
     encoding = 'utf-8'
-    full_prefix = prefix + str(tmpdir)  # append tmp dir on S3
-    fs, fs_prefix_path = fsspec.url_to_fs(full_prefix)
 
-    # remove all existing paths from S3 dir
-    if fs.exists(prefix):
-        fs.rm(prefix, recursive=True)
+    fs, fs_prefix_path = fsspec.url_to_fs(s3_tmpdir)
 
-    writer = cdx_toolkit.warc.get_writer(full_prefix, None, info)
+    writer = cdx_toolkit.warc.get_writer(s3_tmpdir, None, info)
 
     # single record
     input_resource_record_text = 'foo bar text'

From 6441bf67eed184d8f3446966521b6c9e0e4983b8 Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Wed, 24 Sep 2025 17:12:35 +0200
Subject: [PATCH 41/74] Adding docs to README and disable duplicated test
 matrix

---
 .github/workflows/ci.yaml |  13 ++---
 README.md                 | 106 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 113 insertions(+), 6 deletions(-)

diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
index d9ff671..c818e3b 100644
--- a/.github/workflows/ci.yaml
+++ b/.github/workflows/ci.yaml
@@ -35,11 +35,12 @@ jobs:
           - python-version: '3.8'
             os: ubuntu-22.04  # oldest version on github actions
             EXTRA: true
-          - python-version: '3.13'
-            os: ubuntu-latest
-            env:
-              LOGLEVEL=DEBUG
-            EXTRA: true
+          # disabled (duplicated matrix entry)
+          # - python-version: '3.13'
+          #   os: ubuntu-latest
+          #   env:
+          #     LOGLEVEL=DEBUG
+          #   EXTRA: true
           - python-version: '3.13'
             os: macos-latest
             EXTRA: true
@@ -76,7 +77,7 @@ jobs:
           role-to-assume: arn:aws:iam::837454214164:role/GitHubActions-Role
           aws-region: us-east-1
 
-      - name: Disable S3 unit tests for Python 3.8
+      - name: Disable S3 unit tests for Python 3.8 (boto3 requires Python 3.9+)
         if: ${{ startsWith(matrix.python-version, '3.8') }}
         uses: actions/github-script@v7
         with:
diff --git a/README.md b/README.md
index f22aec7..859d103 100644
--- a/README.md
+++ b/README.md
@@ -256,6 +256,112 @@ get the most recent N captures: --limit and limit= will return the
 oldest N captures. With the 'mixed' ordering, a large enough limit=
 will get close to returning the most recent N captures.
 
+## Filtering CDX files
+
+The command line cdxt can be used to filter CDX files based on a given
+whitelist of URLs or SURTs. In particular, the filtering process
+extracts all CDX entries that match with at least one entry in the 
+whitelist. All other CDX entries are discarded. 
+
+For matching, all URLs are converted into SURTs. A match occurs
+when a given SURT from the CDX file starts with one of the prefixes
+defined in the SURTS of whitelist.
+
+The CDX filter can read and write files from local and remote file 
+systems, like S3 buckets. Multiple input files can be defined
+using a glob pattern.
+
+```
+$ cdx filter_cdx <input_cdx_path> <whitelist_path> \
+    --filter-type <url or surt> \
+    [--input-glob <glob pattern like "*_cdx-*.gz"]
+```
+
+For example, you can filter CDX from Common Crawl as follows:
+
+```
+$ cdxt -v filter_cdx \
+    s3://commoncrawl/cc-index/collections \
+    /local/path/to/my-url-whitelist.txt \
+    s3://my-s3-bucket/filtered-cdxs --filter-type url \
+    --input-glob "/CC-MAIN-2024-30/indexes/*.gz" --overwrite
+```
+
+The whitelist file looks like this (one entry per line):
+
+```
+example.com
+github.com/cococrawler
+```
+
+Filtering throughput depends on your machine. For reference,
+on an AWS EC2 c5n.xlarge instance filtering all 300 CDX files 
+from CC-MAIN-2024-30 takes ~1.4 hours with 100k URLs in the whitelist. 
+
+## WARC extraction using CDX files
+
+You can extract parts of WARC files using the cdxt command line script.
+The WARC extraction can read CDX files from local and remote file 
+systems, like S3 buckets. Multiple CDX files can be defined
+using a glob pattern. For downloading WARC parts from HTTP or S3, you can 
+define the download prefix, e.g., `s3://commoncrawl` for S3 download.
+
+```
+$ cdxt -v --cc  warc_by_cdx \
+    <path_to_cdx> [--index-glob <glob pattern, e.g., "*.gz">] \
+    --prefix <output prefix> \
+    --warc-download-prefix=<warc download prefix, e.g., s3://commoncrawl> \
+    --creator <name and contact of creator> \
+    --operator <name and contact of creator> \
+    [--implementation <fsspec or aiobot3, defaults to fsspec>]
+    [--write-paths-as-resource-records <one or more paths for resource records>]
+    [--write-paths-as-resource-records-metadata <one or more paths for metadata of resource records>]
+```
+
+By default, we use a [fsspec](https://filesystem-spec.readthedocs.io/en/latest/index.html) 
+implementation to write and read to local or remote file systems. 
+For better throughput for S3 read/write, we have also a specific implementation 
+using [aioboto3](https://github.com/terricain/aioboto3) that you can enable with 
+the `--implementation=aioboto3` argument. With aioboto3, we achieved ~ 80 requests / second 
+on an AWS EC2 c5n.xlarge instance.
+
+You can add one or multiple files with metadata as resource records to 
+the extracted WARC. For instance, this is useful to maintain the CDX filter 
+inputs, e.g., the whitelist list. To do this, you need to provide the 
+corresponding file paths as arguments `--write-paths-as-resource-records=s3:///my-s3-bucket/path/to/my-url-whitelist.txt`
+and `--write-paths-as-resource-records-metadata=s3:///my-s3-bucket/path/to/metadata.json`. 
+The metadata file is optional and can have the following optional fields:
+
+```json
+{
+    "warc_content_type": "str",
+    "uri": "str",
+    "http_headers": {"k": "v"},
+    "warc_headers_dict": {"k": "v"}
+}
+```
+
+This in one example for a metadata JSON file:
+
+```json
+{
+    "uri": "filter_cdx.gz",
+    "warc_content_type": "application/cdx",
+}
+```
+
+The full WARC extraction command could look like this:
+
+```
+$ cdxt -v --cc  warc_by_cdx \
+    s3://my-s3-bucket/filtered-cdxs --index-glob "*.gz" \
+    --prefix /local/path/filtered-warcs/ \
+    --warc-download-prefix=s3://commoncrawl \
+    --creator foo --operator bob \
+    --write-paths-as-resource-records=s3:///my-s3-bucket/path/to/my-url-whitelist.txt \
+    --write-paths-as-resource-records-metadata=s3:///my-s3-bucket/path/to/metadata.json
+```
+
 ## TODO
 
 Content downloading needs help with charset issues, preferably

From ada22cef543851962726046d8c72fa7c251cf307 Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Fri, 26 Sep 2025 16:45:18 +0200
Subject: [PATCH 42/74] WIP: Refactor for Athena integration

---
 README.md                                     |  4 +--
 cdx_toolkit/cli.py                            |  4 +--
 .../__init__.py                               | 17 +++++-----
 .../aioboto3_utils.py                         |  0
 .../aioboto3_warc_filter.py}                  |  8 ++---
 .../aioboto3_writer.py                        |  2 +-
 .../{warcer_by_cdx => filter_warc}/args.py    |  6 ++--
 .../cdx_utils.py                              |  0
 .../fsspec_warc_filter.py}                    | 10 +++---
 .../warc_utils.py                             |  0
 tests/{warc_by_cdx => filter_cdx}/__init__.py |  0
 .../test_filter_cdx.py                        |  0
 .../test_matcher.py                           |  0
 tests/filter_warc/__init__.py                 |  0
 .../test_aioboto3_utils.py                    |  2 +-
 .../test_aioboto3_warcer.py                   | 10 +++---
 .../test_aioboto3_writer.py                   | 22 ++++++-------
 .../test_cdx_utils.py                         |  4 +--
 .../test_warc_by_cdx.py                       |  6 ++--
 .../test_warc_by_cdx_aioboto3.py              |  6 ++--
 .../test_warc_from_fs.py                      |  0
 tests/filter_warc/test_warc_utils.py          | 31 +++++++++++++++++++
 .../test_warc_writer.py                       |  2 +-
 tests/warc_by_cdx/test_warc_utils.py          | 31 -------------------
 24 files changed, 85 insertions(+), 80 deletions(-)
 rename cdx_toolkit/{warcer_by_cdx => filter_warc}/__init__.py (91%)
 rename cdx_toolkit/{warcer_by_cdx => filter_warc}/aioboto3_utils.py (100%)
 rename cdx_toolkit/{warcer_by_cdx/aioboto3_warcer.py => filter_warc/aioboto3_warc_filter.py} (98%)
 rename cdx_toolkit/{warcer_by_cdx => filter_warc}/aioboto3_writer.py (98%)
 rename cdx_toolkit/{warcer_by_cdx => filter_warc}/args.py (90%)
 rename cdx_toolkit/{warcer_by_cdx => filter_warc}/cdx_utils.py (100%)
 rename cdx_toolkit/{warcer_by_cdx/fsspec_warcer.py => filter_warc/fsspec_warc_filter.py} (94%)
 rename cdx_toolkit/{warcer_by_cdx => filter_warc}/warc_utils.py (100%)
 rename tests/{warc_by_cdx => filter_cdx}/__init__.py (100%)
 rename tests/{warc_by_cdx => filter_cdx}/test_filter_cdx.py (100%)
 rename tests/{warc_by_cdx => filter_cdx}/test_matcher.py (100%)
 create mode 100644 tests/filter_warc/__init__.py
 rename tests/{warc_by_cdx => filter_warc}/test_aioboto3_utils.py (99%)
 rename tests/{warc_by_cdx => filter_warc}/test_aioboto3_warcer.py (89%)
 rename tests/{warc_by_cdx => filter_warc}/test_aioboto3_writer.py (90%)
 rename tests/{warc_by_cdx => filter_warc}/test_cdx_utils.py (92%)
 rename tests/{warc_by_cdx => filter_warc}/test_warc_by_cdx.py (98%)
 rename tests/{warc_by_cdx => filter_warc}/test_warc_by_cdx_aioboto3.py (95%)
 rename tests/{warc_by_cdx => filter_warc}/test_warc_from_fs.py (100%)
 create mode 100644 tests/filter_warc/test_warc_utils.py
 rename tests/{warc_by_cdx => filter_warc}/test_warc_writer.py (98%)
 delete mode 100644 tests/warc_by_cdx/test_warc_utils.py

diff --git a/README.md b/README.md
index 859d103..458eae3 100644
--- a/README.md
+++ b/README.md
@@ -308,7 +308,7 @@ define the download prefix, e.g., `s3://commoncrawl` for S3 download.
 
 ```
 $ cdxt -v --cc  warc_by_cdx \
-    <path_to_cdx> [--index-glob <glob pattern, e.g., "*.gz">] \
+    <path_to_cdx> [--cdx-glob <glob pattern, e.g., "*.gz">] \
     --prefix <output prefix> \
     --warc-download-prefix=<warc download prefix, e.g., s3://commoncrawl> \
     --creator <name and contact of creator> \
@@ -354,7 +354,7 @@ The full WARC extraction command could look like this:
 
 ```
 $ cdxt -v --cc  warc_by_cdx \
-    s3://my-s3-bucket/filtered-cdxs --index-glob "*.gz" \
+    s3://my-s3-bucket/filtered-cdxs --cdx-glob "*.gz" \
     --prefix /local/path/filtered-warcs/ \
     --warc-download-prefix=s3://commoncrawl \
     --creator foo --operator bob \
diff --git a/cdx_toolkit/cli.py b/cdx_toolkit/cli.py
index 2c3fa60..60c63c6 100644
--- a/cdx_toolkit/cli.py
+++ b/cdx_toolkit/cli.py
@@ -12,8 +12,8 @@
 from cdx_toolkit.filter_cdx import run_filter_cdx
 from cdx_toolkit.filter_cdx.args import add_filter_cdx_args
 
-from cdx_toolkit.warcer_by_cdx import run_warcer_by_cdx
-from cdx_toolkit.warcer_by_cdx.args import add_warcer_by_cdx_args
+from cdx_toolkit.filter_warc import run_warcer_by_cdx
+from cdx_toolkit.filter_warc.args import add_warcer_by_cdx_args
 
 
 LOGGER = logging.getLogger(__name__)
diff --git a/cdx_toolkit/warcer_by_cdx/__init__.py b/cdx_toolkit/filter_warc/__init__.py
similarity index 91%
rename from cdx_toolkit/warcer_by_cdx/__init__.py
rename to cdx_toolkit/filter_warc/__init__.py
index 9757ccc..098e69f 100644
--- a/cdx_toolkit/warcer_by_cdx/__init__.py
+++ b/cdx_toolkit/filter_warc/__init__.py
@@ -7,8 +7,8 @@
 
 
 from cdx_toolkit.utils import get_version, setup
-from cdx_toolkit.warcer_by_cdx.aioboto3_warcer import filter_warc_by_cdx_via_aioboto3
-from cdx_toolkit.warcer_by_cdx.fsspec_warcer import filter_warc_by_cdx_via_fsspec
+from cdx_toolkit.filter_warc.aioboto3_warc_filter import filter_warc_by_cdx_via_aioboto3
+from cdx_toolkit.filter_warc.fsspec_warc_filter import filter_warc_by_cdx_via_fsspec
 
 
 logger = logging.getLogger(__name__)
@@ -75,14 +75,14 @@ def run_warcer_by_cdx(args, cmdline):
     # make sure the base dir exists
     prefix_fs.makedirs(prefix_fs._parent(prefix_fs_path), exist_ok=True)
 
-    index_paths = get_index_paths(
-        args.index_path,
-        args.index_glob,
+    cdx_paths = get_cdx_paths(
+        args.cdx_path,
+        args.cdx_glob,
     )
 
     if implementation == 'fsspec':
         records_n = filter_warc_by_cdx_via_fsspec(
-            index_paths=index_paths,
+            index_paths=cdx_paths,
             prefix_path=prefix_path,
             writer_info=info,
             writer_subprefix=args.subprefix,
@@ -100,7 +100,7 @@ def run_warcer_by_cdx(args, cmdline):
             sys.exit(1)
 
         records_n = filter_warc_by_cdx_via_aioboto3(
-            index_paths=index_paths,
+            index_paths=cdx_paths,
             prefix_path=prefix_path,
             writer_info=info,
             writer_subprefix=args.subprefix,
@@ -124,7 +124,8 @@ def run_warcer_by_cdx(args, cmdline):
     logger.info(f'Script execution time: {execution_time:.3f} seconds')
 
 
-def get_index_paths(index_path: str, index_glob: Optional[str] = None) -> List[str]:
+def get_cdx_paths(index_path: str, index_glob: Optional[str] = None) -> List[str]:
+    """Find CDX index paths using glob pattern."""
     if index_glob is None:
         # Read from a single index
         index_paths = [index_path]
diff --git a/cdx_toolkit/warcer_by_cdx/aioboto3_utils.py b/cdx_toolkit/filter_warc/aioboto3_utils.py
similarity index 100%
rename from cdx_toolkit/warcer_by_cdx/aioboto3_utils.py
rename to cdx_toolkit/filter_warc/aioboto3_utils.py
diff --git a/cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py b/cdx_toolkit/filter_warc/aioboto3_warc_filter.py
similarity index 98%
rename from cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py
rename to cdx_toolkit/filter_warc/aioboto3_warc_filter.py
index 5fd8bc4..0a29142 100644
--- a/cdx_toolkit/warcer_by_cdx/aioboto3_warcer.py
+++ b/cdx_toolkit/filter_warc/aioboto3_warc_filter.py
@@ -7,18 +7,18 @@
 from botocore.config import Config
 from warcio import WARCWriter
 
-from cdx_toolkit.warcer_by_cdx.aioboto3_utils import (
+from cdx_toolkit.filter_warc.aioboto3_utils import (
     RangeJob,
     RangePayload,
     ThroughputTracker,
     parse_s3_uri,
     ranged_get_bytes,
 )
-from cdx_toolkit.warcer_by_cdx.aioboto3_writer import ShardWriter
-from cdx_toolkit.warcer_by_cdx.cdx_utils import (
+from cdx_toolkit.filter_warc.aioboto3_writer import ShardWriter
+from cdx_toolkit.filter_warc.cdx_utils import (
     iter_cdx_index_from_path,
 )
-from cdx_toolkit.warcer_by_cdx.warc_utils import get_bytes_from_warc_record, get_resource_record_from_path
+from cdx_toolkit.filter_warc.warc_utils import get_bytes_from_warc_record, get_resource_record_from_path
 
 
 _STOP = object()
diff --git a/cdx_toolkit/warcer_by_cdx/aioboto3_writer.py b/cdx_toolkit/filter_warc/aioboto3_writer.py
similarity index 98%
rename from cdx_toolkit/warcer_by_cdx/aioboto3_writer.py
rename to cdx_toolkit/filter_warc/aioboto3_writer.py
index 0bdf803..4106179 100644
--- a/cdx_toolkit/warcer_by_cdx/aioboto3_writer.py
+++ b/cdx_toolkit/filter_warc/aioboto3_writer.py
@@ -1,7 +1,7 @@
 import logging
 from typing import List, Dict, Optional
 
-from cdx_toolkit.warcer_by_cdx.aioboto3_utils import (
+from cdx_toolkit.filter_warc.aioboto3_utils import (
     mpu_abort,
     mpu_complete,
     mpu_create,
diff --git a/cdx_toolkit/warcer_by_cdx/args.py b/cdx_toolkit/filter_warc/args.py
similarity index 90%
rename from cdx_toolkit/warcer_by_cdx/args.py
rename to cdx_toolkit/filter_warc/args.py
index c54496d..1cac6b3 100644
--- a/cdx_toolkit/warcer_by_cdx/args.py
+++ b/cdx_toolkit/filter_warc/args.py
@@ -6,12 +6,12 @@
 
 
 def add_warcer_by_cdx_args(parser: argparse.ArgumentParser):
-    parser.add_argument('index_path', help='Path to CDX index file (local or remote, e.g. S3)')
+    parser.add_argument('cdx_path', help='Path to CDX index file (local or remote, e.g. S3)')
     parser.add_argument(
-        '--index-glob',
+        '--cdx-glob',
         type=str,
         default=None,
-        help='a glob pattern for read from multiple indices',
+        help='a glob pattern for read from multiple CDX indices',
     )
     parser.add_argument('--prefix', default='TEST', help='prefix for the warc filename')
     parser.add_argument(
diff --git a/cdx_toolkit/warcer_by_cdx/cdx_utils.py b/cdx_toolkit/filter_warc/cdx_utils.py
similarity index 100%
rename from cdx_toolkit/warcer_by_cdx/cdx_utils.py
rename to cdx_toolkit/filter_warc/cdx_utils.py
diff --git a/cdx_toolkit/warcer_by_cdx/fsspec_warcer.py b/cdx_toolkit/filter_warc/fsspec_warc_filter.py
similarity index 94%
rename from cdx_toolkit/warcer_by_cdx/fsspec_warcer.py
rename to cdx_toolkit/filter_warc/fsspec_warc_filter.py
index 7e0fefe..ebaa06f 100644
--- a/cdx_toolkit/warcer_by_cdx/fsspec_warcer.py
+++ b/cdx_toolkit/filter_warc/fsspec_warc_filter.py
@@ -7,8 +7,8 @@
 
 from warcio.recordloader import ArcWarcRecord
 
-from cdx_toolkit.warcer_by_cdx.cdx_utils import get_index_as_string_from_path
-from cdx_toolkit.warcer_by_cdx.warc_utils import get_resource_record_from_path
+from cdx_toolkit.filter_warc.cdx_utils import get_index_as_string_from_path
+from cdx_toolkit.filter_warc.warc_utils import get_resource_record_from_path
 
 
 logger = logging.getLogger(__name__)
@@ -137,7 +137,7 @@ def fetch_records_from_index(
                 warc_download_prefix=warc_download_prefix,
                 limit=limit,
             )
-        )
+        )  # TODO this loads all records into memory
 
         with ThreadPoolExecutor(max_workers=n_parallel) as executor:
             # Submit all tasks
@@ -168,7 +168,9 @@ def generate_caputure_objects_from_index(
             # TODO can there be a different format?
             # surt, timestamp, json_data = cols
             #
-            # CC seems to not follow the specification from https://iipc.github.io/warc-specifications/specifications/cdx-format/cdx-2015/
+            # CC seems to not follow the IIPC pecification
+            # https://iipc.github.io/warc-specifications/specifications/cdx-format/cdx-2015/
+            #
             # > The default first line of a CDX file is:
             # > CDX A b e a m s c k r V v D d g M n
             data = json.loads(cols[2])
diff --git a/cdx_toolkit/warcer_by_cdx/warc_utils.py b/cdx_toolkit/filter_warc/warc_utils.py
similarity index 100%
rename from cdx_toolkit/warcer_by_cdx/warc_utils.py
rename to cdx_toolkit/filter_warc/warc_utils.py
diff --git a/tests/warc_by_cdx/__init__.py b/tests/filter_cdx/__init__.py
similarity index 100%
rename from tests/warc_by_cdx/__init__.py
rename to tests/filter_cdx/__init__.py
diff --git a/tests/warc_by_cdx/test_filter_cdx.py b/tests/filter_cdx/test_filter_cdx.py
similarity index 100%
rename from tests/warc_by_cdx/test_filter_cdx.py
rename to tests/filter_cdx/test_filter_cdx.py
diff --git a/tests/warc_by_cdx/test_matcher.py b/tests/filter_cdx/test_matcher.py
similarity index 100%
rename from tests/warc_by_cdx/test_matcher.py
rename to tests/filter_cdx/test_matcher.py
diff --git a/tests/filter_warc/__init__.py b/tests/filter_warc/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/tests/warc_by_cdx/test_aioboto3_utils.py b/tests/filter_warc/test_aioboto3_utils.py
similarity index 99%
rename from tests/warc_by_cdx/test_aioboto3_utils.py
rename to tests/filter_warc/test_aioboto3_utils.py
index 6054495..a2eb905 100644
--- a/tests/warc_by_cdx/test_aioboto3_utils.py
+++ b/tests/filter_warc/test_aioboto3_utils.py
@@ -4,7 +4,7 @@
 from unittest.mock import AsyncMock
 
 
-from cdx_toolkit.warcer_by_cdx.aioboto3_utils import (
+from cdx_toolkit.filter_warc.aioboto3_utils import (
     _backoff,
     parse_s3_uri,
     mpu_abort,
diff --git a/tests/warc_by_cdx/test_aioboto3_warcer.py b/tests/filter_warc/test_aioboto3_warcer.py
similarity index 89%
rename from tests/warc_by_cdx/test_aioboto3_warcer.py
rename to tests/filter_warc/test_aioboto3_warcer.py
index ad7885c..98d776e 100644
--- a/tests/warc_by_cdx/test_aioboto3_warcer.py
+++ b/tests/filter_warc/test_aioboto3_warcer.py
@@ -1,7 +1,10 @@
 import asyncio
 from unittest.mock import patch, AsyncMock
 
-from cdx_toolkit.warcer_by_cdx.aioboto3_warcer import filter_warc_by_cdx_via_aioboto3, get_range_jobs_from_index_paths
+from cdx_toolkit.filter_warc.aioboto3_warc_filter import (
+    filter_warc_by_cdx_via_aioboto3,
+    get_range_jobs_from_index_paths,
+)
 
 
 def test_filter_warc_by_cdx_via_aioboto3_keyboard_interrupt(caplog):
@@ -12,7 +15,7 @@ async def mock_async_function(*args, **kwargs):
         raise KeyboardInterrupt('User interrupted')
 
     with patch(
-        'cdx_toolkit.warcer_by_cdx.aioboto3_warcer.filter_warc_by_cdx_via_aioboto3_async',
+        'cdx_toolkit.filter_warc.aioboto3_warc_filter.filter_warc_by_cdx_via_aioboto3_async',
         side_effect=mock_async_function,
     ):
         # Call the function with minimal required parameters
@@ -32,7 +35,6 @@ async def mock_async_function(*args, **kwargs):
         assert warning_records[0].message == 'Interrupted by user.'
 
 
-
 def test_get_range_jobs_from_index_paths_exception_handling_with_logging(caplog):
     """Test get_range_jobs_from_index_paths logs errors when iter_cdx_index_from_path raises."""
 
@@ -50,7 +52,7 @@ def mock_iter_cdx_index_from_path(index_path, warc_download_prefix):
             raise ValueError('Simulated CDX parsing error')
 
         with patch(
-            'cdx_toolkit.warcer_by_cdx.aioboto3_warcer.iter_cdx_index_from_path',
+            'cdx_toolkit.filter_warc.aioboto3_warc_filter.iter_cdx_index_from_path',
             side_effect=mock_iter_cdx_index_from_path,
         ):
             # Run the function
diff --git a/tests/warc_by_cdx/test_aioboto3_writer.py b/tests/filter_warc/test_aioboto3_writer.py
similarity index 90%
rename from tests/warc_by_cdx/test_aioboto3_writer.py
rename to tests/filter_warc/test_aioboto3_writer.py
index 22cb38b..3765981 100644
--- a/tests/warc_by_cdx/test_aioboto3_writer.py
+++ b/tests/filter_warc/test_aioboto3_writer.py
@@ -2,7 +2,7 @@
 import asyncio
 from unittest.mock import AsyncMock, patch
 
-from cdx_toolkit.warcer_by_cdx.aioboto3_writer import ShardWriter
+from cdx_toolkit.filter_warc.aioboto3_writer import ShardWriter
 
 
 def test_shard_writer_init():
@@ -40,7 +40,7 @@ def test_shard_writer_start():
     """Test ShardWriter start method."""
 
     async def run_test():
-        with patch('cdx_toolkit.warcer_by_cdx.aioboto3_writer.mpu_create') as mock_mpu_create:
+        with patch('cdx_toolkit.filter_warc.aioboto3_writer.mpu_create') as mock_mpu_create:
             mock_mpu_create.return_value = 'test-upload-id'
 
             writer = ShardWriter(
@@ -98,7 +98,7 @@ def test_shard_writer_write_large_data():
     """Test ShardWriter write method with large data that triggers part uploads."""
 
     async def run_test():
-        with patch('cdx_toolkit.warcer_by_cdx.aioboto3_writer.mpu_upload_part') as mock_upload_part:
+        with patch('cdx_toolkit.filter_warc.aioboto3_writer.mpu_upload_part') as mock_upload_part:
             mock_upload_part.return_value = 'test-etag-1'
 
             writer = ShardWriter(
@@ -134,7 +134,7 @@ def test_shard_writer_flush_full_parts():
     """Test ShardWriter _flush_full_parts private method directly."""
 
     async def run_test():
-        with patch('cdx_toolkit.warcer_by_cdx.aioboto3_writer.mpu_upload_part') as mock_upload_part:
+        with patch('cdx_toolkit.filter_warc.aioboto3_writer.mpu_upload_part') as mock_upload_part:
             mock_upload_part.return_value = 'test-etag-flush'
 
             writer = ShardWriter(
@@ -170,8 +170,8 @@ def test_shard_writer_close_with_buffer():
     """Test ShardWriter close method with data remaining in buffer."""
 
     async def run_test():
-        with patch('cdx_toolkit.warcer_by_cdx.aioboto3_writer.mpu_upload_part') as mock_upload_part, patch(
-            'cdx_toolkit.warcer_by_cdx.aioboto3_writer.mpu_complete'
+        with patch('cdx_toolkit.filter_warc.aioboto3_writer.mpu_upload_part') as mock_upload_part, patch(
+            'cdx_toolkit.filter_warc.aioboto3_writer.mpu_complete'
         ) as mock_complete:
             mock_upload_part.return_value = 'final-etag'
 
@@ -225,8 +225,8 @@ def test_shard_writer_close_empty():
     """Test ShardWriter close method with no data (empty buffer, no parts)."""
 
     async def run_test():
-        with patch('cdx_toolkit.warcer_by_cdx.aioboto3_writer.mpu_upload_part') as mock_upload_part, patch(
-            'cdx_toolkit.warcer_by_cdx.aioboto3_writer.mpu_complete'
+        with patch('cdx_toolkit.filter_warc.aioboto3_writer.mpu_upload_part') as mock_upload_part, patch(
+            'cdx_toolkit.filter_warc.aioboto3_writer.mpu_complete'
         ) as mock_complete:
             writer = ShardWriter(
                 shard_key='test.warc.gz',
@@ -257,9 +257,9 @@ def test_shard_writer_close_with_exception():
     """Test ShardWriter close method with exception and abort handling."""
 
     async def run_test():
-        with patch('cdx_toolkit.warcer_by_cdx.aioboto3_writer.mpu_upload_part') as mock_upload_part, patch(
-            'cdx_toolkit.warcer_by_cdx.aioboto3_writer.mpu_complete'
-        ) as mock_complete, patch('cdx_toolkit.warcer_by_cdx.aioboto3_writer.mpu_abort') as mock_abort:
+        with patch('cdx_toolkit.filter_warc.aioboto3_writer.mpu_upload_part') as mock_upload_part, patch(
+            'cdx_toolkit.filter_warc.aioboto3_writer.mpu_complete'
+        ) as mock_complete, patch('cdx_toolkit.filter_warc.aioboto3_writer.mpu_abort') as mock_abort:
             mock_upload_part.return_value = 'error-etag'
             mock_complete.side_effect = Exception('Complete failed')
 
diff --git a/tests/warc_by_cdx/test_cdx_utils.py b/tests/filter_warc/test_cdx_utils.py
similarity index 92%
rename from tests/warc_by_cdx/test_cdx_utils.py
rename to tests/filter_warc/test_cdx_utils.py
index af46466..378bf85 100644
--- a/tests/warc_by_cdx/test_cdx_utils.py
+++ b/tests/filter_warc/test_cdx_utils.py
@@ -1,6 +1,6 @@
 import fsspec
 import pytest
-from cdx_toolkit.warcer_by_cdx.cdx_utils import get_index_as_string_from_path, read_cdx_line, iter_cdx_index_from_path
+from cdx_toolkit.filter_warc.cdx_utils import get_index_as_string_from_path, read_cdx_line, iter_cdx_index_from_path
 from tests.conftest import TEST_DATA_PATH
 
 import tempfile
@@ -60,7 +60,7 @@ def mock_read_cdx_line(line, warc_download_prefix):
                 raise ValueError(f'Mock error for line: {line}')
             return original_read_cdx_line(line, warc_download_prefix)
 
-        with patch('cdx_toolkit.warcer_by_cdx.cdx_utils.read_cdx_line', side_effect=mock_read_cdx_line):
+        with patch('cdx_toolkit.filter_warc.cdx_utils.read_cdx_line', side_effect=mock_read_cdx_line):
             # Collect results from iterator
             results = list(iter_cdx_index_from_path(tmp_file_path, 'http://warc-prefix'))
 
diff --git a/tests/warc_by_cdx/test_warc_by_cdx.py b/tests/filter_warc/test_warc_by_cdx.py
similarity index 98%
rename from tests/warc_by_cdx/test_warc_by_cdx.py
rename to tests/filter_warc/test_warc_by_cdx.py
index 9fd7cc0..ab7dd63 100644
--- a/tests/warc_by_cdx/test_warc_by_cdx.py
+++ b/tests/filter_warc/test_warc_by_cdx.py
@@ -3,10 +3,10 @@
 
 import fsspec
 from cdx_toolkit.cli import main
-from cdx_toolkit.warcer_by_cdx.cdx_utils import (
+from cdx_toolkit.filter_warc.cdx_utils import (
     get_index_as_string_from_path,
 )
-from cdx_toolkit.warcer_by_cdx.fsspec_warcer import (
+from cdx_toolkit.filter_warc.fsspec_warc_filter import (
     generate_caputure_objects_from_index,
 )
 import pytest
@@ -159,7 +159,7 @@ def test_warc_by_cdx_no_index_files_found_exits(tmpdir, caplog):
                 'warc_by_cdx',
                 f'{str(tmpdir)}',
                 f'--prefix={str(tmpdir)}/TEST',
-                '--index-glob=/nonexistent-pattern-*.gz',
+                '--cdx-glob=/nonexistent-pattern-*.gz',
             ]
         )
 
diff --git a/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py b/tests/filter_warc/test_warc_by_cdx_aioboto3.py
similarity index 95%
rename from tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
rename to tests/filter_warc/test_warc_by_cdx_aioboto3.py
index 97e5b1a..60231ce 100644
--- a/tests/warc_by_cdx/test_warc_by_cdx_aioboto3.py
+++ b/tests/filter_warc/test_warc_by_cdx_aioboto3.py
@@ -6,9 +6,9 @@
 from tests.conftest import requires_aws_s3, TEST_DATA_PATH
 
 from warcio import WARCWriter
-from cdx_toolkit.warcer_by_cdx.aioboto3_warcer import get_range_jobs_from_index_paths, write_warc, _STOP
-from cdx_toolkit.warcer_by_cdx.aioboto3_utils import RangePayload, parse_s3_uri
-from tests.warc_by_cdx.test_warc_by_cdx import assert_cli_warc_by_cdx
+from cdx_toolkit.filter_warc.aioboto3_warc_filter import get_range_jobs_from_index_paths, write_warc, _STOP
+from cdx_toolkit.filter_warc.aioboto3_utils import RangePayload, parse_s3_uri
+from tests.filter_warc.test_warc_by_cdx import assert_cli_warc_by_cdx
 
 fixture_path = TEST_DATA_PATH / 'warc_by_cdx'
 aioboto3_warc_filename = 'TEST_warc_by_index-000000-001.extracted.warc.gz'  # due to parallel writer
diff --git a/tests/warc_by_cdx/test_warc_from_fs.py b/tests/filter_warc/test_warc_from_fs.py
similarity index 100%
rename from tests/warc_by_cdx/test_warc_from_fs.py
rename to tests/filter_warc/test_warc_from_fs.py
diff --git a/tests/filter_warc/test_warc_utils.py b/tests/filter_warc/test_warc_utils.py
new file mode 100644
index 0000000..23de5e1
--- /dev/null
+++ b/tests/filter_warc/test_warc_utils.py
@@ -0,0 +1,31 @@
+import pytest
+from cdx_toolkit.filter_warc.warc_utils import get_resource_record_from_path
+from tests.conftest import TEST_DATA_PATH
+
+
+def test_get_resource_record_from_path():
+    resource_path = TEST_DATA_PATH / 'filter_cdx/whitelist_10_urls.txt'
+    record = get_resource_record_from_path(resource_path)
+
+    assert record.content_type == 'text/plain'
+
+    record_headers = dict(record.rec_headers.headers)
+    assert record_headers['WARC-Target-URI'] == str(resource_path)
+
+
+def test_get_resource_record_from_path_with_metadata():
+    resource_path = TEST_DATA_PATH / 'warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.gz'
+    metadata_path = TEST_DATA_PATH / 'warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.metadata.json'
+
+    record = get_resource_record_from_path(resource_path, metadata_path)
+
+    assert record.content_type == 'application/cdx'
+
+    record_headers = dict(record.rec_headers.headers)
+    assert record_headers['WARC-Target-URI'] == 'filter_cdx.cdx.gz'
+
+
+def test_get_resource_record_from_path_with_invalid_metadata_path():
+    with pytest.raises(ValueError):
+        resource_path = TEST_DATA_PATH / 'filter_cdx/whitelist_10_urls.txt'
+        get_resource_record_from_path(resource_path, 'invalid_metadata.xy')
diff --git a/tests/warc_by_cdx/test_warc_writer.py b/tests/filter_warc/test_warc_writer.py
similarity index 98%
rename from tests/warc_by_cdx/test_warc_writer.py
rename to tests/filter_warc/test_warc_writer.py
index b30e59a..4725ef4 100644
--- a/tests/warc_by_cdx/test_warc_writer.py
+++ b/tests/filter_warc/test_warc_writer.py
@@ -3,7 +3,7 @@
 import pytest
 import cdx_toolkit
 
-from tests.conftest import TEST_S3_BUCKET, requires_aws_s3
+from tests.conftest import requires_aws_s3
 
 from warcio import WARCWriter
 from warcio.archiveiterator import ArchiveIterator
diff --git a/tests/warc_by_cdx/test_warc_utils.py b/tests/warc_by_cdx/test_warc_utils.py
deleted file mode 100644
index f95fbe5..0000000
--- a/tests/warc_by_cdx/test_warc_utils.py
+++ /dev/null
@@ -1,31 +0,0 @@
-import pytest
-from cdx_toolkit.warcer_by_cdx.warc_utils import get_resource_record_from_path
-from tests.conftest import TEST_DATA_PATH
-
-
-def test_get_resource_record_from_path():
-    resource_path = TEST_DATA_PATH / "filter_cdx/whitelist_10_urls.txt"
-    record = get_resource_record_from_path(resource_path)
-
-    assert record.content_type == "text/plain"
-
-    record_headers = dict(record.rec_headers.headers)
-    assert record_headers["WARC-Target-URI"] == str(resource_path)
-    
-
-def test_get_resource_record_from_path_with_metadata():
-    resource_path = TEST_DATA_PATH / "warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.gz"
-    metadata_path = TEST_DATA_PATH / "warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.metadata.json"
-
-    record = get_resource_record_from_path(resource_path, metadata_path)
-
-    assert record.content_type == "application/cdx"
-
-    record_headers = dict(record.rec_headers.headers)
-    assert record_headers["WARC-Target-URI"] == "filter_cdx.cdx.gz"
-    
-
-def test_get_resource_record_from_path_with_invalid_metadata_path():
-    with pytest.raises(ValueError):
-        resource_path = TEST_DATA_PATH / "filter_cdx/whitelist_10_urls.txt"
-        get_resource_record_from_path(resource_path, "invalid_metadata.xy")
\ No newline at end of file

From d0bbd9a227906113669980050df60b0aae3a05cc Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Tue, 30 Sep 2025 13:58:46 +0200
Subject: [PATCH 43/74] Adding log arg

---
 cdx_toolkit/filter_warc/__init__.py           |  2 +-
 .../filter_warc/aioboto3_warc_filter.py       | 24 +++++++++----------
 cdx_toolkit/filter_warc/args.py               |  6 +++++
 3 files changed, 19 insertions(+), 13 deletions(-)

diff --git a/cdx_toolkit/filter_warc/__init__.py b/cdx_toolkit/filter_warc/__init__.py
index 098e69f..9e070a5 100644
--- a/cdx_toolkit/filter_warc/__init__.py
+++ b/cdx_toolkit/filter_warc/__init__.py
@@ -67,7 +67,7 @@ def run_warcer_by_cdx(args, cmdline):
         del kwargs['size']
 
     n_parallel = args.parallel
-    log_every_n = 5
+    log_every_n = args.log_every_n
     limit = 0 if args.limit is None else args.limit
     prefix_path = str(args.prefix)
     prefix_fs, prefix_fs_path = fsspec.url_to_fs(prefix_path)
diff --git a/cdx_toolkit/filter_warc/aioboto3_warc_filter.py b/cdx_toolkit/filter_warc/aioboto3_warc_filter.py
index 0a29142..72fbe51 100644
--- a/cdx_toolkit/filter_warc/aioboto3_warc_filter.py
+++ b/cdx_toolkit/filter_warc/aioboto3_warc_filter.py
@@ -148,10 +148,10 @@ async def filter_warc_by_cdx_via_aioboto3_async(
         ]
 
         await lister_task
-        logger.info('Lister completed, waiting for fetchers to finish')
+        logger.info('Range jobs submitted, waiting for fetchers to finish')
 
         await asyncio.gather(*fetchers)
-        logger.info('All fetchers completed')
+        logger.info('All WARC fetchers completed')
 
         # Send stop signals to consumers
         for _ in range(num_consumers):
@@ -160,7 +160,7 @@ async def filter_warc_by_cdx_via_aioboto3_async(
         consumer_results = await asyncio.gather(*consumers)
         n_records = sum([result['stats']['total_requests'] for result in consumer_results])
 
-        logger.info('All consumers completed')
+        logger.info('All WARC writers completed')
 
     return n_records
 
@@ -205,7 +205,7 @@ async def get_range_jobs_from_index_paths(
     for _ in range(num_fetchers):
         await key_queue.put(_STOP)
 
-    logger.info('Lister enqueued %d jobs from %s', count, index_path)
+    logger.info('Enqueued %d jobs from %s', count, index_path)
 
 
 async def fetch_warc_ranges(
@@ -228,7 +228,7 @@ async def fetch_warc_ranges(
             if job is _STOP:
                 stats = tracker.get_stats()
                 logger.info(
-                    'Fetcher %d stopping. Stats: %.1fs, %d requests, %.1f MB, %.2f MB/s, %.2f req/s',
+                    'WARC Fetcher %d stopping. Stats: %.1fs, %d requests, %.1f MB, %.2f MB/s, %.2f req/s',
                     fetcher_id,
                     stats['elapsed'],
                     stats['total_requests'],
@@ -251,10 +251,10 @@ async def fetch_warc_ranges(
             counter += 1
 
             # Log progress every 10 items
-            if counter % log_every_n == 0:
+            if log_every_n > 0 and counter % log_every_n == 0:
                 stats = tracker.get_stats()
                 logger.info(
-                    'Fetcher %d: %d items, %.1f MB, %.2f MB/s, %.2f req/s',
+                    'WARC Fetcher %d: %d items, %.1f MB, %.2f MB/s, %.2f req/s',
                     fetcher_id,
                     counter,
                     stats['total_bytes'] / (1024 * 1024),
@@ -265,7 +265,7 @@ async def fetch_warc_ranges(
             await item_queue.put(RangePayload(job=job, data=data))
         except Exception:
             logger.exception(
-                'Fetcher %d failed on %s/%s [%d,%d]',
+                'WARC Fetcher %d failed on %s/%s [%d,%d]',
                 fetcher_id,
                 getattr(job, 'bucket', '?'),
                 getattr(job, 'key', '?'),
@@ -418,7 +418,7 @@ async def write_warc(
                 if item is _STOP:
                     stats = tracker.get_stats()
                     logger.info(
-                        'Consumer %d stopping. Stats: %.1fs, %d items, %.1f MB written, %.2f MB/s write speed',
+                        'WARC writer %d stopping. Stats: %.1fs, %d items, %.1f MB written, %.2f MB/s write speed',
                         consumer_id,
                         stats['elapsed'],
                         stats['total_requests'],
@@ -459,17 +459,17 @@ async def write_warc(
                     tracker.add_bytes(len(item.data))
 
                     # Log progress every 10 items
-                    if counter % log_every_n == 0:
+                    if log_every_n > 0 and counter % log_every_n == 0:
                         stats = tracker.get_stats()
                         logger.info(
-                            'Consumer %d: %d items, %.1f MB written, %.2f MB/s',
+                            'WARC writer %d: %d items, %.1f MB written, %.2f MB/s',
                             consumer_id,
                             counter,
                             stats['total_bytes'] / (1024 * 1024),
                             stats['mb_per_sec'],
                         )
             except Exception:
-                logger.exception('Consumer %d failed on %s', consumer_id, getattr(item, 'job', None))
+                logger.exception('WARC writer %d failed on %s', consumer_id, getattr(item, 'job', None))
                 should_stop = False
             finally:
                 item_queue.task_done()
diff --git a/cdx_toolkit/filter_warc/args.py b/cdx_toolkit/filter_warc/args.py
index 1cac6b3..0ab94a7 100644
--- a/cdx_toolkit/filter_warc/args.py
+++ b/cdx_toolkit/filter_warc/args.py
@@ -53,5 +53,11 @@ def add_warcer_by_cdx_args(parser: argparse.ArgumentParser):
         default=1,
         help='Number of parallel workers for fetchin WARC records (default: 1, sequential processing)',
     )
+    parser.add_argument(
+        '--log_every_n',
+        type=int,
+        default=1000,
+        help='Every N extracted record a log message is emitted (0 = no record logs)',
+    )    
     parser.add_argument('--implementation', type=str, default='fsspec', help='implementation (fsspec, aioboto3)')
     return parser

From dfdefbc09a1f844e379f3ed96a33bc45b13c9303 Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Wed, 1 Oct 2025 16:14:00 +0200
Subject: [PATCH 44/74] WIP: unified implementation

---
 cdx_toolkit/filter_warc/__init__.py           |  19 +-
 cdx_toolkit/filter_warc/aioboto3_utils.py     |  59 ++-
 .../filter_warc/aioboto3_warc_filter.py       |  91 ++--
 cdx_toolkit/filter_warc/aioboto3_writer.py    |  26 +-
 cdx_toolkit/filter_warc/cdx_utils.py          |   1 +
 cdx_toolkit/filter_warc/local_writer.py       |  42 ++
 cdx_toolkit/filter_warc/warc_filter.py        | 407 ++++++++++++++++++
 tests/filter_warc/test_aioboto3_writer.py     |  41 +-
 tests/filter_warc/test_warc_filter.py         |  57 +++
 9 files changed, 657 insertions(+), 86 deletions(-)
 create mode 100644 cdx_toolkit/filter_warc/local_writer.py
 create mode 100644 cdx_toolkit/filter_warc/warc_filter.py
 create mode 100644 tests/filter_warc/test_warc_filter.py

diff --git a/cdx_toolkit/filter_warc/__init__.py b/cdx_toolkit/filter_warc/__init__.py
index 9e070a5..a7733b6 100644
--- a/cdx_toolkit/filter_warc/__init__.py
+++ b/cdx_toolkit/filter_warc/__init__.py
@@ -10,10 +10,11 @@
 from cdx_toolkit.filter_warc.aioboto3_warc_filter import filter_warc_by_cdx_via_aioboto3
 from cdx_toolkit.filter_warc.fsspec_warc_filter import filter_warc_by_cdx_via_fsspec
 
+from cdx_toolkit.filter_warc.warc_filter import WARCFilter
 
 logger = logging.getLogger(__name__)
 
-ImplementationType = Literal['fsspec', 'aioboto3']
+ImplementationType = Literal['fsspec', 'aioboto3', 'warc_filter']
 
 
 def run_warcer_by_cdx(args, cmdline):
@@ -112,6 +113,22 @@ def run_warcer_by_cdx(args, cmdline):
             n_parallel=n_parallel,
             writer_kwargs=writer_kwargs,
         )
+    elif implementation == "warc_filter":
+
+        warc_filter = WARCFilter(
+            index_paths=cdx_paths,
+            prefix_path=prefix_path,
+            writer_info=info,
+            writer_subprefix=args.subprefix,
+            write_paths_as_resource_records=write_paths_as_resource_records,
+            write_paths_as_resource_records_metadata=write_paths_as_resource_records_metadata,
+            record_limit=limit,
+            log_every_n=log_every_n,
+            warc_download_prefix=cdx.warc_download_prefix,
+            n_parallel=n_parallel,
+            writer_kwargs=writer_kwargs,
+        )
+        records_n = warc_filter.filter()
     else:
         raise ValueError(f'Invalid implementation: {implementation}')
 
diff --git a/cdx_toolkit/filter_warc/aioboto3_utils.py b/cdx_toolkit/filter_warc/aioboto3_utils.py
index ca68f1f..3f74092 100644
--- a/cdx_toolkit/filter_warc/aioboto3_utils.py
+++ b/cdx_toolkit/filter_warc/aioboto3_utils.py
@@ -2,11 +2,13 @@
 import logging
 import time
 from dataclasses import dataclass
-from typing import Dict, List, Optional, Tuple
+from typing import Dict, List, Optional, Tuple, Union
 from os import urandom
 
 from botocore.exceptions import ClientError, EndpointConnectionError
 
+from cdx_toolkit.myrequests import myrequests_get
+
 
 logger = logging.getLogger(__name__)
 
@@ -41,12 +43,20 @@ def get_stats(self) -> dict:
 
 @dataclass(frozen=True)
 class RangeJob:
-    """Defines a S3 range read request."""
-    bucket: str
-    key: str
+    """Defines a S3 or HTTP range read request."""
+    url: str
     offset: int
     length: int
 
+    def is_s3(self):
+        return is_s3_url(self.url)
+
+    def get_s3_bucket_and_key(self) -> Tuple[str, str]:
+        if self.is_s3():
+            return parse_s3_uri(self.url)
+        else:
+            raise ValueError("Cannot get bucket and key from a HTTP job")
+
 
 @dataclass(frozen=True)
 class RangePayload:
@@ -97,23 +107,34 @@ async def with_retries(coro_factory, *, op_name: str, max_attempts: int, base_ba
 
 
 async def ranged_get_bytes(
-    s3,
-    bucket: str,
-    key: str,
-    offset: int,
-    length: int,
+    job: RangeJob,
     max_attempts: int,
     base_backoff_seconds: float,
+    s3_client=None,
 ) -> bytes:
-    """Ranged get request to S3 with retries and backoff."""
+    """Ranged get request to S3 with retries and backoff or HTTP."""
+    offset = job.offset
+    length = job.length
+
     end = offset + length - 1  # inclusive
-    resp = await with_retries(
-        lambda: s3.get_object(Bucket=bucket, Key=key, Range=f'bytes={offset}-{end}'),
-        op_name=f'ranged_get {bucket}/{key}[{offset}:{end}]',
-        max_attempts=max_attempts,
-        base_backoff_seconds=base_backoff_seconds,
-    )
-    return await resp['Body'].read()
+
+    if job.is_s3():
+        # read from S3
+        bucket, key = job.get_s3_bucket_and_key()
+        resp = await with_retries(
+            lambda: s3_client.get_object(Bucket=bucket, Key=key, Range=f'bytes={offset}-{end}'),
+            op_name=f'ranged_get {bucket}/{key}[{offset}:{end}]',
+            max_attempts=max_attempts,
+            base_backoff_seconds=base_backoff_seconds,
+        )
+        return await resp['Body'].read()
+
+    else:
+        # read from HTTP
+        headers = {'Range': 'bytes={}-{}'.format(offset, end)}
+
+        resp = myrequests_get(job.url, headers=headers)
+        return resp.content
 
 
 async def mpu_create(
@@ -187,3 +208,7 @@ async def mpu_abort(s3, bucket: str, key: str, upload_id: str):
         await s3.abort_multipart_upload(Bucket=bucket, Key=key, UploadId=upload_id)
     except Exception:
         logger.exception('Failed to abort MPU %s on %s/%s', upload_id, bucket, key)
+
+
+def is_s3_url(url: str) -> bool:
+    return url.startswith("s3:/")
diff --git a/cdx_toolkit/filter_warc/aioboto3_warc_filter.py b/cdx_toolkit/filter_warc/aioboto3_warc_filter.py
index 72fbe51..205bb2e 100644
--- a/cdx_toolkit/filter_warc/aioboto3_warc_filter.py
+++ b/cdx_toolkit/filter_warc/aioboto3_warc_filter.py
@@ -11,13 +11,15 @@
     RangeJob,
     RangePayload,
     ThroughputTracker,
+    is_s3_url,
     parse_s3_uri,
     ranged_get_bytes,
 )
-from cdx_toolkit.filter_warc.aioboto3_writer import ShardWriter
+from cdx_toolkit.filter_warc.aioboto3_writer import S3ShardWriter
 from cdx_toolkit.filter_warc.cdx_utils import (
     iter_cdx_index_from_path,
 )
+from cdx_toolkit.filter_warc.local_writer import LocalFileWriter
 from cdx_toolkit.filter_warc.warc_utils import get_bytes_from_warc_record, get_resource_record_from_path
 
 
@@ -185,8 +187,7 @@ async def get_range_jobs_from_index_paths(
                 index_path, warc_download_prefix=warc_download_prefix
             ):
                 # Convert the CDX record back to a RangeJob
-                bucket, key = parse_s3_uri(warc_url)
-                job = RangeJob(bucket=bucket, key=key, offset=offset, length=length)
+                job = RangeJob(url=warc_url, offset=offset, length=length)
                 await key_queue.put(job)
                 count += 1
 
@@ -239,13 +240,10 @@ async def fetch_warc_ranges(
                 break  # Exit loop, but still execute finally block
             assert isinstance(job, RangeJob)
             data = await ranged_get_bytes(
-                s3,
-                job.bucket,
-                job.key,
-                job.offset,
-                job.length,
+                job,
                 max_attempts,
                 base_backoff_seconds,
+                s3_client=s3,
             )
             tracker.add_bytes(len(data))
             counter += 1
@@ -294,11 +292,9 @@ def generate_warc_filename(
 
 
 async def create_new_writer_with_header(
-    s3,
     consumer_id: int,
     sequence: int,
-    dest_bucket: str,
-    dest_prefix: str,
+    output_path_prefix: str,
     max_attempts: int,
     base_backoff_seconds: float,
     min_part_size: int,
@@ -307,26 +303,45 @@ async def create_new_writer_with_header(
     writer_subprefix: Optional[str] = None,
     gzip: bool = False,
     content_type: Optional[str] = None,
+    s3_client=None,
 ):
-    filename = generate_warc_filename(
-        dest_prefix=dest_prefix,
-        consumer_id=consumer_id,
-        sequence=sequence,
-        writer_subprefix=writer_subprefix,
-        gzip=gzip,
-    )
+    if is_s3_url(output_path_prefix):
+        dest_bucket, dest_prefix = parse_s3_uri(output_path_prefix)
+
+        filename = generate_warc_filename(
+            dest_prefix=dest_prefix,
+            consumer_id=consumer_id,
+            sequence=sequence,
+            writer_subprefix=writer_subprefix,
+            gzip=gzip,
+        )
 
-    new_writer = ShardWriter(
-        filename,
-        dest_bucket,
-        content_type,
-        min_part_size,
-        max_attempts,
-        base_backoff_seconds,
-    )
+        new_writer = S3ShardWriter(
+            s3_client,
+            filename,
+            dest_bucket,
+            content_type,
+            min_part_size,
+            max_attempts,
+            base_backoff_seconds,
+        )
+
+    else:
+        # local file system
+        filename = generate_warc_filename(
+            dest_prefix=output_path_prefix,
+            consumer_id=consumer_id,
+            sequence=sequence,
+            writer_subprefix=writer_subprefix,
+            gzip=gzip,
+        )
+
+        new_writer = LocalFileWriter(
+            file_path=filename,
+        )
 
     # Initialize writer
-    await new_writer.start(s3)
+    await new_writer.start()
 
     # Write WARC header
     buffer = BytesIO()
@@ -334,7 +349,7 @@ async def create_new_writer_with_header(
     warcinfo = warc_writer.create_warcinfo_record(filename, writer_info)
     warc_writer.write_record(warcinfo)
     header_data = buffer.getvalue()
-    await new_writer.write(s3, header_data)
+    await new_writer.write(header_data)
 
     return new_writer, len(header_data)
 
@@ -360,19 +375,16 @@ async def write_warc(
 ):
     """Stage 3: Write WARC. Each consumer owns ONE shard MPU and appends ranges to it."""
 
-    dest_bucket, dest_prefix = parse_s3_uri(prefix_path)
-
     # File rotation tracking
     current_file_sequence = 1
     current_file_size = 0
 
     # Initialize first writer with header
     writer, header_size = await create_new_writer_with_header(
-        s3,
+        s3_client=s3,
         consumer_id=consumer_id,
         sequence=current_file_sequence,
-        dest_bucket=dest_bucket,
-        dest_prefix=dest_prefix,
+        output_path_prefix=prefix_path,
         max_attempts=max_attempts,
         base_backoff_seconds=base_backoff_seconds,
         writer_info=writer_info,
@@ -403,7 +415,7 @@ async def write_warc(
             )
             record_data = get_bytes_from_warc_record(resource_record, warc_version=warc_version, gzip=gzip)
 
-            await writer.write(s3, record_data)
+            await writer.write(record_data)
 
             # Keep track but do not rotate resource records
             current_file_size += len(record_data)
@@ -432,15 +444,14 @@ async def write_warc(
 
                     # Check if we need to rotate files due to size limit
                     if max_file_size and current_file_size + len(item.data) > max_file_size:
-                        await writer.close(s3)
+                        await writer.close()
                         current_file_sequence += 1
 
                         writer, header_size = await create_new_writer_with_header(
-                            s3,
+                            s3_client=s3,
                             consumer_id=consumer_id,
                             sequence=current_file_sequence,
-                            dest_bucket=dest_bucket,
-                            dest_prefix=dest_prefix,
+                            output_path_prefix=prefix_path,
                             max_attempts=max_attempts,
                             base_backoff_seconds=base_backoff_seconds,
                             writer_info=writer_info,
@@ -454,7 +465,7 @@ async def write_warc(
                         current_file_size = header_size
                         logger.info(f'Rotated to new WARC file sequence {current_file_sequence} due to size limit')
 
-                    await writer.write(s3, item.data)
+                    await writer.write(item.data)
                     current_file_size += len(item.data)
                     tracker.add_bytes(len(item.data))
 
@@ -477,6 +488,6 @@ async def write_warc(
             if should_stop:
                 break
     finally:
-        await writer.close(s3)
+        await writer.close()
 
     return {'consumer_id': consumer_id, 'stats': tracker.get_stats()}
diff --git a/cdx_toolkit/filter_warc/aioboto3_writer.py b/cdx_toolkit/filter_warc/aioboto3_writer.py
index 4106179..903c23c 100644
--- a/cdx_toolkit/filter_warc/aioboto3_writer.py
+++ b/cdx_toolkit/filter_warc/aioboto3_writer.py
@@ -11,11 +11,12 @@
 logger = logging.getLogger(__name__)
 
 
-class ShardWriter:
+class S3ShardWriter:
     """Manages one MPU: buffers bytes, uploads >=5 MiB parts, completes on close."""
 
     def __init__(
         self,
+        s3_client,
         shard_key: str,
         dest_bucket: str,
         content_type: Optional[str],
@@ -23,6 +24,7 @@ def __init__(
         max_attempts: int,
         base_backoff_seconds: float,
     ):
+        self.s3_client = s3_client
         self.shard_key = shard_key
         self.dest_bucket = dest_bucket
         self.content_type = content_type
@@ -34,9 +36,9 @@ def __init__(
         self.parts: List[Dict] = []
         self.buffer = bytearray()
 
-    async def start(self, s3):
+    async def start(self):
         self.upload_id = await mpu_create(
-            s3,
+            self.s3_client,
             self.dest_bucket,
             self.shard_key,
             max_attempts=self.max_attempts,
@@ -44,12 +46,12 @@ async def start(self, s3):
         )
         logger.info('Started MPU for %s (UploadId=%s)', self.shard_key, self.upload_id)
 
-    async def _flush_full_parts(self, s3):
+    async def _flush_full_parts(self):
         while len(self.buffer) >= self.min_part_size:
             chunk = self.buffer[: self.min_part_size]
             del self.buffer[: self.min_part_size]
             etag = await mpu_upload_part(
-                s3,
+                self.s3_client,
                 self.dest_bucket,
                 self.shard_key,
                 self.upload_id,
@@ -61,15 +63,15 @@ async def _flush_full_parts(self, s3):
             self.parts.append({'PartNumber': self.part_number, 'ETag': etag})
             self.part_number += 1
 
-    async def write(self, s3, data: bytes):
+    async def write(self, data: bytes):
         self.buffer.extend(data)
-        await self._flush_full_parts(s3)
+        await self._flush_full_parts()
 
-    async def close(self, s3):
+    async def close(self):
         try:
             if self.buffer:
                 etag = await mpu_upload_part(
-                    s3,
+                    self.s3_client,
                     self.dest_bucket,
                     self.shard_key,
                     self.upload_id,
@@ -84,7 +86,7 @@ async def close(self, s3):
 
             if self.parts:
                 await mpu_complete(
-                    s3,
+                    self.s3_client,
                     self.dest_bucket,
                     self.shard_key,
                     self.upload_id,
@@ -96,5 +98,7 @@ async def close(self, s3):
         except Exception:
             logger.exception('Completing MPU failed for %s; attempting abort.', self.shard_key)
             if self.upload_id:
-                await mpu_abort(s3, self.dest_bucket, self.shard_key, self.upload_id)
+                await mpu_abort(self.s3_client, self.dest_bucket, self.shard_key, self.upload_id)
             raise
+
+
diff --git a/cdx_toolkit/filter_warc/cdx_utils.py b/cdx_toolkit/filter_warc/cdx_utils.py
index ef8b92c..ea5a0f7 100644
--- a/cdx_toolkit/filter_warc/cdx_utils.py
+++ b/cdx_toolkit/filter_warc/cdx_utils.py
@@ -55,6 +55,7 @@ def iter_cdx_index_from_path(index_path: str, warc_download_prefix: str) -> Iter
     """
     logger.info('Reading CDX from %s', index_path)
 
+
     with fsspec.open(index_path, 'rt', compression='gzip' if index_path.endswith('.gz') else None) as f:
         for line in f:
             try:
diff --git a/cdx_toolkit/filter_warc/local_writer.py b/cdx_toolkit/filter_warc/local_writer.py
new file mode 100644
index 0000000..0ddd735
--- /dev/null
+++ b/cdx_toolkit/filter_warc/local_writer.py
@@ -0,0 +1,42 @@
+import aiofiles
+
+
+class LocalFileWriter:
+    """Async writer for local file system using aiofiles."""
+    
+    def __init__(
+        self,
+        file_path: str,
+        buffer_size: int = 8192,
+        mode: str = 'wb'
+    ):
+        self.file_path = file_path
+        self.buffer_size = buffer_size
+        self.mode = mode
+        self.file_handle = None
+        self.buffer = bytearray()
+
+    async def start(self):
+        self.file_handle = await aiofiles.open(self.file_path, self.mode)
+
+    async def write(self, data: bytes):
+        self.buffer.extend(data)
+        if len(self.buffer) >= self.buffer_size:
+            await self._flush()
+
+    async def _flush(self):
+        if self.buffer and self.file_handle:
+            await self.file_handle.write(bytes(self.buffer))
+            await self.file_handle.flush()
+            self.buffer.clear()
+
+    async def close(self):
+        try:
+            if self.buffer:
+                await self._flush()
+            if self.file_handle:
+                await self.file_handle.close()
+        except Exception:
+            if self.file_handle:
+                await self.file_handle.close()
+            raise
\ No newline at end of file
diff --git a/cdx_toolkit/filter_warc/warc_filter.py b/cdx_toolkit/filter_warc/warc_filter.py
new file mode 100644
index 0000000..965bfdf
--- /dev/null
+++ b/cdx_toolkit/filter_warc/warc_filter.py
@@ -0,0 +1,407 @@
+import asyncio
+from io import BytesIO
+import logging
+from typing import List, Optional, Dict
+
+import aioboto3
+from botocore.config import Config
+from warcio import WARCWriter
+
+from cdx_toolkit.filter_warc.aioboto3_utils import (
+    RangeJob,
+    RangePayload,
+    ThroughputTracker,
+    is_s3_url,
+    parse_s3_uri,
+    ranged_get_bytes,
+)
+from cdx_toolkit.filter_warc.aioboto3_warc_filter import create_new_writer_with_header
+from cdx_toolkit.filter_warc.aioboto3_writer import S3ShardWriter
+from cdx_toolkit.filter_warc.cdx_utils import (
+    iter_cdx_index_from_path,
+)
+from cdx_toolkit.filter_warc.warc_utils import get_bytes_from_warc_record, get_resource_record_from_path
+
+
+_STOP = object()
+
+logger = logging.getLogger(__name__)
+
+
+class WARCFilter:
+    """Filter WARC files using a three stage listner-producer-consumer pattern.
+
+    Filter targets:
+    - CDX index files from local or remote file system.
+
+    WARC reader:
+    - HTTP range reads
+    - S3 range reads
+
+    WARC writer:
+    - Local file system
+    - S3 using multi-part uploads
+    """
+    def __init__(
+        self,
+        index_paths: List[str],
+        prefix_path: str,
+        writer_info: Dict,
+        writer_subprefix: Optional[str] = None,
+        write_paths_as_resource_records: Optional[List[str]] = None,
+        write_paths_as_resource_records_metadata: Optional[List[str]] = None,
+        record_limit: int = 0,
+        log_every_n: int = 1000,
+        warc_download_prefix: Optional[str] = None,
+        n_parallel: int = 1,
+        max_attempts: int = 5,
+        base_backoff_seconds: float = 0.5,
+        writer_kwargs: Optional[Dict] = None,
+        range_jobs_queue_size: int = 1000,
+        warc_records_queue_size: int = 200,
+        fetcher_to_consumer_ratio: int = 6,
+        aws_region_name: str = 'us-east-1',
+        warc_version: str = '1.0',
+        content_type: Optional[str] = None,
+        min_part_size: int = 5 * 1024 * 1024,  # 5 MiB (for upload)
+        max_file_size: Optional[int] = 1 * 1024 * 1024 * 1024,  # 1 GiB (for WARC outputs)
+    ):
+        self.index_paths = index_paths
+        self.prefix_path = prefix_path
+        self.writer_info = writer_info
+        self.writer_subprefix = writer_subprefix
+        self.write_paths_as_resource_records = write_paths_as_resource_records
+        self.write_paths_as_resource_records_metadata = write_paths_as_resource_records_metadata
+        self.record_limit = record_limit
+        self.log_every_n = log_every_n
+        self.warc_download_prefix = warc_download_prefix
+        self.n_parallel = n_parallel
+        self.writer_kwargs = writer_kwargs
+        self.range_jobs_queue_size = range_jobs_queue_size
+        self.warc_records_queue_size = warc_records_queue_size
+        self.aws_region_name = aws_region_name
+        self.fetcher_to_consumer_ratio = fetcher_to_consumer_ratio
+        self.max_attempts = max_attempts
+        self.base_backoff_seconds = base_backoff_seconds
+        self.num_fetchers = n_parallel
+        self.num_consumers = max(int(self.num_fetchers / self.fetcher_to_consumer_ratio), 1)
+        self.gzip = self.index_paths[0].endswith('.gz') if self.index_paths else False
+        self.warc_version = warc_version
+        self.content_type = content_type
+        self.min_part_size = min_part_size
+        self.max_file_size = max_file_size
+
+    def filter(self) -> int:
+        """Perform the filtering process (calls async method via asyncio.run)."""
+        try:
+            return asyncio.run(self.filter_async())
+        except KeyboardInterrupt:
+            logger.warning('Interrupted by user.')
+
+        return -1
+
+    def needs_s3(self) -> bool:
+        """Returns true if S3 is needed at any stage."""
+        return (
+            (self.index_paths is not None and len(self.index_paths) > 0 and is_s3_url(self.index_paths[0]))  # stage 1
+            or is_s3_url(self.warc_download_prefix)  # stage 3
+            or is_s3_url(self.prefix_path)  # stage 3
+        )
+
+    def get_s3_client(self):
+        """Return s3 client if needed."""
+        if self.needs_s3():
+            session = aioboto3.Session()
+
+            return session.client('s3', config=self.get_boto3_config())
+        else:
+            return None
+        
+    async def filter_async(self) -> int:
+        """Filter process using a three stage approach (job generator, warc reader, warc writer)."""
+        range_jobs_queue: asyncio.Queue = asyncio.Queue(maxsize=self.range_jobs_queue_size)
+        warc_records_queue: asyncio.Queue = asyncio.Queue(maxsize=self.warc_records_queue_size)
+
+        async with self.get_s3_client() as s3_client:
+            # Fetch file paths and ranges (offset, length) from index files
+            logger.info('Starting lister, %d fetchers, %d consumers', self.num_fetchers, self.num_consumers)
+
+            job_generators = asyncio.create_task(
+                self.generate_range_jobs(
+                    range_jobs_queue,
+                    s3_client=s3_client,
+                )
+            )
+
+            # Read WARC records based on file paths and ranges
+            warc_readers = [
+                asyncio.create_task(
+                    self.read_warc_records(
+                        fetcher_id=i,
+                        range_jobs_queue=range_jobs_queue,
+                        warc_records_queue=warc_records_queue,
+                        s3_client=s3_client,
+                    )
+                )
+                for i in range(self.num_fetchers)
+            ]
+
+            # Write WARC records
+            warc_writers = [
+                asyncio.create_task(
+                    self.write_warc_records(
+                        consumer_id=i,
+                        warc_records_queue=warc_records_queue,
+                        s3_client=s3_client,
+                    )
+                )
+                for i in range(self.num_consumers)
+            ]
+
+            await job_generators
+            logger.info('Range jobs submitted, waiting for readers to finish')
+
+            await asyncio.gather(*warc_readers)
+            logger.info('All WARC readers completed')
+
+            # Send stop signals to consumers
+            for _ in range(self.num_consumers):
+                await warc_records_queue.put(_STOP)
+
+            consumer_results = await asyncio.gather(*warc_writers)
+            n_records = sum([result['stats']['total_requests'] for result in consumer_results])
+
+            logger.info('All WARC writers completed')
+
+        return n_records
+
+    async def generate_range_jobs(
+        self,
+        range_jobs_queue: asyncio.Queue,
+        s3_client=None,
+    ):
+        """Read the CDX paths, parse lines -> RangeJob (WARC files and offets) -> key_queue."""
+
+        logger.info('Range index limit: %i', self.record_limit)
+        count = 0
+
+        # Iterate over index files
+        for index_path in self.index_paths:
+            # Fetch range queries from index
+            try:
+                for warc_url, offset, length in iter_cdx_index_from_path(
+                    index_path, warc_download_prefix=self.warc_download_prefix
+                ):
+                    # Convert the CDX record back to a RangeJob
+                    job = RangeJob(url=warc_url, offset=offset, length=length)
+                    await range_jobs_queue.put(job)
+                    count += 1
+
+                    if self.record_limit > 0 and count >= self.record_limit:
+                        logger.warning('Index limit reached at %i', count)
+                        break
+
+            except Exception as e:
+                logger.error('Failed to read CDX index from %s: %s', index_path, e)
+
+            if self.record_limit > 0 and count >= self.record_limit:
+                logger.warning('Limit reached at %i', count)
+                break
+
+        # signal fetchers to stop
+        for _ in range(self.num_fetchers):
+            await range_jobs_queue.put(_STOP)
+
+        logger.info('Enqueued %d jobs from %s', count, index_path)
+
+    async def read_warc_records(
+        self,
+        fetcher_id: int,
+        range_jobs_queue: asyncio.Queue,
+        warc_records_queue: asyncio.Queue,
+        s3_client=None,
+    ):
+        """Read WARC records based on range jobs -> enqueue RangePayload."""
+        tracker = ThroughputTracker()
+        tracker.start()
+        counter = 0
+
+        while True:
+            job = await range_jobs_queue.get()
+            try:
+                if job is _STOP:
+                    stats = tracker.get_stats()
+                    logger.info(
+                        'WARC Fetcher %d stopping. Stats: %.1fs, %d requests, %.1f MB, %.2f MB/s, %.2f req/s',
+                        fetcher_id,
+                        stats['elapsed'],
+                        stats['total_requests'],
+                        stats['total_bytes'] / (1024 * 1024),
+                        stats['mb_per_sec'],
+                        stats['requests_per_sec'],
+                    )
+                    break  # Exit loop, but still execute finally block
+                assert isinstance(job, RangeJob)
+                data = await ranged_get_bytes(                    
+                    job,
+                    self.max_attempts,
+                    self.base_backoff_seconds,
+                    s3_client=s3_client,
+                )
+                tracker.add_bytes(len(data))
+                counter += 1
+
+                # Log progress every 10 items
+                if self.log_every_n > 0 and counter % self.log_every_n == 0:
+                    stats = tracker.get_stats()
+                    logger.info(
+                        'WARC Fetcher %d: %d items, %.1f MB, %.2f MB/s, %.2f req/s',
+                        fetcher_id,
+                        counter,
+                        stats['total_bytes'] / (1024 * 1024),
+                        stats['mb_per_sec'],
+                        stats['requests_per_sec'],
+                    )
+
+                await warc_records_queue.put(RangePayload(job=job, data=data))
+            except Exception:
+                logger.exception(
+                    'WARC Fetcher %d failed on %s/%s [%d,%d]',
+                    fetcher_id,
+                    getattr(job, 'bucket', '?'),
+                    getattr(job, 'key', '?'),
+                    getattr(job, 'offset', -1),
+                    getattr(job, 'length', -1),
+                )
+            finally:
+                range_jobs_queue.task_done()
+
+    async def write_warc_records(
+        self,
+        consumer_id: int,
+        warc_records_queue: asyncio.Queue,
+        s3_client=None,
+    ):
+        """Write WARC records. Each consumer owns ONE shard MPU and appends ranges to it."""
+        # File rotation tracking
+        current_file_sequence = 1
+        current_file_size = 0
+
+        new_writer_kwargs = dict(
+            s3_client=s3_client,
+            consumer_id=consumer_id,
+            output_path_prefix=self.prefix_path,
+            max_attempts=self.max_attempts,
+            base_backoff_seconds=self.base_backoff_seconds,
+            writer_info=self.writer_info,
+            warc_version=self.warc_version,
+            writer_subprefix=self.writer_subprefix,
+            gzip=self.gzip,
+            content_type=self.content_type,
+            min_part_size=self.min_part_size,
+        )
+
+        # Initialize first writer with header
+        writer, header_size = await create_new_writer_with_header(
+            sequence=current_file_sequence,
+            **new_writer_kwargs,
+        )
+        current_file_size = header_size
+
+        tracker = ThroughputTracker()
+        tracker.start()
+        counter = 0
+
+        # Write WARC resource records
+        if self.write_paths_as_resource_records:
+            logger.info(f'Writing {len(self.write_paths_as_resource_records)} resource records to WARC ... ')
+
+            # Resource records are written at the beginning the WARC file.
+            for i, resource_record_path in enumerate(self.write_paths_as_resource_records):
+                logger.info(f'Writing resource record from {resource_record_path} ...')
+                resource_record = get_resource_record_from_path(
+                    file_path=resource_record_path,
+                    metadata_path=(
+                        self.write_paths_as_resource_records_metadata[i]
+                        if self.write_paths_as_resource_records_metadata
+                        else None
+                    ),
+                )
+                record_data = get_bytes_from_warc_record(
+                    resource_record, warc_version=self.warc_version, gzip=self.gzip
+                )
+
+                await writer.write(record_data)
+
+                # Keep track but do not rotate resource records
+                current_file_size += len(record_data)
+
+            logger.info(f'Resource records added: {len(self.write_paths_as_resource_records)}')
+
+        try:
+            while True:
+                item = await warc_records_queue.get()
+                counter += 1
+                try:
+                    if item is _STOP:
+                        stats = tracker.get_stats()
+                        logger.info(
+                            'WARC writer %d stopping. Stats: %.1fs, %d items, %.1f MB written, %.2f MB/s write speed',
+                            consumer_id,
+                            stats['elapsed'],
+                            stats['total_requests'],
+                            stats['total_bytes'] / (1024 * 1024),
+                            stats['mb_per_sec'],
+                        )
+                        should_stop = True
+                    else:
+                        should_stop = False
+                        assert isinstance(item, RangePayload)
+
+                        # Check if we need to rotate files due to size limit
+                        if self.max_file_size and current_file_size + len(item.data) > self.max_file_size:
+                            await writer.close()
+                            current_file_sequence += 1
+
+                            writer, header_size = await create_new_writer_with_header(
+                                sequence=current_file_sequence,
+                                **new_writer_kwargs,
+                            )
+
+                            current_file_size = header_size
+                            logger.info(f'Rotated to new WARC file sequence {current_file_sequence} due to size limit')
+
+                        await writer.write(item.data)
+                        current_file_size += len(item.data)
+                        tracker.add_bytes(len(item.data))
+
+                        # Log progress every 10 items
+                        if self.log_every_n > 0 and counter % self.log_every_n == 0:
+                            stats = tracker.get_stats()
+                            logger.info(
+                                'WARC writer %d: %d items, %.1f MB written, %.2f MB/s',
+                                consumer_id,
+                                counter,
+                                stats['total_bytes'] / (1024 * 1024),
+                                stats['mb_per_sec'],
+                            )
+                except Exception:
+                    logger.exception('WARC writer %d failed on %s', consumer_id, getattr(item, 'job', None))
+                    should_stop = False
+                finally:
+                    warc_records_queue.task_done()
+
+                if should_stop:
+                    break
+        finally:
+            await writer.close()
+
+        return {'consumer_id': consumer_id, 'stats': tracker.get_stats()}
+
+    def get_boto3_config(self):
+        return Config(
+            region_name=self.aws_region_name,
+            retries={'max_attempts': max(2, self.max_attempts), 'mode': 'standard'},
+            connect_timeout=10,
+            read_timeout=120,
+        )
diff --git a/tests/filter_warc/test_aioboto3_writer.py b/tests/filter_warc/test_aioboto3_writer.py
index 3765981..c2f094b 100644
--- a/tests/filter_warc/test_aioboto3_writer.py
+++ b/tests/filter_warc/test_aioboto3_writer.py
@@ -2,7 +2,7 @@
 import asyncio
 from unittest.mock import AsyncMock, patch
 
-from cdx_toolkit.filter_warc.aioboto3_writer import ShardWriter
+from cdx_toolkit.filter_warc.aioboto3_writer import S3ShardWriter
 
 
 def test_shard_writer_init():
@@ -14,7 +14,7 @@ def test_shard_writer_init():
     max_attempts = 3
     base_backoff_seconds = 0.1
 
-    writer = ShardWriter(
+    writer = S3ShardWriter(
         shard_key=shard_key,
         dest_bucket=dest_bucket,
         content_type=content_type,
@@ -43,7 +43,7 @@ async def run_test():
         with patch('cdx_toolkit.filter_warc.aioboto3_writer.mpu_create') as mock_mpu_create:
             mock_mpu_create.return_value = 'test-upload-id'
 
-            writer = ShardWriter(
+            writer = S3ShardWriter(
                 shard_key='test.warc.gz',
                 dest_bucket='test-bucket',
                 content_type='application/gzip',
@@ -71,7 +71,10 @@ def test_shard_writer_write_small_data():
     """Test ShardWriter write method with small data that stays in buffer."""
 
     async def run_test():
-        writer = ShardWriter(
+        mock_s3 = AsyncMock()
+
+        writer = S3ShardWriter(
+            s3_client=mock_s3,
             shard_key='test.warc.gz',
             dest_bucket='test-bucket',
             content_type='application/gzip',
@@ -80,10 +83,9 @@ async def run_test():
             base_backoff_seconds=0.1,
         )
 
-        mock_s3 = AsyncMock()
         small_data = b'small test data'
 
-        await writer.write(mock_s3, small_data)
+        await writer.write(small_data)
 
         # Data should be in buffer, no parts uploaded yet
         assert len(writer.buffer) == len(small_data)
@@ -101,7 +103,10 @@ async def run_test():
         with patch('cdx_toolkit.filter_warc.aioboto3_writer.mpu_upload_part') as mock_upload_part:
             mock_upload_part.return_value = 'test-etag-1'
 
-            writer = ShardWriter(
+            mock_s3 = AsyncMock()
+
+            writer = S3ShardWriter(
+                s3_client=mock_s3,
                 shard_key='test.warc.gz',
                 dest_bucket='test-bucket',
                 content_type='application/gzip',
@@ -111,10 +116,9 @@ async def run_test():
             )
             writer.upload_id = 'test-upload-id'
 
-            mock_s3 = AsyncMock()
             large_data = b'x' * 250  # 250 bytes, should create 2 parts
 
-            await writer.write(mock_s3, large_data)
+            await writer.write(large_data)
 
             # Should have uploaded 2 parts (100 bytes each) with 50 bytes remaining in buffer
             assert mock_upload_part.call_count == 2
@@ -137,7 +141,9 @@ async def run_test():
         with patch('cdx_toolkit.filter_warc.aioboto3_writer.mpu_upload_part') as mock_upload_part:
             mock_upload_part.return_value = 'test-etag-flush'
 
-            writer = ShardWriter(
+            mock_s3 = AsyncMock()
+            writer = S3ShardWriter(
+                s3_client=mock_s3,
                 shard_key='test.warc.gz',
                 dest_bucket='test-bucket',
                 content_type='application/gzip',
@@ -150,8 +156,7 @@ async def run_test():
             # Pre-fill buffer with 150 bytes (should create 3 parts of 50 bytes each)
             writer.buffer.extend(b'a' * 150)
 
-            mock_s3 = AsyncMock()
-            await writer._flush_full_parts(mock_s3)
+            await writer._flush_full_parts()
 
             # Should have uploaded 3 full parts, no remainder
             assert mock_upload_part.call_count == 3
@@ -175,7 +180,10 @@ async def run_test():
         ) as mock_complete:
             mock_upload_part.return_value = 'final-etag'
 
-            writer = ShardWriter(
+            mock_s3 = AsyncMock()
+
+            writer = S3ShardWriter(
+                s3_client=mock_s3,
                 shard_key='test.warc.gz',
                 dest_bucket='test-bucket',
                 content_type='application/gzip',
@@ -189,8 +197,7 @@ async def run_test():
             remaining_data = b'final chunk data'
             writer.buffer.extend(remaining_data)
 
-            mock_s3 = AsyncMock()
-            await writer.close(mock_s3)
+            await writer.close()
 
             # Should upload the final part and complete MPU
             mock_upload_part.assert_called_once_with(
@@ -228,7 +235,7 @@ async def run_test():
         with patch('cdx_toolkit.filter_warc.aioboto3_writer.mpu_upload_part') as mock_upload_part, patch(
             'cdx_toolkit.filter_warc.aioboto3_writer.mpu_complete'
         ) as mock_complete:
-            writer = ShardWriter(
+            writer = S3ShardWriter(
                 shard_key='test.warc.gz',
                 dest_bucket='test-bucket',
                 content_type='application/gzip',
@@ -263,7 +270,7 @@ async def run_test():
             mock_upload_part.return_value = 'error-etag'
             mock_complete.side_effect = Exception('Complete failed')
 
-            writer = ShardWriter(
+            writer = S3ShardWriter(
                 shard_key='test.warc.gz',
                 dest_bucket='test-bucket',
                 content_type='application/gzip',
diff --git a/tests/filter_warc/test_warc_filter.py b/tests/filter_warc/test_warc_filter.py
new file mode 100644
index 0000000..c0b62bc
--- /dev/null
+++ b/tests/filter_warc/test_warc_filter.py
@@ -0,0 +1,57 @@
+import asyncio
+from io import BytesIO
+
+import aioboto3
+
+from tests.conftest import requires_aws_s3, TEST_DATA_PATH
+
+from warcio import WARCWriter
+from cdx_toolkit.filter_warc.aioboto3_warc_filter import get_range_jobs_from_index_paths, write_warc, _STOP
+from cdx_toolkit.filter_warc.aioboto3_utils import RangePayload, parse_s3_uri
+from tests.filter_warc.test_warc_by_cdx import assert_cli_warc_by_cdx
+
+fixture_path = TEST_DATA_PATH / 'warc_by_cdx'
+aioboto3_warc_filename = 'TEST_warc_by_index-000000-001.extracted.warc.gz'  # due to parallel writer
+
+
+@requires_aws_s3
+def test_cli_warc_by_cdx_over_s3_to_s3_in_parallel_warc_filter(s3_tmpdir, caplog):
+    assert_cli_warc_by_cdx(
+        's3://commoncrawl',
+        base_prefix=s3_tmpdir,
+        caplog=caplog,
+        extra_args=[
+            '--parallel=3',
+            '--implementation=warc_filter',
+        ],
+        warc_filename=aioboto3_warc_filename,
+    )
+
+
+@requires_aws_s3
+def test_cli_warc_by_cdx_over_http_to_s3_in_parallel_warc_filter(s3_tmpdir, caplog):
+    assert_cli_warc_by_cdx(
+        'https://data.commoncrawl.org',
+        base_prefix=s3_tmpdir,
+        caplog=caplog,
+        extra_args=[
+            '--parallel=3',
+            '--implementation=warc_filter',
+        ],
+        warc_filename=aioboto3_warc_filename,
+    )
+
+
+@requires_aws_s3
+def test_cli_warc_by_cdx_over_s3_to_local_in_parallel_warc_filter(tmpdir, caplog):
+    assert_cli_warc_by_cdx(
+        's3://commoncrawl',
+        base_prefix=tmpdir,
+        caplog=caplog,
+        extra_args=[
+            '--parallel=3',
+            '--implementation=warc_filter',
+        ],
+        warc_filename=aioboto3_warc_filename,
+    )
+

From faca33e7599910ef82c88b2952cb52838d1367b7 Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Wed, 1 Oct 2025 19:14:12 +0200
Subject: [PATCH 45/74] WIP: unified implementation (2)

---
 cdx_toolkit/filter_warc/aioboto3_utils.py     |  9 +++-
 .../filter_warc/aioboto3_warc_filter.py       | 12 +++--
 cdx_toolkit/filter_warc/warc_filter.py        | 49 ++++++++++++-------
 3 files changed, 46 insertions(+), 24 deletions(-)

diff --git a/cdx_toolkit/filter_warc/aioboto3_utils.py b/cdx_toolkit/filter_warc/aioboto3_utils.py
index 3f74092..2e27e07 100644
--- a/cdx_toolkit/filter_warc/aioboto3_utils.py
+++ b/cdx_toolkit/filter_warc/aioboto3_utils.py
@@ -20,13 +20,15 @@ class ThroughputTracker:
     start_time: float = 0.0
     total_bytes: int = 0
     total_requests: int = 0
+    total_records: int = 0
 
     def start(self):
         self.start_time = time.time()
 
-    def add_bytes(self, bytes_count: int):
+    def add(self, bytes_count: int = 0, records_count: int = 0, requests_count: int = 1):
         self.total_bytes += bytes_count
-        self.total_requests += 1
+        self.total_requests += requests_count
+        self.total_records += records_count
 
     def get_stats(self) -> dict:
         elapsed = time.time() - self.start_time
@@ -35,9 +37,11 @@ def get_stats(self) -> dict:
             'elapsed': elapsed,
             'total_bytes': self.total_bytes,
             'total_requests': self.total_requests,
+            'total_records': self.total_records,
             'bytes_per_sec': self.total_bytes / elapsed if elapsed > 0 else 0,
             'mb_per_sec': (self.total_bytes / elapsed) / (1024 * 1024) if elapsed > 0 else 0,
             'requests_per_sec': self.total_requests / elapsed if elapsed > 0 else 0,
+            'records_per_sec': self.total_records / elapsed if elapsed > 0 else 0,
         }
 
 
@@ -47,6 +51,7 @@ class RangeJob:
     url: str
     offset: int
     length: int
+    records_count: int = 1
 
     def is_s3(self):
         return is_s3_url(self.url)
diff --git a/cdx_toolkit/filter_warc/aioboto3_warc_filter.py b/cdx_toolkit/filter_warc/aioboto3_warc_filter.py
index 205bb2e..73f8a96 100644
--- a/cdx_toolkit/filter_warc/aioboto3_warc_filter.py
+++ b/cdx_toolkit/filter_warc/aioboto3_warc_filter.py
@@ -152,15 +152,17 @@ async def filter_warc_by_cdx_via_aioboto3_async(
         await lister_task
         logger.info('Range jobs submitted, waiting for fetchers to finish')
 
-        await asyncio.gather(*fetchers)
+        fetcher_results = await asyncio.gather(*fetchers)
         logger.info('All WARC fetchers completed')
 
+        fetcher_total_requests = sum([result['stats']['total_requests'] for result in fetcher_results])
+
         # Send stop signals to consumers
         for _ in range(num_consumers):
             await item_queue.put(_STOP)
 
         consumer_results = await asyncio.gather(*consumers)
-        n_records = sum([result['stats']['total_requests'] for result in consumer_results])
+        n_records = sum([result['stats']['total_records'] for result in consumer_results])
 
         logger.info('All WARC writers completed')
 
@@ -187,7 +189,7 @@ async def get_range_jobs_from_index_paths(
                 index_path, warc_download_prefix=warc_download_prefix
             ):
                 # Convert the CDX record back to a RangeJob
-                job = RangeJob(url=warc_url, offset=offset, length=length)
+                job = RangeJob(url=warc_url, offset=offset, length=length, records_count=1)
                 await key_queue.put(job)
                 count += 1
 
@@ -245,7 +247,7 @@ async def fetch_warc_ranges(
                 base_backoff_seconds,
                 s3_client=s3,
             )
-            tracker.add_bytes(len(data))
+            tracker.add(bytes_count=len(data), records_count=job.records_count)
             counter += 1
 
             # Log progress every 10 items
@@ -467,7 +469,7 @@ async def write_warc(
 
                     await writer.write(item.data)
                     current_file_size += len(item.data)
-                    tracker.add_bytes(len(item.data))
+                    tracker.add(bytes_count=len(item.data), records_count=item.job.records_count)
 
                     # Log progress every 10 items
                     if log_every_n > 0 and counter % log_every_n == 0:
diff --git a/cdx_toolkit/filter_warc/warc_filter.py b/cdx_toolkit/filter_warc/warc_filter.py
index 965bfdf..c675525 100644
--- a/cdx_toolkit/filter_warc/warc_filter.py
+++ b/cdx_toolkit/filter_warc/warc_filter.py
@@ -1,22 +1,19 @@
 import asyncio
-from io import BytesIO
 import logging
+import statistics
 from typing import List, Optional, Dict
 
 import aioboto3
 from botocore.config import Config
-from warcio import WARCWriter
 
 from cdx_toolkit.filter_warc.aioboto3_utils import (
     RangeJob,
     RangePayload,
     ThroughputTracker,
     is_s3_url,
-    parse_s3_uri,
     ranged_get_bytes,
 )
 from cdx_toolkit.filter_warc.aioboto3_warc_filter import create_new_writer_with_header
-from cdx_toolkit.filter_warc.aioboto3_writer import S3ShardWriter
 from cdx_toolkit.filter_warc.cdx_utils import (
     iter_cdx_index_from_path,
 )
@@ -42,6 +39,7 @@ class WARCFilter:
     - Local file system
     - S3 using multi-part uploads
     """
+
     def __init__(
         self,
         index_paths: List[str],
@@ -116,7 +114,7 @@ def get_s3_client(self):
             return session.client('s3', config=self.get_boto3_config())
         else:
             return None
-        
+
     async def filter_async(self) -> int:
         """Filter process using a three stage approach (job generator, warc reader, warc writer)."""
         range_jobs_queue: asyncio.Queue = asyncio.Queue(maxsize=self.range_jobs_queue_size)
@@ -161,19 +159,34 @@ async def filter_async(self) -> int:
             await job_generators
             logger.info('Range jobs submitted, waiting for readers to finish')
 
-            await asyncio.gather(*warc_readers)
-            logger.info('All WARC readers completed')
+            readers_results = await asyncio.gather(*warc_readers)
+
+            readers_records = sum([result['stats']['total_records'] for result in readers_results])
+            readers_mb_per_sec = statistics.mean([result['stats']['mb_per_sec'] for result in readers_results])
+            readers_records_per_sec = statistics.mean(
+                [result['stats']['records_per_sec'] for result in readers_results]
+            )
+
+            logger.info(f'All WARC readers completed: {readers_records} records')
+            logger.info(f'Reader throughput: {readers_mb_per_sec:.2f} MB/s; {readers_records_per_sec:.2f} rec/s')
 
             # Send stop signals to consumers
             for _ in range(self.num_consumers):
                 await warc_records_queue.put(_STOP)
 
-            consumer_results = await asyncio.gather(*warc_writers)
-            n_records = sum([result['stats']['total_requests'] for result in consumer_results])
+            writers_results = await asyncio.gather(*warc_writers)
 
-            logger.info('All WARC writers completed')
+            writers_records = sum([result['stats']['total_records'] for result in writers_results])
+            writers_mb_per_sec = statistics.mean([result['stats']['mb_per_sec'] for result in writers_results])
+            writers_records_per_sec = statistics.mean(
+                [result['stats']['records_per_sec'] for result in writers_results]
+            )
+            # warc_writers_bytes = sum([result['stats']['total_bytes'] for result in consumer_results])
+
+            logger.info(f'All WARC writers completed: {writers_records} records')
+            logger.info(f'Writer throughput: {writers_mb_per_sec:.2f} MB/s; {writers_records_per_sec:.2f} r/s')
 
-        return n_records
+        return writers_records
 
     async def generate_range_jobs(
         self,
@@ -193,7 +206,7 @@ async def generate_range_jobs(
                     index_path, warc_download_prefix=self.warc_download_prefix
                 ):
                     # Convert the CDX record back to a RangeJob
-                    job = RangeJob(url=warc_url, offset=offset, length=length)
+                    job = RangeJob(url=warc_url, offset=offset, length=length, records_count=1)
                     await range_jobs_queue.put(job)
                     count += 1
 
@@ -220,7 +233,7 @@ async def read_warc_records(
         range_jobs_queue: asyncio.Queue,
         warc_records_queue: asyncio.Queue,
         s3_client=None,
-    ):
+    ) -> dict:
         """Read WARC records based on range jobs -> enqueue RangePayload."""
         tracker = ThroughputTracker()
         tracker.start()
@@ -242,13 +255,13 @@ async def read_warc_records(
                     )
                     break  # Exit loop, but still execute finally block
                 assert isinstance(job, RangeJob)
-                data = await ranged_get_bytes(                    
+                data = await ranged_get_bytes(
                     job,
                     self.max_attempts,
                     self.base_backoff_seconds,
                     s3_client=s3_client,
                 )
-                tracker.add_bytes(len(data))
+                tracker.add(bytes_count=len(data), records_count=job.records_count)
                 counter += 1
 
                 # Log progress every 10 items
@@ -276,12 +289,14 @@ async def read_warc_records(
             finally:
                 range_jobs_queue.task_done()
 
+        return {'fetcher_id': fetcher_id, 'stats': tracker.get_stats()}
+
     async def write_warc_records(
         self,
         consumer_id: int,
         warc_records_queue: asyncio.Queue,
         s3_client=None,
-    ):
+    ) -> dict:
         """Write WARC records. Each consumer owns ONE shard MPU and appends ranges to it."""
         # File rotation tracking
         current_file_sequence = 1
@@ -373,7 +388,7 @@ async def write_warc_records(
 
                         await writer.write(item.data)
                         current_file_size += len(item.data)
-                        tracker.add_bytes(len(item.data))
+                        tracker.add(bytes_count=len(item.data), records_count=item.job.records_count)
 
                         # Log progress every 10 items
                         if self.log_every_n > 0 and counter % self.log_every_n == 0:

From 9d03d8065b7d1fcc9126ec42c1ac6b603dbe5f89 Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Wed, 1 Oct 2025 20:40:23 +0200
Subject: [PATCH 46/74] WIP: unified implementation (3)

---
 cdx_toolkit/filter_cdx/__init__.py            |  54 +-
 cdx_toolkit/filter_cdx/args.py                |   6 -
 cdx_toolkit/filter_cdx/matcher.py             |  86 ---
 cdx_toolkit/filter_warc/__init__.py           |  72 +--
 cdx_toolkit/filter_warc/aioboto3_utils.py     | 219 --------
 .../filter_warc/aioboto3_warc_filter.py       | 495 ------------------
 cdx_toolkit/filter_warc/args.py               |  17 +-
 cdx_toolkit/filter_warc/cdx_utils.py          |   1 -
 cdx_toolkit/filter_warc/data_classes.py       |  97 ++++
 cdx_toolkit/filter_warc/fsspec_warc_filter.py | 181 -------
 cdx_toolkit/filter_warc/s3_utils.py           |  55 ++
 .../{aioboto3_writer.py => s3_writer.py}      |  80 ++-
 cdx_toolkit/filter_warc/warc_filter.py        | 179 ++++---
 cdx_toolkit/filter_warc/warc_utils.py         |  88 +++-
 requirements.txt                              |   1 +
 setup.py                                      |   2 +-
 tests/filter_cdx/test_filter_cdx.py           |   6 +-
 tests/filter_cdx/test_matcher.py              | 314 -----------
 tests/filter_warc/test_aioboto3_warcer.py     |  75 ---
 ...est_aioboto3_utils.py => test_s3_utils.py} |  39 +-
 ...t_aioboto3_writer.py => test_s3_writer.py} | 116 ++--
 tests/filter_warc/test_warc_by_cdx.py         |  41 +-
 .../filter_warc/test_warc_by_cdx_aioboto3.py  | 159 ------
 tests/filter_warc/test_warc_filter.py         |  15 -
 tests/filter_warc/test_warc_writer.py         |  30 +-
 25 files changed, 568 insertions(+), 1860 deletions(-)
 delete mode 100644 cdx_toolkit/filter_cdx/matcher.py
 delete mode 100644 cdx_toolkit/filter_warc/aioboto3_utils.py
 delete mode 100644 cdx_toolkit/filter_warc/aioboto3_warc_filter.py
 create mode 100644 cdx_toolkit/filter_warc/data_classes.py
 delete mode 100644 cdx_toolkit/filter_warc/fsspec_warc_filter.py
 create mode 100644 cdx_toolkit/filter_warc/s3_utils.py
 rename cdx_toolkit/filter_warc/{aioboto3_writer.py => s3_writer.py} (62%)
 delete mode 100644 tests/filter_cdx/test_matcher.py
 delete mode 100644 tests/filter_warc/test_aioboto3_warcer.py
 rename tests/filter_warc/{test_aioboto3_utils.py => test_s3_utils.py} (82%)
 rename tests/filter_warc/{test_aioboto3_writer.py => test_s3_writer.py} (78%)
 delete mode 100644 tests/filter_warc/test_warc_by_cdx_aioboto3.py

diff --git a/cdx_toolkit/filter_cdx/__init__.py b/cdx_toolkit/filter_cdx/__init__.py
index 1efebe6..0c8cb37 100644
--- a/cdx_toolkit/filter_cdx/__init__.py
+++ b/cdx_toolkit/filter_cdx/__init__.py
@@ -4,12 +4,12 @@
 import sys
 from concurrent.futures import ProcessPoolExecutor, as_completed
 from functools import partial
-from typing import List, Tuple
+from typing import List, Tuple, Union
 
 import fsspec
-from surt import surt
 
-from cdx_toolkit.filter_cdx.matcher import Matcher, TupleMatcher, TrieMatcher
+from url_is_in import URLMatcher, SURTMatcher
+
 
 
 logger = logging.getLogger(__name__)
@@ -50,25 +50,19 @@ def run_filter_cdx(args, cmdline: str):
     with filter_fs.open(filter_fs_path, 'rt') as input_f:
         include_prefixes = [line.strip() for line in input_f.readlines()]
 
-    # Convert to SURT if filter file contains URLs
+    logger.info(f'Loaded {len(include_prefixes):,} filter entries')
+
+    # Use matcher based on URL or SURT inputs
     if args.filter_type == 'url':
-        logger.info('Converting urls to surts ...')
-        include_surt_prefixes = [surt(url) for url in include_prefixes]
+        matcher = URLMatcher(include_prefixes, match_subdomains=True)
     else:
-        # Filter is already given as surts
-        include_surt_prefixes = include_prefixes
-
-    # Create matcher based on selected approach
-    matcher_classes = {
-        'trie': TrieMatcher,
-        'tuple': TupleMatcher,
-    }
+        matcher = SURTMatcher(include_prefixes, match_subdomains=True)
+
     limit = 0 if args.limit is None else args.limit
-    logger.info(f'Loaded {len(include_surt_prefixes):,} filter entries using {args.matching_approach} approach')
 
     # Process files in parallel
     total_lines_n, total_included_n, total_errors_n = filter_cdx(
-        matcher=matcher_classes[args.matching_approach](include_surt_prefixes),
+        matcher=matcher,
         input_paths=input_paths,
         output_paths=output_paths,
         limit=limit,
@@ -77,15 +71,11 @@ def run_filter_cdx(args, cmdline: str):
 
     # Calculate ratio safely to avoid division by zero
     ratio = total_included_n / total_lines_n if total_lines_n > 0 else 0.0
-    logger.info(
-        f'Filter statistics: {total_included_n} / {total_lines_n} lines ({ratio:.4f})'
-    )
-    logger.info(
-        f'Errors: {total_errors_n}'
-    )
+    logger.info(f'Filter statistics: {total_included_n} / {total_lines_n} lines ({ratio:.4f})')
+    logger.info(f'Errors: {total_errors_n}')
 
     if limit > 0 and total_included_n >= 0:
-        logger.info(f"Limit reached at {limit}")
+        logger.info(f'Limit reached at {limit}')
 
     # End timing and log execution time
     end_time = time.time()
@@ -95,7 +85,7 @@ def run_filter_cdx(args, cmdline: str):
 
 
 def filter_cdx(
-    matcher: Matcher,
+    matcher: Union[URLMatcher, SURTMatcher],
     input_paths: List[str],
     output_paths: List[str],
     n_parallel: int = 1,
@@ -124,9 +114,7 @@ def filter_cdx(
             input_path, output_path = future_to_paths[future]
             try:
                 lines_n, included_n = future.result()
-                logger.info(
-                    f'File statistics: included {total_included_n} / {total_lines_n} lines: {input_path}'
-                )
+                logger.info(f'File statistics: included {total_included_n} / {total_lines_n} lines: {input_path}')
 
                 total_lines_n += lines_n
                 total_included_n += included_n
@@ -155,7 +143,7 @@ def resolve_paths(input_base_path: str, input_glob: str, output_base_path: str):
     input_file_paths = []
     for input_path in input_fs_file_paths:
         # Get relative path from input_base_path without last slash
-        rel_path = input_path[len(input_fs_base_path)+1:]
+        rel_path = input_path[len(input_fs_base_path) + 1 :]
 
         # Create corresponding full input and output path
         # Use forward slashes for URL paths (S3, HTTP, etc.) to ensure cross-platform compatibility
@@ -176,7 +164,13 @@ def resolve_paths(input_base_path: str, input_glob: str, output_base_path: str):
     return input_file_paths, output_file_paths
 
 
-def _process_single_file(input_path, output_path, matcher, limit: int = 0, log_every_n: int = 100_000):
+def _process_single_file(
+    input_path: str,
+    output_path: str,
+    matcher: Union[SURTMatcher, URLMatcher],
+    limit: int = 0,
+    log_every_n: int = 100_000,
+):
     """Process a single input/output file pair. Returns (lines_n, included_n)."""
     lines_n = 0
     included_n = 0
@@ -203,7 +197,7 @@ def _process_single_file(input_path, output_path, matcher, limit: int = 0, log_e
                 lines_n += 1
 
                 # Use SURT matcher
-                include_record = matcher.matches(record_surt)
+                include_record = matcher.is_in(record_surt)
 
                 if include_record:
                     output_f.write(line)
diff --git a/cdx_toolkit/filter_cdx/args.py b/cdx_toolkit/filter_cdx/args.py
index 5e72553..03d6f9e 100644
--- a/cdx_toolkit/filter_cdx/args.py
+++ b/cdx_toolkit/filter_cdx/args.py
@@ -25,12 +25,6 @@ def add_filter_cdx_args(parser: argparse.ArgumentParser):
         '--input-glob',
         help="Glob pattern relative to input_base_path (e.g., '**/*.cdx.gz' or 'collections/*/indexes/*.gz')",
     )
-    parser.add_argument(
-        '--matching-approach',
-        choices=['trie', 'tuple'],
-        default='trie',
-        help='Matching approach to use (default: trie)',
-    )
     parser.add_argument(
         '--overwrite',
         action='store_true',
diff --git a/cdx_toolkit/filter_cdx/matcher.py b/cdx_toolkit/filter_cdx/matcher.py
deleted file mode 100644
index d6da16d..0000000
--- a/cdx_toolkit/filter_cdx/matcher.py
+++ /dev/null
@@ -1,86 +0,0 @@
-from typing import List, Tuple, Union
-import logging
-from abc import ABC, abstractmethod
-
-logger = logging.getLogger(__name__)
-
-
-class Matcher(ABC):
-    """Base class for all matching approaches."""
-
-    @abstractmethod
-    def __init__(self, prefixes: Union[Tuple[str], List[str]]):
-        """Initialize the matcher with a list of prefixes."""
-        pass
-
-    @abstractmethod
-    def matches(self, text: str) -> bool:
-        """Check if text starts with any of the prefixes."""
-        pass
-
-    @staticmethod
-    def validate_prefixes(prefixes: Union[Tuple[str], List[str]]) -> Tuple[str]:
-        valid_prefixes = []
-
-        for prefix in prefixes:
-            if prefix is None or not isinstance(prefix, str):
-                raise ValueError('Prefix must be a string and not none.')
-
-            # remove white spaces
-            prefix = prefix.strip()
-
-            if len(prefix) == 0:
-                raise ValueError('Empty prefixes are not allowed')
-
-            valid_prefixes.append(prefix)
-
-        return tuple(valid_prefixes)
-
-
-class TrieNode:
-    def __init__(self):
-        self.children = {}
-        self.is_end = False
-
-
-class TrieMatcher(Matcher):
-    """Trie-based matching approach."""
-
-    def __init__(self, prefixes: Union[Tuple[str], List[str]]):
-        logger.info(f'Building trie matcher based on {len(prefixes):,} inputs')
-        self.root = self._build_trie(self.validate_prefixes(prefixes))
-
-    def _build_trie(self, prefixes: Tuple[str]):
-        """Build a trie from a collection of prefixes."""
-        root = TrieNode()
-        for prefix in prefixes:
-            node = root
-            for char in prefix:
-                if char not in node.children:
-                    node.children[char] = TrieNode()
-                node = node.children[char]
-            node.is_end = True
-        return root
-
-    def matches(self, text: str) -> bool:
-        """Check if text starts with any prefix in the trie."""
-        node = self.root
-        for char in text:
-            if char not in node.children:
-                return False
-            node = node.children[char]
-            if node.is_end:
-                return True
-        return False
-
-
-class TupleMatcher(Matcher):
-    """Tuple-based matching approach using the built-in method `str.startswith`."""
-
-    def __init__(self, prefixes: Union[Tuple[str], List[str]]):
-        logger.info(f'Building Tuple matcher based on {len(prefixes):,} inputs')
-        self.prefixes_Tuple = self.validate_prefixes(prefixes)
-
-    def matches(self, text: str) -> bool:
-        """Check if text starts with any prefix in the Tuple."""
-        return text.startswith(self.prefixes_Tuple)
diff --git a/cdx_toolkit/filter_warc/__init__.py b/cdx_toolkit/filter_warc/__init__.py
index a7733b6..6b38a8f 100644
--- a/cdx_toolkit/filter_warc/__init__.py
+++ b/cdx_toolkit/filter_warc/__init__.py
@@ -1,21 +1,17 @@
 import logging
 import sys
 import time
-from typing import List, Literal, Optional
+from typing import List, Optional
 
 import fsspec
 
 
 from cdx_toolkit.utils import get_version, setup
-from cdx_toolkit.filter_warc.aioboto3_warc_filter import filter_warc_by_cdx_via_aioboto3
-from cdx_toolkit.filter_warc.fsspec_warc_filter import filter_warc_by_cdx_via_fsspec
 
 from cdx_toolkit.filter_warc.warc_filter import WARCFilter
 
 logger = logging.getLogger(__name__)
 
-ImplementationType = Literal['fsspec', 'aioboto3', 'warc_filter']
-
 
 def run_warcer_by_cdx(args, cmdline):
     """Like warcer but fetches WARC records based on one or more CDX index files.
@@ -35,8 +31,6 @@ def run_warcer_by_cdx(args, cmdline):
     # Start timing
     start_time = time.time()
 
-    implementation: ImplementationType = args.implementation
-
     write_paths_as_resource_records = args.write_paths_as_resource_records
     write_paths_as_resource_records_metadata = args.write_paths_as_resource_records_metadata
 
@@ -81,56 +75,20 @@ def run_warcer_by_cdx(args, cmdline):
         args.cdx_glob,
     )
 
-    if implementation == 'fsspec':
-        records_n = filter_warc_by_cdx_via_fsspec(
-            index_paths=cdx_paths,
-            prefix_path=prefix_path,
-            writer_info=info,
-            writer_subprefix=args.subprefix,
-            write_paths_as_resource_records=write_paths_as_resource_records,
-            write_paths_as_resource_records_metadata=write_paths_as_resource_records_metadata,
-            limit=limit,
-            log_every_n=log_every_n,
-            warc_download_prefix=cdx.warc_download_prefix,
-            n_parallel=n_parallel,
-            writer_kwargs=writer_kwargs,
-        )
-    elif implementation == 'aioboto3':
-        if sys.version_info.major < 3 or (sys.version_info.major >= 3 and sys.version_info.minor < 9):
-            logger.error('The `aioboto3` implementation requires Python version >= 3.9')
-            sys.exit(1)
-
-        records_n = filter_warc_by_cdx_via_aioboto3(
-            index_paths=cdx_paths,
-            prefix_path=prefix_path,
-            writer_info=info,
-            writer_subprefix=args.subprefix,
-            write_paths_as_resource_records=write_paths_as_resource_records,
-            write_paths_as_resource_records_metadata=write_paths_as_resource_records_metadata,
-            limit=limit,
-            log_every_n=log_every_n,
-            warc_download_prefix=cdx.warc_download_prefix,
-            n_parallel=n_parallel,
-            writer_kwargs=writer_kwargs,
-        )
-    elif implementation == "warc_filter":
-
-        warc_filter = WARCFilter(
-            index_paths=cdx_paths,
-            prefix_path=prefix_path,
-            writer_info=info,
-            writer_subprefix=args.subprefix,
-            write_paths_as_resource_records=write_paths_as_resource_records,
-            write_paths_as_resource_records_metadata=write_paths_as_resource_records_metadata,
-            record_limit=limit,
-            log_every_n=log_every_n,
-            warc_download_prefix=cdx.warc_download_prefix,
-            n_parallel=n_parallel,
-            writer_kwargs=writer_kwargs,
-        )
-        records_n = warc_filter.filter()
-    else:
-        raise ValueError(f'Invalid implementation: {implementation}')
+    warc_filter = WARCFilter(
+        index_paths=cdx_paths,
+        prefix_path=prefix_path,
+        writer_info=info,
+        writer_subprefix=args.subprefix,
+        write_paths_as_resource_records=write_paths_as_resource_records,
+        write_paths_as_resource_records_metadata=write_paths_as_resource_records_metadata,
+        record_limit=limit,
+        log_every_n=log_every_n,
+        warc_download_prefix=cdx.warc_download_prefix,
+        n_parallel=n_parallel,
+        writer_kwargs=writer_kwargs,
+    )
+    records_n = warc_filter.filter()
 
     logger.info('WARC records extracted: %i', records_n)
 
diff --git a/cdx_toolkit/filter_warc/aioboto3_utils.py b/cdx_toolkit/filter_warc/aioboto3_utils.py
deleted file mode 100644
index 2e27e07..0000000
--- a/cdx_toolkit/filter_warc/aioboto3_utils.py
+++ /dev/null
@@ -1,219 +0,0 @@
-import asyncio
-import logging
-import time
-from dataclasses import dataclass
-from typing import Dict, List, Optional, Tuple, Union
-from os import urandom
-
-from botocore.exceptions import ClientError, EndpointConnectionError
-
-from cdx_toolkit.myrequests import myrequests_get
-
-
-logger = logging.getLogger(__name__)
-
-
-@dataclass
-class ThroughputTracker:
-    """Track throughput metrics for fetchers and consumers."""
-
-    start_time: float = 0.0
-    total_bytes: int = 0
-    total_requests: int = 0
-    total_records: int = 0
-
-    def start(self):
-        self.start_time = time.time()
-
-    def add(self, bytes_count: int = 0, records_count: int = 0, requests_count: int = 1):
-        self.total_bytes += bytes_count
-        self.total_requests += requests_count
-        self.total_records += records_count
-
-    def get_stats(self) -> dict:
-        elapsed = time.time() - self.start_time
-
-        return {
-            'elapsed': elapsed,
-            'total_bytes': self.total_bytes,
-            'total_requests': self.total_requests,
-            'total_records': self.total_records,
-            'bytes_per_sec': self.total_bytes / elapsed if elapsed > 0 else 0,
-            'mb_per_sec': (self.total_bytes / elapsed) / (1024 * 1024) if elapsed > 0 else 0,
-            'requests_per_sec': self.total_requests / elapsed if elapsed > 0 else 0,
-            'records_per_sec': self.total_records / elapsed if elapsed > 0 else 0,
-        }
-
-
-@dataclass(frozen=True)
-class RangeJob:
-    """Defines a S3 or HTTP range read request."""
-    url: str
-    offset: int
-    length: int
-    records_count: int = 1
-
-    def is_s3(self):
-        return is_s3_url(self.url)
-
-    def get_s3_bucket_and_key(self) -> Tuple[str, str]:
-        if self.is_s3():
-            return parse_s3_uri(self.url)
-        else:
-            raise ValueError("Cannot get bucket and key from a HTTP job")
-
-
-@dataclass(frozen=True)
-class RangePayload:
-    """Bytes output from S3 range read."""
-    job: RangeJob
-    data: bytes
-
-
-def _backoff(attempt: int, base_backoff_seconds: float) -> float:
-    """Time to sleep based on number of attempts"""
-    base = base_backoff_seconds * (2 ** (attempt - 1))
-
-    # Add random jitter between 80-120% of base delay
-    return max(0.05, base * (0.8 + 0.4 * urandom(1)[0] / 255))
-
-
-def parse_s3_uri(uri: str) -> Tuple[str, str]:
-    """Parse a S3 URI and return bucket and prefix."""
-    if not uri.startswith('s3://'):
-        raise ValueError(f'Not an S3 URI: {uri}')
-    rest = uri[5:]
-    i = rest.find('/')
-    if i <= 0 or i == len(rest) - 1:
-        raise ValueError(f'Malformed S3 URI: {uri}')
-    return rest[:i], rest[i + 1 :]
-
-
-async def with_retries(coro_factory, *, op_name: str, max_attempts: int, base_backoff_seconds: float):
-    last_exc = None
-    for attempt in range(1, max_attempts + 1):
-        try:
-            return await coro_factory()
-        except (TimeoutError, ClientError, EndpointConnectionError) as exc:
-            last_exc = exc
-            if attempt >= max_attempts:
-                logger.error('%s failed after %d attempts: %r', op_name, attempt, exc)
-                break
-            sleep_s = _backoff(attempt, base_backoff_seconds)
-            logger.warning(
-                '%s failed (attempt %d/%d) – retrying in %.2fs',
-                op_name,
-                attempt,
-                max_attempts,
-                sleep_s,
-            )
-            await asyncio.sleep(sleep_s)
-    raise last_exc
-
-
-async def ranged_get_bytes(
-    job: RangeJob,
-    max_attempts: int,
-    base_backoff_seconds: float,
-    s3_client=None,
-) -> bytes:
-    """Ranged get request to S3 with retries and backoff or HTTP."""
-    offset = job.offset
-    length = job.length
-
-    end = offset + length - 1  # inclusive
-
-    if job.is_s3():
-        # read from S3
-        bucket, key = job.get_s3_bucket_and_key()
-        resp = await with_retries(
-            lambda: s3_client.get_object(Bucket=bucket, Key=key, Range=f'bytes={offset}-{end}'),
-            op_name=f'ranged_get {bucket}/{key}[{offset}:{end}]',
-            max_attempts=max_attempts,
-            base_backoff_seconds=base_backoff_seconds,
-        )
-        return await resp['Body'].read()
-
-    else:
-        # read from HTTP
-        headers = {'Range': 'bytes={}-{}'.format(offset, end)}
-
-        resp = myrequests_get(job.url, headers=headers)
-        return resp.content
-
-
-async def mpu_create(
-    s3,
-    bucket: str,
-    key: str,
-    *,
-    max_attempts: int,
-    base_backoff_seconds: float,
-):
-    """Create multi part upload to S3."""
-    kwargs = {'Bucket': bucket, 'Key': key}
-    resp = await with_retries(
-        lambda: s3.create_multipart_upload(**kwargs),
-        op_name=f'create_multipart_upload {bucket}/{key}',
-        max_attempts=max_attempts,
-        base_backoff_seconds=base_backoff_seconds,
-    )
-    return resp['UploadId']
-
-
-async def mpu_upload_part(
-    s3,
-    bucket: str,
-    key: str,
-    upload_id: str,
-    part_number: int,
-    body: bytes,
-    max_attempts: int,
-    base_backoff_seconds: float,
-) -> str:
-    """Upload a part of a multi-part upload to S3."""
-    resp = await with_retries(
-        lambda: s3.upload_part(
-            Bucket=bucket,
-            Key=key,
-            UploadId=upload_id,
-            PartNumber=part_number,
-            Body=body,
-        ),
-        op_name=f'upload_part {bucket}/{key}#{part_number}',
-        max_attempts=max_attempts,
-        base_backoff_seconds=base_backoff_seconds,
-    )
-    return resp['ETag']
-
-
-async def mpu_complete(
-    s3,
-    bucket: str,
-    key: str,
-    upload_id: str,
-    parts: List[Dict],
-    max_attempts: int,
-    base_backoff_seconds: float,
-):
-    """Send complete for multi-part upload."""
-    await with_retries(
-        lambda: s3.complete_multipart_upload(
-            Bucket=bucket, Key=key, UploadId=upload_id, MultipartUpload={'Parts': parts}
-        ),
-        op_name=f'complete_multipart_upload {bucket}/{key}',
-        max_attempts=max_attempts,
-        base_backoff_seconds=base_backoff_seconds,
-    )
-
-
-async def mpu_abort(s3, bucket: str, key: str, upload_id: str):
-    """Abort mult-part upload."""
-    try:
-        await s3.abort_multipart_upload(Bucket=bucket, Key=key, UploadId=upload_id)
-    except Exception:
-        logger.exception('Failed to abort MPU %s on %s/%s', upload_id, bucket, key)
-
-
-def is_s3_url(url: str) -> bool:
-    return url.startswith("s3:/")
diff --git a/cdx_toolkit/filter_warc/aioboto3_warc_filter.py b/cdx_toolkit/filter_warc/aioboto3_warc_filter.py
deleted file mode 100644
index 73f8a96..0000000
--- a/cdx_toolkit/filter_warc/aioboto3_warc_filter.py
+++ /dev/null
@@ -1,495 +0,0 @@
-import asyncio
-from io import BytesIO
-import logging
-from typing import List, Optional, Dict
-
-import aioboto3
-from botocore.config import Config
-from warcio import WARCWriter
-
-from cdx_toolkit.filter_warc.aioboto3_utils import (
-    RangeJob,
-    RangePayload,
-    ThroughputTracker,
-    is_s3_url,
-    parse_s3_uri,
-    ranged_get_bytes,
-)
-from cdx_toolkit.filter_warc.aioboto3_writer import S3ShardWriter
-from cdx_toolkit.filter_warc.cdx_utils import (
-    iter_cdx_index_from_path,
-)
-from cdx_toolkit.filter_warc.local_writer import LocalFileWriter
-from cdx_toolkit.filter_warc.warc_utils import get_bytes_from_warc_record, get_resource_record_from_path
-
-
-_STOP = object()
-
-logger = logging.getLogger(__name__)
-
-
-def filter_warc_by_cdx_via_aioboto3(
-    index_paths: List[str],
-    prefix_path: str,
-    writer_info: Dict,
-    writer_subprefix: Optional[str] = None,
-    write_paths_as_resource_records: Optional[List[str]] = None,
-    write_paths_as_resource_records_metadata: Optional[List[str]] = None,
-    limit: int = 0,
-    log_every_n: int = 1000,
-    warc_download_prefix: Optional[str] = None,
-    n_parallel: int = 1,
-    writer_kwargs: Optional[Dict] = None,
-) -> int:
-    try:
-        return asyncio.run(
-            filter_warc_by_cdx_via_aioboto3_async(
-                index_paths=index_paths,
-                prefix_path=prefix_path,
-                writer_info=writer_info,
-                writer_subprefix=writer_subprefix,
-                write_paths_as_resource_records=write_paths_as_resource_records,
-                write_paths_as_resource_records_metadata=write_paths_as_resource_records_metadata,
-                limit=limit,
-                log_every_n=log_every_n,
-                warc_download_prefix=warc_download_prefix,
-                writer_kwargs=writer_kwargs,
-                n_parallel=n_parallel,
-            )
-        )
-    except KeyboardInterrupt:
-        logger.warning('Interrupted by user.')
-
-    return -1
-
-
-async def filter_warc_by_cdx_via_aioboto3_async(
-    index_paths: List[str],
-    prefix_path: str,
-    writer_info: Dict,
-    writer_subprefix: Optional[str] = None,
-    write_paths_as_resource_records: Optional[List[str]] = None,
-    write_paths_as_resource_records_metadata: Optional[List[str]] = None,
-    limit: int = 0,
-    log_every_n: int = 1000,
-    warc_download_prefix: Optional[str] = None,
-    n_parallel: int = 1,
-    writer_kwargs: Optional[Dict] = None,
-    max_attempts: int = 5,
-    key_queue_size: int = 1000,
-    item_queue_size: int = 200,
-    base_backoff_seconds=0.5,
-    s3_region_name: str = 'us-east-1',
-) -> int:
-    n_records = 0
-    fetcher_to_consumer_ratio = 6
-    num_fetchers = n_parallel
-    num_consumers = max(int(num_fetchers / fetcher_to_consumer_ratio), 1)
-
-    key_queue: asyncio.Queue = asyncio.Queue(maxsize=key_queue_size)
-    item_queue: asyncio.Queue = asyncio.Queue(maxsize=item_queue_size)
-
-    boto_cfg = Config(
-        region_name=s3_region_name,
-        retries={'max_attempts': max(2, max_attempts), 'mode': 'standard'},
-        connect_timeout=10,
-        read_timeout=120,
-    )
-
-    session = aioboto3.Session()
-
-    async with session.client('s3', config=boto_cfg) as s3:
-        # Fetch file paths and ranges (offset, length) from index files
-        logger.info('Starting lister, %d fetchers, %d consumers', num_fetchers, num_consumers)
-        lister_task = asyncio.create_task(
-            get_range_jobs_from_index_paths(
-                key_queue=key_queue,
-                index_paths=index_paths,
-                warc_download_prefix=warc_download_prefix,
-                num_fetchers=num_fetchers,
-                limit=limit,
-            )
-        )
-
-        # Read WARC records based on file paths and ranges
-        fetchers = [
-            asyncio.create_task(
-                fetch_warc_ranges(
-                    fetcher_id=i,
-                    key_queue=key_queue,
-                    item_queue=item_queue,
-                    s3=s3,
-                    max_attempts=max_attempts,
-                    base_backoff_seconds=base_backoff_seconds,
-                    log_every_n=log_every_n,
-                )
-            )
-            for i in range(num_fetchers)
-        ]
-
-        # Write WARC records
-        consumers = [
-            asyncio.create_task(
-                write_warc(
-                    consumer_id=i,
-                    item_queue=item_queue,
-                    s3=s3,
-                    prefix_path=prefix_path,
-                    max_attempts=max_attempts,
-                    base_backoff_seconds=base_backoff_seconds,
-                    write_paths_as_resource_records=write_paths_as_resource_records,
-                    write_paths_as_resource_records_metadata=write_paths_as_resource_records_metadata,
-                    writer_info=writer_info,
-                    writer_subprefix=writer_subprefix,
-                    writer_kwargs=writer_kwargs,
-                    log_every_n=log_every_n,
-                    gzip=index_paths[0].endswith('.gz') if index_paths else False,
-                )
-            )
-            for i in range(num_consumers)
-        ]
-
-        await lister_task
-        logger.info('Range jobs submitted, waiting for fetchers to finish')
-
-        fetcher_results = await asyncio.gather(*fetchers)
-        logger.info('All WARC fetchers completed')
-
-        fetcher_total_requests = sum([result['stats']['total_requests'] for result in fetcher_results])
-
-        # Send stop signals to consumers
-        for _ in range(num_consumers):
-            await item_queue.put(_STOP)
-
-        consumer_results = await asyncio.gather(*consumers)
-        n_records = sum([result['stats']['total_records'] for result in consumer_results])
-
-        logger.info('All WARC writers completed')
-
-    return n_records
-
-
-async def get_range_jobs_from_index_paths(
-    key_queue: asyncio.Queue,
-    index_paths: List[str],
-    warc_download_prefix: str,
-    num_fetchers: int,
-    limit: int = 0,
-):
-    """Stage 1: stream the CDX paths, parse lines -> RangeJob (WARC files and offets) -> key_queue."""
-
-    logger.info('Range index limit: %i', limit)
-    count = 0
-
-    # Iterate over index files
-    for index_path in index_paths:
-        # Fetch range queries from index
-        try:
-            for warc_url, offset, length in iter_cdx_index_from_path(
-                index_path, warc_download_prefix=warc_download_prefix
-            ):
-                # Convert the CDX record back to a RangeJob
-                job = RangeJob(url=warc_url, offset=offset, length=length, records_count=1)
-                await key_queue.put(job)
-                count += 1
-
-                if limit > 0 and count >= limit:
-                    logger.warning('Index limit reached at %i', count)
-                    break
-
-        except Exception as e:
-            logger.error('Failed to read CDX index from %s: %s', index_path, e)
-
-        if limit > 0 and count >= limit:
-            logger.warning('Limit reached at %i', count)
-            break
-
-    # signal fetchers to stop
-    for _ in range(num_fetchers):
-        await key_queue.put(_STOP)
-
-    logger.info('Enqueued %d jobs from %s', count, index_path)
-
-
-async def fetch_warc_ranges(
-    fetcher_id: int,
-    key_queue: asyncio.Queue,
-    item_queue: asyncio.Queue,
-    s3,
-    max_attempts: int,
-    base_backoff_seconds: float,
-    log_every_n: int = 1000,
-):
-    """Stage 2: ranged GET per job -> enqueue RangePayload."""
-    tracker = ThroughputTracker()
-    tracker.start()
-    counter = 0
-
-    while True:
-        job = await key_queue.get()
-        try:
-            if job is _STOP:
-                stats = tracker.get_stats()
-                logger.info(
-                    'WARC Fetcher %d stopping. Stats: %.1fs, %d requests, %.1f MB, %.2f MB/s, %.2f req/s',
-                    fetcher_id,
-                    stats['elapsed'],
-                    stats['total_requests'],
-                    stats['total_bytes'] / (1024 * 1024),
-                    stats['mb_per_sec'],
-                    stats['requests_per_sec'],
-                )
-                break  # Exit loop, but still execute finally block
-            assert isinstance(job, RangeJob)
-            data = await ranged_get_bytes(
-                job,
-                max_attempts,
-                base_backoff_seconds,
-                s3_client=s3,
-            )
-            tracker.add(bytes_count=len(data), records_count=job.records_count)
-            counter += 1
-
-            # Log progress every 10 items
-            if log_every_n > 0 and counter % log_every_n == 0:
-                stats = tracker.get_stats()
-                logger.info(
-                    'WARC Fetcher %d: %d items, %.1f MB, %.2f MB/s, %.2f req/s',
-                    fetcher_id,
-                    counter,
-                    stats['total_bytes'] / (1024 * 1024),
-                    stats['mb_per_sec'],
-                    stats['requests_per_sec'],
-                )
-
-            await item_queue.put(RangePayload(job=job, data=data))
-        except Exception:
-            logger.exception(
-                'WARC Fetcher %d failed on %s/%s [%d,%d]',
-                fetcher_id,
-                getattr(job, 'bucket', '?'),
-                getattr(job, 'key', '?'),
-                getattr(job, 'offset', -1),
-                getattr(job, 'length', -1),
-            )
-        finally:
-            key_queue.task_done()
-
-
-def generate_warc_filename(
-    dest_prefix: str,
-    consumer_id: int,
-    sequence: int,
-    writer_subprefix: Optional[str] = None,
-    gzip: bool = False,
-) -> str:
-    file_name = dest_prefix + '-'
-    if writer_subprefix is not None:
-        file_name += writer_subprefix + '-'
-    file_name += '{:06d}-{:03d}'.format(consumer_id, sequence) + '.extracted.warc'
-    if gzip:
-        file_name += '.gz'
-
-    return file_name
-
-
-async def create_new_writer_with_header(
-    consumer_id: int,
-    sequence: int,
-    output_path_prefix: str,
-    max_attempts: int,
-    base_backoff_seconds: float,
-    min_part_size: int,
-    writer_info: Dict,
-    warc_version: str = '1.0',
-    writer_subprefix: Optional[str] = None,
-    gzip: bool = False,
-    content_type: Optional[str] = None,
-    s3_client=None,
-):
-    if is_s3_url(output_path_prefix):
-        dest_bucket, dest_prefix = parse_s3_uri(output_path_prefix)
-
-        filename = generate_warc_filename(
-            dest_prefix=dest_prefix,
-            consumer_id=consumer_id,
-            sequence=sequence,
-            writer_subprefix=writer_subprefix,
-            gzip=gzip,
-        )
-
-        new_writer = S3ShardWriter(
-            s3_client,
-            filename,
-            dest_bucket,
-            content_type,
-            min_part_size,
-            max_attempts,
-            base_backoff_seconds,
-        )
-
-    else:
-        # local file system
-        filename = generate_warc_filename(
-            dest_prefix=output_path_prefix,
-            consumer_id=consumer_id,
-            sequence=sequence,
-            writer_subprefix=writer_subprefix,
-            gzip=gzip,
-        )
-
-        new_writer = LocalFileWriter(
-            file_path=filename,
-        )
-
-    # Initialize writer
-    await new_writer.start()
-
-    # Write WARC header
-    buffer = BytesIO()
-    warc_writer = WARCWriter(buffer, gzip=gzip, warc_version=warc_version)
-    warcinfo = warc_writer.create_warcinfo_record(filename, writer_info)
-    warc_writer.write_record(warcinfo)
-    header_data = buffer.getvalue()
-    await new_writer.write(header_data)
-
-    return new_writer, len(header_data)
-
-
-async def write_warc(
-    consumer_id: int,
-    item_queue: asyncio.Queue,
-    s3,
-    max_attempts: int,
-    base_backoff_seconds: float,
-    prefix_path: str,
-    writer_info: Dict,
-    writer_subprefix: Optional[str] = None,
-    write_paths_as_resource_records: Optional[List[str]] = None,
-    write_paths_as_resource_records_metadata: Optional[List[str]] = None,
-    writer_kwargs: Optional[Dict] = None,
-    warc_version: str = '1.0',
-    log_every_n: int = 1000,
-    gzip: bool = False,
-    content_type=None,
-    min_part_size: int = 5 * 1024 * 1024,  # 5 MiB (for upload)
-    max_file_size: Optional[int] = 1 * 1024 * 1024 * 1024,  # 1 GiB (for WARC outputs)
-):
-    """Stage 3: Write WARC. Each consumer owns ONE shard MPU and appends ranges to it."""
-
-    # File rotation tracking
-    current_file_sequence = 1
-    current_file_size = 0
-
-    # Initialize first writer with header
-    writer, header_size = await create_new_writer_with_header(
-        s3_client=s3,
-        consumer_id=consumer_id,
-        sequence=current_file_sequence,
-        output_path_prefix=prefix_path,
-        max_attempts=max_attempts,
-        base_backoff_seconds=base_backoff_seconds,
-        writer_info=writer_info,
-        warc_version=warc_version,
-        writer_subprefix=writer_subprefix,
-        gzip=gzip,
-        content_type=content_type,
-        min_part_size=min_part_size,
-    )
-    current_file_size = header_size
-
-    tracker = ThroughputTracker()
-    tracker.start()
-    counter = 0
-
-    # Write WARC resource records
-    if write_paths_as_resource_records:
-        logger.info(f'Writing {len(write_paths_as_resource_records)} resource records to WARC ... ')
-
-        # Resource records are written at the beginning the WARC file.
-        for i, resource_record_path in enumerate(write_paths_as_resource_records):
-            logger.info(f'Writing resource record from {resource_record_path} ...')
-            resource_record = get_resource_record_from_path(
-                file_path=resource_record_path,
-                metadata_path=(
-                    write_paths_as_resource_records_metadata[i] if write_paths_as_resource_records_metadata else None
-                ),
-            )
-            record_data = get_bytes_from_warc_record(resource_record, warc_version=warc_version, gzip=gzip)
-
-            await writer.write(record_data)
-
-            # Keep track but do not rotate resource records
-            current_file_size += len(record_data)
-
-        logger.info(f'Resource records added: {len(write_paths_as_resource_records)}')
-
-    try:
-        while True:
-            item = await item_queue.get()
-            counter += 1
-            try:
-                if item is _STOP:
-                    stats = tracker.get_stats()
-                    logger.info(
-                        'WARC writer %d stopping. Stats: %.1fs, %d items, %.1f MB written, %.2f MB/s write speed',
-                        consumer_id,
-                        stats['elapsed'],
-                        stats['total_requests'],
-                        stats['total_bytes'] / (1024 * 1024),
-                        stats['mb_per_sec'],
-                    )
-                    should_stop = True
-                else:
-                    should_stop = False
-                    assert isinstance(item, RangePayload)
-
-                    # Check if we need to rotate files due to size limit
-                    if max_file_size and current_file_size + len(item.data) > max_file_size:
-                        await writer.close()
-                        current_file_sequence += 1
-
-                        writer, header_size = await create_new_writer_with_header(
-                            s3_client=s3,
-                            consumer_id=consumer_id,
-                            sequence=current_file_sequence,
-                            output_path_prefix=prefix_path,
-                            max_attempts=max_attempts,
-                            base_backoff_seconds=base_backoff_seconds,
-                            writer_info=writer_info,
-                            warc_version=warc_version,
-                            writer_subprefix=writer_subprefix,
-                            gzip=gzip,
-                            content_type=content_type,
-                            min_part_size=min_part_size,
-                        )
-
-                        current_file_size = header_size
-                        logger.info(f'Rotated to new WARC file sequence {current_file_sequence} due to size limit')
-
-                    await writer.write(item.data)
-                    current_file_size += len(item.data)
-                    tracker.add(bytes_count=len(item.data), records_count=item.job.records_count)
-
-                    # Log progress every 10 items
-                    if log_every_n > 0 and counter % log_every_n == 0:
-                        stats = tracker.get_stats()
-                        logger.info(
-                            'WARC writer %d: %d items, %.1f MB written, %.2f MB/s',
-                            consumer_id,
-                            counter,
-                            stats['total_bytes'] / (1024 * 1024),
-                            stats['mb_per_sec'],
-                        )
-            except Exception:
-                logger.exception('WARC writer %d failed on %s', consumer_id, getattr(item, 'job', None))
-                should_stop = False
-            finally:
-                item_queue.task_done()
-
-            if should_stop:
-                break
-    finally:
-        await writer.close()
-
-    return {'consumer_id': consumer_id, 'stats': tracker.get_stats()}
diff --git a/cdx_toolkit/filter_warc/args.py b/cdx_toolkit/filter_warc/args.py
index 0ab94a7..b813742 100644
--- a/cdx_toolkit/filter_warc/args.py
+++ b/cdx_toolkit/filter_warc/args.py
@@ -51,13 +51,24 @@ def add_warcer_by_cdx_args(parser: argparse.ArgumentParser):
         '--parallel',
         type=int,
         default=1,
-        help='Number of parallel workers for fetchin WARC records (default: 1, sequential processing)',
+        help='Number of parallel workers for reading and writing WARC records (default: 1, sequential processing)',
+    )
+    parser.add_argument(
+        '--parallel_readers',
+        type=int,
+        default=None,
+        help='Number of parallel workers for reading WARC records (default: same as `parallel`)',
+    )
+    parser.add_argument(
+        '--parallel_writers',
+        type=int,
+        default=None,
+        help='Number of parallel workers for writing WARC records (default: same as `parallel`)',
     )
     parser.add_argument(
         '--log_every_n',
         type=int,
         default=1000,
         help='Every N extracted record a log message is emitted (0 = no record logs)',
-    )    
-    parser.add_argument('--implementation', type=str, default='fsspec', help='implementation (fsspec, aioboto3)')
+    )
     return parser
diff --git a/cdx_toolkit/filter_warc/cdx_utils.py b/cdx_toolkit/filter_warc/cdx_utils.py
index ea5a0f7..ef8b92c 100644
--- a/cdx_toolkit/filter_warc/cdx_utils.py
+++ b/cdx_toolkit/filter_warc/cdx_utils.py
@@ -55,7 +55,6 @@ def iter_cdx_index_from_path(index_path: str, warc_download_prefix: str) -> Iter
     """
     logger.info('Reading CDX from %s', index_path)
 
-
     with fsspec.open(index_path, 'rt', compression='gzip' if index_path.endswith('.gz') else None) as f:
         for line in f:
             try:
diff --git a/cdx_toolkit/filter_warc/data_classes.py b/cdx_toolkit/filter_warc/data_classes.py
new file mode 100644
index 0000000..422857a
--- /dev/null
+++ b/cdx_toolkit/filter_warc/data_classes.py
@@ -0,0 +1,97 @@
+import time
+from dataclasses import dataclass
+
+from cdx_toolkit.filter_warc.s3_utils import is_s3_url, parse_s3_uri, with_retries
+from typing import Tuple
+
+from cdx_toolkit.myrequests import myrequests_get
+
+
+
+@dataclass
+class ThroughputTracker:
+    """Track throughput metrics for fetchers and consumers."""
+
+    start_time: float = 0.0
+    total_bytes: int = 0
+    total_requests: int = 0
+    total_records: int = 0
+
+    def start(self):
+        self.start_time = time.time()
+
+    def add(self, bytes_count: int = 0, records_count: int = 0, requests_count: int = 1):
+        self.total_bytes += bytes_count
+        self.total_requests += requests_count
+        self.total_records += records_count
+
+    def get_stats(self) -> dict:
+        elapsed = time.time() - self.start_time
+
+        return {
+            'elapsed': elapsed,
+            'total_bytes': self.total_bytes,
+            'total_requests': self.total_requests,
+            'total_records': self.total_records,
+            'bytes_per_sec': self.total_bytes / elapsed if elapsed > 0 else 0,
+            'mb_per_sec': (self.total_bytes / elapsed) / (1024 * 1024) if elapsed > 0 else 0,
+            'requests_per_sec': self.total_requests / elapsed if elapsed > 0 else 0,
+            'records_per_sec': self.total_records / elapsed if elapsed > 0 else 0,
+        }
+
+
+@dataclass(frozen=True)
+class RangeJob:
+    """Defines a S3 or HTTP range read request."""
+
+    url: str
+    offset: int
+    length: int
+    records_count: int = 1
+
+    def is_s3(self):
+        return is_s3_url(self.url)
+
+    def get_s3_bucket_and_key(self) -> Tuple[str, str]:
+        if self.is_s3():
+            return parse_s3_uri(self.url)
+        else:
+            raise ValueError('Cannot get bucket and key from a HTTP job')
+
+    async def ranged_get_bytes(
+        self,
+        max_attempts: int,
+        base_backoff_seconds: float,
+        s3_client=None,
+    ) -> bytes:
+        """Ranged get request to S3 with retries and backoff or HTTP."""
+        offset = self.offset
+        length = self.length
+
+        end = offset + length - 1  # inclusive
+
+        if self.is_s3():
+            # read from S3
+            bucket, key = self.get_s3_bucket_and_key()
+            resp = await with_retries(
+                lambda: s3_client.get_object(Bucket=bucket, Key=key, Range=f'bytes={offset}-{end}'),
+                op_name=f'ranged_get {bucket}/{key}[{offset}:{end}]',
+                max_attempts=max_attempts,
+                base_backoff_seconds=base_backoff_seconds,
+            )
+            return await resp['Body'].read()
+
+        else:
+            # read from HTTP
+            headers = {'Range': 'bytes={}-{}'.format(offset, end)}
+
+            resp = myrequests_get(self.url, headers=headers)
+            return resp.content
+
+
+@dataclass(frozen=True)
+class RangePayload:
+    """Bytes output from S3 or HTTP range read."""
+
+    job: RangeJob
+    data: bytes
\ No newline at end of file
diff --git a/cdx_toolkit/filter_warc/fsspec_warc_filter.py b/cdx_toolkit/filter_warc/fsspec_warc_filter.py
deleted file mode 100644
index ebaa06f..0000000
--- a/cdx_toolkit/filter_warc/fsspec_warc_filter.py
+++ /dev/null
@@ -1,181 +0,0 @@
-import json
-import logging
-from typing import Dict, Iterable, List, Optional
-
-import cdx_toolkit
-from concurrent.futures import ThreadPoolExecutor, as_completed
-
-from warcio.recordloader import ArcWarcRecord
-
-from cdx_toolkit.filter_warc.cdx_utils import get_index_as_string_from_path
-from cdx_toolkit.filter_warc.warc_utils import get_resource_record_from_path
-
-
-logger = logging.getLogger(__name__)
-
-
-def filter_warc_by_cdx_via_fsspec(
-    index_paths: List[str],
-    prefix_path: str,
-    writer_info: Dict,
-    writer_subprefix: Optional[str] = None,
-    write_paths_as_resource_records: Optional[List[str]] = None,
-    write_paths_as_resource_records_metadata: Optional[List[str]] = None,
-    limit: int = 0,
-    log_every_n: int = 1000,
-    warc_download_prefix: Optional[str] = None,
-    n_parallel: int = 1,
-    writer_kwargs: Optional[Dict] = None,
-) -> int:
-    writer = cdx_toolkit.warc.get_writer(
-        prefix_path,
-        writer_subprefix,
-        writer_info,
-        **(writer_kwargs if writer_kwargs else {}),
-    )
-
-    # Iterate over index files
-    records_n = 0
-    for index_path in index_paths:
-        logger.info('Filtering WARC based on CDX from %s', index_path)
-
-        # Read index completely (for the WARC resource record)
-        index = get_index_as_string_from_path(index_path)
-
-        if not index:
-            # skip empty indicies
-            continue
-
-        # Write file content from paths as resource records to WARC
-        if write_paths_as_resource_records:
-            logger.info('Writing resource records to WARC ... ')
-
-            # Resource records are written at the beginning the WARC file.
-            for i, resource_record_path in enumerate(write_paths_as_resource_records):
-                logger.info(f'Writing resource record from {resource_record_path} ...')
-                resource_record = get_resource_record_from_path(
-                    file_path=resource_record_path,
-                    metadata_path=(
-                        write_paths_as_resource_records_metadata[i]
-                        if write_paths_as_resource_records_metadata
-                        else None
-                    ),
-                )
-                writer.write_record(resource_record)
-            
-            logger.info(f'Resource records added: {len(write_paths_as_resource_records)}')
-
-        # The index file holds all the information to download specific objects (file, offset, length etc.)
-        index_lines = index.splitlines()
-        index_limit = limit - records_n
-
-        if index_limit > 0:
-            index_lines = index_lines[:index_limit]
-
-        records_gen = fetch_records_from_index(
-            index_lines=index_lines, warc_download_prefix=warc_download_prefix, n_parallel=n_parallel
-        )
-        # records_gen = tqdm(fetch_records_from_index(
-        #     index_lines=index_lines, warc_download_prefix=cdx.warc_download_prefix, n_parallel=n_parallel
-        # ), desc="Fetch and write WARC", total=len(index_lines))
-
-        for record in records_gen:
-            writer.write_record(record)
-            records_n += 1
-
-            if (records_n % log_every_n) == 0:
-                logger.info(f'Record progress: {records_n:,} from {index_path}')
-
-        if limit > 0 and records_n >= limit:
-            # stop index loop
-            logger.info('Limit reached')
-            break
-
-        logger.info('Filtering completed (index file: %s)', index_path)
-
-    writer.close()
-
-    return records_n
-
-
-def fetch_single_record(obj):
-    """Fetch a single WARC record with error handling."""
-    url = obj['url']
-    timestamp = obj['timestamp']
-
-    try:
-        record = obj.fetch_warc_record()
-        if obj.is_revisit():
-            logger.warning('revisit record being resolved for url %s %s', url, timestamp)
-        return record
-    except RuntimeError:  # pragma: no cover
-        logger.warning('skipping capture for RuntimeError 404: %s %s', url, timestamp)
-        return None
-
-
-def fetch_records_from_index(
-    index_lines: List[str], warc_download_prefix=None, limit: int = 0, n_parallel: int = 1
-) -> Iterable[ArcWarcRecord]:
-    """Fetch WARC records based on CDX index."""
-
-    if n_parallel <= 1:
-        # Sequential processing
-        for obj in generate_caputure_objects_from_index(
-            index_lines=index_lines,
-            warc_download_prefix=warc_download_prefix,
-            limit=limit,
-        ):
-            record = fetch_single_record(obj)
-            if record is not None:
-                yield record
-    else:
-        # Parallel processing
-        logger.info(f'Fetch records in parallel with {n_parallel=}')
-        objects = list(
-            generate_caputure_objects_from_index(
-                index_lines=index_lines,
-                warc_download_prefix=warc_download_prefix,
-                limit=limit,
-            )
-        )  # TODO this loads all records into memory
-
-        with ThreadPoolExecutor(max_workers=n_parallel) as executor:
-            # Submit all tasks
-            future_to_obj = {executor.submit(fetch_single_record, obj): obj for obj in objects}
-
-            # Yield results as they complete
-            for future in as_completed(future_to_obj):
-                record = future.result()
-                if record is not None:
-                    yield record
-
-
-def generate_caputure_objects_from_index(
-    index_lines: List[str], warc_download_prefix=None, limit: int = 0, progress_bar: bool = False
-) -> Iterable[cdx_toolkit.CaptureObject]:
-    """Read CDX index and generate CaptureObject objects."""
-
-    if limit > 0:
-        index_lines = index_lines[:limit]
-
-    # if progress_bar:
-    #     index_lines = tqdm(index_lines, desc="Extracting from WARC", total=len(index_lines))
-
-    for i, line in enumerate(index_lines, 1):
-        cols = line.split(' ', maxsplit=2)
-
-        if len(cols) == 3:
-            # TODO can there be a different format?
-            # surt, timestamp, json_data = cols
-            #
-            # CC seems to not follow the IIPC pecification
-            # https://iipc.github.io/warc-specifications/specifications/cdx-format/cdx-2015/
-            #
-            # > The default first line of a CDX file is:
-            # > CDX A b e a m s c k r V v D d g M n
-            data = json.loads(cols[2])
-            data['timestamp'] = cols[1]
-        else:
-            raise ValueError(f'Cannot parse line: {line}')
-
-        yield cdx_toolkit.CaptureObject(data=data, wb=None, warc_download_prefix=warc_download_prefix)
diff --git a/cdx_toolkit/filter_warc/s3_utils.py b/cdx_toolkit/filter_warc/s3_utils.py
new file mode 100644
index 0000000..1a0cf7c
--- /dev/null
+++ b/cdx_toolkit/filter_warc/s3_utils.py
@@ -0,0 +1,55 @@
+import asyncio
+import logging
+from typing import Tuple
+from os import urandom
+
+from botocore.exceptions import ClientError, EndpointConnectionError
+
+
+logger = logging.getLogger(__name__)
+
+
+def parse_s3_uri(uri: str) -> Tuple[str, str]:
+    """Parse a S3 URI and return bucket and prefix."""
+    if not uri.startswith('s3://'):
+        raise ValueError(f'Not an S3 URI: {uri}')
+    rest = uri[5:]
+    i = rest.find('/')
+    if i <= 0 or i == len(rest) - 1:
+        raise ValueError(f'Malformed S3 URI: {uri}')
+    return rest[:i], rest[i+1:]
+
+
+def is_s3_url(url: str) -> bool:
+    return url.startswith('s3:/')
+
+
+async def with_retries(coro_factory, *, op_name: str, max_attempts: int, base_backoff_seconds: float):
+    """Perform operation with retries and backoff."""
+    last_exc = None
+    for attempt in range(1, max_attempts + 1):
+        try:
+            return await coro_factory()
+        except (TimeoutError, ClientError, EndpointConnectionError) as exc:
+            last_exc = exc
+            if attempt >= max_attempts:
+                logger.error('%s failed after %d attempts: %r', op_name, attempt, exc)
+                break
+            sleep_s = _backoff(attempt, base_backoff_seconds)
+            logger.warning(
+                '%s failed (attempt %d/%d) - retrying in %.2fs',
+                op_name,
+                attempt,
+                max_attempts,
+                sleep_s,
+            )
+            await asyncio.sleep(sleep_s)
+    raise last_exc
+
+
+def _backoff(attempt: int, base_backoff_seconds: float) -> float:
+    """Time to sleep based on number of attempts"""
+    base = base_backoff_seconds * (2 ** (attempt - 1))
+
+    # Add random jitter between 80-120% of base delay
+    return max(0.05, base * (0.8 + 0.4 * urandom(1)[0] / 255))
diff --git a/cdx_toolkit/filter_warc/aioboto3_writer.py b/cdx_toolkit/filter_warc/s3_writer.py
similarity index 62%
rename from cdx_toolkit/filter_warc/aioboto3_writer.py
rename to cdx_toolkit/filter_warc/s3_writer.py
index 903c23c..b67e646 100644
--- a/cdx_toolkit/filter_warc/aioboto3_writer.py
+++ b/cdx_toolkit/filter_warc/s3_writer.py
@@ -1,16 +1,86 @@
 import logging
 from typing import List, Dict, Optional
 
-from cdx_toolkit.filter_warc.aioboto3_utils import (
-    mpu_abort,
-    mpu_complete,
-    mpu_create,
-    mpu_upload_part,
+from cdx_toolkit.filter_warc.s3_utils import (
+    with_retries,
 )
 
 logger = logging.getLogger(__name__)
 
 
+async def mpu_create(
+    s3,
+    bucket: str,
+    key: str,
+    *,
+    max_attempts: int,
+    base_backoff_seconds: float,
+):
+    """Create multi part upload to S3."""
+    kwargs = {'Bucket': bucket, 'Key': key}
+    resp = await with_retries(
+        lambda: s3.create_multipart_upload(**kwargs),
+        op_name=f'create_multipart_upload {bucket}/{key}',
+        max_attempts=max_attempts,
+        base_backoff_seconds=base_backoff_seconds,
+    )
+    return resp['UploadId']
+
+
+async def mpu_upload_part(
+    s3,
+    bucket: str,
+    key: str,
+    upload_id: str,
+    part_number: int,
+    body: bytes,
+    max_attempts: int,
+    base_backoff_seconds: float,
+) -> str:
+    """Upload a part of a multi-part upload to S3."""
+    resp = await with_retries(
+        lambda: s3.upload_part(
+            Bucket=bucket,
+            Key=key,
+            UploadId=upload_id,
+            PartNumber=part_number,
+            Body=body,
+        ),
+        op_name=f'upload_part {bucket}/{key}#{part_number}',
+        max_attempts=max_attempts,
+        base_backoff_seconds=base_backoff_seconds,
+    )
+    return resp['ETag']
+
+
+async def mpu_complete(
+    s3,
+    bucket: str,
+    key: str,
+    upload_id: str,
+    parts: List[Dict],
+    max_attempts: int,
+    base_backoff_seconds: float,
+):
+    """Send complete for multi-part upload."""
+    await with_retries(
+        lambda: s3.complete_multipart_upload(
+            Bucket=bucket, Key=key, UploadId=upload_id, MultipartUpload={'Parts': parts}
+        ),
+        op_name=f'complete_multipart_upload {bucket}/{key}',
+        max_attempts=max_attempts,
+        base_backoff_seconds=base_backoff_seconds,
+    )
+
+
+async def mpu_abort(s3, bucket: str, key: str, upload_id: str):
+    """Abort mult-part upload."""
+    try:
+        await s3.abort_multipart_upload(Bucket=bucket, Key=key, UploadId=upload_id)
+    except Exception:
+        logger.exception('Failed to abort MPU %s on %s/%s', upload_id, bucket, key)
+
+
 class S3ShardWriter:
     """Manages one MPU: buffers bytes, uploads >=5 MiB parts, completes on close."""
 
diff --git a/cdx_toolkit/filter_warc/warc_filter.py b/cdx_toolkit/filter_warc/warc_filter.py
index c675525..21c9da4 100644
--- a/cdx_toolkit/filter_warc/warc_filter.py
+++ b/cdx_toolkit/filter_warc/warc_filter.py
@@ -1,19 +1,17 @@
 import asyncio
 import logging
 import statistics
+import sys
 from typing import List, Optional, Dict
 
-import aioboto3
+
 from botocore.config import Config
 
-from cdx_toolkit.filter_warc.aioboto3_utils import (
-    RangeJob,
-    RangePayload,
-    ThroughputTracker,
+from cdx_toolkit.filter_warc.s3_utils import (
     is_s3_url,
-    ranged_get_bytes,
 )
-from cdx_toolkit.filter_warc.aioboto3_warc_filter import create_new_writer_with_header
+from cdx_toolkit.filter_warc.data_classes import RangeJob, RangePayload, ThroughputTracker
+from cdx_toolkit.filter_warc.warc_utils import create_new_writer_with_header
 from cdx_toolkit.filter_warc.cdx_utils import (
     iter_cdx_index_from_path,
 )
@@ -52,6 +50,8 @@ def __init__(
         log_every_n: int = 1000,
         warc_download_prefix: Optional[str] = None,
         n_parallel: int = 1,
+        n_parallel_readers: Optional[int] = None,
+        n_parallel_writers: Optional[int] = None,
         max_attempts: int = 5,
         base_backoff_seconds: float = 0.5,
         writer_kwargs: Optional[Dict] = None,
@@ -73,7 +73,7 @@ def __init__(
         self.record_limit = record_limit
         self.log_every_n = log_every_n
         self.warc_download_prefix = warc_download_prefix
-        self.n_parallel = n_parallel
+
         self.writer_kwargs = writer_kwargs
         self.range_jobs_queue_size = range_jobs_queue_size
         self.warc_records_queue_size = warc_records_queue_size
@@ -81,8 +81,11 @@ def __init__(
         self.fetcher_to_consumer_ratio = fetcher_to_consumer_ratio
         self.max_attempts = max_attempts
         self.base_backoff_seconds = base_backoff_seconds
-        self.num_fetchers = n_parallel
-        self.num_consumers = max(int(self.num_fetchers / self.fetcher_to_consumer_ratio), 1)
+
+        self.n_parallel = n_parallel
+        self.num_readers = n_parallel_readers if n_parallel_readers is not None else n_parallel
+        self.num_writers = n_parallel_writers if n_parallel_writers is not None else max(int(self.num_readers / self.fetcher_to_consumer_ratio), 1)
+
         self.gzip = self.index_paths[0].endswith('.gz') if self.index_paths else False
         self.warc_version = warc_version
         self.content_type = content_type
@@ -106,9 +109,15 @@ def needs_s3(self) -> bool:
             or is_s3_url(self.prefix_path)  # stage 3
         )
 
-    def get_s3_client(self):
-        """Return s3 client if needed."""
+    def get_s3_client_context(self):
+        """Return s3 client context if needed."""
         if self.needs_s3():
+            if sys.version_info.major < 3 or (sys.version_info.major >= 3 and sys.version_info.minor < 9):
+                logger.error('Reading and writing to S3 requires Python version >= 3.9')
+                sys.exit(1)
+
+            import aioboto3
+
             session = aioboto3.Session()
 
             return session.client('s3', config=self.get_boto3_config())
@@ -120,71 +129,78 @@ async def filter_async(self) -> int:
         range_jobs_queue: asyncio.Queue = asyncio.Queue(maxsize=self.range_jobs_queue_size)
         warc_records_queue: asyncio.Queue = asyncio.Queue(maxsize=self.warc_records_queue_size)
 
-        async with self.get_s3_client() as s3_client:
-            # Fetch file paths and ranges (offset, length) from index files
-            logger.info('Starting lister, %d fetchers, %d consumers', self.num_fetchers, self.num_consumers)
+        s3_client_context = self.get_s3_client_context()
+        if s3_client_context is not None:
+            async with s3_client_context as s3_client:
+                return await self._run_filter_pipeline(range_jobs_queue, warc_records_queue, s3_client)
+        else:
+            return await self._run_filter_pipeline(range_jobs_queue, warc_records_queue, None)
+
+    async def _run_filter_pipeline(self, range_jobs_queue: asyncio.Queue, warc_records_queue: asyncio.Queue, s3_client) -> int:
+        """Run the actual filter pipeline with or without S3 client."""
+        # Fetch file paths and ranges (offset, length) from index files
+        logger.info('Starting lister, %d fetchers, %d consumers', self.num_readers, self.num_writers)
 
-            job_generators = asyncio.create_task(
-                self.generate_range_jobs(
-                    range_jobs_queue,
-                    s3_client=s3_client,
-                )
+        job_generators = asyncio.create_task(
+            self.generate_range_jobs(
+                range_jobs_queue,
+                s3_client=s3_client,
             )
+        )
 
-            # Read WARC records based on file paths and ranges
-            warc_readers = [
-                asyncio.create_task(
-                    self.read_warc_records(
-                        fetcher_id=i,
-                        range_jobs_queue=range_jobs_queue,
-                        warc_records_queue=warc_records_queue,
-                        s3_client=s3_client,
-                    )
+        # Read WARC records based on file paths and ranges
+        warc_readers = [
+            asyncio.create_task(
+                self.read_warc_records(
+                    reader_id=i,
+                    range_jobs_queue=range_jobs_queue,
+                    warc_records_queue=warc_records_queue,
+                    s3_client=s3_client,
                 )
-                for i in range(self.num_fetchers)
-            ]
-
-            # Write WARC records
-            warc_writers = [
-                asyncio.create_task(
-                    self.write_warc_records(
-                        consumer_id=i,
-                        warc_records_queue=warc_records_queue,
-                        s3_client=s3_client,
-                    )
+            )
+            for i in range(self.num_readers)
+        ]
+
+        # Write WARC records
+        warc_writers = [
+            asyncio.create_task(
+                self.write_warc_records(
+                    writer_id=i,
+                    warc_records_queue=warc_records_queue,
+                    s3_client=s3_client,
                 )
-                for i in range(self.num_consumers)
-            ]
+            )
+            for i in range(self.num_writers)
+        ]
 
-            await job_generators
-            logger.info('Range jobs submitted, waiting for readers to finish')
+        await job_generators
+        logger.info('Range jobs submitted, waiting for readers to finish')
 
-            readers_results = await asyncio.gather(*warc_readers)
+        readers_results = await asyncio.gather(*warc_readers)
 
-            readers_records = sum([result['stats']['total_records'] for result in readers_results])
-            readers_mb_per_sec = statistics.mean([result['stats']['mb_per_sec'] for result in readers_results])
-            readers_records_per_sec = statistics.mean(
-                [result['stats']['records_per_sec'] for result in readers_results]
-            )
+        readers_records = sum([result['stats']['total_records'] for result in readers_results])
+        readers_mb_per_sec = statistics.mean([result['stats']['mb_per_sec'] for result in readers_results])
+        readers_records_per_sec = statistics.mean(
+            [result['stats']['records_per_sec'] for result in readers_results]
+        )
 
-            logger.info(f'All WARC readers completed: {readers_records} records')
-            logger.info(f'Reader throughput: {readers_mb_per_sec:.2f} MB/s; {readers_records_per_sec:.2f} rec/s')
+        logger.info(f'All WARC readers completed: {readers_records} records')
+        logger.info(f'Reader throughput: {readers_mb_per_sec:.2f} MB/s; {readers_records_per_sec:.2f} rec/s')
 
-            # Send stop signals to consumers
-            for _ in range(self.num_consumers):
-                await warc_records_queue.put(_STOP)
+        # Send stop signals to consumers
+        for _ in range(self.num_writers):
+            await warc_records_queue.put(_STOP)
 
-            writers_results = await asyncio.gather(*warc_writers)
+        writers_results = await asyncio.gather(*warc_writers)
 
-            writers_records = sum([result['stats']['total_records'] for result in writers_results])
-            writers_mb_per_sec = statistics.mean([result['stats']['mb_per_sec'] for result in writers_results])
-            writers_records_per_sec = statistics.mean(
-                [result['stats']['records_per_sec'] for result in writers_results]
-            )
-            # warc_writers_bytes = sum([result['stats']['total_bytes'] for result in consumer_results])
+        writers_records = sum([result['stats']['total_records'] for result in writers_results])
+        writers_mb_per_sec = statistics.mean([result['stats']['mb_per_sec'] for result in writers_results])
+        writers_records_per_sec = statistics.mean(
+            [result['stats']['records_per_sec'] for result in writers_results]
+        )
 
-            logger.info(f'All WARC writers completed: {writers_records} records')
-            logger.info(f'Writer throughput: {writers_mb_per_sec:.2f} MB/s; {writers_records_per_sec:.2f} r/s')
+        logger.info(f'All WARC writers completed: {writers_records} records')
+        logger.info(f'Writer throughput: {writers_mb_per_sec:.2f} MB/s; {writers_records_per_sec:.2f} r/s')
 
         return writers_records
 
@@ -222,14 +238,14 @@ async def generate_range_jobs(
                 break
 
         # signal fetchers to stop
-        for _ in range(self.num_fetchers):
+        for _ in range(self.num_readers):
             await range_jobs_queue.put(_STOP)
 
         logger.info('Enqueued %d jobs from %s', count, index_path)
 
     async def read_warc_records(
         self,
-        fetcher_id: int,
+        reader_id: int,
         range_jobs_queue: asyncio.Queue,
         warc_records_queue: asyncio.Queue,
         s3_client=None,
@@ -245,8 +261,8 @@ async def read_warc_records(
                 if job is _STOP:
                     stats = tracker.get_stats()
                     logger.info(
-                        'WARC Fetcher %d stopping. Stats: %.1fs, %d requests, %.1f MB, %.2f MB/s, %.2f req/s',
-                        fetcher_id,
+                        'WARC Reader %d stopping. Stats: %.1fs, %d requests, %.1f MB, %.2f MB/s, %.2f req/s',
+                        reader_id,
                         stats['elapsed'],
                         stats['total_requests'],
                         stats['total_bytes'] / (1024 * 1024),
@@ -255,8 +271,7 @@ async def read_warc_records(
                     )
                     break  # Exit loop, but still execute finally block
                 assert isinstance(job, RangeJob)
-                data = await ranged_get_bytes(
-                    job,
+                data = await job.ranged_get_bytes(
                     self.max_attempts,
                     self.base_backoff_seconds,
                     s3_client=s3_client,
@@ -268,8 +283,8 @@ async def read_warc_records(
                 if self.log_every_n > 0 and counter % self.log_every_n == 0:
                     stats = tracker.get_stats()
                     logger.info(
-                        'WARC Fetcher %d: %d items, %.1f MB, %.2f MB/s, %.2f req/s',
-                        fetcher_id,
+                        'WARC Reader %d: %d items, %.1f MB, %.2f MB/s, %.2f req/s',
+                        reader_id,
                         counter,
                         stats['total_bytes'] / (1024 * 1024),
                         stats['mb_per_sec'],
@@ -279,8 +294,8 @@ async def read_warc_records(
                 await warc_records_queue.put(RangePayload(job=job, data=data))
             except Exception:
                 logger.exception(
-                    'WARC Fetcher %d failed on %s/%s [%d,%d]',
-                    fetcher_id,
+                    'WARC Reader %d failed on %s/%s [%d,%d]',
+                    reader_id,
                     getattr(job, 'bucket', '?'),
                     getattr(job, 'key', '?'),
                     getattr(job, 'offset', -1),
@@ -289,22 +304,22 @@ async def read_warc_records(
             finally:
                 range_jobs_queue.task_done()
 
-        return {'fetcher_id': fetcher_id, 'stats': tracker.get_stats()}
+        return {'reader_id': reader_id, 'stats': tracker.get_stats()}
 
     async def write_warc_records(
         self,
-        consumer_id: int,
+        writer_id: int,
         warc_records_queue: asyncio.Queue,
         s3_client=None,
     ) -> dict:
-        """Write WARC records. Each consumer owns ONE shard MPU and appends ranges to it."""
+        """Write WARC records. Each writer owns ONE shard MPU and appends ranges to it."""
         # File rotation tracking
         current_file_sequence = 1
         current_file_size = 0
 
         new_writer_kwargs = dict(
             s3_client=s3_client,
-            consumer_id=consumer_id,
+            writer_id=writer_id,
             output_path_prefix=self.prefix_path,
             max_attempts=self.max_attempts,
             base_backoff_seconds=self.base_backoff_seconds,
@@ -362,7 +377,7 @@ async def write_warc_records(
                         stats = tracker.get_stats()
                         logger.info(
                             'WARC writer %d stopping. Stats: %.1fs, %d items, %.1f MB written, %.2f MB/s write speed',
-                            consumer_id,
+                            writer_id,
                             stats['elapsed'],
                             stats['total_requests'],
                             stats['total_bytes'] / (1024 * 1024),
@@ -395,13 +410,13 @@ async def write_warc_records(
                             stats = tracker.get_stats()
                             logger.info(
                                 'WARC writer %d: %d items, %.1f MB written, %.2f MB/s',
-                                consumer_id,
+                                writer_id,
                                 counter,
                                 stats['total_bytes'] / (1024 * 1024),
                                 stats['mb_per_sec'],
                             )
                 except Exception:
-                    logger.exception('WARC writer %d failed on %s', consumer_id, getattr(item, 'job', None))
+                    logger.exception('WARC writer %d failed on %s', writer_id, getattr(item, 'job', None))
                     should_stop = False
                 finally:
                     warc_records_queue.task_done()
@@ -411,7 +426,7 @@ async def write_warc_records(
         finally:
             await writer.close()
 
-        return {'consumer_id': consumer_id, 'stats': tracker.get_stats()}
+        return {'writer_id': writer_id, 'stats': tracker.get_stats()}
 
     def get_boto3_config(self):
         return Config(
diff --git a/cdx_toolkit/filter_warc/warc_utils.py b/cdx_toolkit/filter_warc/warc_utils.py
index 0a75f2f..8f42ca9 100644
--- a/cdx_toolkit/filter_warc/warc_utils.py
+++ b/cdx_toolkit/filter_warc/warc_utils.py
@@ -5,10 +5,14 @@
 from warcio.recordloader import ArcWarcRecord
 from warcio import WARCWriter
 
-from typing import Optional, Union
+from typing import Dict, Optional, Union
 
 import mimetypes
 
+from cdx_toolkit.filter_warc.s3_utils import is_s3_url, parse_s3_uri
+from cdx_toolkit.filter_warc.local_writer import LocalFileWriter
+from cdx_toolkit.filter_warc.s3_writer import S3ShardWriter
+
 def get_bytes_from_warc_record(
     record, 
     warc_version: str = '1.0',
@@ -75,4 +79,84 @@ def get_resource_record_from_path(
         http_headers=http_headers,
         warc_content_type=warc_content_type,
         warc_headers_dict=warc_headers_dict,
-    )
\ No newline at end of file
+    )
+
+
+def generate_warc_filename(
+    dest_prefix: str,
+    writer_id: int,
+    sequence: int,
+    writer_subprefix: Optional[str] = None,
+    gzip: bool = False,
+) -> str:
+    file_name = dest_prefix + '-'
+    if writer_subprefix is not None:
+        file_name += writer_subprefix + '-'
+    file_name += '{:06d}-{:03d}'.format(writer_id, sequence) + '.extracted.warc'
+    if gzip:
+        file_name += '.gz'
+
+    return file_name
+
+
+async def create_new_writer_with_header(
+    writer_id: int,
+    sequence: int,
+    output_path_prefix: str,
+    max_attempts: int,
+    base_backoff_seconds: float,
+    min_part_size: int,
+    writer_info: Dict,
+    warc_version: str = '1.0',
+    writer_subprefix: Optional[str] = None,
+    gzip: bool = False,
+    content_type: Optional[str] = None,
+    s3_client=None,
+):
+    if is_s3_url(output_path_prefix):
+        dest_bucket, dest_prefix = parse_s3_uri(output_path_prefix)
+
+        filename = generate_warc_filename(
+            dest_prefix=dest_prefix,
+            writer_id=writer_id,
+            sequence=sequence,
+            writer_subprefix=writer_subprefix,
+            gzip=gzip,
+        )
+
+        new_writer = S3ShardWriter(
+            s3_client,
+            filename,
+            dest_bucket,
+            content_type,
+            min_part_size,
+            max_attempts,
+            base_backoff_seconds,
+        )
+
+    else:
+        # local file system
+        filename = generate_warc_filename(
+            dest_prefix=output_path_prefix,
+            writer_id=writer_id,
+            sequence=sequence,
+            writer_subprefix=writer_subprefix,
+            gzip=gzip,
+        )
+
+        new_writer = LocalFileWriter(
+            file_path=filename,
+        )
+
+    # Initialize writer
+    await new_writer.start()
+
+    # Write WARC header
+    buffer = BytesIO()
+    warc_writer = WARCWriter(buffer, gzip=gzip, warc_version=warc_version)
+    warcinfo = warc_writer.create_warcinfo_record(filename, writer_info)
+    warc_writer.write_record(warcinfo)
+    header_data = buffer.getvalue()
+    await new_writer.write(header_data)
+
+    return new_writer, len(header_data)
\ No newline at end of file
diff --git a/requirements.txt b/requirements.txt
index 04af6dd..586889b 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -6,6 +6,7 @@ warcio==1.7.4
 fsspec[s3]
 surt>=0.3.1
 tqdm>=4.67.1
+url-is-in>=0.1.1
 
 # used by Makefile
 pytest==6.2.4
diff --git a/setup.py b/setup.py
index e1bdee5..73f76f2 100755
--- a/setup.py
+++ b/setup.py
@@ -8,7 +8,7 @@
 packages = find_packages(include=['cdx_toolkit*'])
 
 # remember: keep requires synchronized with requirements.txt
-requires = ['requests', 'warcio', 'fsspec[s3]', 'aioboto3', 'surt', 'tqdm']
+requires = ['requests', 'warcio', 'fsspec[s3]', 'aioboto3', 'surt', 'tqdm', 'url-is-in>=0.1.1']
 
 test_requirements = ['pytest', 'pytest-cov', 'responses']
 
diff --git a/tests/filter_cdx/test_filter_cdx.py b/tests/filter_cdx/test_filter_cdx.py
index fcb7e0b..a6cde32 100644
--- a/tests/filter_cdx/test_filter_cdx.py
+++ b/tests/filter_cdx/test_filter_cdx.py
@@ -5,7 +5,9 @@
 
 from cdx_toolkit.cli import main
 from cdx_toolkit.filter_cdx import _process_single_file, resolve_paths, validate_resolved_paths, filter_cdx
-from cdx_toolkit.filter_cdx.matcher import TupleMatcher
+
+from url_is_in import SURTMatcher
+
 from tests.conftest import requires_aws_s3, TEST_DATA_PATH
 
 fixture_path = TEST_DATA_PATH / 'filter_cdx'
@@ -174,7 +176,7 @@ def test_cli_filter_cdx_with_parallel_processing(tmpdir, caplog):
 
 def test_process_single_file(tmpdir):
     input_path = TEST_DATA_PATH / 'warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.gz'
-    matcher = TupleMatcher(prefixes=['fr,'])
+    matcher = SURTMatcher(['fr,'])
 
     lines_n, included_n = _process_single_file(
         input_path=input_path,
diff --git a/tests/filter_cdx/test_matcher.py b/tests/filter_cdx/test_matcher.py
deleted file mode 100644
index b449fc9..0000000
--- a/tests/filter_cdx/test_matcher.py
+++ /dev/null
@@ -1,314 +0,0 @@
-import pytest
-from cdx_toolkit.filter_cdx.matcher import TupleMatcher, TrieMatcher
-
-
-@pytest.mark.parametrize(
-    'prefixes,test_strings,expected_results',
-    [
-        # Basic functionality
-        (
-            ['http://', 'https://'],
-            ['http://example.com', 'https://example.com', 'ftp://example.com'],
-            [True, True, False],
-        ),
-        # Empty prefix list
-        ([], ['any string', '', 'test'], [False, False, False]),
-        # Single character prefixes
-        (
-            ['a', 'b', 'c'],
-            ['apple', 'banana', 'cherry', 'dog', ''],
-            [True, True, True, False, False],
-        ),
-        # Overlapping prefixes
-        (
-            ['test', 'testing', 'te'],
-            ['test', 'testing', 'tea', 'other'],
-            [True, True, True, False],
-        ),
-        # Unicode characters
-        (
-            ['café', 'naïve', 'résumé'],
-            ['café au lait', 'naïve person', 'résumé.pdf', 'regular text'],
-            [True, True, True, False],
-        ),
-        # Special characters
-        (
-            ['[test]', '.*', '\\n'],
-            ['[test] case', '.*regex', '\\newline', 'normal'],
-            [True, True, True, False],
-        ),
-        # Case sensitivity
-        (
-            ['HTTP', 'Https'],
-            ['HTTP://example.com', 'https://example.com', 'HTTPS://EXAMPLE.COM'],
-            [True, False, True],
-        ),
-        # Very long prefixes
-        (
-            ['a' * 1000],
-            ['a' * 1000 + 'suffix', 'a' * 999, 'b' * 1000],
-            [True, False, False],
-        ),
-        # Duplicate prefixes
-        (
-            ['test', 'test', 'demo'],
-            ['testing', 'demo version', 'other'],
-            [True, True, False],
-        ),
-        # Prefixes that are substrings of each other
-        (
-            ['ab', 'abc', 'abcd'],
-            ['ab', 'abc', 'abcd', 'abcde', 'a'],
-            [True, True, True, True, False],
-        ),
-        # Numbers and mixed content
-        (
-            ['123', '4.56'],
-            ['123test', '4.56789', '789', 'test123'],
-            [True, True, False, False],
-        ),
-        # Whitespace handling (note: whitespace is stripped from prefixes, so " test" becomes "test")
-        (
-            [' test', '\tindent', '\nline'],
-            ['test case', 'indented', 'line break', ' test case', 'nowhitespace'],
-            [True, True, True, False, False],
-        ),
-    ],
-)
-def test_matcher_approaches(prefixes, test_strings, expected_results):
-    """Test that TupleMatcher and TrieMatcher produce identical results."""
-    tuple_matcher = TupleMatcher(prefixes)
-    trie_matcher = TrieMatcher(prefixes)
-
-    for test_string, expected_result in zip(test_strings, expected_results):
-        tuple_result = tuple_matcher.matches(test_string)
-        trie_result = trie_matcher.matches(test_string)
-
-        # Both matchers should agree with each other
-        assert tuple_result == trie_result, (
-            f'TupleMatcher({tuple_result}) != TrieMatcher({trie_result}) '
-            f"for prefixes {prefixes} and string '{test_string}'"
-        )
-
-        # Both should match the expected result
-        assert tuple_result == expected_result, (
-            f"Expected {expected_result}, got {tuple_result} for prefixes {prefixes} and string '{test_string}'"
-        )
-
-
-@pytest.mark.parametrize(
-    'invalid_prefixes,expected_error',
-    [
-        # Empty string prefixes
-        ([''], 'Empty prefixes are not allowed'),
-        # Whitespace-only prefixes (should be stripped to empty and raise error)
-        (['   '], 'Empty prefixes are not allowed'),
-        (['\t\n '], 'Empty prefixes are not allowed'),
-        # None values
-        ([None], 'Prefix must be a string and not none'),
-        (['test', None, 'demo'], 'Prefix must be a string and not none'),
-        # Non-string types
-        ([123], 'Prefix must be a string and not none'),
-        (['test', 456, 'demo'], 'Prefix must be a string and not none'),
-        ([[], {}, set()], 'Prefix must be a string and not none'),
-    ],
-)
-def test_prefix_validation_errors(invalid_prefixes, expected_error):
-    """Test that invalid prefixes raise appropriate ValueErrors."""
-
-    with pytest.raises(ValueError, match=expected_error):
-        TupleMatcher(invalid_prefixes)
-
-    with pytest.raises(ValueError, match=expected_error):
-        TrieMatcher(invalid_prefixes)
-
-
-@pytest.mark.parametrize(
-    'test_string,expected',
-    [
-        ('test', True),
-        ('testing', True),
-        ('demo', True),
-        ('demonstration', True),
-        ('example', True),
-        ('examples', True),
-        ('  test', False),  # Leading whitespace in test string shouldn't match
-        ('other', False),
-    ],
-)
-def test_whitespace_stripping(test_string, expected):
-    """Test that whitespace is properly stripped from prefixes."""
-
-    # Prefixes with leading/trailing whitespace should be stripped
-    prefixes_with_whitespace = ['  test  ', '\tdemo\n', ' example ']
-
-    tuple_matcher = TupleMatcher(prefixes_with_whitespace)
-    trie_matcher = TrieMatcher(prefixes_with_whitespace)
-
-    tuple_result = tuple_matcher.matches(test_string)
-    trie_result = trie_matcher.matches(test_string)
-
-    assert tuple_result == trie_result == expected, (
-        f"Whitespace stripping test failed for '{test_string}': "
-        f'expected {expected}, got Tuple({tuple_result}), Trie({trie_result})'
-    )
-
-
-@pytest.mark.parametrize('test_string', ['anything', '', 'test', 'a', '123'])
-def test_empty_prefix_list(test_string):
-    """Test with empty prefix list - should never match anything."""
-    empty_prefixes = []
-
-    tuple_matcher = TupleMatcher(empty_prefixes)
-    trie_matcher = TrieMatcher(empty_prefixes)
-
-    tuple_result = tuple_matcher.matches(test_string)
-    trie_result = trie_matcher.matches(test_string)
-
-    # Both should return False for empty prefix list
-    assert not tuple_result and not trie_result, (
-        f"Both matchers should return False for '{test_string}' with empty prefixes, "
-        f'got Tuple({tuple_result}), Trie({trie_result})'
-    )
-
-
-def test_empty_string_against_prefixes():
-    """Test matching empty strings against non-empty prefixes."""
-    non_empty_prefixes = ['test', 'demo', 'example']
-    empty_test_string = ''
-
-    tuple_matcher = TupleMatcher(non_empty_prefixes)
-    trie_matcher = TrieMatcher(non_empty_prefixes)
-
-    tuple_result = tuple_matcher.matches(empty_test_string)
-    trie_result = trie_matcher.matches(empty_test_string)
-
-    # Both should return False when testing empty string against non-empty prefixes
-    assert not tuple_result and not trie_result, (
-        f'Both matchers should return False for empty string with non-empty prefixes, '
-        f'got Tuple({tuple_result}), Trie({trie_result})'
-    )
-
-
-@pytest.mark.parametrize(
-    'test_string,expected',
-    [
-        ('a', True),
-        ('1', True),
-        ('!', True),
-        ('ab', True),
-        ('12', True),
-        ('!@', True),
-        ('other', False),
-        ('', False),
-    ],
-)
-def test_single_character_edge_cases(test_string, expected):
-    """Test single character prefixes and strings (without empty prefixes)."""
-    prefixes = ['a', '1', '!']
-
-    tuple_matcher = TupleMatcher(prefixes)
-    trie_matcher = TrieMatcher(prefixes)
-
-    tuple_result = tuple_matcher.matches(test_string)
-    trie_result = trie_matcher.matches(test_string)
-
-    assert tuple_result == trie_result == expected, (
-        f"Mismatch for '{test_string}': Tuple({tuple_result}), Trie({trie_result}), Expected({expected})"
-    )
-
-
-def test_performance_with_many_prefixes():
-    """Test with a large number of prefixes to ensure both matchers handle it."""
-    # Create many prefixes
-    prefixes = [f'prefix_{i}' for i in range(1000)]
-    test_strings = ['prefix_500test', 'prefix_999', 'nomatch', 'prefix_1000']
-
-    tuple_matcher = TupleMatcher(prefixes)
-    trie_matcher = TrieMatcher(prefixes)
-
-    for test_string in test_strings:
-        tuple_result = tuple_matcher.matches(test_string)
-        trie_result = trie_matcher.matches(test_string)
-        assert tuple_result == trie_result
-
-
-@pytest.mark.parametrize(
-    'test_string,expected',
-    [
-        ('', False),
-        ('a', True),
-        ('ab', True),
-        ('abc', True),
-        ('abcd', True),
-        ('abcde', True),
-        ('abcdef', True),
-        ('b', False),
-        ('ac', True),
-    ],
-)
-def test_nested_prefixes(test_string, expected):
-    """Test with prefixes that are nested within each other."""
-    prefixes = ['a', 'ab', 'abc', 'abcd', 'abcde']
-
-    tuple_matcher = TupleMatcher(prefixes)
-    trie_matcher = TrieMatcher(prefixes)
-
-    tuple_result = tuple_matcher.matches(test_string)
-    trie_result = trie_matcher.matches(test_string)
-
-    assert tuple_result == trie_result == expected, (
-        f"Nested prefix test failed for '{test_string}': "
-        f'expected {expected}, got Tuple({tuple_result}), Trie({trie_result})'
-    )
-
-
-@pytest.mark.parametrize(
-    'test_string,expected',
-    [
-        ('🌟test', True),
-        ('café au lait', True),
-        ('𝓤𝓷𝓲𝓬𝓸𝓭𝓮 text', True),
-        ('regular', False),
-        ('', False),
-    ],
-)
-def test_unicode_edge_cases(test_string, expected):
-    """Test Unicode handling edge cases (without empty prefixes)."""
-    prefixes = ['🌟', 'café', '𝓤𝓷𝓲𝓬𝓸𝓭𝓮']
-
-    tuple_matcher = TupleMatcher(prefixes)
-    trie_matcher = TrieMatcher(prefixes)
-
-    tuple_result = tuple_matcher.matches(test_string)
-    trie_result = trie_matcher.matches(test_string)
-
-    assert tuple_result == trie_result == expected, (
-        f"Unicode mismatch for '{test_string}': Tuple({tuple_result}), Trie({trie_result}), Expected({expected})"
-    )
-
-
-def test_with_list_and_tuple_inputs():
-    """Test that both list and tuple inputs work identically."""
-    prefixes_list = ['test', 'demo', 'example']
-    prefixes_tuple = ('test', 'demo', 'example')
-    test_strings = ['testing', 'demo version', 'example.com', 'other']
-
-    # Test with list input
-    tuple_matcher_list = TupleMatcher(prefixes_list)
-    trie_matcher_list = TrieMatcher(prefixes_list)
-
-    # Test with tuple input
-    tuple_matcher_tuple = TupleMatcher(prefixes_tuple)
-    trie_matcher_tuple = TrieMatcher(prefixes_tuple)
-
-    for test_string in test_strings:
-        # All four matchers should give same result
-        results = [
-            tuple_matcher_list.matches(test_string),
-            trie_matcher_list.matches(test_string),
-            tuple_matcher_tuple.matches(test_string),
-            trie_matcher_tuple.matches(test_string),
-        ]
-
-        assert all(r == results[0] for r in results), f"Inconsistent results for '{test_string}': {results}"
diff --git a/tests/filter_warc/test_aioboto3_warcer.py b/tests/filter_warc/test_aioboto3_warcer.py
deleted file mode 100644
index 98d776e..0000000
--- a/tests/filter_warc/test_aioboto3_warcer.py
+++ /dev/null
@@ -1,75 +0,0 @@
-import asyncio
-from unittest.mock import patch, AsyncMock
-
-from cdx_toolkit.filter_warc.aioboto3_warc_filter import (
-    filter_warc_by_cdx_via_aioboto3,
-    get_range_jobs_from_index_paths,
-)
-
-
-def test_filter_warc_by_cdx_via_aioboto3_keyboard_interrupt(caplog):
-    """Test filter_warc_by_cdx_via_aioboto3 KeyboardInterrupt exception handling."""
-
-    # Mock the async function to raise KeyboardInterrupt
-    async def mock_async_function(*args, **kwargs):
-        raise KeyboardInterrupt('User interrupted')
-
-    with patch(
-        'cdx_toolkit.filter_warc.aioboto3_warc_filter.filter_warc_by_cdx_via_aioboto3_async',
-        side_effect=mock_async_function,
-    ):
-        # Call the function with minimal required parameters
-        result = filter_warc_by_cdx_via_aioboto3(
-            index_paths=['test_index.cdx'], prefix_path='s3://test-bucket/test-prefix', writer_info={'software': 'test'}
-        )
-
-        # Verify that KeyboardInterrupt was handled correctly
-        assert result == -1, 'Should return -1 when KeyboardInterrupt is caught'
-
-        # Check that the warning message was logged
-        assert 'Interrupted by user.' in caplog.text
-
-        # Verify the log level is warning
-        warning_records = [record for record in caplog.records if record.levelname == 'WARNING']
-        assert len(warning_records) == 1
-        assert warning_records[0].message == 'Interrupted by user.'
-
-
-def test_get_range_jobs_from_index_paths_exception_handling_with_logging(caplog):
-    """Test get_range_jobs_from_index_paths logs errors when iter_cdx_index_from_path raises."""
-
-    async def run_test():
-        # Create a mock queue
-        key_queue = AsyncMock(spec=asyncio.Queue)
-
-        # Test parameters
-        index_paths = ['failing_index.cdx']
-        warc_download_prefix = 'http://test-prefix'
-        num_fetchers = 1
-
-        # Mock iter_cdx_index_from_path to always raise exception
-        def mock_iter_cdx_index_from_path(index_path, warc_download_prefix):
-            raise ValueError('Simulated CDX parsing error')
-
-        with patch(
-            'cdx_toolkit.filter_warc.aioboto3_warc_filter.iter_cdx_index_from_path',
-            side_effect=mock_iter_cdx_index_from_path,
-        ):
-            # Run the function
-            await get_range_jobs_from_index_paths(
-                key_queue=key_queue,
-                index_paths=index_paths,
-                warc_download_prefix=warc_download_prefix,
-                num_fetchers=num_fetchers,
-                limit=0,
-            )
-
-            # Verify error was logged
-            assert 'Failed to read CDX index from failing_index.cdx' in caplog.text
-            assert 'Simulated CDX parsing error' in caplog.text
-
-            # Verify that only STOP signal was sent (no jobs due to exception)
-            assert key_queue.put.call_count == 1  # Only 1 STOP signal
-
-    # Run the test
-    asyncio.run(run_test())
diff --git a/tests/filter_warc/test_aioboto3_utils.py b/tests/filter_warc/test_s3_utils.py
similarity index 82%
rename from tests/filter_warc/test_aioboto3_utils.py
rename to tests/filter_warc/test_s3_utils.py
index a2eb905..e3ab56d 100644
--- a/tests/filter_warc/test_aioboto3_utils.py
+++ b/tests/filter_warc/test_s3_utils.py
@@ -1,13 +1,11 @@
 import pytest
 
 import asyncio
-from unittest.mock import AsyncMock
 
 
-from cdx_toolkit.filter_warc.aioboto3_utils import (
+from cdx_toolkit.filter_warc.s3_utils import (
     _backoff,
     parse_s3_uri,
-    mpu_abort,
     with_retries,
 )
 from botocore.exceptions import EndpointConnectionError
@@ -94,41 +92,6 @@ def test_parse_s3_uri():
         parse_s3_uri('s3:///file')
 
 
-def test_mpu_abort_success():
-    """Test mpu_abort function with successful abort."""
-
-    async def run_test():
-        mock_s3 = AsyncMock()
-        bucket = 'test-bucket'
-        key = 'test-key'
-        upload_id = 'test-upload-id'
-
-        await mpu_abort(mock_s3, bucket, key, upload_id)
-
-        mock_s3.abort_multipart_upload.assert_called_once_with(Bucket=bucket, Key=key, UploadId=upload_id)
-
-    asyncio.run(run_test())
-
-
-def test_mpu_abort_with_exception():
-    """Test mpu_abort function when abort fails (should catch exception)."""
-
-    async def run_test():
-        mock_s3 = AsyncMock()
-        mock_s3.abort_multipart_upload.side_effect = Exception('S3 error')
-
-        bucket = 'test-bucket'
-        key = 'test-key'
-        upload_id = 'test-upload-id'
-
-        # Should not raise exception, should log it instead
-        await mpu_abort(mock_s3, bucket, key, upload_id)
-
-        mock_s3.abort_multipart_upload.assert_called_once_with(Bucket=bucket, Key=key, UploadId=upload_id)
-
-    asyncio.run(run_test())
-
-
 def test_with_retries_success():
     """Test with_retries function with successful operation on first attempt."""
 
diff --git a/tests/filter_warc/test_aioboto3_writer.py b/tests/filter_warc/test_s3_writer.py
similarity index 78%
rename from tests/filter_warc/test_aioboto3_writer.py
rename to tests/filter_warc/test_s3_writer.py
index c2f094b..c6cb722 100644
--- a/tests/filter_warc/test_aioboto3_writer.py
+++ b/tests/filter_warc/test_s3_writer.py
@@ -1,49 +1,26 @@
 import pytest
+
 import asyncio
-from unittest.mock import AsyncMock, patch
-
-from cdx_toolkit.filter_warc.aioboto3_writer import S3ShardWriter
-
-
-def test_shard_writer_init():
-    """Test ShardWriter initialization."""
-    shard_key = 'test-shard.warc.gz'
-    dest_bucket = 'test-bucket'
-    content_type = 'application/gzip'
-    min_part_size = 5 * 1024 * 1024  # 5 MiB
-    max_attempts = 3
-    base_backoff_seconds = 0.1
-
-    writer = S3ShardWriter(
-        shard_key=shard_key,
-        dest_bucket=dest_bucket,
-        content_type=content_type,
-        min_part_size=min_part_size,
-        max_attempts=max_attempts,
-        base_backoff_seconds=base_backoff_seconds,
-    )
-
-    assert writer.shard_key == shard_key
-    assert writer.dest_bucket == dest_bucket
-    assert writer.content_type == content_type
-    assert writer.min_part_size == min_part_size
-    assert writer.max_attempts == max_attempts
-    assert writer.base_backoff_seconds == base_backoff_seconds
-    assert writer.upload_id is None
-    assert writer.part_number == 1
-    assert writer.parts == []
-    assert isinstance(writer.buffer, bytearray)
-    assert len(writer.buffer) == 0
+from unittest.mock import AsyncMock
+from unittest.mock import patch
+
+from cdx_toolkit.filter_warc.s3_writer import mpu_abort
+
+
+from cdx_toolkit.filter_warc.s3_writer import S3ShardWriter
 
 
 def test_shard_writer_start():
     """Test ShardWriter start method."""
 
     async def run_test():
-        with patch('cdx_toolkit.filter_warc.aioboto3_writer.mpu_create') as mock_mpu_create:
+        with patch('cdx_toolkit.filter_warc.s3_writer.mpu_create') as mock_mpu_create:
             mock_mpu_create.return_value = 'test-upload-id'
 
+            mock_s3 = AsyncMock()
+
             writer = S3ShardWriter(
+                s3_client=mock_s3,
                 shard_key='test.warc.gz',
                 dest_bucket='test-bucket',
                 content_type='application/gzip',
@@ -52,8 +29,7 @@ async def run_test():
                 base_backoff_seconds=0.1,
             )
 
-            mock_s3 = AsyncMock()
-            await writer.start(mock_s3)
+            await writer.start()
 
             assert writer.upload_id == 'test-upload-id'
             mock_mpu_create.assert_called_once_with(
@@ -100,7 +76,7 @@ def test_shard_writer_write_large_data():
     """Test ShardWriter write method with large data that triggers part uploads."""
 
     async def run_test():
-        with patch('cdx_toolkit.filter_warc.aioboto3_writer.mpu_upload_part') as mock_upload_part:
+        with patch('cdx_toolkit.filter_warc.s3_writer.mpu_upload_part') as mock_upload_part:
             mock_upload_part.return_value = 'test-etag-1'
 
             mock_s3 = AsyncMock()
@@ -138,7 +114,7 @@ def test_shard_writer_flush_full_parts():
     """Test ShardWriter _flush_full_parts private method directly."""
 
     async def run_test():
-        with patch('cdx_toolkit.filter_warc.aioboto3_writer.mpu_upload_part') as mock_upload_part:
+        with patch('cdx_toolkit.filter_warc.s3_writer.mpu_upload_part') as mock_upload_part:
             mock_upload_part.return_value = 'test-etag-flush'
 
             mock_s3 = AsyncMock()
@@ -175,8 +151,8 @@ def test_shard_writer_close_with_buffer():
     """Test ShardWriter close method with data remaining in buffer."""
 
     async def run_test():
-        with patch('cdx_toolkit.filter_warc.aioboto3_writer.mpu_upload_part') as mock_upload_part, patch(
-            'cdx_toolkit.filter_warc.aioboto3_writer.mpu_complete'
+        with patch('cdx_toolkit.filter_warc.s3_writer.mpu_upload_part') as mock_upload_part, patch(
+            'cdx_toolkit.filter_warc.s3_writer.mpu_complete'
         ) as mock_complete:
             mock_upload_part.return_value = 'final-etag'
 
@@ -232,10 +208,13 @@ def test_shard_writer_close_empty():
     """Test ShardWriter close method with no data (empty buffer, no parts)."""
 
     async def run_test():
-        with patch('cdx_toolkit.filter_warc.aioboto3_writer.mpu_upload_part') as mock_upload_part, patch(
-            'cdx_toolkit.filter_warc.aioboto3_writer.mpu_complete'
+        with patch('cdx_toolkit.filter_warc.s3_writer.mpu_upload_part') as mock_upload_part, patch(
+            'cdx_toolkit.filter_warc.s3_writer.mpu_complete'
         ) as mock_complete:
+            mock_s3 = AsyncMock()
+
             writer = S3ShardWriter(
+                s3_client=mock_s3,
                 shard_key='test.warc.gz',
                 dest_bucket='test-bucket',
                 content_type='application/gzip',
@@ -246,8 +225,7 @@ async def run_test():
             writer.upload_id = 'test-upload-id'
 
             # No data in buffer, no parts uploaded
-            mock_s3 = AsyncMock()
-            await writer.close(mock_s3)
+            await writer.close()
 
             # Should not upload any parts or complete MPU since there's no data
             mock_upload_part.assert_not_called()
@@ -264,13 +242,16 @@ def test_shard_writer_close_with_exception():
     """Test ShardWriter close method with exception and abort handling."""
 
     async def run_test():
-        with patch('cdx_toolkit.filter_warc.aioboto3_writer.mpu_upload_part') as mock_upload_part, patch(
-            'cdx_toolkit.filter_warc.aioboto3_writer.mpu_complete'
-        ) as mock_complete, patch('cdx_toolkit.filter_warc.aioboto3_writer.mpu_abort') as mock_abort:
+        with patch('cdx_toolkit.filter_warc.s3_writer.mpu_upload_part') as mock_upload_part, patch(
+            'cdx_toolkit.filter_warc.s3_writer.mpu_complete'
+        ) as mock_complete, patch('cdx_toolkit.filter_warc.s3_writer.mpu_abort') as mock_abort:
             mock_upload_part.return_value = 'error-etag'
             mock_complete.side_effect = Exception('Complete failed')
 
+            mock_s3 = AsyncMock()
+
             writer = S3ShardWriter(
+                s3_client=mock_s3,
                 shard_key='test.warc.gz',
                 dest_bucket='test-bucket',
                 content_type='application/gzip',
@@ -283,11 +264,9 @@ async def run_test():
             # Add some data to buffer to trigger upload and complete
             writer.buffer.extend(b'some data')
 
-            mock_s3 = AsyncMock()
-
             # Should raise the exception after attempting abort
             with pytest.raises(Exception, match='Complete failed'):
-                await writer.close(mock_s3)
+                await writer.close()
 
             # Should have attempted to upload part and complete, then abort on failure
             mock_upload_part.assert_called_once()
@@ -295,3 +274,38 @@ async def run_test():
             mock_abort.assert_called_once_with(mock_s3, 'test-bucket', 'test.warc.gz', 'test-upload-id')
 
     asyncio.run(run_test())
+
+
+def test_mpu_abort_success():
+    """Test mpu_abort function with successful abort."""
+
+    async def run_test():
+        mock_s3 = AsyncMock()
+        bucket = 'test-bucket'
+        key = 'test-key'
+        upload_id = 'test-upload-id'
+
+        await mpu_abort(mock_s3, bucket, key, upload_id)
+
+        mock_s3.abort_multipart_upload.assert_called_once_with(Bucket=bucket, Key=key, UploadId=upload_id)
+
+    asyncio.run(run_test())
+
+
+def test_mpu_abort_with_exception():
+    """Test mpu_abort function when abort fails (should catch exception)."""
+
+    async def run_test():
+        mock_s3 = AsyncMock()
+        mock_s3.abort_multipart_upload.side_effect = Exception('S3 error')
+
+        bucket = 'test-bucket'
+        key = 'test-key'
+        upload_id = 'test-upload-id'
+
+        # Should not raise exception, should log it instead
+        await mpu_abort(mock_s3, bucket, key, upload_id)
+
+        mock_s3.abort_multipart_upload.assert_called_once_with(Bucket=bucket, Key=key, UploadId=upload_id)
+
+    asyncio.run(run_test())
diff --git a/tests/filter_warc/test_warc_by_cdx.py b/tests/filter_warc/test_warc_by_cdx.py
index ab7dd63..058685a 100644
--- a/tests/filter_warc/test_warc_by_cdx.py
+++ b/tests/filter_warc/test_warc_by_cdx.py
@@ -3,12 +3,7 @@
 
 import fsspec
 from cdx_toolkit.cli import main
-from cdx_toolkit.filter_warc.cdx_utils import (
-    get_index_as_string_from_path,
-)
-from cdx_toolkit.filter_warc.fsspec_warc_filter import (
-    generate_caputure_objects_from_index,
-)
+
 import pytest
 from warcio.archiveiterator import ArchiveIterator
 
@@ -23,7 +18,8 @@ def assert_cli_warc_by_cdx(
     base_prefix,
     caplog,
     extra_args: Optional[List[str]] = None,
-    warc_filename: str = 'TEST_warc_by_index-000000.extracted.warc.gz',
+    # warc_filename: str = 'TEST_warc_by_index-000000.extracted.warc.gz',
+    warc_filename: str = 'TEST_warc_by_index-000000-001.extracted.warc.gz',  # due to parallel writer
 ):
     # test cli and check output
     index_path = fixture_path / 'filtered_CC-MAIN-2024-30_cdx-00187.gz'
@@ -139,15 +135,6 @@ def test_cli_warc_by_cdx_over_s3_to_s3_in_parallel(s3_tmpdir, caplog):
     )
 
 
-def test_get_caputure_objects_from_index():
-    index_path = fixture_path / 'filtered_CC-MAIN-2024-30_cdx-00187.gz'
-
-    for obj in generate_caputure_objects_from_index(get_index_as_string_from_path(index_path).splitlines()):
-        break
-
-    assert obj.data['length'] == '9754'
-
-
 def test_warc_by_cdx_no_index_files_found_exits(tmpdir, caplog):
     # Test that warc_by_cdx exits when no index files match the glob pattern
     with pytest.raises(SystemExit) as exc_info:
@@ -167,24 +154,6 @@ def test_warc_by_cdx_no_index_files_found_exits(tmpdir, caplog):
     assert 'no index files found' in caplog.text
 
 
-def test_generate_caputure_objects_invalid_cdx_line():
-    # Test invalid CDX line parsing (line with wrong number of columns)
-    with pytest.raises(ValueError):
-        list(generate_caputure_objects_from_index('invalid-format'))
-
-
-def test_generate_caputure_objects_with_limit():
-    # Test limit functionality in get_caputure_objects_from_index
-    index_path = fixture_path / 'filtered_CC-MAIN-2024-30_cdx-00187.gz'
-    index_content = get_index_as_string_from_path(index_path)
-
-    # Count objects with limit=2
-    objects = list(generate_caputure_objects_from_index(index_content.splitlines(), limit=2))
-
-    # Should stop after 2 objects
-    assert len(objects) == 2
-
-
 def test_warc_by_cdx_subprefix_and_metadata(tmpdir):
     # Test subprefix functionality and creator/operator metadata
     index_path = fixture_path / 'filtered_CC-MAIN-2024-30_cdx-00187.gz'
@@ -205,7 +174,7 @@ def test_warc_by_cdx_subprefix_and_metadata(tmpdir):
     )
 
     # Check that WARC file was created with subprefix
-    warc_path = os.path.join(tmpdir, 'TEST-SUB-000000.extracted.warc.gz')
+    warc_path = os.path.join(tmpdir, 'TEST-SUB-000000-001.extracted.warc.gz')
     assert os.path.exists(warc_path)
 
     # Validate metadata in warcinfo record
@@ -238,7 +207,7 @@ def test_warc_by_cdx_without_creator_operator(tmpdir):
     )
 
     # Check that WARC file was created
-    warc_path = os.path.join(tmpdir, 'TEST_NO_META-000000.extracted.warc.gz')
+    warc_path = os.path.join(tmpdir, 'TEST_NO_META-000000-001.extracted.warc.gz')
     assert os.path.exists(warc_path)
 
     # Validate that creator/operator are not in warcinfo record
diff --git a/tests/filter_warc/test_warc_by_cdx_aioboto3.py b/tests/filter_warc/test_warc_by_cdx_aioboto3.py
deleted file mode 100644
index 60231ce..0000000
--- a/tests/filter_warc/test_warc_by_cdx_aioboto3.py
+++ /dev/null
@@ -1,159 +0,0 @@
-import asyncio
-from io import BytesIO
-
-import aioboto3
-
-from tests.conftest import requires_aws_s3, TEST_DATA_PATH
-
-from warcio import WARCWriter
-from cdx_toolkit.filter_warc.aioboto3_warc_filter import get_range_jobs_from_index_paths, write_warc, _STOP
-from cdx_toolkit.filter_warc.aioboto3_utils import RangePayload, parse_s3_uri
-from tests.filter_warc.test_warc_by_cdx import assert_cli_warc_by_cdx
-
-fixture_path = TEST_DATA_PATH / 'warc_by_cdx'
-aioboto3_warc_filename = 'TEST_warc_by_index-000000-001.extracted.warc.gz'  # due to parallel writer
-
-
-@requires_aws_s3
-def test_cli_warc_by_cdx_over_s3_to_s3_in_parallel_aioboto3(s3_tmpdir, caplog):
-    assert_cli_warc_by_cdx(
-        's3://commoncrawl',
-        base_prefix=s3_tmpdir,
-        caplog=caplog,
-        extra_args=[
-            '--parallel=3',
-            '--implementation=aioboto3',
-        ],
-        warc_filename=aioboto3_warc_filename,
-    )
-
-
-def test_warc_info():
-    warc_version = '1.0'
-    gzip = False
-    file_handler = BytesIO()
-    filename = 'foo.warc'
-
-    info = {
-        'software': 'pypi_cdx_toolkit/123',
-        'isPartOf': 'bar',
-        'description': 'warc extraction based on CDX generated with: xx',
-        'format': 'WARC file version 1.0',
-    }
-
-    writer = WARCWriter(file_handler, gzip=gzip, warc_version=warc_version)
-    warcinfo = writer.create_warcinfo_record(filename, info)
-
-    writer.write_record(warcinfo)
-
-    file_value = file_handler.getvalue().decode('utf-8')
-
-    assert 'pypi_cdx_toolkit/123' in file_value
-
-
-@requires_aws_s3
-def test_write_warc_with_file_rotation(s3_tmpdir):
-    """Test write_warc function with file size rotation"""
-
-    async def run_test():
-        # Setup test data
-        index_path = fixture_path / 'filtered_CC-MAIN-2024-30_cdx-00187.gz'
-        warc_download_prefix = 's3://commoncrawl'
-        output_prefix_path = f'{s3_tmpdir}/file_rotation_test'
-
-        # Use small file size to force rotation (100 KB)
-        max_file_size = 100 * 1024  # 100 KB
-
-        # Create asyncio queues
-        key_queue = asyncio.Queue()
-        item_queue = asyncio.Queue()
-
-        # Writer info for WARC header
-        writer_info = {
-            'software': 'cdx_toolkit test',
-            'operator': 'test',
-            'creator': 'test',
-            'description': 'Test WARC with file rotation',
-        }
-
-        # Setup S3 client
-        from botocore.config import Config
-
-        boto_cfg = Config(
-            region_name='us-east-1',
-            retries={'max_attempts': 3, 'mode': 'standard'},
-            connect_timeout=10,
-            read_timeout=120,
-        )
-
-        session = aioboto3.Session()
-
-        async with session.client('s3', config=boto_cfg) as s3:
-            # Generate range jobs from CDX file
-            await get_range_jobs_from_index_paths(
-                key_queue=key_queue,
-                index_paths=[str(index_path)],
-                warc_download_prefix=warc_download_prefix,
-                num_fetchers=1,
-                limit=10,  # Use 10 records to ensure we have enough data
-            )
-
-            # Collect all range jobs
-            range_jobs = []
-            while not key_queue.empty():
-                job = await key_queue.get()
-                if job is not _STOP:
-                    range_jobs.append(job)
-                key_queue.task_done()
-
-            # Create mock RangePayload objects with dummy data to simulate large content
-            # Each payload will be ~30KB to force multiple file rotations
-            dummy_data = b'A' * (30 * 1024)  # 30KB of dummy data
-
-            for job in range_jobs:
-                payload = RangePayload(job=job, data=dummy_data)
-                await item_queue.put(payload)
-
-            # Add stop signal
-            await item_queue.put(_STOP)
-
-            # Run write_warc function
-            await write_warc(
-                consumer_id=0,
-                item_queue=item_queue,
-                s3=s3,
-                max_attempts=3,
-                base_backoff_seconds=0.5,
-                prefix_path=output_prefix_path,
-                writer_info=writer_info,
-                max_file_size=max_file_size,
-                gzip=True,
-            )
-
-            # Verify that multiple WARC files were created
-            dest_bucket, dest_prefix = parse_s3_uri(output_prefix_path)
-
-            # List objects to find all created WARC files
-            response = await s3.list_objects_v2(Bucket=dest_bucket, Prefix=dest_prefix)
-
-            warc_files = []
-            if 'Contents' in response:
-                for obj in response['Contents']:
-                    if obj['Key'].endswith('.extracted.warc.gz'):
-                        warc_files.append(obj['Key'])
-
-            # Assert that more than one WARC file was created
-            assert len(warc_files) == 4, f'Expected multiple WARC files, but found {len(warc_files)}: {warc_files}'
-
-            # Verify filename pattern includes sequence numbers
-            for warc_file in warc_files:
-                filename = warc_file.split('/')[-1]
-                # Should match pattern: prefix-000000-XXX.extracted.warc.gz
-                assert '-000000-' in filename, f"Filename doesn't contain expected sequence pattern: {filename}"
-
-            # Clean up created files
-            for warc_file in warc_files:
-                await s3.delete_object(Bucket=dest_bucket, Key=warc_file)
-
-    # Run the async test
-    asyncio.run(run_test())
diff --git a/tests/filter_warc/test_warc_filter.py b/tests/filter_warc/test_warc_filter.py
index c0b62bc..5da2935 100644
--- a/tests/filter_warc/test_warc_filter.py
+++ b/tests/filter_warc/test_warc_filter.py
@@ -1,17 +1,9 @@
-import asyncio
-from io import BytesIO
-
-import aioboto3
 
 from tests.conftest import requires_aws_s3, TEST_DATA_PATH
 
-from warcio import WARCWriter
-from cdx_toolkit.filter_warc.aioboto3_warc_filter import get_range_jobs_from_index_paths, write_warc, _STOP
-from cdx_toolkit.filter_warc.aioboto3_utils import RangePayload, parse_s3_uri
 from tests.filter_warc.test_warc_by_cdx import assert_cli_warc_by_cdx
 
 fixture_path = TEST_DATA_PATH / 'warc_by_cdx'
-aioboto3_warc_filename = 'TEST_warc_by_index-000000-001.extracted.warc.gz'  # due to parallel writer
 
 
 @requires_aws_s3
@@ -22,9 +14,7 @@ def test_cli_warc_by_cdx_over_s3_to_s3_in_parallel_warc_filter(s3_tmpdir, caplog
         caplog=caplog,
         extra_args=[
             '--parallel=3',
-            '--implementation=warc_filter',
         ],
-        warc_filename=aioboto3_warc_filename,
     )
 
 
@@ -36,9 +26,7 @@ def test_cli_warc_by_cdx_over_http_to_s3_in_parallel_warc_filter(s3_tmpdir, capl
         caplog=caplog,
         extra_args=[
             '--parallel=3',
-            '--implementation=warc_filter',
         ],
-        warc_filename=aioboto3_warc_filename,
     )
 
 
@@ -50,8 +38,5 @@ def test_cli_warc_by_cdx_over_s3_to_local_in_parallel_warc_filter(tmpdir, caplog
         caplog=caplog,
         extra_args=[
             '--parallel=3',
-            '--implementation=warc_filter',
         ],
-        warc_filename=aioboto3_warc_filename,
     )
-
diff --git a/tests/filter_warc/test_warc_writer.py b/tests/filter_warc/test_warc_writer.py
index 4725ef4..19e5f19 100644
--- a/tests/filter_warc/test_warc_writer.py
+++ b/tests/filter_warc/test_warc_writer.py
@@ -3,19 +3,22 @@
 import pytest
 import cdx_toolkit
 
-from tests.conftest import requires_aws_s3
+from tests.conftest import TEST_DATA_PATH, requires_aws_s3
 
 from warcio import WARCWriter
 from warcio.archiveiterator import ArchiveIterator
 
 
+fixture_path = TEST_DATA_PATH / 'warc_by_cdx'
+
+
 @pytest.mark.parametrize(
     'prefix,gzip',
     [
         pytest.param('test-prefix', False, id='File name prefix on local'),
         pytest.param('test-prefix', True, id='File name prefix on local with gzip'),
         # raised FileNotFound error (parent dir does not exist)
-        # pytest.param("test-prefix-folder/file-prefix", None, id="Folder as prefix"),  
+        # pytest.param("test-prefix-folder/file-prefix", None, id="Folder as prefix"),
     ],
 )
 def test_write_to_local(prefix, gzip, tmpdir):
@@ -114,3 +117,26 @@ def test_write_to_s3(s3_tmpdir):
 
     assert 'description: test' in info_record
     assert resource_record == input_resource_record_text
+
+
+def test_warc_info():
+    warc_version = '1.0'
+    gzip = False
+    file_handler = BytesIO()
+    filename = 'foo.warc'
+
+    info = {
+        'software': 'pypi_cdx_toolkit/123',
+        'isPartOf': 'bar',
+        'description': 'warc extraction based on CDX generated with: xx',
+        'format': 'WARC file version 1.0',
+    }
+
+    writer = WARCWriter(file_handler, gzip=gzip, warc_version=warc_version)
+    warcinfo = writer.create_warcinfo_record(filename, info)
+
+    writer.write_record(warcinfo)
+
+    file_value = file_handler.getvalue().decode('utf-8')
+
+    assert 'pypi_cdx_toolkit/123' in file_value

From 7e4c80bd6fed8559b085720d66bc1bd570805d4b Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Wed, 1 Oct 2025 21:20:47 +0200
Subject: [PATCH 47/74] Adding keyboard interupt handling

---
 cdx_toolkit/filter_cdx/__init__.py | 50 ++++++++++++++++--------------
 1 file changed, 27 insertions(+), 23 deletions(-)

diff --git a/cdx_toolkit/filter_cdx/__init__.py b/cdx_toolkit/filter_cdx/__init__.py
index 0c8cb37..822ffac 100644
--- a/cdx_toolkit/filter_cdx/__init__.py
+++ b/cdx_toolkit/filter_cdx/__init__.py
@@ -99,29 +99,33 @@ def filter_cdx(
     # Parallel processing
     logger.info('Filtering with %i processes in parallel (limit: %i)', n_parallel, limit)
 
-    with ProcessPoolExecutor(max_workers=n_parallel) as executor:
-        # Create partial function with common arguments
-        process_file_partial = partial(_process_single_file, matcher=matcher, limit=limit)
-
-        # Submit all jobs
-        future_to_paths = {
-            executor.submit(process_file_partial, input_path, output_path): (input_path, output_path)
-            for input_path, output_path in zip(input_paths, output_paths)
-        }
-
-        # Collect results
-        for future in as_completed(future_to_paths):
-            input_path, output_path = future_to_paths[future]
-            try:
-                lines_n, included_n = future.result()
-                logger.info(f'File statistics: included {total_included_n} / {total_lines_n} lines: {input_path}')
-
-                total_lines_n += lines_n
-                total_included_n += included_n
-
-            except Exception as exc:
-                logger.error(f'File {input_path} generated an exception: {exc}')
-                total_errors_n += 1
+    try:
+        with ProcessPoolExecutor(max_workers=n_parallel) as executor:
+            # Create partial function with common arguments
+            process_file_partial = partial(_process_single_file, matcher=matcher, limit=limit)
+
+            # Submit all jobs
+            future_to_paths = {
+                executor.submit(process_file_partial, input_path, output_path): (input_path, output_path)
+                for input_path, output_path in zip(input_paths, output_paths)
+            }
+
+            # Collect results
+            for future in as_completed(future_to_paths):
+                input_path, output_path = future_to_paths[future]
+                try:
+                    lines_n, included_n = future.result()
+                    logger.info(f'File statistics: included {total_included_n} / {total_lines_n} lines: {input_path}')
+
+                    total_lines_n += lines_n
+                    total_included_n += included_n
+
+                except Exception as exc:
+                    logger.error(f'File {input_path} generated an exception: {exc}')
+                    total_errors_n += 1
+    except KeyboardInterrupt:
+        logger.warning('Process interrupted by user (Ctrl+C)')
+        # The executor context manager will handle cleanup automatically
 
     return total_lines_n, total_included_n, total_errors_n
 

From bb3f3a7955cd8a8535b84d6e713ab04f6d1a5891 Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Wed, 1 Oct 2025 21:40:40 +0200
Subject: [PATCH 48/74] Adding wild card test

---
 cdx_toolkit/filter_cdx/__init__.py            | 80 +++++++++++--------
 .../filter_cdx/whitelist_wildcard_urls.txt    |  2 +
 tests/filter_cdx/test_filter_cdx.py           | 23 ++++++
 3 files changed, 73 insertions(+), 32 deletions(-)
 create mode 100644 tests/data/filter_cdx/whitelist_wildcard_urls.txt

diff --git a/cdx_toolkit/filter_cdx/__init__.py b/cdx_toolkit/filter_cdx/__init__.py
index 822ffac..c865ae1 100644
--- a/cdx_toolkit/filter_cdx/__init__.py
+++ b/cdx_toolkit/filter_cdx/__init__.py
@@ -8,7 +8,7 @@
 
 import fsspec
 
-from url_is_in import URLMatcher, SURTMatcher
+from url_is_in import convert_url_to_surt_with_wildcard, SURTMatcher
 
 
 
@@ -52,11 +52,11 @@ def run_filter_cdx(args, cmdline: str):
 
     logger.info(f'Loaded {len(include_prefixes):,} filter entries')
 
-    # Use matcher based on URL or SURT inputs
+    # Convert URLs to SURTs
     if args.filter_type == 'url':
-        matcher = URLMatcher(include_prefixes, match_subdomains=True)
-    else:
-        matcher = SURTMatcher(include_prefixes, match_subdomains=True)
+        include_prefixes = [convert_url_to_surt_with_wildcard(item_url) for item_url in include_prefixes]
+
+    matcher = SURTMatcher(include_prefixes, match_subdomains=True)
 
     limit = 0 if args.limit is None else args.limit
 
@@ -85,7 +85,7 @@ def run_filter_cdx(args, cmdline: str):
 
 
 def filter_cdx(
-    matcher: Union[URLMatcher, SURTMatcher],
+    matcher: SURTMatcher,
     input_paths: List[str],
     output_paths: List[str],
     n_parallel: int = 1,
@@ -99,33 +99,49 @@ def filter_cdx(
     # Parallel processing
     logger.info('Filtering with %i processes in parallel (limit: %i)', n_parallel, limit)
 
+    executor = ProcessPoolExecutor(max_workers=n_parallel)
+    future_to_paths = {}
+
     try:
-        with ProcessPoolExecutor(max_workers=n_parallel) as executor:
-            # Create partial function with common arguments
-            process_file_partial = partial(_process_single_file, matcher=matcher, limit=limit)
-
-            # Submit all jobs
-            future_to_paths = {
-                executor.submit(process_file_partial, input_path, output_path): (input_path, output_path)
-                for input_path, output_path in zip(input_paths, output_paths)
-            }
-
-            # Collect results
-            for future in as_completed(future_to_paths):
-                input_path, output_path = future_to_paths[future]
-                try:
-                    lines_n, included_n = future.result()
-                    logger.info(f'File statistics: included {total_included_n} / {total_lines_n} lines: {input_path}')
-
-                    total_lines_n += lines_n
-                    total_included_n += included_n
-
-                except Exception as exc:
-                    logger.error(f'File {input_path} generated an exception: {exc}')
-                    total_errors_n += 1
+        # Create partial function with common arguments
+        process_file_partial = partial(_process_single_file, matcher=matcher, limit=limit)
+
+        # Submit all jobs
+        future_to_paths = {
+            executor.submit(process_file_partial, input_path, output_path): (input_path, output_path)
+            for input_path, output_path in zip(input_paths, output_paths)
+        }
+
+        # Collect results
+        for future in as_completed(future_to_paths):
+            input_path, output_path = future_to_paths[future]
+            try:
+                lines_n, included_n = future.result()
+                logger.info(f'File statistics: included {total_included_n} / {total_lines_n} lines: {input_path}')
+
+                total_lines_n += lines_n
+                total_included_n += included_n
+
+            except Exception as exc:
+                logger.error(f'File {input_path} generated an exception: {exc}')
+                total_errors_n += 1
+
     except KeyboardInterrupt:
-        logger.warning('Process interrupted by user (Ctrl+C)')
-        # The executor context manager will handle cleanup automatically
+        logger.warning('Process interrupted by user (Ctrl+C). Cancelling running tasks...')
+
+        # Cancel all pending futures
+        for future in future_to_paths:
+            future.cancel()
+
+        # Force shutdown the executor
+        executor.shutdown(wait=False)
+
+        logger.info('All tasks cancelled.')
+        return total_lines_n, total_included_n, total_errors_n
+
+    finally:
+        # Clean shutdown in normal case
+        executor.shutdown(wait=True)
 
     return total_lines_n, total_included_n, total_errors_n
 
@@ -171,7 +187,7 @@ def resolve_paths(input_base_path: str, input_glob: str, output_base_path: str):
 def _process_single_file(
     input_path: str,
     output_path: str,
-    matcher: Union[SURTMatcher, URLMatcher],
+    matcher: SURTMatcher,
     limit: int = 0,
     log_every_n: int = 100_000,
 ):
diff --git a/tests/data/filter_cdx/whitelist_wildcard_urls.txt b/tests/data/filter_cdx/whitelist_wildcard_urls.txt
new file mode 100644
index 0000000..0371ef3
--- /dev/null
+++ b/tests/data/filter_cdx/whitelist_wildcard_urls.txt
@@ -0,0 +1,2 @@
+*.com
+*.fr
\ No newline at end of file
diff --git a/tests/filter_cdx/test_filter_cdx.py b/tests/filter_cdx/test_filter_cdx.py
index a6cde32..97a83d7 100644
--- a/tests/filter_cdx/test_filter_cdx.py
+++ b/tests/filter_cdx/test_filter_cdx.py
@@ -59,6 +59,29 @@ def test_cli_filter_cdx_with_urls(tmpdir, caplog):
     assert 'Limit reached' in caplog.text
 
 
+@requires_aws_s3
+def test_cli_filter_cdx_with_wildcard_urls(tmpdir, caplog):
+    # check if expected number is reached
+    index_path = 's3://commoncrawl/cc-index/collections'
+    index_glob = '/CC-MAIN-2024-30/indexes/cdx-00187.gz'
+    whitelist_path = fixture_path / 'whitelist_wildcard_urls.txt'  # matches on all .com and .fr host names
+
+    main(
+        args=[
+            '-v',
+            '--limit=10',
+            'filter_cdx',
+            f'{index_path}',
+            f'{str(whitelist_path)}',
+            f'{tmpdir}',
+            '--filter-type=url',
+            f'--input-glob={index_glob}',
+        ]
+    )
+
+    assert 'Limit reached' in caplog.text
+
+
 @requires_aws_s3
 def test_resolve_cdx_paths_from_cc_s3_to_local(tmpdir):
     tmpdir = str(tmpdir)

From ad2b3260f9d6ba702a68d8fe996cbe174cb9cec2 Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Wed, 1 Oct 2025 21:56:46 +0200
Subject: [PATCH 49/74] Refactor to imap

---
 cdx_toolkit/filter_cdx/__init__.py | 62 +++++++++++-------------------
 1 file changed, 23 insertions(+), 39 deletions(-)

diff --git a/cdx_toolkit/filter_cdx/__init__.py b/cdx_toolkit/filter_cdx/__init__.py
index c865ae1..ca1d077 100644
--- a/cdx_toolkit/filter_cdx/__init__.py
+++ b/cdx_toolkit/filter_cdx/__init__.py
@@ -2,8 +2,8 @@
 import os
 import time
 import sys
-from concurrent.futures import ProcessPoolExecutor, as_completed
 from functools import partial
+from multiprocessing import Pool
 from typing import List, Tuple, Union
 
 import fsspec
@@ -99,49 +99,33 @@ def filter_cdx(
     # Parallel processing
     logger.info('Filtering with %i processes in parallel (limit: %i)', n_parallel, limit)
 
-    executor = ProcessPoolExecutor(max_workers=n_parallel)
-    future_to_paths = {}
+    # Create partial function with common arguments
+    process_file_partial = partial(_process_single_file, matcher=matcher, limit=limit)
 
-    try:
-        # Create partial function with common arguments
-        process_file_partial = partial(_process_single_file, matcher=matcher, limit=limit)
-
-        # Submit all jobs
-        future_to_paths = {
-            executor.submit(process_file_partial, input_path, output_path): (input_path, output_path)
-            for input_path, output_path in zip(input_paths, output_paths)
-        }
-
-        # Collect results
-        for future in as_completed(future_to_paths):
-            input_path, output_path = future_to_paths[future]
-            try:
-                lines_n, included_n = future.result()
-                logger.info(f'File statistics: included {total_included_n} / {total_lines_n} lines: {input_path}')
+    # Prepare arguments for each task
+    task_args = list(zip(input_paths, output_paths))
 
-                total_lines_n += lines_n
-                total_included_n += included_n
-
-            except Exception as exc:
-                logger.error(f'File {input_path} generated an exception: {exc}')
-                total_errors_n += 1
+    pool = None
+    try:
+        pool = Pool(processes=n_parallel)
+        # Use imap for better interrupt handling
+        for lines_n, included_n in pool.imap(lambda args: process_file_partial(*args), task_args):
+            total_lines_n += lines_n
+            total_included_n += included_n
 
     except KeyboardInterrupt:
-        logger.warning('Process interrupted by user (Ctrl+C). Cancelling running tasks...')
-
-        # Cancel all pending futures
-        for future in future_to_paths:
-            future.cancel()
-
-        # Force shutdown the executor
-        executor.shutdown(wait=False)
-
-        logger.info('All tasks cancelled.')
-        return total_lines_n, total_included_n, total_errors_n
-
+        logger.warning('Process interrupted by user (Ctrl+C). Terminating running tasks...')
+        if pool:
+            pool.terminate()
+            pool.join()
+        logger.info('All tasks terminated.')
+    except Exception as exc:
+        logger.error(f'Error during parallel processing: {exc}')
+        total_errors_n += 1
     finally:
-        # Clean shutdown in normal case
-        executor.shutdown(wait=True)
+        if pool:
+            pool.close()
+            pool.join()
 
     return total_lines_n, total_included_n, total_errors_n
 

From cca857a591aa6bff677081590d53ff693288e752 Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Wed, 1 Oct 2025 22:06:53 +0200
Subject: [PATCH 50/74] Refactor to imap (2)

---
 cdx_toolkit/filter_cdx/__init__.py | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/cdx_toolkit/filter_cdx/__init__.py b/cdx_toolkit/filter_cdx/__init__.py
index ca1d077..db61e6d 100644
--- a/cdx_toolkit/filter_cdx/__init__.py
+++ b/cdx_toolkit/filter_cdx/__init__.py
@@ -84,6 +84,12 @@ def run_filter_cdx(args, cmdline: str):
     logger.info(f'Script execution time: {execution_time:.3f} seconds')
 
 
+def _process_file_args(args) -> Tuple[str, str, int, int]:
+    """Wrapper function to unpack arguments for multiprocessing."""
+    input_path, output_path, matcher, limit = args
+    return _process_single_file(input_path, output_path, matcher, limit)
+
+
 def filter_cdx(
     matcher: SURTMatcher,
     input_paths: List[str],
@@ -99,19 +105,18 @@ def filter_cdx(
     # Parallel processing
     logger.info('Filtering with %i processes in parallel (limit: %i)', n_parallel, limit)
 
-    # Create partial function with common arguments
-    process_file_partial = partial(_process_single_file, matcher=matcher, limit=limit)
-
-    # Prepare arguments for each task
-    task_args = list(zip(input_paths, output_paths))
+    # Prepare arguments for each task (input_path, output_path, matcher, limit)
+    task_args = [(input_path, output_path, matcher, limit)
+                 for input_path, output_path in zip(input_paths, output_paths)]
 
     pool = None
     try:
         pool = Pool(processes=n_parallel)
         # Use imap for better interrupt handling
-        for lines_n, included_n in pool.imap(lambda args: process_file_partial(*args), task_args):
+        for input_path, _, lines_n, included_n in pool.imap(_process_file_args, task_args):
             total_lines_n += lines_n
             total_included_n += included_n
+            logger.info(f'File statistics: included {total_included_n} / {total_lines_n} lines: {input_path}')
 
     except KeyboardInterrupt:
         logger.warning('Process interrupted by user (Ctrl+C). Terminating running tasks...')
@@ -174,7 +179,7 @@ def _process_single_file(
     matcher: SURTMatcher,
     limit: int = 0,
     log_every_n: int = 100_000,
-):
+) -> Tuple[str, str, int, int]:
     """Process a single input/output file pair. Returns (lines_n, included_n)."""
     lines_n = 0
     included_n = 0
@@ -219,7 +224,7 @@ def _process_single_file(
         logger.warning('Output file is empty, removing it: %s', output_fs_path)
         output_fs.rm(output_fs_path)
 
-    return lines_n, included_n
+    return input_path, output_path, lines_n, included_n
 
 
 def validate_resolved_paths(output_paths, overwrite):

From 0e034754582c073ce7b1f231dd23df648b4adcfd Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Thu, 2 Oct 2025 10:45:32 +0000
Subject: [PATCH 51/74] Make sure tests run with empty cache dir

---
 cdx_toolkit/filter_cdx/__init__.py  | 80 +++++++++++++++++------------
 requirements.txt                    | 18 +++----
 tests/conftest.py                   |  9 ++++
 tests/filter_cdx/test_filter_cdx.py |  8 +--
 4 files changed, 70 insertions(+), 45 deletions(-)

diff --git a/cdx_toolkit/filter_cdx/__init__.py b/cdx_toolkit/filter_cdx/__init__.py
index db61e6d..0404223 100644
--- a/cdx_toolkit/filter_cdx/__init__.py
+++ b/cdx_toolkit/filter_cdx/__init__.py
@@ -84,7 +84,7 @@ def run_filter_cdx(args, cmdline: str):
     logger.info(f'Script execution time: {execution_time:.3f} seconds')
 
 
-def _process_file_args(args) -> Tuple[str, str, int, int]:
+def _process_file_args(args) -> Tuple[str, str, int, int, int]:
     """Wrapper function to unpack arguments for multiprocessing."""
     input_path, output_path, matcher, limit = args
     return _process_single_file(input_path, output_path, matcher, limit)
@@ -113,9 +113,11 @@ def filter_cdx(
     try:
         pool = Pool(processes=n_parallel)
         # Use imap for better interrupt handling
-        for input_path, _, lines_n, included_n in pool.imap(_process_file_args, task_args):
+        for input_path, _, lines_n, included_n, errors_n in pool.imap(_process_file_args, task_args):
             total_lines_n += lines_n
             total_included_n += included_n
+            total_errors_n += errors_n
+
             logger.info(f'File statistics: included {total_included_n} / {total_lines_n} lines: {input_path}')
 
     except KeyboardInterrupt:
@@ -132,6 +134,8 @@ def filter_cdx(
             pool.close()
             pool.join()
 
+    logger.warning(f"Filter CDX errors: {total_errors_n}")
+
     return total_lines_n, total_included_n, total_errors_n
 
 
@@ -179,52 +183,64 @@ def _process_single_file(
     matcher: SURTMatcher,
     limit: int = 0,
     log_every_n: int = 100_000,
-) -> Tuple[str, str, int, int]:
+) -> Tuple[str, str, int, int, int]:
     """Process a single input/output file pair. Returns (lines_n, included_n)."""
     lines_n = 0
     included_n = 0
+    errors_n = 0
 
     logger.info('Reading index from %s', input_path)
     logger.info('Writing filter output to %s', output_path)
 
-    # Input/output from local or remote file system
-    input_fs, input_fs_path = fsspec.url_to_fs(input_path)
-    output_fs, output_fs_path = fsspec.url_to_fs(output_path)
+    try:
+
+        # Input/output from local or remote file system
+        input_fs, input_fs_path = fsspec.url_to_fs(input_path)
+        output_fs, output_fs_path = fsspec.url_to_fs(output_path)
+
+        # Make sure output directory exists
+        output_fs.makedirs(output_fs._parent(output_fs_path), exist_ok=True)
+
+        # Read and write compressed file if needed
+        compression = 'gzip' if input_fs_path.endswith('.gz') else None
 
-    # Make sure output directory exists
-    output_fs.makedirs(output_fs._parent(output_fs_path), exist_ok=True)
+        with output_fs.open(output_fs_path, 'w', compression=compression) as output_f:
+            with input_fs.open(input_fs_path, 'rt', compression=compression) as input_f:
+                for i, line in enumerate(input_f, 1):
+                    try:
+                        # Read CDX line
+                        surt_length = line.find(' ')  # we do not need to parse the full line
+                        record_surt = line[:surt_length]
+                        lines_n += 1
 
-    # Read and write compressed file if needed
-    compression = 'gzip' if input_fs_path.endswith('.gz') else None
+                        # Use SURT matcher
+                        include_record = matcher.is_in(record_surt)
 
-    with output_fs.open(output_fs_path, 'w', compression=compression) as output_f:
-        with input_fs.open(input_fs_path, 'rt', compression=compression) as input_f:
-            for i, line in enumerate(input_f, 1):
-                # Read CDX line
-                surt_length = line.find(' ')  # we do not need to parse the full line
-                record_surt = line[:surt_length]
-                lines_n += 1
+                        if include_record:
+                            output_f.write(line)
+                            included_n += 1
 
-                # Use SURT matcher
-                include_record = matcher.is_in(record_surt)
+                            if limit > 0 and included_n >= limit:
+                                logger.info('Limit reached at %i from %s', limit, input_path)
+                                break
 
-                if include_record:
-                    output_f.write(line)
-                    included_n += 1
+                        if (i % log_every_n) == 0:
+                            logger.info(f'Lines completed: {i:,} (matched: {included_n:,}) from {input_path}')
 
-                    if limit > 0 and included_n >= limit:
-                        logger.info('Limit reached at %i from %s', limit, input_path)
-                        break
+                    except Exception as e:
+                        logger.error(f"Line processing error: {e}")
+                        errors_n += 1
 
-                if (i % log_every_n) == 0:
-                    logger.info(f'Lines completed: {i:,} (matched: {included_n:,}) from {input_path}')
+        # Delete file if empty
+        if included_n == 0:
+            logger.warning('Output file is empty, removing it: %s', output_fs_path)
+            output_fs.rm(output_fs_path)
 
-    # Delete file if empty
-    if included_n == 0:
-        logger.warning('Output file is empty, removing it: %s', output_fs_path)
-        output_fs.rm(output_fs_path)
+    except Exception as e:
+        logger.error(f"File processing error: {e}")
+        errors_n += 1
 
-    return input_path, output_path, lines_n, included_n
+    return input_path, output_path, lines_n, included_n, errors_n
 
 
 def validate_resolved_paths(output_paths, overwrite):
diff --git a/requirements.txt b/requirements.txt
index 586889b..5599f31 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,7 +1,7 @@
 # Install with "python -m pip install -r requirements.txt".
 # must be kept in sync with setup.py
 
-requests==2.25.1
+requests>=2.25.1
 warcio==1.7.4
 fsspec[s3]
 surt>=0.3.1
@@ -9,14 +9,14 @@ tqdm>=4.67.1
 url-is-in>=0.1.1
 
 # used by Makefile
-pytest==6.2.4
-pytest-cov==2.12.1
-pytest-sugar==0.9.4
-coveralls==3.1.0
+pytest>=6.2.4
+pytest-cov>=2.12.1
+pytest-sugar>=0.9.4
+coveralls>=3.1.0
 botocore>=1.39.11
-responses==0.25.8
+responses>=0.25.8
 
 # packaging
-twine==3.4.1
-setuptools==57.0.0
-setuptools-scm==6.0.1
+twine>=3.4.1
+setuptools>=57.0.0
+setuptools-scm>=6.0.1
diff --git a/tests/conftest.py b/tests/conftest.py
index 82afa44..3697229 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -11,6 +11,7 @@
 import responses
 import base64
 import uuid
+import shutil
 
 from unittest.mock import patch
 
@@ -21,6 +22,14 @@
 TEST_DATA_BASE_PATH = Path(__file__).parent / 'data'
 
 
+@pytest.fixture(scope="session", autouse=True)
+def cleanup_cache():
+    """Delete cache directory before test session starts"""
+    cache_dir = os.path.expanduser('~/.cache/cdx_toolkit/')
+    if os.path.exists(cache_dir):
+        shutil.rmtree(cache_dir)
+
+
 def check_aws_s3_access():
     """Check if AWS S3 access is available."""
     try:
diff --git a/tests/filter_cdx/test_filter_cdx.py b/tests/filter_cdx/test_filter_cdx.py
index 97a83d7..bed4783 100644
--- a/tests/filter_cdx/test_filter_cdx.py
+++ b/tests/filter_cdx/test_filter_cdx.py
@@ -201,7 +201,7 @@ def test_process_single_file(tmpdir):
     input_path = TEST_DATA_PATH / 'warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.gz'
     matcher = SURTMatcher(['fr,'])
 
-    lines_n, included_n = _process_single_file(
+    _, _, lines_n, included_n = _process_single_file(
         input_path=input_path,
         output_path=tmpdir + '/filter_cdx',
         matcher=matcher,
@@ -218,7 +218,7 @@ def test_process_single_file_empty(tmpdir):
     with open(input_path, 'w') as f:
         f.write('')
 
-    lines_n, included_n = _process_single_file(
+    _, _, lines_n, included_n = _process_single_file(
         input_path=input_path,
         output_path=tmpdir + '/output',
         matcher=None,
@@ -247,9 +247,9 @@ def mock_process_single_file(*args, **kwargs):
         )
 
         # Verify error handling results
-        assert total_errors == 2, f'Should have 1 error from the failed file, got {total_errors}'
+        assert total_errors == 1, f'Should have 1 error from the first failed file, got {total_errors}'
         assert total_lines == 0, 'Should have lines from the successful file'
         assert total_included == 0, 'Should have included lines from the successful file'
 
         # Check that error was logged correctly
-        assert 'generated an exception' in caplog.text
+        assert 'Error during parallel processing' in caplog.text

From 3664db140733e4f6f1eb75321963801dfe461164 Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Thu, 2 Oct 2025 17:52:23 +0000
Subject: [PATCH 52/74] CI tests only feature

---
 .github/workflows/ci.yaml              |   6 +-
 cdx_toolkit/filter_warc/warc_filter.py | 122 ++++++++++++++++++++++---
 2 files changed, 113 insertions(+), 15 deletions(-)

diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
index c818e3b..af07c13 100644
--- a/.github/workflows/ci.yaml
+++ b/.github/workflows/ci.yaml
@@ -84,9 +84,11 @@ jobs:
           script: |
             core.exportVariable('CDXT_DISABLE_S3_TESTS', '1')
 
-      - name: Run tests
+      - name: Run tests (only feature)
         run: |
-          make test_coverage
+          # make test_coverage
+          pytest -rA -s --doctest-modules --cov-report=xml --cov-append --cov cdx_toolkit tests/filter_warc tests/filter_cdx -v -v
+          coverage report
 
       - name: Upload coverage to Codecov
         uses: codecov/codecov-action@v4
diff --git a/cdx_toolkit/filter_warc/warc_filter.py b/cdx_toolkit/filter_warc/warc_filter.py
index 21c9da4..85a3f06 100644
--- a/cdx_toolkit/filter_warc/warc_filter.py
+++ b/cdx_toolkit/filter_warc/warc_filter.py
@@ -24,7 +24,9 @@
 
 
 class WARCFilter:
-    """Filter WARC files using a three stage listner-producer-consumer pattern.
+    """Filter or extract specific records from WARC files based on CDX indexes.
+    
+    The WARC filter uses a three stage listner-producer-consumer pattern.
 
     Filter targets:
     - CDX index files from local or remote file system.
@@ -64,6 +66,33 @@ def __init__(
         min_part_size: int = 5 * 1024 * 1024,  # 5 MiB (for upload)
         max_file_size: Optional[int] = 1 * 1024 * 1024 * 1024,  # 1 GiB (for WARC outputs)
     ):
+        """Initialize the WARC filter.
+
+        Args:
+            index_paths: List of paths to CDX index files.
+            prefix_path: Output path prefix for filtered WARC files.
+            writer_info: Dictionary containing writer metadata.
+            writer_subprefix: Optional subprefix for writer output paths.
+            write_paths_as_resource_records: Optional list of file paths to write as resource records.
+            write_paths_as_resource_records_metadata: Optional list of metadata paths for resource records.
+            record_limit: Maximum number of records to process (0 for unlimited).
+            log_every_n: Log progress every N records.
+            warc_download_prefix: Optional prefix to prepend to WARC URLs.
+            n_parallel: Number of parallel workers (default for readers/writers).
+            n_parallel_readers: Number of parallel reader tasks (overrides n_parallel).
+            n_parallel_writers: Number of parallel writer tasks (overrides n_parallel).
+            max_attempts: Maximum retry attempts for failed operations.
+            base_backoff_seconds: Base backoff time in seconds for retries.
+            writer_kwargs: Optional additional kwargs for writers.
+            range_jobs_queue_size: Maximum size of range jobs queue.
+            warc_records_queue_size: Maximum size of WARC records queue.
+            fetcher_to_consumer_ratio: Ratio of readers to writers for auto-scaling.
+            aws_region_name: AWS region name for S3 operations.
+            warc_version: WARC format version (e.g., '1.0' or '1.1').
+            content_type: Optional content type for WARC output.
+            min_part_size: Minimum part size for multipart uploads (5 MiB).
+            max_file_size: Maximum size for individual WARC files (1 GiB).
+        """
         self.index_paths = index_paths
         self.prefix_path = prefix_path
         self.writer_info = writer_info
@@ -93,7 +122,11 @@ def __init__(
         self.max_file_size = max_file_size
 
     def filter(self) -> int:
-        """Perform the filtering process (calls async method via asyncio.run)."""
+        """Perform the filtering process (calls async method via asyncio.run).
+
+        Returns:
+            int: Number of records written, or -1 if interrupted.
+        """
         try:
             return asyncio.run(self.filter_async())
         except KeyboardInterrupt:
@@ -102,7 +135,11 @@ def filter(self) -> int:
         return -1
 
     def needs_s3(self) -> bool:
-        """Returns true if S3 is needed at any stage."""
+        """Returns true if S3 is needed at any stage.
+
+        Returns:
+            bool: True if S3 client is needed for any operation.
+        """
         return (
             (self.index_paths is not None and len(self.index_paths) > 0 and is_s3_url(self.index_paths[0]))  # stage 1
             or is_s3_url(self.warc_download_prefix)  # stage 3
@@ -110,7 +147,14 @@ def needs_s3(self) -> bool:
         )
 
     def get_s3_client_context(self):
-        """Return s3 client context if needed."""
+        """Return s3 client context if needed.
+
+        Returns:
+            Optional[aioboto3.Session.client]: S3 client context manager if S3 is needed, None otherwise.
+
+        Raises:
+            SystemExit: If S3 is needed but Python version is < 3.9.
+        """
         if self.needs_s3():
             if sys.version_info.major < 3 or (sys.version_info.major >= 3 and sys.version_info.minor < 9):
                 logger.error('Reading and writing to S3 requires Python version >= 3.9')
@@ -125,7 +169,11 @@ def get_s3_client_context(self):
             return None
 
     async def filter_async(self) -> int:
-        """Filter process using a three stage approach (job generator, warc reader, warc writer)."""
+        """Filter process using a three stage approach (job generator, warc reader, warc writer).
+
+        Returns:
+            int: Number of records written.
+        """
         range_jobs_queue: asyncio.Queue = asyncio.Queue(maxsize=self.range_jobs_queue_size)
         warc_records_queue: asyncio.Queue = asyncio.Queue(maxsize=self.warc_records_queue_size)
 
@@ -134,10 +182,24 @@ async def filter_async(self) -> int:
             async with s3_client_context as s3_client:
                 return await self._run_filter_pipeline(range_jobs_queue, warc_records_queue, s3_client)
         else:
-            return await self._run_filter_pipeline(range_jobs_queue, warc_records_queue, None)
-
-    async def _run_filter_pipeline(self, range_jobs_queue: asyncio.Queue, warc_records_queue: asyncio.Queue, s3_client) -> int:
-        """Run the actual filter pipeline with or without S3 client."""
+            return await self._run_filter_pipeline(range_jobs_queue, warc_records_queue)
+
+    async def _run_filter_pipeline(
+            self,
+            range_jobs_queue: asyncio.Queue,
+            warc_records_queue: asyncio.Queue,
+            s3_client=None,
+        ) -> int:
+        """Run the actual filter pipeline with or without S3 client.
+
+        Args:
+            range_jobs_queue: Queue for range jobs from CDX index.
+            warc_records_queue: Queue for WARC record payloads.
+            s3_client: Optional S3 client for reading/writing to S3.
+
+        Returns:
+            int: Number of records written.
+        """
         # Fetch file paths and ranges (offset, length) from index files
         logger.info('Starting lister, %d fetchers, %d consumers', self.num_readers, self.num_writers)
 
@@ -200,7 +262,7 @@ async def _run_filter_pipeline(self, range_jobs_queue: asyncio.Queue, warc_recor
         )
 
         logger.info(f'All WARC writers completed: {writers_records} records')
-        logger.info(f'Writer throughput: {writers_mb_per_sec:.2f} MB/s; {writers_records_per_sec:.2f} r/s')
+        logger.info(f'Writer throughput: {writers_mb_per_sec:.2f} MB/s; {writers_records_per_sec:.2f} rec/s')
 
         return writers_records
 
@@ -209,7 +271,12 @@ async def generate_range_jobs(
         range_jobs_queue: asyncio.Queue,
         s3_client=None,
     ):
-        """Read the CDX paths, parse lines -> RangeJob (WARC files and offets) -> key_queue."""
+        """Read the CDX paths, parse lines -> RangeJob (WARC files and offets) -> key_queue.
+
+        Args:
+            range_jobs_queue: Queue to put RangeJob objects into.
+            s3_client: Optional S3 client for reading CDX indexes from S3.
+        """
 
         logger.info('Range index limit: %i', self.record_limit)
         count = 0
@@ -250,7 +317,17 @@ async def read_warc_records(
         warc_records_queue: asyncio.Queue,
         s3_client=None,
     ) -> dict:
-        """Read WARC records based on range jobs -> enqueue RangePayload."""
+        """Read WARC records based on range jobs -> enqueue RangePayload.
+
+        Args:
+            reader_id: Unique identifier for this reader task.
+            range_jobs_queue: Queue to read RangeJob objects from.
+            warc_records_queue: Queue to put RangePayload objects into.
+            s3_client: Optional S3 client for reading WARC files from S3.
+
+        Returns:
+            dict: Statistics dictionary with reader_id and throughput stats.
+        """
         tracker = ThroughputTracker()
         tracker.start()
         counter = 0
@@ -312,7 +389,16 @@ async def write_warc_records(
         warc_records_queue: asyncio.Queue,
         s3_client=None,
     ) -> dict:
-        """Write WARC records. Each writer owns ONE shard MPU and appends ranges to it."""
+        """Write WARC records. Each writer owns ONE shard MPU and appends ranges to it.
+
+        Args:
+            writer_id: Unique identifier for this writer task.
+            warc_records_queue: Queue to read RangePayload objects from.
+            s3_client: Optional S3 client for writing WARC files to S3.
+
+        Returns:
+            dict: Statistics dictionary with writer_id and throughput stats.
+        """
         # File rotation tracking
         current_file_sequence = 1
         current_file_size = 0
@@ -429,9 +515,19 @@ async def write_warc_records(
         return {'writer_id': writer_id, 'stats': tracker.get_stats()}
 
     def get_boto3_config(self):
+        """Get boto3 configuration for S3 client.
+
+        Returns:
+            Config: Boto3 configuration object with retry and timeout settings.
+        """
+        # Calculate max connections based on parallelism
+        # Each reader + writer needs connections, plus some overhead for retries
+        max_pool_connections = max(50, (self.num_readers + self.num_writers) * 2)
+
         return Config(
             region_name=self.aws_region_name,
             retries={'max_attempts': max(2, self.max_attempts), 'mode': 'standard'},
             connect_timeout=10,
             read_timeout=120,
+            max_pool_connections=max_pool_connections,
         )

From ced19e52ee678e16098d7ab93ba0cb17e89cd620 Mon Sep 17 00:00:00 2001
From: malteos <malte@commoncrawl.org>
Date: Thu, 2 Oct 2025 18:06:06 +0000
Subject: [PATCH 53/74] Adding args; minor fix

---
 cdx_toolkit/filter_warc/__init__.py    | 22 +++++++++++++---------
 cdx_toolkit/filter_warc/args.py        | 10 ++++++++++
 cdx_toolkit/filter_warc/warc_filter.py | 10 +++++-----
 tests/filter_cdx/test_filter_cdx.py    |  6 ++++--
 4 files changed, 32 insertions(+), 16 deletions(-)

diff --git a/cdx_toolkit/filter_warc/__init__.py b/cdx_toolkit/filter_warc/__init__.py
index 6b38a8f..e4f2fe7 100644
--- a/cdx_toolkit/filter_warc/__init__.py
+++ b/cdx_toolkit/filter_warc/__init__.py
@@ -41,14 +41,17 @@ def run_warcer_by_cdx(args, cmdline):
     if not write_paths_as_resource_records and write_paths_as_resource_records_metadata:
         raise ValueError("Metadata paths are set but resource records paths are missing.")
 
-    ispartof = args.prefix
-    if args.subprefix:
-        ispartof += '-' + args.subprefix
+    if args.is_part_of:
+        ispartof = args.is_part_of
+    else:
+        ispartof = args.prefix
+        if args.subprefix:
+            ispartof += '-' + args.subprefix
 
     info = {
         'software': 'pypi_cdx_toolkit/' + get_version(),
         'isPartOf': ispartof,
-        'description': 'warc extraction based on CDX generated with: ' + cmdline,
+        'description': args.description if args.description else 'warc extraction based on CDX generated with: ' + cmdline,
         'format': 'WARC file version 1.0',
     }
     if args.creator:
@@ -56,10 +59,10 @@ def run_warcer_by_cdx(args, cmdline):
     if args.operator:
         info['operator'] = args.operator
 
-    writer_kwargs = {}
-    if 'size' in kwargs:
-        writer_kwargs['size'] = kwargs['size']
-        del kwargs['size']
+    # writer_kwargs = {}
+    # if 'size' in kwargs:
+    #     writer_kwargs['size'] = kwargs['size']
+    #     del kwargs['size']
 
     n_parallel = args.parallel
     log_every_n = args.log_every_n
@@ -86,7 +89,8 @@ def run_warcer_by_cdx(args, cmdline):
         log_every_n=log_every_n,
         warc_download_prefix=cdx.warc_download_prefix,
         n_parallel=n_parallel,
-        writer_kwargs=writer_kwargs,
+        max_file_size=args.size,
+        # writer_kwargs=writer_kwargs,
     )
     records_n = warc_filter.filter()
 
diff --git a/cdx_toolkit/filter_warc/args.py b/cdx_toolkit/filter_warc/args.py
index b813742..72db4f9 100644
--- a/cdx_toolkit/filter_warc/args.py
+++ b/cdx_toolkit/filter_warc/args.py
@@ -32,6 +32,16 @@ def add_warcer_by_cdx_args(parser: argparse.ArgumentParser):
         help='creator of the warc: person, organization, service',
     )
     parser.add_argument('--operator', action='store', help='a person, if the creator is an organization')
+    parser.add_argument(
+        '--description',
+        action='store',
+        help='the `description` field in the `warcinfo` record (auto-generated if not set)',
+    )
+    parser.add_argument(
+        '--is-part-of',
+        action='store',
+        help='the `isPartOf` field in the `warcinfo` record (auto-generated if not set)',
+    )
     parser.add_argument(
         '--warc-download-prefix',
         action='store',
diff --git a/cdx_toolkit/filter_warc/warc_filter.py b/cdx_toolkit/filter_warc/warc_filter.py
index 85a3f06..d929aa4 100644
--- a/cdx_toolkit/filter_warc/warc_filter.py
+++ b/cdx_toolkit/filter_warc/warc_filter.py
@@ -56,7 +56,7 @@ def __init__(
         n_parallel_writers: Optional[int] = None,
         max_attempts: int = 5,
         base_backoff_seconds: float = 0.5,
-        writer_kwargs: Optional[Dict] = None,
+        # writer_kwargs: Optional[Dict] = None,
         range_jobs_queue_size: int = 1000,
         warc_records_queue_size: int = 200,
         fetcher_to_consumer_ratio: int = 6,
@@ -90,8 +90,8 @@ def __init__(
             aws_region_name: AWS region name for S3 operations.
             warc_version: WARC format version (e.g., '1.0' or '1.1').
             content_type: Optional content type for WARC output.
-            min_part_size: Minimum part size for multipart uploads (5 MiB).
-            max_file_size: Maximum size for individual WARC files (1 GiB).
+            min_part_size: Minimum part byte size for multipart uploads (default: 5 MiB).
+            max_file_size: Maximum byte size for individual WARC files (default: 1 GiB).
         """
         self.index_paths = index_paths
         self.prefix_path = prefix_path
@@ -103,7 +103,7 @@ def __init__(
         self.log_every_n = log_every_n
         self.warc_download_prefix = warc_download_prefix
 
-        self.writer_kwargs = writer_kwargs
+        # self.writer_kwargs = writer_kwargs
         self.range_jobs_queue_size = range_jobs_queue_size
         self.warc_records_queue_size = warc_records_queue_size
         self.aws_region_name = aws_region_name
@@ -356,7 +356,7 @@ async def read_warc_records(
                 tracker.add(bytes_count=len(data), records_count=job.records_count)
                 counter += 1
 
-                # Log progress every 10 items
+                # Log progress every N items
                 if self.log_every_n > 0 and counter % self.log_every_n == 0:
                     stats = tracker.get_stats()
                     logger.info(
diff --git a/tests/filter_cdx/test_filter_cdx.py b/tests/filter_cdx/test_filter_cdx.py
index bed4783..67839a9 100644
--- a/tests/filter_cdx/test_filter_cdx.py
+++ b/tests/filter_cdx/test_filter_cdx.py
@@ -201,7 +201,7 @@ def test_process_single_file(tmpdir):
     input_path = TEST_DATA_PATH / 'warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.gz'
     matcher = SURTMatcher(['fr,'])
 
-    _, _, lines_n, included_n = _process_single_file(
+    _, _, lines_n, included_n, errors_n = _process_single_file(
         input_path=input_path,
         output_path=tmpdir + '/filter_cdx',
         matcher=matcher,
@@ -211,6 +211,7 @@ def test_process_single_file(tmpdir):
 
     assert included_n == 100
     assert lines_n == 100
+    assert errors_n == 0
 
 
 def test_process_single_file_empty(tmpdir):
@@ -218,13 +219,14 @@ def test_process_single_file_empty(tmpdir):
     with open(input_path, 'w') as f:
         f.write('')
 
-    _, _, lines_n, included_n = _process_single_file(
+    _, _, lines_n, included_n, errors_n = _process_single_file(
         input_path=input_path,
         output_path=tmpdir + '/output',
         matcher=None,
     )
     assert lines_n == 0
     assert included_n == 0
+    assert errors_n == 0
 
 
 def test_filter_cdx_error_handling(tmpdir, caplog):

From d6e5a2560882f0a53ca922adf78688b26f6e86c0 Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Thu, 2 Oct 2025 21:04:22 +0200
Subject: [PATCH 54/74] force consitent multiprocessing behaviour across
 platforms

---
 tests/filter_cdx/test_filter_cdx.py | 59 +++++++++++++++++------------
 1 file changed, 35 insertions(+), 24 deletions(-)

diff --git a/tests/filter_cdx/test_filter_cdx.py b/tests/filter_cdx/test_filter_cdx.py
index 67839a9..5ab0616 100644
--- a/tests/filter_cdx/test_filter_cdx.py
+++ b/tests/filter_cdx/test_filter_cdx.py
@@ -231,27 +231,38 @@ def test_process_single_file_empty(tmpdir):
 
 def test_filter_cdx_error_handling(tmpdir, caplog):
     """Test filter_cdx function error handling when exceptions occur during processing."""
-
-    def mock_process_single_file(*args, **kwargs):
-        raise ValueError()
-
-    # Create test input and output paths
-    input_paths = [str(tmpdir / 'input1.cdx'), str(tmpdir / 'input2.cdx')]
-    output_paths = [str(tmpdir / 'output1.cdx'), str(tmpdir / 'output2.cdx')]
-
-    # Replace the _process_single_file function with our mock
-    with patch('cdx_toolkit.filter_cdx._process_single_file', side_effect=mock_process_single_file):
-        # Test the error handling
-        total_lines, total_included, total_errors = filter_cdx(
-            matcher=None,
-            input_paths=input_paths,
-            output_paths=output_paths,
-        )
-
-        # Verify error handling results
-        assert total_errors == 1, f'Should have 1 error from the first failed file, got {total_errors}'
-        assert total_lines == 0, 'Should have lines from the successful file'
-        assert total_included == 0, 'Should have included lines from the successful file'
-
-        # Check that error was logged correctly
-        assert 'Error during parallel processing' in caplog.text
+    import multiprocessing
+
+    # Store original start method to restore later
+    original_start_method = multiprocessing.get_start_method()
+
+    try:
+        # Force fork method for consistent behavior across platforms
+        multiprocessing.set_start_method('fork', force=True)
+
+        def mock_process_single_file(*args, **kwargs):
+            raise ValueError()
+
+        # Create test input and output paths
+        input_paths = [str(tmpdir / 'input1.cdx'), str(tmpdir / 'input2.cdx')]
+        output_paths = [str(tmpdir / 'output1.cdx'), str(tmpdir / 'output2.cdx')]
+
+        # Replace the _process_single_file function with our mock
+        with patch('cdx_toolkit.filter_cdx._process_single_file', side_effect=mock_process_single_file):
+            # Test the error handling
+            total_lines, total_included, total_errors = filter_cdx(
+                matcher=None,
+                input_paths=input_paths,
+                output_paths=output_paths,
+            )
+
+            # Verify error handling results
+            assert total_errors == 1, f'Should have 1 error from the first failed file, got {total_errors}'
+            assert total_lines == 0, 'Should have lines from the successful file'
+            assert total_included == 0, 'Should have included lines from the successful file'
+
+            # Check that error was logged correctly
+            assert 'Error during parallel processing' in caplog.text
+    finally:
+        # Restore original start method
+        multiprocessing.set_start_method(original_start_method, force=True)

From 9b2aa35fc3e0b2e260d3ab2bceb95ab9510b1d9d Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Thu, 2 Oct 2025 21:34:20 +0200
Subject: [PATCH 55/74] Adding resource records with warcinfo id

---
 cdx_toolkit/filter_warc/warc_filter.py | 68 ++++++++++++++++----------
 cdx_toolkit/filter_warc/warc_utils.py  | 17 +++++--
 tests/filter_warc/test_warc_filter.py  |  9 ++++
 3 files changed, 62 insertions(+), 32 deletions(-)

diff --git a/cdx_toolkit/filter_warc/warc_filter.py b/cdx_toolkit/filter_warc/warc_filter.py
index d929aa4..37da7dc 100644
--- a/cdx_toolkit/filter_warc/warc_filter.py
+++ b/cdx_toolkit/filter_warc/warc_filter.py
@@ -383,6 +383,36 @@ async def read_warc_records(
 
         return {'reader_id': reader_id, 'stats': tracker.get_stats()}
 
+    async def write_resource_records(self, writer, warcinfo_id: str) -> int:
+        """Write WARC resource records based on paths"""
+        resource_records_size = 0
+
+        logger.info(f'Writing {len(self.write_paths_as_resource_records)} resource records to WARC ... ')
+
+        # Resource records are written at the beginning the WARC file.
+        for i, resource_record_path in enumerate(self.write_paths_as_resource_records):
+            logger.info(f'Writing resource record from {resource_record_path} ...')
+            resource_record = get_resource_record_from_path(
+                file_path=resource_record_path,
+                metadata_path=(
+                    self.write_paths_as_resource_records_metadata[i]
+                    if self.write_paths_as_resource_records_metadata
+                    else None
+                ),
+                warcinfo_id=warcinfo_id,
+            )
+            record_data = get_bytes_from_warc_record(
+                resource_record, warc_version=self.warc_version, gzip=self.gzip
+            )
+            await writer.write(record_data)
+
+            # Keep track but do not rotate resource records
+            resource_records_size += len(record_data)
+
+        logger.info(f'Resource records added: {len(self.write_paths_as_resource_records)}')
+
+        return resource_records_size
+
     async def write_warc_records(
         self,
         writer_id: int,
@@ -418,7 +448,7 @@ async def write_warc_records(
         )
 
         # Initialize first writer with header
-        writer, header_size = await create_new_writer_with_header(
+        writer, header_size, warcinfo_id = await create_new_writer_with_header(
             sequence=current_file_sequence,
             **new_writer_kwargs,
         )
@@ -428,32 +458,11 @@ async def write_warc_records(
         tracker.start()
         counter = 0
 
-        # Write WARC resource records
+        # Resource records
         if self.write_paths_as_resource_records:
-            logger.info(f'Writing {len(self.write_paths_as_resource_records)} resource records to WARC ... ')
-
-            # Resource records are written at the beginning the WARC file.
-            for i, resource_record_path in enumerate(self.write_paths_as_resource_records):
-                logger.info(f'Writing resource record from {resource_record_path} ...')
-                resource_record = get_resource_record_from_path(
-                    file_path=resource_record_path,
-                    metadata_path=(
-                        self.write_paths_as_resource_records_metadata[i]
-                        if self.write_paths_as_resource_records_metadata
-                        else None
-                    ),
-                )
-                record_data = get_bytes_from_warc_record(
-                    resource_record, warc_version=self.warc_version, gzip=self.gzip
-                )
-
-                await writer.write(record_data)
-
-                # Keep track but do not rotate resource records
-                current_file_size += len(record_data)
-
-            logger.info(f'Resource records added: {len(self.write_paths_as_resource_records)}')
+            current_file_size += await self.write_resource_records(writer, warcinfo_id=warcinfo_id)
 
+        # Response records
         try:
             while True:
                 item = await warc_records_queue.get()
@@ -479,7 +488,7 @@ async def write_warc_records(
                             await writer.close()
                             current_file_sequence += 1
 
-                            writer, header_size = await create_new_writer_with_header(
+                            writer, header_size, warcinfo_id = await create_new_writer_with_header(
                                 sequence=current_file_sequence,
                                 **new_writer_kwargs,
                             )
@@ -487,11 +496,16 @@ async def write_warc_records(
                             current_file_size = header_size
                             logger.info(f'Rotated to new WARC file sequence {current_file_sequence} due to size limit')
 
+                            # Resource records also to new files
+                            if self.write_paths_as_resource_records:
+                                current_file_size += await self.write_resource_records(writer, warcinfo_id=warcinfo_id)
+
+                        # Write actual response record
                         await writer.write(item.data)
                         current_file_size += len(item.data)
                         tracker.add(bytes_count=len(item.data), records_count=item.job.records_count)
 
-                        # Log progress every 10 items
+                        # Log progress every N items
                         if self.log_every_n > 0 and counter % self.log_every_n == 0:
                             stats = tracker.get_stats()
                             logger.info(
diff --git a/cdx_toolkit/filter_warc/warc_utils.py b/cdx_toolkit/filter_warc/warc_utils.py
index 8f42ca9..99642af 100644
--- a/cdx_toolkit/filter_warc/warc_utils.py
+++ b/cdx_toolkit/filter_warc/warc_utils.py
@@ -5,7 +5,7 @@
 from warcio.recordloader import ArcWarcRecord
 from warcio import WARCWriter
 
-from typing import Dict, Optional, Union
+from typing import Dict, Optional, Tuple, Union
 
 import mimetypes
 
@@ -26,6 +26,7 @@ def get_bytes_from_warc_record(
 
 def get_resource_record_from_path(
     file_path: Union[str, Path],
+    warcinfo_id: str,
     metadata_path: Optional[Union[str, Path]] = None,
     ) -> ArcWarcRecord:
     """Build WARC resource record for file path and metdata path.
@@ -58,13 +59,13 @@ def get_resource_record_from_path(
             warc_content_type = metadata.get("warc_content_type", None)
             uri = metadata.get("uri", None)
             http_headers = metadata.get("http_headers", None)
-            warc_headers_dict = metadata.get("warc_headers_dict", None)
+            warc_headers_dict = metadata.get("warc_headers_dict", {})
     else:
         # Without metdata
         warc_content_type = None
         uri = None
         http_headers = None
-        warc_headers_dict = None
+        warc_headers_dict = {}
 
     if warc_content_type is None:
         warc_content_type = mimetypes.guess_type(file_path)[0]
@@ -72,6 +73,9 @@ def get_resource_record_from_path(
     if uri is None:
         uri = file_path
 
+    # Set WARC-Warcinfo-ID
+    warc_headers_dict["WARC-Warcinfo-ID"] = warcinfo_id
+
     return WARCWriter(None).create_warc_record(
         uri=uri,
         record_type='resource',
@@ -112,7 +116,7 @@ async def create_new_writer_with_header(
     gzip: bool = False,
     content_type: Optional[str] = None,
     s3_client=None,
-):
+) -> Tuple[Union[S3ShardWriter, LocalFileWriter], int, str]:
     if is_s3_url(output_path_prefix):
         dest_bucket, dest_prefix = parse_s3_uri(output_path_prefix)
 
@@ -159,4 +163,7 @@ async def create_new_writer_with_header(
     header_data = buffer.getvalue()
     await new_writer.write(header_data)
 
-    return new_writer, len(header_data)
\ No newline at end of file
+    # WARC-Warcinfo-ID indicates the WARC-Record-ID of the associated ‘warcinfo’ record
+    warcinfo_id = warcinfo.rec_headers.get("WARC-Record-ID")
+
+    return new_writer, len(header_data), warcinfo_id
diff --git a/tests/filter_warc/test_warc_filter.py b/tests/filter_warc/test_warc_filter.py
index 5da2935..7819074 100644
--- a/tests/filter_warc/test_warc_filter.py
+++ b/tests/filter_warc/test_warc_filter.py
@@ -6,6 +6,15 @@
 fixture_path = TEST_DATA_PATH / 'warc_by_cdx'
 
 
+@requires_aws_s3
+def test_cli_warc_by_cdx_over_s3_to_s3_warc_filter(s3_tmpdir, caplog):
+    assert_cli_warc_by_cdx(
+        's3://commoncrawl',
+        base_prefix=s3_tmpdir,
+        caplog=caplog,
+    )
+
+
 @requires_aws_s3
 def test_cli_warc_by_cdx_over_s3_to_s3_in_parallel_warc_filter(s3_tmpdir, caplog):
     assert_cli_warc_by_cdx(

From 494fbc555cc7436b627312818b9d28fdccded6e9 Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Wed, 8 Oct 2025 18:18:17 -0400
Subject: [PATCH 56/74] Adding tests for unified implementation

---
 cdx_toolkit/cli.py                            |   4 +-
 cdx_toolkit/filter_cdx/__init__.py            | 257 ----------
 cdx_toolkit/filter_cdx/cdx_filter.py          | 134 +++++
 cdx_toolkit/filter_cdx/command.py             |  83 ++++
 cdx_toolkit/filter_cdx/path_utils.py          |  67 +++
 cdx_toolkit/filter_warc/__init__.py           | 128 -----
 cdx_toolkit/filter_warc/cdx_utils.py          |  28 +-
 cdx_toolkit/filter_warc/command.py            | 102 ++++
 cdx_toolkit/filter_warc/data_classes.py       |   3 +-
 cdx_toolkit/filter_warc/local_writer.py       |   2 +-
 cdx_toolkit/filter_warc/warc_filter.py        | 121 +++--
 tests/conftest.py                             |  37 +-
 tests/filter_cdx/test_command.py              | 126 +++++
 tests/filter_cdx/test_filter_cdx.py           | 294 ++++-------
 tests/filter_cdx/test_path_utils.py           |  84 ++++
 .../{test_warc_by_cdx.py => test_command.py}  |  35 +-
 tests/filter_warc/test_data_classes.py        |  12 +
 tests/filter_warc/test_grouped_range_jobs.py  |  51 ++
 tests/filter_warc/test_local_writer.py        | 454 +++++++++++++++++
 tests/filter_warc/test_s3_utils.py            |   4 +-
 tests/filter_warc/test_warc_filter.py         | 459 ++++++++++++++++--
 tests/filter_warc/test_warc_utils.py          |   8 +-
 22 files changed, 1802 insertions(+), 691 deletions(-)
 create mode 100644 cdx_toolkit/filter_cdx/cdx_filter.py
 create mode 100644 cdx_toolkit/filter_cdx/command.py
 create mode 100644 cdx_toolkit/filter_cdx/path_utils.py
 create mode 100644 cdx_toolkit/filter_warc/command.py
 create mode 100644 tests/filter_cdx/test_command.py
 create mode 100644 tests/filter_cdx/test_path_utils.py
 rename tests/filter_warc/{test_warc_by_cdx.py => test_command.py} (90%)
 create mode 100644 tests/filter_warc/test_data_classes.py
 create mode 100644 tests/filter_warc/test_grouped_range_jobs.py
 create mode 100644 tests/filter_warc/test_local_writer.py

diff --git a/cdx_toolkit/cli.py b/cdx_toolkit/cli.py
index 60c63c6..dc266ce 100644
--- a/cdx_toolkit/cli.py
+++ b/cdx_toolkit/cli.py
@@ -9,10 +9,10 @@
 
 from cdx_toolkit.utils import get_version, setup
 
-from cdx_toolkit.filter_cdx import run_filter_cdx
+from cdx_toolkit.filter_cdx.command import run_filter_cdx
 from cdx_toolkit.filter_cdx.args import add_filter_cdx_args
 
-from cdx_toolkit.filter_warc import run_warcer_by_cdx
+from cdx_toolkit.filter_warc.command import run_warcer_by_cdx
 from cdx_toolkit.filter_warc.args import add_warcer_by_cdx_args
 
 
diff --git a/cdx_toolkit/filter_cdx/__init__.py b/cdx_toolkit/filter_cdx/__init__.py
index 0404223..e69de29 100644
--- a/cdx_toolkit/filter_cdx/__init__.py
+++ b/cdx_toolkit/filter_cdx/__init__.py
@@ -1,257 +0,0 @@
-import logging
-import os
-import time
-import sys
-from functools import partial
-from multiprocessing import Pool
-from typing import List, Tuple, Union
-
-import fsspec
-
-from url_is_in import convert_url_to_surt_with_wildcard, SURTMatcher
-
-
-
-logger = logging.getLogger(__name__)
-
-
-def run_filter_cdx(args, cmdline: str):
-    """Filter CDX index files based on a given URL or SURT whitelist.
-
-    - If a URL filter is provided, it is converted to a SURT filter.
-    - A index entry's SURT must start with one of the SURTs from the whitelist to be considered.
-    - All other index entries are discarded.
-    - All input/output paths can be local or remote paths (S3, ...) and compressed (*.gz).
-    """
-    logger.info('Filtering CDX files based on whitelist')
-
-    # Start timing
-    start_time = time.time()
-
-    # Resolve input and output paths using glob pattern
-    # This should support glob via S3 (e.g., to fetch the indices from s3://commoncrawl/cc-index/collections/* ...)
-    input_paths, output_paths = resolve_paths(
-        input_base_path=args.input_base_path,
-        input_glob=args.input_glob,
-        output_base_path=args.output_base_path,
-    )
-    validate_resolved_paths(output_paths, args.overwrite)
-
-    logger.info(f'Found {len(input_paths)} files matching pattern: {args.input_base_path}/{args.input_glob}')
-
-    # Load URL or SURT prefixes from file (each line is a surt)
-    filter_fs, filter_fs_path = fsspec.url_to_fs(args.filter_file)
-    logger.info('Loading whitelist from %s', filter_fs_path)
-
-    if not filter_fs.exists(filter_fs_path):  # Check that surts file exists
-        logger.error(f'Filter file not found: {filter_fs_path}')
-        sys.exit(1)
-
-    with filter_fs.open(filter_fs_path, 'rt') as input_f:
-        include_prefixes = [line.strip() for line in input_f.readlines()]
-
-    logger.info(f'Loaded {len(include_prefixes):,} filter entries')
-
-    # Convert URLs to SURTs
-    if args.filter_type == 'url':
-        include_prefixes = [convert_url_to_surt_with_wildcard(item_url) for item_url in include_prefixes]
-
-    matcher = SURTMatcher(include_prefixes, match_subdomains=True)
-
-    limit = 0 if args.limit is None else args.limit
-
-    # Process files in parallel
-    total_lines_n, total_included_n, total_errors_n = filter_cdx(
-        matcher=matcher,
-        input_paths=input_paths,
-        output_paths=output_paths,
-        limit=limit,
-        n_parallel=max(1, args.parallel),
-    )
-
-    # Calculate ratio safely to avoid division by zero
-    ratio = total_included_n / total_lines_n if total_lines_n > 0 else 0.0
-    logger.info(f'Filter statistics: {total_included_n} / {total_lines_n} lines ({ratio:.4f})')
-    logger.info(f'Errors: {total_errors_n}')
-
-    if limit > 0 and total_included_n >= 0:
-        logger.info(f'Limit reached at {limit}')
-
-    # End timing and log execution time
-    end_time = time.time()
-    execution_time = end_time - start_time
-
-    logger.info(f'Script execution time: {execution_time:.3f} seconds')
-
-
-def _process_file_args(args) -> Tuple[str, str, int, int, int]:
-    """Wrapper function to unpack arguments for multiprocessing."""
-    input_path, output_path, matcher, limit = args
-    return _process_single_file(input_path, output_path, matcher, limit)
-
-
-def filter_cdx(
-    matcher: SURTMatcher,
-    input_paths: List[str],
-    output_paths: List[str],
-    n_parallel: int = 1,
-    limit: int = 0,
-    total_lines_n: int = 0,
-    total_included_n: int = 0,
-    total_errors_n: int = 0,
-) -> Tuple[int, int, int]:
-    """Filter CDX files from input paths using a matcher to output paths."""
-
-    # Parallel processing
-    logger.info('Filtering with %i processes in parallel (limit: %i)', n_parallel, limit)
-
-    # Prepare arguments for each task (input_path, output_path, matcher, limit)
-    task_args = [(input_path, output_path, matcher, limit)
-                 for input_path, output_path in zip(input_paths, output_paths)]
-
-    pool = None
-    try:
-        pool = Pool(processes=n_parallel)
-        # Use imap for better interrupt handling
-        for input_path, _, lines_n, included_n, errors_n in pool.imap(_process_file_args, task_args):
-            total_lines_n += lines_n
-            total_included_n += included_n
-            total_errors_n += errors_n
-
-            logger.info(f'File statistics: included {total_included_n} / {total_lines_n} lines: {input_path}')
-
-    except KeyboardInterrupt:
-        logger.warning('Process interrupted by user (Ctrl+C). Terminating running tasks...')
-        if pool:
-            pool.terminate()
-            pool.join()
-        logger.info('All tasks terminated.')
-    except Exception as exc:
-        logger.error(f'Error during parallel processing: {exc}')
-        total_errors_n += 1
-    finally:
-        if pool:
-            pool.close()
-            pool.join()
-
-    logger.warning(f"Filter CDX errors: {total_errors_n}")
-
-    return total_lines_n, total_included_n, total_errors_n
-
-
-def resolve_paths(input_base_path: str, input_glob: str, output_base_path: str):
-    """Resolve input paths from glob pattern and generate corresponding output paths."""
-    # Use fsspec to handle local and remote file systems
-    input_fs, input_fs_base_path = fsspec.url_to_fs(input_base_path)
-    input_full_glob = input_fs_base_path + input_glob
-
-    # Get input files from glob pattern
-    input_fs_file_paths = sorted(input_fs.glob(input_full_glob))
-    if not input_fs_file_paths:
-        logger.error(f'No files found matching glob pattern: {input_full_glob}')
-        sys.exit(1)
-
-    # Generate corresponding output paths
-    output_file_paths = []
-    input_file_paths = []
-    for input_path in input_fs_file_paths:
-        # Get relative path from input_base_path without last slash
-        rel_path = input_path[len(input_fs_base_path) + 1 :]
-
-        # Create corresponding full input and output path
-        # Use forward slashes for URL paths (S3, HTTP, etc.) to ensure cross-platform compatibility
-        if '://' in output_base_path:
-            output_file_paths.append(output_base_path + '/' + rel_path)
-        else:
-            # Normalize path separators for local filesystem
-            normalized_rel_path = rel_path.replace('/', os.sep)
-            output_file_paths.append(os.path.join(output_base_path, normalized_rel_path))
-
-        if '://' in input_base_path:
-            input_file_paths.append(input_base_path + '/' + rel_path)
-        else:
-            # Normalize path separators for local filesystem
-            normalized_rel_path = rel_path.replace('/', os.sep)
-            input_file_paths.append(os.path.join(input_base_path, normalized_rel_path))
-
-    return input_file_paths, output_file_paths
-
-
-def _process_single_file(
-    input_path: str,
-    output_path: str,
-    matcher: SURTMatcher,
-    limit: int = 0,
-    log_every_n: int = 100_000,
-) -> Tuple[str, str, int, int, int]:
-    """Process a single input/output file pair. Returns (lines_n, included_n)."""
-    lines_n = 0
-    included_n = 0
-    errors_n = 0
-
-    logger.info('Reading index from %s', input_path)
-    logger.info('Writing filter output to %s', output_path)
-
-    try:
-
-        # Input/output from local or remote file system
-        input_fs, input_fs_path = fsspec.url_to_fs(input_path)
-        output_fs, output_fs_path = fsspec.url_to_fs(output_path)
-
-        # Make sure output directory exists
-        output_fs.makedirs(output_fs._parent(output_fs_path), exist_ok=True)
-
-        # Read and write compressed file if needed
-        compression = 'gzip' if input_fs_path.endswith('.gz') else None
-
-        with output_fs.open(output_fs_path, 'w', compression=compression) as output_f:
-            with input_fs.open(input_fs_path, 'rt', compression=compression) as input_f:
-                for i, line in enumerate(input_f, 1):
-                    try:
-                        # Read CDX line
-                        surt_length = line.find(' ')  # we do not need to parse the full line
-                        record_surt = line[:surt_length]
-                        lines_n += 1
-
-                        # Use SURT matcher
-                        include_record = matcher.is_in(record_surt)
-
-                        if include_record:
-                            output_f.write(line)
-                            included_n += 1
-
-                            if limit > 0 and included_n >= limit:
-                                logger.info('Limit reached at %i from %s', limit, input_path)
-                                break
-
-                        if (i % log_every_n) == 0:
-                            logger.info(f'Lines completed: {i:,} (matched: {included_n:,}) from {input_path}')
-
-                    except Exception as e:
-                        logger.error(f"Line processing error: {e}")
-                        errors_n += 1
-
-        # Delete file if empty
-        if included_n == 0:
-            logger.warning('Output file is empty, removing it: %s', output_fs_path)
-            output_fs.rm(output_fs_path)
-
-    except Exception as e:
-        logger.error(f"File processing error: {e}")
-        errors_n += 1
-
-    return input_path, output_path, lines_n, included_n, errors_n
-
-
-def validate_resolved_paths(output_paths, overwrite):
-    """Validate resolved output paths and create directories if needed."""
-    # Check if output files exist and overwrite flag
-    if not overwrite:
-        output_fs, _ = fsspec.url_to_fs(output_paths[0])
-        for output_path in output_paths:
-            if output_fs.exists(output_path):
-                logger.error(f'Output file already exists: {output_path}. Use --overwrite to overwrite existing files.')
-                sys.exit(1)
-
-            # Make sure directory exists
-            output_fs.makedirs(output_fs._parent(output_path), exist_ok=True)
diff --git a/cdx_toolkit/filter_cdx/cdx_filter.py b/cdx_toolkit/filter_cdx/cdx_filter.py
new file mode 100644
index 0000000..245b87b
--- /dev/null
+++ b/cdx_toolkit/filter_cdx/cdx_filter.py
@@ -0,0 +1,134 @@
+import logging
+
+from url_is_in import SURTMatcher
+import fsspec
+
+from multiprocessing import Pool
+from typing import List, Tuple
+
+
+logger = logging.getLogger(__name__)
+
+
+def _filter_single_cdx_file(
+    input_path: str,
+    output_path: str,
+    matcher: SURTMatcher,
+    limit: int = 0,
+    log_every_n: int = 100_000,
+) -> Tuple[str, str, int, int, int]:
+    """Process a single input/output file pair. Returns (lines_n, included_n)."""
+    lines_n = 0
+    included_n = 0
+    errors_n = 0
+
+    logger.info('Reading index from %s', input_path)
+    logger.info('Writing filter output to %s', output_path)
+
+    try:
+
+        # Input/output from local or remote file system
+        input_fs, input_fs_path = fsspec.url_to_fs(input_path)
+        output_fs, output_fs_path = fsspec.url_to_fs(output_path)
+
+        # Make sure output directory exists
+        output_fs.makedirs(output_fs._parent(output_fs_path), exist_ok=True)
+
+        # Read and write compressed file if needed
+        compression = 'gzip' if input_fs_path.endswith('.gz') else None
+
+        with output_fs.open(output_fs_path, 'w', compression=compression) as output_f:
+            with input_fs.open(input_fs_path, 'rt', compression=compression) as input_f:
+                for i, line in enumerate(input_f, 1):
+                    try:
+                        # Read CDX line
+                        surt_length = line.find(' ')  # we do not need to parse the full line
+                        record_surt = line[:surt_length]
+                        lines_n += 1
+
+                        # Use SURT matcher
+                        include_record = matcher.is_in(record_surt)
+
+                        if include_record:
+                            output_f.write(line)
+                            included_n += 1
+
+                            if limit > 0 and included_n >= limit:
+                                logger.info('Limit reached at %i from %s', limit, input_path)
+                                break
+
+                        if (i % log_every_n) == 0:
+                            logger.info(f'Lines completed: {i:,} (matched: {included_n:,}) from {input_path}')
+
+                    except Exception as e:
+                        logger.error(f"Line processing error: {e}")
+                        errors_n += 1
+
+        # Delete file if empty
+        if included_n == 0:
+            logger.warning('Output file is empty, removing it: %s', output_fs_path)
+            output_fs.rm(output_fs_path)
+
+    except Exception as e:
+        logger.error(f"File processing error: {e}")
+        errors_n += 1
+
+    return input_path, output_path, lines_n, included_n, errors_n
+
+
+def _filter_single_cdx_file_args(kwargs: dict) -> Tuple[str, str, int, int, int]:
+    """Wrapper function to unpack arguments for multiprocessing."""
+
+    return _filter_single_cdx_file(**kwargs)
+
+
+def filter_cdx(
+    matcher: SURTMatcher,
+    input_paths: List[str],
+    output_paths: List[str],
+    n_parallel: int = 1,
+    limit: int = 0,
+    total_lines_n: int = 0,
+    total_included_n: int = 0,
+    total_errors_n: int = 0,
+    log_every_n: int = 100_000,
+) -> Tuple[int, int, int]:
+    """Filter CDX files from input paths using a matcher to output paths."""
+
+    # Parallel processing
+    logger.info('Filtering with %i processes in parallel (limit: %i)', n_parallel, limit)
+
+    # Prepare arguments for each task (input_path, output_path, matcher, limit)
+    task_args = [dict(
+                    input_path=input_path, 
+                    output_path=output_path, matcher=matcher, limit=limit, log_every_n=log_every_n)
+                 for input_path, output_path in zip(input_paths, output_paths)]
+
+    pool = None
+    try:
+        pool = Pool(processes=n_parallel)
+        # Use imap for better interrupt handling
+        for input_path, _, lines_n, included_n, errors_n in pool.imap(_filter_single_cdx_file_args, task_args):
+            total_lines_n += lines_n
+            total_included_n += included_n
+            total_errors_n += errors_n
+
+            logger.info(f'File statistics: included {total_included_n} / {total_lines_n} lines: {input_path}')
+
+    except KeyboardInterrupt:
+        logger.warning('Process interrupted by user (Ctrl+C). Terminating running tasks...')
+        if pool:
+            pool.terminate()
+            pool.join()
+        logger.info('All tasks terminated.')
+    except Exception as exc:
+        logger.error(f'Error during parallel processing: {exc}')
+        total_errors_n += 1
+    finally:
+        if pool:
+            pool.close()
+            pool.join()
+
+    logger.warning(f"Filter CDX errors: {total_errors_n}")
+
+    return total_lines_n, total_included_n, total_errors_n
\ No newline at end of file
diff --git a/cdx_toolkit/filter_cdx/command.py b/cdx_toolkit/filter_cdx/command.py
new file mode 100644
index 0000000..0ca10ce
--- /dev/null
+++ b/cdx_toolkit/filter_cdx/command.py
@@ -0,0 +1,83 @@
+from cdx_toolkit.filter_cdx.path_utils import validate_resolved_paths
+
+import logging
+import fsspec
+from url_is_in import SURTMatcher, convert_url_to_surt_with_wildcard
+
+
+import sys
+import time
+
+from cdx_toolkit.filter_cdx.cdx_filter import filter_cdx
+from cdx_toolkit.filter_cdx.path_utils import resolve_paths
+
+logger = logging.getLogger(__name__)
+
+
+def run_filter_cdx(args, cmdline: str):
+    """Filter CDX index files based on a given URL or SURT whitelist.
+
+    - If a URL filter is provided, it is converted to a SURT filter.
+    - A index entry's SURT must start with one of the SURTs from the whitelist to be considered.
+    - All other index entries are discarded.
+    - All input/output paths can be local or remote paths (S3, ...) and compressed (*.gz).
+    """
+    logger.info('Filtering CDX files based on whitelist')
+
+    # Start timing
+    start_time = time.time()
+
+    # Resolve input and output paths using glob pattern
+    # This should support glob via S3 (e.g., to fetch the indices from s3://commoncrawl/cc-index/collections/* ...)
+    input_paths, output_paths = resolve_paths(
+        input_base_path=args.input_base_path,
+        input_glob=args.input_glob,
+        output_base_path=args.output_base_path,
+    )
+    validate_resolved_paths(output_paths, args.overwrite)
+
+    logger.info(f'Found {len(input_paths)} files matching pattern: {args.input_base_path}/{args.input_glob}')
+
+    # Load URL or SURT prefixes from file (each line is a surt)
+    filter_fs, filter_fs_path = fsspec.url_to_fs(args.filter_file)
+    logger.info('Loading whitelist from %s', filter_fs_path)
+
+    if not filter_fs.exists(filter_fs_path):  # Check that surts file exists
+        logger.error(f'Filter file not found: {filter_fs_path}')
+        sys.exit(1)
+
+    with filter_fs.open(filter_fs_path, 'rt') as input_f:
+        include_prefixes = [line.strip() for line in input_f.readlines()]
+
+    logger.info(f'Loaded {len(include_prefixes):,} filter entries')
+
+    # Convert URLs to SURTs
+    if args.filter_type == 'url':
+        include_prefixes = [convert_url_to_surt_with_wildcard(item_url) for item_url in include_prefixes]
+
+    matcher = SURTMatcher(include_prefixes, match_subdomains=True)
+
+    limit = 0 if args.limit is None else args.limit
+
+    # Process files in parallel
+    total_lines_n, total_included_n, total_errors_n = filter_cdx(
+        matcher=matcher,
+        input_paths=input_paths,
+        output_paths=output_paths,
+        limit=limit,
+        n_parallel=max(1, args.parallel),
+    )
+
+    # Calculate ratio safely to avoid division by zero
+    ratio = total_included_n / total_lines_n if total_lines_n > 0 else 0.0
+    logger.info(f'Filter statistics: {total_included_n} / {total_lines_n} lines ({ratio:.4f})')
+    logger.info(f'Errors: {total_errors_n}')
+
+    if limit > 0 and total_included_n >= 0:
+        logger.info(f'Limit reached at {limit}')
+
+    # End timing and log execution time
+    end_time = time.time()
+    execution_time = end_time - start_time
+
+    logger.info(f'Script execution time: {execution_time:.3f} seconds')
\ No newline at end of file
diff --git a/cdx_toolkit/filter_cdx/path_utils.py b/cdx_toolkit/filter_cdx/path_utils.py
new file mode 100644
index 0000000..e77da72
--- /dev/null
+++ b/cdx_toolkit/filter_cdx/path_utils.py
@@ -0,0 +1,67 @@
+import logging
+
+import fsspec
+
+
+import os
+import sys
+
+
+logger = logging.getLogger(__name__)
+
+
+def resolve_paths(input_base_path: str, input_glob: str | None, output_base_path: str):
+    """Resolve input paths from glob pattern and generate corresponding output paths."""
+    # Use fsspec to handle local and remote file systems
+    input_fs, input_fs_base_path = fsspec.url_to_fs(input_base_path)
+
+    if input_glob is None:
+        # No glob pattern
+        input_fs_file_paths = [input_fs_base_path]
+    else:
+        input_full_glob = input_fs_base_path + input_glob
+
+        # Get input files from glob pattern
+        input_fs_file_paths = sorted(input_fs.glob(input_full_glob))
+        if not input_fs_file_paths:
+            logger.error(f'No files found matching glob pattern: {input_full_glob}')
+            sys.exit(1)
+
+    # Generate corresponding output paths
+    output_file_paths = []
+    input_file_paths = []
+    for input_path in input_fs_file_paths:
+        # Get relative path from input_base_path without last slash
+        rel_path = input_path[len(input_fs_base_path)+1:]
+
+        # Create corresponding full input and output path
+        # Use forward slashes for URL paths (S3, HTTP, etc.) to ensure cross-platform compatibility
+        if '://' in output_base_path:
+            output_file_paths.append(output_base_path + '/' + rel_path)
+        else:
+            # Normalize path separators for local filesystem
+            normalized_rel_path = rel_path.replace('/', os.sep)
+            output_file_paths.append(os.path.join(output_base_path, normalized_rel_path))
+
+        if '://' in input_base_path:
+            input_file_paths.append(input_base_path + '/' + rel_path)
+        else:
+            # Normalize path separators for local filesystem
+            normalized_rel_path = rel_path.replace('/', os.sep)
+            input_file_paths.append(os.path.join(input_base_path, normalized_rel_path))
+
+    return input_file_paths, output_file_paths
+
+
+def validate_resolved_paths(output_paths, overwrite):
+    """Validate resolved output paths and create directories if needed."""
+    # Check if output files exist and overwrite flag
+    if not overwrite:
+        output_fs, _ = fsspec.url_to_fs(output_paths[0])
+        for output_path in output_paths:
+            if output_fs.exists(output_path):
+                logger.error(f'Output file already exists: {output_path}. Use --overwrite to overwrite existing files.')
+                sys.exit(1)
+
+            # Make sure directory exists
+            output_fs.makedirs(output_fs._parent(output_path), exist_ok=True)
diff --git a/cdx_toolkit/filter_warc/__init__.py b/cdx_toolkit/filter_warc/__init__.py
index e4f2fe7..e69de29 100644
--- a/cdx_toolkit/filter_warc/__init__.py
+++ b/cdx_toolkit/filter_warc/__init__.py
@@ -1,128 +0,0 @@
-import logging
-import sys
-import time
-from typing import List, Optional
-
-import fsspec
-
-
-from cdx_toolkit.utils import get_version, setup
-
-from cdx_toolkit.filter_warc.warc_filter import WARCFilter
-
-logger = logging.getLogger(__name__)
-
-
-def run_warcer_by_cdx(args, cmdline):
-    """Like warcer but fetches WARC records based on one or more CDX index files.
-
-    The CDX files can be filtered using the `filter_cdx` commands based a given URL/SURT list.
-
-    Approach:
-    - Iterate over one or more CDX files to extract capture object (file, offset, length)
-    - Fetch WARC record based on capture object
-    - Write to new WARC file with metadata including resource record with index.
-    - The CDX resource record is written to the WARC directly before for response records that matches to the CDX.
-    """
-    logger.info('Filtering WARC files based on CDX')
-
-    cdx, kwargs = setup(args)
-
-    # Start timing
-    start_time = time.time()
-
-    write_paths_as_resource_records = args.write_paths_as_resource_records
-    write_paths_as_resource_records_metadata = args.write_paths_as_resource_records_metadata
-
-    if write_paths_as_resource_records and write_paths_as_resource_records_metadata:
-        if len(write_paths_as_resource_records) != len(write_paths_as_resource_records_metadata):
-            raise ValueError("Number of paths to resource records must be equal to metadata paths.")
-
-    if not write_paths_as_resource_records and write_paths_as_resource_records_metadata:
-        raise ValueError("Metadata paths are set but resource records paths are missing.")
-
-    if args.is_part_of:
-        ispartof = args.is_part_of
-    else:
-        ispartof = args.prefix
-        if args.subprefix:
-            ispartof += '-' + args.subprefix
-
-    info = {
-        'software': 'pypi_cdx_toolkit/' + get_version(),
-        'isPartOf': ispartof,
-        'description': args.description if args.description else 'warc extraction based on CDX generated with: ' + cmdline,
-        'format': 'WARC file version 1.0',
-    }
-    if args.creator:
-        info['creator'] = args.creator
-    if args.operator:
-        info['operator'] = args.operator
-
-    # writer_kwargs = {}
-    # if 'size' in kwargs:
-    #     writer_kwargs['size'] = kwargs['size']
-    #     del kwargs['size']
-
-    n_parallel = args.parallel
-    log_every_n = args.log_every_n
-    limit = 0 if args.limit is None else args.limit
-    prefix_path = str(args.prefix)
-    prefix_fs, prefix_fs_path = fsspec.url_to_fs(prefix_path)
-
-    # make sure the base dir exists
-    prefix_fs.makedirs(prefix_fs._parent(prefix_fs_path), exist_ok=True)
-
-    cdx_paths = get_cdx_paths(
-        args.cdx_path,
-        args.cdx_glob,
-    )
-
-    warc_filter = WARCFilter(
-        index_paths=cdx_paths,
-        prefix_path=prefix_path,
-        writer_info=info,
-        writer_subprefix=args.subprefix,
-        write_paths_as_resource_records=write_paths_as_resource_records,
-        write_paths_as_resource_records_metadata=write_paths_as_resource_records_metadata,
-        record_limit=limit,
-        log_every_n=log_every_n,
-        warc_download_prefix=cdx.warc_download_prefix,
-        n_parallel=n_parallel,
-        max_file_size=args.size,
-        # writer_kwargs=writer_kwargs,
-    )
-    records_n = warc_filter.filter()
-
-    logger.info('WARC records extracted: %i', records_n)
-
-    # End timing and log execution time
-    end_time = time.time()
-    execution_time = end_time - start_time
-
-    logger.info(f'Script execution time: {execution_time:.3f} seconds')
-
-
-def get_cdx_paths(index_path: str, index_glob: Optional[str] = None) -> List[str]:
-    """Find CDX index paths using glob pattern."""
-    if index_glob is None:
-        # Read from a single index
-        index_paths = [index_path]
-    else:
-        # Prepare index paths
-        index_fs, index_fs_path = fsspec.url_to_fs(index_path)
-
-        # Fetch multiple indicies via glob
-        full_glob = index_fs_path + index_glob
-
-        logger.info('glob pattern from %s (%s)', full_glob, index_fs.protocol)
-
-        index_paths = sorted(index_fs.glob(full_glob))
-
-        logger.info('glob pattern found %i index files in %s', len(index_paths), index_fs_path)
-
-        if not index_paths:
-            logger.error('no index files found via glob')
-            sys.exit(1)
-
-    return index_paths
diff --git a/cdx_toolkit/filter_warc/cdx_utils.py b/cdx_toolkit/filter_warc/cdx_utils.py
index ef8b92c..2a0c4ec 100644
--- a/cdx_toolkit/filter_warc/cdx_utils.py
+++ b/cdx_toolkit/filter_warc/cdx_utils.py
@@ -1,7 +1,8 @@
 import json
 from pathlib import Path
 
-from typing import Iterable, Optional, Tuple, Union
+import sys
+from typing import Iterable, List, Optional, Tuple, Union
 
 import fsspec
 import logging
@@ -65,3 +66,28 @@ def iter_cdx_index_from_path(index_path: str, warc_download_prefix: str) -> Iter
                 continue
 
     logger.info(f'CDX completed from {index_path}')
+
+
+def get_cdx_paths(index_path: str, index_glob: Optional[str] = None) -> List[str]:
+    """Find CDX index paths using glob pattern."""
+    if index_glob is None:
+        # Read from a single index
+        index_paths = [index_path]
+    else:
+        # Prepare index paths
+        index_fs, index_fs_path = fsspec.url_to_fs(index_path)
+
+        # Fetch multiple indicies via glob
+        full_glob = index_fs_path + index_glob
+
+        logger.info('glob pattern from %s (%s)', full_glob, index_fs.protocol)
+
+        index_paths = sorted(index_fs.glob(full_glob))
+
+        logger.info('glob pattern found %i index files in %s', len(index_paths), index_fs_path)
+
+        if not index_paths:
+            logger.error('no index files found via glob')
+            sys.exit(1)
+
+    return index_paths
diff --git a/cdx_toolkit/filter_warc/command.py b/cdx_toolkit/filter_warc/command.py
new file mode 100644
index 0000000..bd08c0e
--- /dev/null
+++ b/cdx_toolkit/filter_warc/command.py
@@ -0,0 +1,102 @@
+from cdx_toolkit.filter_warc.cdx_utils import get_cdx_paths
+from cdx_toolkit.filter_warc.warc_filter import WARCFilter
+from cdx_toolkit.utils import get_version, setup
+
+
+import fsspec
+
+
+import time
+import logging
+
+logger = logging.getLogger(__name__)
+
+
+def run_warcer_by_cdx(args, cmdline):
+    """Like warcer but fetches WARC records based on one or more CDX index files.
+
+    The CDX files can be filtered using the `filter_cdx` commands based a given URL/SURT list.
+
+    Approach:
+    - Iterate over one or more CDX files to extract capture object (file, offset, length)
+    - Fetch WARC record based on capture object
+    - Write to new WARC file with metadata including resource record with index.
+    - The CDX resource record is written to the WARC directly before for response records that matches to the CDX.
+    """
+    logger.info('Filtering WARC files based on CDX')
+
+    cdx, kwargs = setup(args)
+
+    # Start timing
+    start_time = time.time()
+
+    write_paths_as_resource_records = args.write_paths_as_resource_records
+    write_paths_as_resource_records_metadata = args.write_paths_as_resource_records_metadata
+
+    if write_paths_as_resource_records and write_paths_as_resource_records_metadata:
+        if len(write_paths_as_resource_records) != len(write_paths_as_resource_records_metadata):
+            raise ValueError("Number of paths to resource records must be equal to metadata paths.")
+
+    if not write_paths_as_resource_records and write_paths_as_resource_records_metadata:
+        raise ValueError("Metadata paths are set but resource records paths are missing.")
+
+    if args.is_part_of:
+        ispartof = args.is_part_of
+    else:
+        ispartof = args.prefix
+        if args.subprefix:
+            ispartof += '-' + args.subprefix
+
+    info = {
+        'software': 'pypi_cdx_toolkit/' + get_version(),
+        'isPartOf': ispartof,
+        'description': args.description if args.description else 'warc extraction based on CDX generated with: ' + cmdline,
+        'format': 'WARC file version 1.0',
+    }
+    if args.creator:
+        info['creator'] = args.creator
+    if args.operator:
+        info['operator'] = args.operator
+
+    # writer_kwargs = {}
+    # if 'size' in kwargs:
+    #     writer_kwargs['size'] = kwargs['size']
+    #     del kwargs['size']
+
+    n_parallel = args.parallel
+    log_every_n = args.log_every_n
+    limit = 0 if args.limit is None else args.limit
+    prefix_path = str(args.prefix)
+    prefix_fs, prefix_fs_path = fsspec.url_to_fs(prefix_path)
+
+    # make sure the base dir exists
+    prefix_fs.makedirs(prefix_fs._parent(prefix_fs_path), exist_ok=True)
+
+    cdx_paths = get_cdx_paths(
+        args.cdx_path,
+        args.cdx_glob,
+    )
+
+    warc_filter = WARCFilter(
+        index_paths=cdx_paths,
+        prefix_path=prefix_path,
+        writer_info=info,
+        writer_subprefix=args.subprefix,
+        write_paths_as_resource_records=write_paths_as_resource_records,
+        write_paths_as_resource_records_metadata=write_paths_as_resource_records_metadata,
+        record_limit=limit,
+        log_every_n=log_every_n,
+        warc_download_prefix=cdx.warc_download_prefix,
+        n_parallel=n_parallel,
+        max_file_size=args.size,
+        # writer_kwargs=writer_kwargs,
+    )
+    records_n = warc_filter.filter()
+
+    logger.info('WARC records extracted: %i', records_n)
+
+    # End timing and log execution time
+    end_time = time.time()
+    execution_time = end_time - start_time
+
+    logger.info(f'Script execution time: {execution_time:.3f} seconds')
\ No newline at end of file
diff --git a/cdx_toolkit/filter_warc/data_classes.py b/cdx_toolkit/filter_warc/data_classes.py
index 422857a..8f36325 100644
--- a/cdx_toolkit/filter_warc/data_classes.py
+++ b/cdx_toolkit/filter_warc/data_classes.py
@@ -7,7 +7,6 @@
 from cdx_toolkit.myrequests import myrequests_get
 
 
-
 @dataclass
 class ThroughputTracker:
     """Track throughput metrics for fetchers and consumers."""
@@ -94,4 +93,4 @@ class RangePayload:
     """Bytes output from S3 or HTTP range read."""
 
     job: RangeJob
-    data: bytes
\ No newline at end of file
+    data: bytes
diff --git a/cdx_toolkit/filter_warc/local_writer.py b/cdx_toolkit/filter_warc/local_writer.py
index 0ddd735..e85b052 100644
--- a/cdx_toolkit/filter_warc/local_writer.py
+++ b/cdx_toolkit/filter_warc/local_writer.py
@@ -39,4 +39,4 @@ async def close(self):
         except Exception:
             if self.file_handle:
                 await self.file_handle.close()
-            raise
\ No newline at end of file
+            raise
diff --git a/cdx_toolkit/filter_warc/warc_filter.py b/cdx_toolkit/filter_warc/warc_filter.py
index 37da7dc..775de40 100644
--- a/cdx_toolkit/filter_warc/warc_filter.py
+++ b/cdx_toolkit/filter_warc/warc_filter.py
@@ -25,7 +25,7 @@
 
 class WARCFilter:
     """Filter or extract specific records from WARC files based on CDX indexes.
-    
+
     The WARC filter uses a three stage listner-producer-consumer pattern.
 
     Filter targets:
@@ -113,7 +113,11 @@ def __init__(
 
         self.n_parallel = n_parallel
         self.num_readers = n_parallel_readers if n_parallel_readers is not None else n_parallel
-        self.num_writers = n_parallel_writers if n_parallel_writers is not None else max(int(self.num_readers / self.fetcher_to_consumer_ratio), 1)
+        self.num_writers = (
+            n_parallel_writers
+            if n_parallel_writers is not None
+            else max(int(self.num_readers / self.fetcher_to_consumer_ratio), 1)
+        )
 
         self.gzip = self.index_paths[0].endswith('.gz') if self.index_paths else False
         self.warc_version = warc_version
@@ -185,11 +189,11 @@ async def filter_async(self) -> int:
             return await self._run_filter_pipeline(range_jobs_queue, warc_records_queue)
 
     async def _run_filter_pipeline(
-            self,
-            range_jobs_queue: asyncio.Queue,
-            warc_records_queue: asyncio.Queue,
-            s3_client=None,
-        ) -> int:
+        self,
+        range_jobs_queue: asyncio.Queue,
+        warc_records_queue: asyncio.Queue,
+        s3_client=None,
+    ) -> int:
         """Run the actual filter pipeline with or without S3 client.
 
         Args:
@@ -242,9 +246,7 @@ async def _run_filter_pipeline(
 
         readers_records = sum([result['stats']['total_records'] for result in readers_results])
         readers_mb_per_sec = statistics.mean([result['stats']['mb_per_sec'] for result in readers_results])
-        readers_records_per_sec = statistics.mean(
-            [result['stats']['records_per_sec'] for result in readers_results]
-        )
+        readers_records_per_sec = statistics.mean([result['stats']['records_per_sec'] for result in readers_results])
 
         logger.info(f'All WARC readers completed: {readers_records} records')
         logger.info(f'Reader throughput: {readers_mb_per_sec:.2f} MB/s; {readers_records_per_sec:.2f} rec/s')
@@ -257,9 +259,7 @@ async def _run_filter_pipeline(
 
         writers_records = sum([result['stats']['total_records'] for result in writers_results])
         writers_mb_per_sec = statistics.mean([result['stats']['mb_per_sec'] for result in writers_results])
-        writers_records_per_sec = statistics.mean(
-            [result['stats']['records_per_sec'] for result in writers_results]
-        )
+        writers_records_per_sec = statistics.mean([result['stats']['records_per_sec'] for result in writers_results])
 
         logger.info(f'All WARC writers completed: {writers_records} records')
         logger.info(f'Writer throughput: {writers_mb_per_sec:.2f} MB/s; {writers_records_per_sec:.2f} rec/s')
@@ -357,16 +357,7 @@ async def read_warc_records(
                 counter += 1
 
                 # Log progress every N items
-                if self.log_every_n > 0 and counter % self.log_every_n == 0:
-                    stats = tracker.get_stats()
-                    logger.info(
-                        'WARC Reader %d: %d items, %.1f MB, %.2f MB/s, %.2f req/s',
-                        reader_id,
-                        counter,
-                        stats['total_bytes'] / (1024 * 1024),
-                        stats['mb_per_sec'],
-                        stats['requests_per_sec'],
-                    )
+                self.log_reader(reader_id=reader_id, counter=counter, tracker=tracker)
 
                 await warc_records_queue.put(RangePayload(job=job, data=data))
             except Exception:
@@ -401,9 +392,7 @@ async def write_resource_records(self, writer, warcinfo_id: str) -> int:
                 ),
                 warcinfo_id=warcinfo_id,
             )
-            record_data = get_bytes_from_warc_record(
-                resource_record, warc_version=self.warc_version, gzip=self.gzip
-            )
+            record_data = get_bytes_from_warc_record(resource_record, warc_version=self.warc_version, gzip=self.gzip)
             await writer.write(record_data)
 
             # Keep track but do not rotate resource records
@@ -484,21 +473,13 @@ async def write_warc_records(
                         assert isinstance(item, RangePayload)
 
                         # Check if we need to rotate files due to size limit
-                        if self.max_file_size and current_file_size + len(item.data) > self.max_file_size:
-                            await writer.close()
-                            current_file_sequence += 1
-
-                            writer, header_size, warcinfo_id = await create_new_writer_with_header(
-                                sequence=current_file_sequence,
-                                **new_writer_kwargs,
-                            )
-
-                            current_file_size = header_size
-                            logger.info(f'Rotated to new WARC file sequence {current_file_sequence} due to size limit')
-
-                            # Resource records also to new files
-                            if self.write_paths_as_resource_records:
-                                current_file_size += await self.write_resource_records(writer, warcinfo_id=warcinfo_id)
+                        writer, current_file_sequence, current_file_size = await self.rotate_files(
+                            writer=writer,
+                            current_file_sequence=current_file_sequence,
+                            current_file_size=current_file_size,
+                            added_byte_size=len(item.data),
+                            **new_writer_kwargs,
+                        )
 
                         # Write actual response record
                         await writer.write(item.data)
@@ -506,15 +487,8 @@ async def write_warc_records(
                         tracker.add(bytes_count=len(item.data), records_count=item.job.records_count)
 
                         # Log progress every N items
-                        if self.log_every_n > 0 and counter % self.log_every_n == 0:
-                            stats = tracker.get_stats()
-                            logger.info(
-                                'WARC writer %d: %d items, %.1f MB written, %.2f MB/s',
-                                writer_id,
-                                counter,
-                                stats['total_bytes'] / (1024 * 1024),
-                                stats['mb_per_sec'],
-                            )
+                        self.log_writer(writer_id=writer_id, counter=counter, tracker=tracker)
+
                 except Exception:
                     logger.exception('WARC writer %d failed on %s', writer_id, getattr(item, 'job', None))
                     should_stop = False
@@ -528,6 +502,53 @@ async def write_warc_records(
 
         return {'writer_id': writer_id, 'stats': tracker.get_stats()}
 
+    def log_reader(self, reader_id: int, counter: int, tracker: ThroughputTracker):
+        """Log progress every N items."""
+        if self.log_every_n > 0 and counter % self.log_every_n == 0:
+            stats = tracker.get_stats()
+            logger.info(
+                'WARC Reader %d: %d items, %.1f MB, %.2f MB/s, %.2f req/s',
+                reader_id,
+                counter,
+                stats['total_bytes'] / (1024 * 1024),
+                stats['mb_per_sec'],
+                stats['requests_per_sec'],
+            )
+
+    def log_writer(self, writer_id: int, counter: int, tracker: ThroughputTracker):
+        """Log progress every N items."""
+        if self.log_every_n > 0 and counter % self.log_every_n == 0:
+            stats = tracker.get_stats()
+            logger.info(
+                'WARC Writer %d: %d items, %.1f MB written, %.2f MB/s',
+                writer_id,
+                counter,
+                stats['total_bytes'] / (1024 * 1024),
+                stats['mb_per_sec'],
+            )
+
+    async def rotate_files(
+        self, writer, current_file_sequence: int, current_file_size: int, added_byte_size: int, **new_writer_kwargs
+    ):
+        """Check if we need to rotate files due to size limit and perform rotation if needed."""
+        if self.max_file_size and current_file_size + added_byte_size > self.max_file_size:
+            await writer.close()
+            current_file_sequence += 1
+
+            writer, header_size, warcinfo_id = await create_new_writer_with_header(
+                sequence=current_file_sequence,
+                **new_writer_kwargs,
+            )
+
+            current_file_size = header_size
+            logger.info(f'Rotated to new WARC file sequence {current_file_sequence} due to size limit')
+
+            # Resource records also to new files
+            if self.write_paths_as_resource_records:
+                current_file_size += await self.write_resource_records(writer, warcinfo_id=warcinfo_id)
+
+        return writer, current_file_sequence, current_file_size
+
     def get_boto3_config(self):
         """Get boto3 configuration for S3 client.
 
diff --git a/tests/conftest.py b/tests/conftest.py
index 3697229..d7c6dc0 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -2,7 +2,8 @@
 from pathlib import Path
 import pytest
 import boto3
-from botocore.exceptions import NoCredentialsError, ClientError
+from botocore.config import Config
+from botocore.exceptions import NoCredentialsError, ClientError, EndpointConnectionError
 
 import json
 import functools
@@ -30,16 +31,33 @@ def cleanup_cache():
         shutil.rmtree(cache_dir)
 
 
+# Cache for AWS S3 access check to avoid repeated network calls
+_aws_s3_access_cache = None
+
+
 def check_aws_s3_access():
-    """Check if AWS S3 access is available."""
+    """Check if AWS S3 access is available (cached result)."""
+    global _aws_s3_access_cache
+
+    if _aws_s3_access_cache is not None:
+        return _aws_s3_access_cache
+
     try:
-        s3_client = boto3.client('s3')
+        config = Config(
+            retries={
+                'max_attempts': 1,
+                'mode': 'standard'
+            }
+        )
+        s3_client = boto3.client('s3', config=config)
 
         # Try list objects on test bucket
         s3_client.list_objects_v2(Bucket=TEST_S3_BUCKET, MaxKeys=1)
-        return True
-    except (NoCredentialsError, ClientError):
-        return False
+        _aws_s3_access_cache = True
+    except (NoCredentialsError, ClientError, ConnectionError, EndpointConnectionError):
+        _aws_s3_access_cache = False
+
+    return _aws_s3_access_cache
 
 
 def requires_aws_s3(func):
@@ -62,9 +80,10 @@ def s3_tmpdir():
     # Yield the S3 path
     yield f's3://{bucket_name}/{temp_prefix}'
 
-    # Cleanup: delete all objects with this prefix
-    s3_client = boto3.client('s3')
     try:
+        # Cleanup: delete all objects with this prefix
+        s3_client = boto3.client('s3')
+
         # List all objects with the temp prefix
         response = s3_client.list_objects_v2(Bucket=bucket_name, Prefix=temp_prefix)
 
@@ -72,7 +91,7 @@ def s3_tmpdir():
             # Delete all objects
             objects_to_delete = [{'Key': obj['Key']} for obj in response['Contents']]
             s3_client.delete_objects(Bucket=bucket_name, Delete={'Objects': objects_to_delete})
-    except ClientError:
+    except (NoCredentialsError, ClientError, ConnectionError, EndpointConnectionError):
         # Ignore cleanup errors - test objects will eventually expire
         pass
 
diff --git a/tests/filter_cdx/test_command.py b/tests/filter_cdx/test_command.py
new file mode 100644
index 0000000..d854b5d
--- /dev/null
+++ b/tests/filter_cdx/test_command.py
@@ -0,0 +1,126 @@
+import pytest
+
+
+from cdx_toolkit.cli import main
+from tests.conftest import TEST_DATA_PATH, requires_aws_s3
+
+fixture_path = TEST_DATA_PATH / 'filter_cdx'
+
+
+@requires_aws_s3
+def test_cli_filter_cdx_from_s3_with_parallel_processing(tmpdir, caplog):
+    """Test that parallel processing works correctly and processes multiple files."""
+    index_path = 's3://commoncrawl/cc-index/collections'
+    index_glob = '/CC-MAIN-2024-30/indexes/cdx-0018[78].gz'  # Multiple files pattern
+    whitelist_path = fixture_path / 'whitelist_11_surts.txt'  # Additonal entry for cdx-00188.gz
+
+    # Run with parallel processing (2 workers)
+    main(
+        args=[
+            '-v',
+            '--limit=10',
+            'filter_cdx',
+            f'{index_path}',
+            f'{str(whitelist_path)}',
+            f'{tmpdir}',
+            '--filter-type=surt',
+            f'--input-glob={index_glob}',
+            '--parallel=2',
+        ]
+    )
+
+    # Check that multiple files were processed in parallel
+    assert 'Found' in caplog.text and 'files matching pattern' in caplog.text
+    assert 'File statistics' in caplog.text
+    assert 'Filter statistics' in caplog.text
+
+    # Should have processed multiple files (pattern matches 2 files: cdx-00187.gz and cdx-00188.gz)
+    file_stats_count = caplog.text.count('File statistics')
+    assert file_stats_count == 2, 'Should process exactly 2 files with the glob pattern'
+
+
+def test_filter_cdx_nonexistent_surt_file_exits(tmpdir, caplog):
+    index_path = TEST_DATA_PATH / 'warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.gz'
+    nonexistent_surt_file_name = 'nonexistent_surts.txt'
+    nonexistent_surt_file = str(tmpdir / nonexistent_surt_file_name)
+
+    # Test that the command exits when SURT file doesn't exist
+    with pytest.raises(SystemExit) as exc_info:
+        main(
+            args=[
+                '-v',
+                '--limit=1140',
+                'filter_cdx',
+                f'{str(index_path)}',
+                f'{nonexistent_surt_file}',
+                f'{tmpdir}',
+                '--overwrite',
+            ]
+        )
+
+    assert exc_info.value.code == 1
+    assert 'Filter file not found: ' in caplog.text
+    assert nonexistent_surt_file_name in caplog.text
+
+
+def test_cli_filter_cdx_with_wildcard_urls(tmpdir, caplog):
+    # check if expected number is reached
+    index_path = TEST_DATA_PATH / 'warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.gz'
+    whitelist_path = fixture_path / 'whitelist_wildcard_urls.txt'  # matches on all .com and .fr host names
+
+    main(
+        args=[
+            '-v',
+            '--limit=10',
+            'filter_cdx',
+            f'{index_path}',
+            f'{str(whitelist_path)}',
+            f'{tmpdir}',
+            '--filter-type=url',
+            '--overwrite',
+        ]
+    )
+
+    assert 'Limit reached' in caplog.text
+
+
+def test_cli_filter_cdx_with_urls(tmpdir, caplog):
+    # check if expected number is reached
+    index_path = TEST_DATA_PATH / 'warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.gz'
+    whitelist_path = fixture_path / 'whitelist_10_urls.txt'  # matches on first domain and after 100k and 200k lines
+
+    main(
+        args=[
+            '-v',
+            '--limit=1140',
+            'filter_cdx',
+            f'{index_path}',
+            f'{str(whitelist_path)}',
+            f'{tmpdir}',
+            '--filter-type=url',
+            '--overwrite',
+        ]
+    )
+
+    assert 'Limit reached' in caplog.text
+
+
+def test_cli_filter_cdx_with_surts(tmpdir, caplog):
+    # check if expected number is reached
+    index_path = TEST_DATA_PATH / 'warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.gz'
+    whitelist_path = fixture_path / 'whitelist_10_surts.txt'  # matches on first domain and after 100k and 200k lines
+
+    main(
+        args=[
+            '-v',
+            '--limit=1140',
+            'filter_cdx',
+            f'{index_path}',
+            f'{str(whitelist_path)}',
+            f'{tmpdir}',
+            '--filter-type=surt',
+            '--overwrite',
+        ]
+    )
+
+    assert 'Limit reached' in caplog.text
diff --git a/tests/filter_cdx/test_filter_cdx.py b/tests/filter_cdx/test_filter_cdx.py
index 5ab0616..c2c4ed2 100644
--- a/tests/filter_cdx/test_filter_cdx.py
+++ b/tests/filter_cdx/test_filter_cdx.py
@@ -1,225 +1,41 @@
-import os
-import pytest
+import multiprocessing
+import signal
+import time
 
-from unittest.mock import patch
+from unittest.mock import patch, MagicMock
 
-from cdx_toolkit.cli import main
-from cdx_toolkit.filter_cdx import _process_single_file, resolve_paths, validate_resolved_paths, filter_cdx
 
 from url_is_in import SURTMatcher
 
-from tests.conftest import requires_aws_s3, TEST_DATA_PATH
+from cdx_toolkit.filter_cdx.cdx_filter import _filter_single_cdx_file, _filter_single_cdx_file_args, filter_cdx
+from tests.conftest import TEST_DATA_PATH
 
 fixture_path = TEST_DATA_PATH / 'filter_cdx'
 
 
-@requires_aws_s3
-def test_cli_filter_cdx_with_surts(tmpdir, caplog):
-    # check if expected number is reached
-    index_path = 's3://commoncrawl/cc-index/collections'
-    index_glob = '/CC-MAIN-2024-30/indexes/cdx-00187.gz'
-    whitelist_path = fixture_path / 'whitelist_10_surts.txt'  # matches on first domain and after 100k and 200k lines
-
-    main(
-        args=[
-            '-v',
-            '--limit=1140',
-            'filter_cdx',
-            f'{index_path}',
-            f'{str(whitelist_path)}',
-            f'{tmpdir}',
-            '--filter-type=surt',
-            f'--input-glob={index_glob}',
-        ]
-    )
-
-    assert 'Limit reached' in caplog.text
-
-
-@requires_aws_s3
-def test_cli_filter_cdx_with_urls(tmpdir, caplog):
-    # check if expected number is reached
-    index_path = 's3://commoncrawl/cc-index/collections'
-    index_glob = '/CC-MAIN-2024-30/indexes/cdx-00187.gz'
-    whitelist_path = fixture_path / 'whitelist_10_urls.txt'  # matches on first domain and after 100k and 200k lines
-
-    main(
-        args=[
-            '-v',
-            '--limit=1140',
-            'filter_cdx',
-            f'{index_path}',
-            f'{str(whitelist_path)}',
-            f'{tmpdir}',
-            '--filter-type=url',
-            f'--input-glob={index_glob}',
-        ]
-    )
-
-    assert 'Limit reached' in caplog.text
-
-
-@requires_aws_s3
-def test_cli_filter_cdx_with_wildcard_urls(tmpdir, caplog):
-    # check if expected number is reached
-    index_path = 's3://commoncrawl/cc-index/collections'
-    index_glob = '/CC-MAIN-2024-30/indexes/cdx-00187.gz'
-    whitelist_path = fixture_path / 'whitelist_wildcard_urls.txt'  # matches on all .com and .fr host names
-
-    main(
-        args=[
-            '-v',
-            '--limit=10',
-            'filter_cdx',
-            f'{index_path}',
-            f'{str(whitelist_path)}',
-            f'{tmpdir}',
-            '--filter-type=url',
-            f'--input-glob={index_glob}',
-        ]
-    )
-
-    assert 'Limit reached' in caplog.text
-
-
-@requires_aws_s3
-def test_resolve_cdx_paths_from_cc_s3_to_local(tmpdir):
-    tmpdir = str(tmpdir)
-    base_path = 's3://commoncrawl/cc-index/collections'
-    glob_pattern = '/CC-MAIN-2016-30/indexes/*.gz'
-
-    input_files, output_files = resolve_paths(base_path, glob_pattern, output_base_path=tmpdir)
-
-    assert len(input_files) == len(output_files), 'Input and output count must be the same'
-    assert len(input_files) == 300, 'Invalid input count'
-    assert input_files[0] == base_path + '/CC-MAIN-2016-30/indexes/cdx-00000.gz', 'Invalid input file'
-    assert output_files[0] == tmpdir + '/CC-MAIN-2016-30/indexes/cdx-00000.gz'.replace('/', os.sep), (
-        'Invalid output file'
-    )
-    assert input_files[-1] == base_path + '/CC-MAIN-2016-30/indexes/cdx-00299.gz'
-
-
-@requires_aws_s3
-def test_resolve_cdx_paths_from_cc_s3_to_another_s3():
-    output_base_path = 's3://some-other-bucket/filter-cdx'
-    base_path = 's3://commoncrawl/cc-index/collections'
-    glob_pattern = '/CC-MAIN-2016-30/indexes/cdx-000*.gz'
-
-    input_files, output_files = resolve_paths(base_path, glob_pattern, output_base_path=output_base_path)
-
-    assert len(input_files) == len(output_files), 'Input and output count must be the same'
-    assert len(input_files) == 100, 'Invalid input count'
-    assert input_files[0] == base_path + '/CC-MAIN-2016-30/indexes/cdx-00000.gz', 'Invalid input file'
-    assert output_files[0] == output_base_path + '/CC-MAIN-2016-30/indexes/cdx-00000.gz', 'Invalid output file'
-    assert input_files[-1] == base_path + '/CC-MAIN-2016-30/indexes/cdx-00099.gz'
-
-
-@requires_aws_s3
-def test_filter_cdx_nonexistent_surt_file_exits(tmpdir, caplog):
-    index_path = 's3://commoncrawl/cc-index/collections'
-    index_glob = '/CC-MAIN-2024-30/indexes/cdx-00187.gz'
-    nonexistent_surt_file_name = 'nonexistent_surts.txt'
-    nonexistent_surt_file = str(tmpdir / nonexistent_surt_file_name)
-
-    # Test that the command exits when SURT file doesn't exist
-    with pytest.raises(SystemExit) as exc_info:
-        main(
-            args=[
-                '-v',
-                '--limit=1140',
-                'filter_cdx',
-                f'{index_path}',
-                f'{nonexistent_surt_file}',
-                f'{tmpdir}',
-                f'--input-glob={index_glob}',
-            ]
-        )
-
-    assert exc_info.value.code == 1
-    assert 'Filter file not found: ' in caplog.text
-    assert nonexistent_surt_file_name in caplog.text
-
-
-def test_resolve_paths_no_files_found_exits(tmpdir, caplog):
-    # Test that resolve_paths exits when no files match the glob pattern
-    with pytest.raises(SystemExit) as exc_info:
-        resolve_paths(input_base_path=str(tmpdir), input_glob='/nonexistent-pattern-*.gz', output_base_path=str(tmpdir))
-
-    assert exc_info.value.code == 1
-    assert 'No files found matching glob pattern:' in caplog.text
-
-
-def test_validate_resolved_paths_existing_file_exits(tmpdir, caplog):
-    # Create an existing output file
-    existing_file = tmpdir / 'existing_output.txt'
-    existing_file.write_text('existing content', encoding='utf-8')
-
-    output_paths = [str(existing_file)]
-
-    # Test that validate_resolved_paths exits when output file exists and overwrite=False
-    with pytest.raises(SystemExit) as exc_info:
-        validate_resolved_paths(output_paths, overwrite=False)
-
-    assert exc_info.value.code == 1
-    assert f'Output file already exists: {str(existing_file)}' in caplog.text
-    assert 'Use --overwrite to overwrite existing files' in caplog.text
-
-
-@requires_aws_s3
-def test_cli_filter_cdx_with_parallel_processing(tmpdir, caplog):
-    """Test that parallel processing works correctly and processes multiple files."""
-    index_path = 's3://commoncrawl/cc-index/collections'
-    index_glob = '/CC-MAIN-2024-30/indexes/cdx-0018[78].gz'  # Multiple files pattern
-    whitelist_path = fixture_path / 'whitelist_11_surts.txt'  # Additonal entry for cdx-00188.gz
-
-    # Run with parallel processing (2 workers)
-    main(
-        args=[
-            '-v',
-            '--limit=10',
-            'filter_cdx',
-            f'{index_path}',
-            f'{str(whitelist_path)}',
-            f'{tmpdir}',
-            '--filter-type=surt',
-            f'--input-glob={index_glob}',
-            '--parallel=2',
-        ]
-    )
-
-    # Check that multiple files were processed in parallel
-    assert 'Found' in caplog.text and 'files matching pattern' in caplog.text
-    assert 'File statistics' in caplog.text
-    assert 'Filter statistics' in caplog.text
-
-    # Should have processed multiple files (pattern matches 2 files: cdx-00187.gz and cdx-00188.gz)
-    file_stats_count = caplog.text.count('File statistics')
-    assert file_stats_count == 2, 'Should process exactly 2 files with the glob pattern'
-
-
-def test_process_single_file(tmpdir):
+def test_filter_single_file(tmpdir):
     input_path = TEST_DATA_PATH / 'warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.gz'
     matcher = SURTMatcher(['fr,'])
-
-    _, _, lines_n, included_n, errors_n = _process_single_file(
+    args = dict(
         input_path=input_path,
         output_path=tmpdir + '/filter_cdx',
         matcher=matcher,
         log_every_n=10,
         limit=100,
     )
+    _, _, lines_n, included_n, errors_n = _filter_single_cdx_file_args(args)
 
     assert included_n == 100
     assert lines_n == 100
     assert errors_n == 0
 
 
-def test_process_single_file_empty(tmpdir):
+def test_filter_single_file_empty(tmpdir):
     input_path = tmpdir + '/input'
     with open(input_path, 'w') as f:
         f.write('')
 
-    _, _, lines_n, included_n, errors_n = _process_single_file(
+    _, _, lines_n, included_n, errors_n = _filter_single_cdx_file(
         input_path=input_path,
         output_path=tmpdir + '/output',
         matcher=None,
@@ -229,6 +45,36 @@ def test_process_single_file_empty(tmpdir):
     assert errors_n == 0
 
 
+def test_filter_single_cdx_file_input_not_found(tmpdir):
+
+    _, _, lines_n, included_n, errors_n = _filter_single_cdx_file(
+        input_path=tmpdir + "/input-not-found",
+        output_path=tmpdir + '/output',
+        matcher=SURTMatcher([]),
+    )
+    assert lines_n == 0
+    assert included_n == 0
+    assert errors_n == 1, 'Invalid error count'
+
+
+def test_filter_single_cdx_file_with_matcher_error(tmpdir):
+    class MockMatcher(SURTMatcher):
+        def is_in(self, surt):
+            raise ValueError()
+
+    mock_matcher = MockMatcher([])
+    input_path = TEST_DATA_PATH / 'warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.gz'
+
+    _, _, lines_n, included_n, errors_n = _filter_single_cdx_file(
+        input_path=input_path,
+        output_path=tmpdir + '/output',
+        matcher=mock_matcher,
+    )
+    assert lines_n == 1140
+    assert included_n == 0
+    assert errors_n == 1140, 'Invalid error count'
+
+
 def test_filter_cdx_error_handling(tmpdir, caplog):
     """Test filter_cdx function error handling when exceptions occur during processing."""
     import multiprocessing
@@ -240,7 +86,7 @@ def test_filter_cdx_error_handling(tmpdir, caplog):
         # Force fork method for consistent behavior across platforms
         multiprocessing.set_start_method('fork', force=True)
 
-        def mock_process_single_file(*args, **kwargs):
+        def mock_filter_single_file(*args, **kwargs):
             raise ValueError()
 
         # Create test input and output paths
@@ -248,7 +94,7 @@ def mock_process_single_file(*args, **kwargs):
         output_paths = [str(tmpdir / 'output1.cdx'), str(tmpdir / 'output2.cdx')]
 
         # Replace the _process_single_file function with our mock
-        with patch('cdx_toolkit.filter_cdx._process_single_file', side_effect=mock_process_single_file):
+        with patch('cdx_toolkit.filter_cdx.cdx_filter._filter_single_cdx_file', side_effect=mock_filter_single_file):
             # Test the error handling
             total_lines, total_included, total_errors = filter_cdx(
                 matcher=None,
@@ -266,3 +112,57 @@ def mock_process_single_file(*args, **kwargs):
     finally:
         # Restore original start method
         multiprocessing.set_start_method(original_start_method, force=True)
+
+
+def test_filter_cdx_keyboard_interrupt_handling(tmpdir, caplog):
+    """Test that filter_cdx properly handles KeyboardInterrupt and terminates the pool."""
+    # Store original start method to restore later
+    original_start_method = multiprocessing.get_start_method()
+
+    try:
+        # Force fork method for consistent behavior across platforms
+        multiprocessing.set_start_method('fork', force=True)
+
+        def slow_filter_single_file(*args, **kwargs):
+            """Mock function that simulates a slow process that can be interrupted."""
+            time.sleep(1)  # Simulate slow processing
+            return args[0], args[1], 10, 5, 0  # Return some dummy stats
+
+        # Create test input and output paths
+        input_paths = [str(tmpdir / 'input1.cdx'), str(tmpdir / 'input2.cdx')]
+        output_paths = [str(tmpdir / 'output1.cdx'), str(tmpdir / 'output2.cdx')]
+
+        # Set caplog to capture INFO level messages
+        caplog.set_level('INFO')
+
+        # Mock the Pool class to allow us to verify terminate() and join() are called
+        with patch('cdx_toolkit.filter_cdx.cdx_filter.Pool') as mock_pool_class:
+            mock_pool = MagicMock()
+            mock_pool_class.return_value = mock_pool
+
+            # Make imap raise KeyboardInterrupt after a short delay
+            def interrupt_after_delay(*args, **kwargs):
+                time.sleep(0.1)  # Brief delay before interrupt
+                raise KeyboardInterrupt()
+
+            mock_pool.imap.side_effect = interrupt_after_delay
+
+            # Test the keyboard interrupt handling
+            total_lines, total_included, total_errors = filter_cdx(
+                matcher=None, input_paths=input_paths, output_paths=output_paths, n_parallel=2
+            )
+
+            # Verify that pool.terminate() and pool.join() were called
+            mock_pool.terminate.assert_called_once()
+            mock_pool.join.assert_called()
+
+            # Verify that the interrupt was logged
+            assert 'Process interrupted by user (Ctrl+C). Terminating running tasks...' in caplog.text
+            assert 'All tasks terminated.' in caplog.text
+
+            # Verify pool cleanup in finally block
+            mock_pool.close.assert_called_once()
+
+    finally:
+        # Restore original start method
+        multiprocessing.set_start_method(original_start_method, force=True)
diff --git a/tests/filter_cdx/test_path_utils.py b/tests/filter_cdx/test_path_utils.py
new file mode 100644
index 0000000..f1fddc7
--- /dev/null
+++ b/tests/filter_cdx/test_path_utils.py
@@ -0,0 +1,84 @@
+import tempfile
+from cdx_toolkit.filter_cdx.path_utils import resolve_paths, validate_resolved_paths
+from tests.conftest import TEST_S3_BUCKET, requires_aws_s3
+
+import pytest
+import os
+
+
+def test_resolve_s3_paths_without_glob():
+    input_files, output_files = resolve_paths(
+        input_base_path="s3://commoncraw/cc-index/collections/CC-MAIN-2016-30/indexes/cdx-00001.gz", 
+        input_glob=None, 
+        output_base_path=f"s3://{TEST_S3_BUCKET}/output",
+    )
+    assert len(input_files) == 1
+    assert len(output_files) == len(input_files)
+
+
+def test_validate_resolved_paths_with_makedirs():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        validate_resolved_paths(
+            output_paths=[
+                os.path.join(tmpdir, "1"),
+                os.path.join(tmpdir, "2"),
+            ],
+            overwrite=False
+        )
+
+
+@requires_aws_s3
+def test_resolve_cdx_paths_from_cc_s3_to_local(tmpdir):
+    tmpdir = str(tmpdir)
+    base_path = 's3://commoncrawl/cc-index/collections'
+    glob_pattern = '/CC-MAIN-2016-30/indexes/*.gz'
+
+    input_files, output_files = resolve_paths(base_path, glob_pattern, output_base_path=tmpdir)
+
+    assert len(input_files) == len(output_files), 'Input and output count must be the same'
+    assert len(input_files) == 300, 'Invalid input count'
+    assert input_files[0] == base_path + '/CC-MAIN-2016-30/indexes/cdx-00000.gz', 'Invalid input file'
+    assert output_files[0] == tmpdir + '/CC-MAIN-2016-30/indexes/cdx-00000.gz'.replace('/', os.sep), (
+        'Invalid output file'
+    )
+    assert input_files[-1] == base_path + '/CC-MAIN-2016-30/indexes/cdx-00299.gz'
+
+
+@requires_aws_s3
+def test_resolve_cdx_paths_from_cc_s3_to_another_s3():
+    output_base_path = 's3://some-other-bucket/filter-cdx'
+    base_path = 's3://commoncrawl/cc-index/collections'
+    glob_pattern = '/CC-MAIN-2016-30/indexes/cdx-000*.gz'
+
+    input_files, output_files = resolve_paths(base_path, glob_pattern, output_base_path=output_base_path)
+
+    assert len(input_files) == len(output_files), 'Input and output count must be the same'
+    assert len(input_files) == 100, 'Invalid input count'
+    assert input_files[0] == base_path + '/CC-MAIN-2016-30/indexes/cdx-00000.gz', 'Invalid input file'
+    assert output_files[0] == output_base_path + '/CC-MAIN-2016-30/indexes/cdx-00000.gz', 'Invalid output file'
+    assert input_files[-1] == base_path + '/CC-MAIN-2016-30/indexes/cdx-00099.gz'
+
+
+def test_resolve_paths_no_files_found_exits(tmpdir, caplog):
+    # Test that resolve_paths exits when no files match the glob pattern
+    with pytest.raises(SystemExit) as exc_info:
+        resolve_paths(input_base_path=str(tmpdir), input_glob='/nonexistent-pattern-*.gz', output_base_path=str(tmpdir))
+
+    assert exc_info.value.code == 1
+    assert 'No files found matching glob pattern:' in caplog.text
+
+
+def test_validate_resolved_paths_existing_file_exits(tmpdir, caplog):
+    # Create an existing output file
+    existing_file = tmpdir / 'existing_output.txt'
+    existing_file.write_text('existing content', encoding='utf-8')
+
+    output_paths = [str(existing_file)]
+
+    # Test that validate_resolved_paths exits when output file exists and overwrite=False
+    with pytest.raises(SystemExit) as exc_info:
+        validate_resolved_paths(output_paths, overwrite=False)
+
+    assert exc_info.value.code == 1
+    assert f'Output file already exists: {str(existing_file)}' in caplog.text
+    assert 'Use --overwrite to overwrite existing files' in caplog.text
\ No newline at end of file
diff --git a/tests/filter_warc/test_warc_by_cdx.py b/tests/filter_warc/test_command.py
similarity index 90%
rename from tests/filter_warc/test_warc_by_cdx.py
rename to tests/filter_warc/test_command.py
index 058685a..c3c5ed9 100644
--- a/tests/filter_warc/test_warc_by_cdx.py
+++ b/tests/filter_warc/test_command.py
@@ -131,7 +131,40 @@ def test_cli_warc_by_cdx_over_s3_to_s3_in_parallel(s3_tmpdir, caplog):
         's3://commoncrawl',
         base_prefix=s3_tmpdir,
         caplog=caplog,
-        extra_args=['--parallel=3'],
+        extra_args=['--parallel=3', '--is-part-of=foobar'],
+    )
+
+
+@requires_aws_s3
+def test_cli_warc_by_cdx_over_s3_to_s3_warc_filter(s3_tmpdir, caplog):
+    assert_cli_warc_by_cdx(
+        's3://commoncrawl',
+        base_prefix=s3_tmpdir,
+        caplog=caplog,
+    )
+
+
+@requires_aws_s3
+def test_cli_warc_by_cdx_over_http_to_s3_in_parallel(s3_tmpdir, caplog):
+    assert_cli_warc_by_cdx(
+        'https://data.commoncrawl.org',
+        base_prefix=s3_tmpdir,
+        caplog=caplog,
+        extra_args=[
+            '--parallel=3',
+        ],
+    )
+
+
+@requires_aws_s3
+def test_cli_warc_by_cdx_over_s3_to_local_in_parallel(tmpdir, caplog):
+    assert_cli_warc_by_cdx(
+        's3://commoncrawl',
+        base_prefix=tmpdir,
+        caplog=caplog,
+        extra_args=[
+            '--parallel=3',
+        ],
     )
 
 
diff --git a/tests/filter_warc/test_data_classes.py b/tests/filter_warc/test_data_classes.py
new file mode 100644
index 0000000..f86d96d
--- /dev/null
+++ b/tests/filter_warc/test_data_classes.py
@@ -0,0 +1,12 @@
+import pytest
+from cdx_toolkit.filter_warc.data_classes import RangeJob
+
+
+def test_get_s3_bucket_and_key_from_http_job():
+    job = RangeJob(
+        url='http://foo.com/example',
+        offset=0,
+        length=10,
+    )
+    with pytest.raises(ValueError):
+        job.get_s3_bucket_and_key()
diff --git a/tests/filter_warc/test_grouped_range_jobs.py b/tests/filter_warc/test_grouped_range_jobs.py
new file mode 100644
index 0000000..adf9a07
--- /dev/null
+++ b/tests/filter_warc/test_grouped_range_jobs.py
@@ -0,0 +1,51 @@
+import fsspec
+import pytest
+from cdx_toolkit.filter_warc.cdx_utils import get_index_as_string_from_path, read_cdx_line, iter_cdx_index_from_path
+from tests.conftest import TEST_DATA_PATH
+
+import tempfile
+import gzip
+import os
+from unittest.mock import patch
+
+
+
+def test_iter_cdx_index_from_test_data():
+    cdx_path = TEST_DATA_PATH / 'warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.gz'
+    results = list(iter_cdx_index_from_path(str(cdx_path), 'http://warc-prefix'))
+    # [(url, offset, length)]
+
+    # sort results by offsets
+    results.sort(key=lambda x: x[1])
+
+    # group into neighbor chunks
+    def group_neighbor_chunks(items):
+        """Group items into chunks where items have same URL and are contiguous."""
+        if not items:
+            return []
+
+        chunks = []
+        current_chunk = [items[0]]
+
+        for i in range(1, len(items)):
+            prev_url, prev_offset, prev_length = items[i-1]
+            curr_url, curr_offset, curr_length = items[i]
+
+            # Check if current item is a neighbor (same URL and contiguous)
+            if curr_url == prev_url and curr_offset == prev_offset + prev_length + 4:
+                current_chunk.append(items[i])
+            else:
+                # Start new chunk
+                chunks.append(current_chunk)
+                current_chunk = [items[i]]
+
+        # Add the last chunk
+        chunks.append(current_chunk)
+        return chunks
+
+    grouped_chunks = group_neighbor_chunks(results)
+    print(len(results), len(grouped_chunks))
+
+
+def test_grouped_ranges():
+    cdx_path = ""
\ No newline at end of file
diff --git a/tests/filter_warc/test_local_writer.py b/tests/filter_warc/test_local_writer.py
new file mode 100644
index 0000000..36a88c5
--- /dev/null
+++ b/tests/filter_warc/test_local_writer.py
@@ -0,0 +1,454 @@
+import asyncio
+import pytest
+from unittest.mock import patch
+
+from cdx_toolkit.filter_warc.local_writer import LocalFileWriter
+
+
+def test_init_default_values():
+    """Test initialization with default values."""
+    writer = LocalFileWriter("/tmp/test.txt")
+    assert writer.file_path == "/tmp/test.txt"
+    assert writer.buffer_size == 8192
+    assert writer.mode == 'wb'
+    assert writer.file_handle is None
+    assert isinstance(writer.buffer, bytearray)
+    assert len(writer.buffer) == 0
+
+
+def test_init_custom_values():
+    """Test initialization with custom values."""
+    writer = LocalFileWriter("/tmp/test.txt", buffer_size=4096, mode='ab')
+    assert writer.file_path == "/tmp/test.txt"
+    assert writer.buffer_size == 4096
+    assert writer.mode == 'ab'
+    assert writer.file_handle is None
+    assert isinstance(writer.buffer, bytearray)
+    assert len(writer.buffer) == 0
+
+
+def test_start_opens_file(tmp_path):
+    """Test that start() opens the file correctly."""
+    async def run_test():
+        temp_file = tmp_path / "test.txt"
+        writer = LocalFileWriter(str(temp_file))
+        await writer.start()
+
+        assert writer.file_handle is not None
+        await writer.close()
+
+    asyncio.run(run_test())
+
+
+def test_start_with_different_modes(tmp_path):
+    """Test start() with different file modes."""
+    async def run_test():
+        temp_file = tmp_path / "test.txt"
+
+        # Test binary write mode
+        writer = LocalFileWriter(str(temp_file), mode='wb')
+        await writer.start()
+        assert writer.file_handle is not None
+        await writer.close()
+
+        # Test binary append mode
+        writer = LocalFileWriter(str(temp_file), mode='ab')
+        await writer.start()
+        assert writer.file_handle is not None
+        await writer.close()
+
+    asyncio.run(run_test())
+
+
+def test_start_creates_directory_if_needed(tmp_path):
+    """Test that start() works when parent directory exists."""
+    async def run_test():
+        subdir = tmp_path / "subdir"
+        subdir.mkdir()
+        temp_file = subdir / "test.txt"
+
+        writer = LocalFileWriter(str(temp_file))
+        await writer.start()
+        assert writer.file_handle is not None
+        await writer.close()
+
+    asyncio.run(run_test())
+
+
+def test_write_small_data_buffers(tmp_path):
+    """Test writing data that doesn't exceed buffer size."""
+    async def run_test():
+        temp_file = tmp_path / "test.txt"
+        writer = LocalFileWriter(str(temp_file), buffer_size=100)
+        await writer.start()
+
+        test_data = b"Hello, World!"
+        await writer.write(test_data)
+
+        # Data should be in buffer, not yet written to file
+        assert len(writer.buffer) == len(test_data)
+        assert writer.buffer == test_data
+
+        await writer.close()
+
+        # After close, data should be written to file
+        assert temp_file.read_bytes() == test_data
+
+    asyncio.run(run_test())
+
+
+def test_write_large_data_triggers_flush(tmp_path):
+    """Test writing data that exceeds buffer size triggers flush."""
+    async def run_test():
+        temp_file = tmp_path / "test.txt"
+        buffer_size = 50
+        writer = LocalFileWriter(str(temp_file), buffer_size=buffer_size)
+        await writer.start()
+
+        # Write data larger than buffer size
+        test_data = b"x" * (buffer_size + 10)
+        await writer.write(test_data)
+
+        # Buffer should be empty after automatic flush
+        assert len(writer.buffer) == 0
+
+        await writer.close()
+
+        # Data should be written to file
+        assert temp_file.read_bytes() == test_data
+
+    asyncio.run(run_test())
+
+
+def test_write_multiple_small_chunks(tmp_path):
+    """Test writing multiple small chunks that eventually trigger flush."""
+    async def run_test():
+        temp_file = tmp_path / "test.txt"
+        buffer_size = 50
+        writer = LocalFileWriter(str(temp_file), buffer_size=buffer_size)
+        await writer.start()
+
+        chunk1 = b"a" * 30
+        chunk2 = b"b" * 25  # Total: 55 bytes, exceeds buffer
+
+        await writer.write(chunk1)
+        assert len(writer.buffer) == 30
+
+        await writer.write(chunk2)
+        # Should have triggered flush, buffer should be empty
+        assert len(writer.buffer) == 0
+
+        await writer.close()
+
+        assert temp_file.read_bytes() == chunk1 + chunk2
+
+    asyncio.run(run_test())
+
+
+def test_write_empty_data(tmp_path):
+    """Test writing empty data."""
+    async def run_test():
+        temp_file = tmp_path / "test.txt"
+        writer = LocalFileWriter(str(temp_file))
+        await writer.start()
+
+        await writer.write(b"")
+        assert len(writer.buffer) == 0
+
+        await writer.close()
+
+        assert temp_file.read_bytes() == b""
+
+    asyncio.run(run_test())
+
+
+def test_write_without_start_graceful_handling(tmp_path):
+    """Test that writing without calling start() is handled gracefully."""
+    async def run_test():
+        temp_file = tmp_path / "test.txt"
+        writer = LocalFileWriter(str(temp_file), buffer_size=10)  # Small buffer to force flush
+
+        # This should work fine as long as we don't exceed buffer size
+        await writer.write(b"small")
+        assert len(writer.buffer) == 5
+
+        # When buffer exceeds size, flush is called but does nothing since file_handle is None
+        # The data stays in buffer instead of being written
+        await writer.write(b"data that exceeds buffer size")
+
+        # Buffer should contain all the data since flush did nothing
+        expected_data = b"small" + b"data that exceeds buffer size"
+        assert writer.buffer == expected_data
+
+    asyncio.run(run_test())
+
+
+def test_flush_empty_buffer(tmp_path):
+    """Test flushing when buffer is empty."""
+    async def run_test():
+        temp_file = tmp_path / "test.txt"
+        writer = LocalFileWriter(str(temp_file))
+        await writer.start()
+
+        # Flush empty buffer should not raise error
+        await writer._flush()
+        assert len(writer.buffer) == 0
+
+        await writer.close()
+
+    asyncio.run(run_test())
+
+
+def test_flush_without_file_handle(tmp_path):
+    """Test flushing without file handle."""
+    async def run_test():
+        temp_file = tmp_path / "test.txt"
+        writer = LocalFileWriter(str(temp_file))
+        writer.buffer.extend(b"test data")
+
+        # Should not raise error, just do nothing
+        await writer._flush()
+        assert len(writer.buffer) == len(b"test data")  # Buffer unchanged
+
+    asyncio.run(run_test())
+
+
+def test_close_flushes_remaining_data(tmp_path):
+    """Test that close() flushes any remaining buffered data."""
+    async def run_test():
+        temp_file = tmp_path / "test.txt"
+        writer = LocalFileWriter(str(temp_file), buffer_size=100)
+        await writer.start()
+
+        test_data = b"This data should be flushed on close"
+        await writer.write(test_data)
+
+        # Data should still be in buffer
+        assert len(writer.buffer) == len(test_data)
+
+        await writer.close()
+
+        # Data should now be written to file
+        assert temp_file.read_bytes() == test_data
+
+    asyncio.run(run_test())
+
+
+def test_close_without_start(tmp_path):
+    """Test closing without calling start()."""
+    async def run_test():
+        temp_file = tmp_path / "test.txt"
+        writer = LocalFileWriter(str(temp_file))
+
+        # Should not raise error
+        await writer.close()
+
+    asyncio.run(run_test())
+
+
+def test_close_twice(tmp_path):
+    """Test calling close() multiple times."""
+    async def run_test():
+        temp_file = tmp_path / "test.txt"
+        writer = LocalFileWriter(str(temp_file))
+        await writer.start()
+
+        await writer.close()
+
+        # Second close should not raise error
+        await writer.close()
+
+    asyncio.run(run_test())
+
+
+def test_close_handles_flush_exception(tmp_path):
+    """Test that close() handles exceptions during flush properly."""
+    async def run_test():
+        temp_file = tmp_path / "test.txt"
+        writer = LocalFileWriter(str(temp_file))
+        await writer.start()
+
+        # Add some data to buffer
+        await writer.write(b"test data")
+
+        # Mock flush to raise an exception
+        with patch.object(writer, '_flush', side_effect=Exception("Flush error")):
+            with pytest.raises(Exception, match="Flush error"):
+                await writer.close()
+
+    asyncio.run(run_test())
+
+
+def test_close_handles_file_close_exception(tmp_path):
+    """Test that close() handles exceptions during file close."""
+    async def run_test():
+        temp_file = tmp_path / "test.txt"
+        writer = LocalFileWriter(str(temp_file))
+        await writer.start()
+
+        # Mock file handle close to raise an exception
+        with patch.object(writer.file_handle, 'close', side_effect=Exception("Close error")):
+            with pytest.raises(Exception, match="Close error"):
+                await writer.close()
+
+    asyncio.run(run_test())
+
+
+def test_large_file_write(tmp_path):
+    """Test writing a large amount of data."""
+    async def run_test():
+        temp_file = tmp_path / "test.txt"
+        writer = LocalFileWriter(str(temp_file), buffer_size=1024)
+        await writer.start()
+
+        # Write 1MB of data in chunks
+        chunk_size = 1024  # Make chunk size same as buffer for exact division
+        total_size = 1024 * 1024  # 1MB
+        chunk_data = b"x" * chunk_size
+
+        for _ in range(total_size // chunk_size):
+            await writer.write(chunk_data)
+
+        await writer.close()
+
+        # Verify file size
+        assert temp_file.stat().st_size == total_size
+
+    asyncio.run(run_test())
+
+
+def test_binary_data_integrity(tmp_path):
+    """Test that binary data is written correctly."""
+    async def run_test():
+        temp_file = tmp_path / "test.txt"
+        writer = LocalFileWriter(str(temp_file))
+        await writer.start()
+
+        # Create binary data with all byte values
+        binary_data = bytes(range(256))
+        await writer.write(binary_data)
+
+        await writer.close()
+
+        assert temp_file.read_bytes() == binary_data
+
+    asyncio.run(run_test())
+
+
+def test_concurrent_writes(tmp_path):
+    """Test concurrent write operations."""
+    async def run_test():
+        temp_file = tmp_path / "test.txt"
+        writer = LocalFileWriter(str(temp_file), buffer_size=100)
+        await writer.start()
+
+        # Create multiple write tasks
+        async def write_chunk(data):
+            await writer.write(data)
+
+        tasks = [
+            write_chunk(f"chunk{i}".encode() * 10)
+            for i in range(10)
+        ]
+
+        await asyncio.gather(*tasks)
+        await writer.close()
+
+        # Verify file exists and has data
+        assert temp_file.exists()
+        assert temp_file.stat().st_size > 0
+
+    asyncio.run(run_test())
+
+
+def test_file_permissions_error(tmp_path):
+    """Test handling of file permission errors."""
+    async def run_test():
+        # Create a file path in a directory we can't write to
+        readonly_file = tmp_path / "readonly.txt"
+
+        # Create the file first
+        readonly_file.write_text("test")
+
+        # Make the file read-only
+        readonly_file.chmod(0o444)
+
+        writer = LocalFileWriter(str(readonly_file), mode='wb')
+
+        with pytest.raises(PermissionError):
+            await writer.start()
+
+    asyncio.run(run_test())
+
+
+def test_nonexistent_directory():
+    """Test writing to a file in a nonexistent directory."""
+    async def run_test():
+        nonexistent_path = "/nonexistent/directory/file.txt"
+        writer = LocalFileWriter(nonexistent_path)
+
+        with pytest.raises(FileNotFoundError):
+            await writer.start()
+
+    asyncio.run(run_test())
+
+
+def test_context_manager_like_usage(tmp_path):
+    """Test typical usage pattern similar to context manager."""
+    async def run_test():
+        temp_file = tmp_path / "test.txt"
+        writer = LocalFileWriter(str(temp_file))
+
+        try:
+            await writer.start()
+            await writer.write(b"Hello, World!")
+            await writer.write(b" How are you?")
+        finally:
+            await writer.close()
+
+        assert temp_file.read_bytes() == b"Hello, World! How are you?"
+
+    asyncio.run(run_test())
+
+
+def test_buffer_size_edge_cases(tmp_path):
+    """Test edge cases with different buffer sizes."""
+    async def run_test():
+        temp_file = tmp_path / "test.txt"
+        # Test with buffer size of 1
+        writer = LocalFileWriter(str(temp_file), buffer_size=1)
+        await writer.start()
+
+        await writer.write(b"a")  # Should trigger flush immediately
+        assert len(writer.buffer) == 0
+
+        await writer.write(b"bc")  # Should trigger flush after 'b', leaving 'c'
+        assert len(writer.buffer) == 0
+
+        await writer.close()
+
+        assert temp_file.read_bytes() == b"abc"
+
+    asyncio.run(run_test())
+
+
+def test_append_mode(tmp_path):
+    """Test append mode functionality."""
+    async def run_test():
+        temp_file = tmp_path / "test.txt"
+
+        # First, write some initial data
+        temp_file.write_bytes(b"Initial data\n")
+
+        # Now append using LocalFileWriter
+        writer = LocalFileWriter(str(temp_file), mode='ab')
+        await writer.start()
+
+        await writer.write(b"Appended data\n")
+        await writer.close()
+
+        # Verify both pieces of data are present
+        content = temp_file.read_bytes()
+        assert content == b"Initial data\nAppended data\n"
+
+    asyncio.run(run_test())
\ No newline at end of file
diff --git a/tests/filter_warc/test_s3_utils.py b/tests/filter_warc/test_s3_utils.py
index e3ab56d..fe4c53a 100644
--- a/tests/filter_warc/test_s3_utils.py
+++ b/tests/filter_warc/test_s3_utils.py
@@ -20,9 +20,9 @@ def test_backoff():
     result1 = _backoff(1, base_backoff)
     assert 0.8 <= result1 <= 1.2
 
-    # Test attempt 2: should be between 1.6 and 2.4 seconds (2^1 * base * jitter)
+    # Test attempt 2: should be between 1.6 and 2.41 seconds (2^1 * base * jitter)
     result2 = _backoff(2, base_backoff)
-    assert 1.6 <= result2 <= 2.4
+    assert 1.6 <= result2 <= 2.41
 
     # Test attempt 3: should be between 3.2 and 4.8 seconds (2^2 * base * jitter)
     result3 = _backoff(3, base_backoff)
diff --git a/tests/filter_warc/test_warc_filter.py b/tests/filter_warc/test_warc_filter.py
index 7819074..0c03063 100644
--- a/tests/filter_warc/test_warc_filter.py
+++ b/tests/filter_warc/test_warc_filter.py
@@ -1,51 +1,434 @@
+import asyncio
+import pytest
+from unittest.mock import AsyncMock, patch
+from cdx_toolkit.filter_warc.data_classes import ThroughputTracker
+from tests.conftest import TEST_DATA_PATH
 
-from tests.conftest import requires_aws_s3, TEST_DATA_PATH
-
-from tests.filter_warc.test_warc_by_cdx import assert_cli_warc_by_cdx
+from cdx_toolkit.filter_warc.warc_filter import WARCFilter
 
 fixture_path = TEST_DATA_PATH / 'warc_by_cdx'
 
 
-@requires_aws_s3
-def test_cli_warc_by_cdx_over_s3_to_s3_warc_filter(s3_tmpdir, caplog):
-    assert_cli_warc_by_cdx(
-        's3://commoncrawl',
-        base_prefix=s3_tmpdir,
-        caplog=caplog,
-    )
+def test_filter_keyboard_interrupt_handling(caplog):
+    """Test that KeyboardInterrupt is properly handled in the filter method."""
+    import logging
 
+    # Set log level to capture WARNING messages
+    caplog.set_level(logging.WARNING, logger='cdx_toolkit.filter_warc.warc_filter')
 
-@requires_aws_s3
-def test_cli_warc_by_cdx_over_s3_to_s3_in_parallel_warc_filter(s3_tmpdir, caplog):
-    assert_cli_warc_by_cdx(
-        's3://commoncrawl',
-        base_prefix=s3_tmpdir,
-        caplog=caplog,
-        extra_args=[
-            '--parallel=3',
-        ],
-    )
+    warc_filter = WARCFilter(index_paths=['/fake/path'], prefix_path='/fake/prefix', writer_info={'writer_id': 1})
+
+    # Mock filter_async to raise KeyboardInterrupt
+    with patch.object(warc_filter, 'filter_async', side_effect=KeyboardInterrupt('Simulated user interrupt')):
+        # Call the filter method
+        result = warc_filter.filter()
+
+        # Should return -1 when interrupted
+        assert result == -1
+
+        # Should log the warning message
+        assert 'Interrupted by user.' in caplog.text
+
+
+def test_rotate_files_no_rotation_needed():
+    """Test rotate_files when no rotation is needed (file size below limit)."""
+
+    async def run_test():
+        warc_filter = WARCFilter(
+            index_paths=['/fake/path'],
+            prefix_path='/fake/prefix',
+            writer_info={'writer_id': 1},
+            max_file_size=1000,  # 1KB limit
+        )
+
+        mock_writer = AsyncMock()
+        current_file_sequence = 1
+        current_file_size = 500  # 500 bytes
+        added_byte_size = 200  # Adding 200 bytes, total would be 700 (below limit)
+
+        # Call rotate_files
+        result_writer, result_sequence, result_size = await warc_filter.rotate_files(
+            writer=mock_writer,
+            current_file_sequence=current_file_sequence,
+            current_file_size=current_file_size,
+            added_byte_size=added_byte_size,
+            writer_id=1,
+            output_path_prefix='/fake/output',
+            max_attempts=3,
+            base_backoff_seconds=1.0,
+            min_part_size=1024,
+            writer_info={'writer_id': 1},
+        )
+
+        # Should return original values since no rotation occurred
+        assert result_writer == mock_writer
+        assert result_sequence == current_file_sequence
+        assert result_size == current_file_size
+
+        # Writer should not be closed
+        mock_writer.close.assert_not_called()
+
+    asyncio.run(run_test())
+
+
+def test_rotate_files_rotation_needed_without_resource_records():
+    """Test rotate_files when rotation is needed and no resource records to write."""
+
+    async def run_test():
+        warc_filter = WARCFilter(
+            index_paths=['/fake/path'],
+            prefix_path='/fake/prefix',
+            writer_info={'writer_id': 1},
+            max_file_size=1000,  # 1KB limit
+            write_paths_as_resource_records=None,  # No resource records
+        )
+
+        mock_writer = AsyncMock()
+        mock_new_writer = AsyncMock()
+        current_file_sequence = 1
+        current_file_size = 800  # 800 bytes
+        added_byte_size = 300  # Adding 300 bytes, total would be 1100 (above limit)
+
+        # Mock create_new_writer_with_header
+        with patch('cdx_toolkit.filter_warc.warc_filter.create_new_writer_with_header') as mock_create:
+            mock_create.return_value = (mock_new_writer, 150, 'warcinfo-123')  # (writer, header_size, warcinfo_id)
+
+            # Call rotate_files
+            result_writer, result_sequence, result_size = await warc_filter.rotate_files(
+                writer=mock_writer,
+                current_file_sequence=current_file_sequence,
+                current_file_size=current_file_size,
+                added_byte_size=added_byte_size,
+                writer_id=1,
+                output_path_prefix='/fake/output',
+                max_attempts=3,
+                base_backoff_seconds=1.0,
+                min_part_size=1024,
+                writer_info={'writer_id': 1},
+            )
+
+            # Should have rotated
+            assert result_writer == mock_new_writer
+            assert result_sequence == current_file_sequence + 1  # Incremented
+            assert result_size == 150  # Header size only
+
+            # Old writer should be closed
+            mock_writer.close.assert_called_once()
+
+            # New writer should be created
+            mock_create.assert_called_once_with(
+                sequence=current_file_sequence + 1,
+                writer_id=1,
+                output_path_prefix='/fake/output',
+                max_attempts=3,
+                base_backoff_seconds=1.0,
+                min_part_size=1024,
+                writer_info={'writer_id': 1},
+            )
+
+    asyncio.run(run_test())
+
+
+def test_rotate_files_rotation_needed_with_resource_records():
+    """Test rotate_files when rotation is needed and resource records need to be written."""
+
+    async def run_test():
+        warc_filter = WARCFilter(
+            index_paths=['/fake/path'],
+            prefix_path='/fake/prefix',
+            writer_info={'writer_id': 1},
+            max_file_size=1000,  # 1KB limit
+            write_paths_as_resource_records=['/fake/resource1.txt', '/fake/resource2.txt'],
+        )
+
+        mock_writer = AsyncMock()
+        mock_new_writer = AsyncMock()
+        current_file_sequence = 1
+        current_file_size = 800  # 800 bytes
+        added_byte_size = 300  # Adding 300 bytes, total would be 1100 (above limit)
+
+        # Mock create_new_writer_with_header
+        with patch('cdx_toolkit.filter_warc.warc_filter.create_new_writer_with_header') as mock_create:
+            mock_create.return_value = (mock_new_writer, 150, 'warcinfo-123')
+
+            # Mock write_resource_records
+            with patch.object(warc_filter, 'write_resource_records', return_value=75) as mock_write_resources:
+                # Call rotate_files
+                result_writer, result_sequence, result_size = await warc_filter.rotate_files(
+                    writer=mock_writer,
+                    current_file_sequence=current_file_sequence,
+                    current_file_size=current_file_size,
+                    added_byte_size=added_byte_size,
+                    writer_id=1,
+                    output_path_prefix='/fake/output',
+                    max_attempts=3,
+                    base_backoff_seconds=1.0,
+                    min_part_size=1024,
+                    writer_info={'writer_id': 1},
+                )
+
+                # Should have rotated
+                assert result_writer == mock_new_writer
+                assert result_sequence == current_file_sequence + 1
+                assert result_size == 150 + 75  # Header size + resource records size
+
+                # Old writer should be closed
+                mock_writer.close.assert_called_once()
+
+                # New writer should be created
+                mock_create.assert_called_once()
+
+                # Resource records should be written
+                mock_write_resources.assert_called_once_with(mock_new_writer, warcinfo_id='warcinfo-123')
+
+    asyncio.run(run_test())
+
+
+def test_rotate_files_no_max_file_size_set():
+    """Test rotate_files when max_file_size is not set (None)."""
+
+    async def run_test():
+        warc_filter = WARCFilter(
+            index_paths=['/fake/path'],
+            prefix_path='/fake/prefix',
+            writer_info={'writer_id': 1},
+            max_file_size=None,  # No limit
+        )
+
+        mock_writer = AsyncMock()
+        current_file_sequence = 1
+        current_file_size = 999999999  # Very large file
+        added_byte_size = 999999999  # Very large addition
+
+        # Call rotate_files
+        result_writer, result_sequence, result_size = await warc_filter.rotate_files(
+            writer=mock_writer,
+            current_file_sequence=current_file_sequence,
+            current_file_size=current_file_size,
+            added_byte_size=added_byte_size,
+            writer_id=1,
+            output_path_prefix='/fake/output',
+            max_attempts=3,
+            base_backoff_seconds=1.0,
+            min_part_size=1024,
+            writer_info={'writer_id': 1},
+        )
+
+        # Should not rotate regardless of size
+        assert result_writer == mock_writer
+        assert result_sequence == current_file_sequence
+        assert result_size == current_file_size
 
+        # Writer should not be closed
+        mock_writer.close.assert_not_called()
 
-@requires_aws_s3
-def test_cli_warc_by_cdx_over_http_to_s3_in_parallel_warc_filter(s3_tmpdir, caplog):
-    assert_cli_warc_by_cdx(
-        'https://data.commoncrawl.org',
-        base_prefix=s3_tmpdir,
-        caplog=caplog,
-        extra_args=[
-            '--parallel=3',
-        ],
+    asyncio.run(run_test())
+
+
+def test_rotate_files_edge_case_exact_limit():
+    """Test rotate_files when the total size exactly equals the limit."""
+
+    async def run_test():
+        warc_filter = WARCFilter(
+            index_paths=['/fake/path'],
+            prefix_path='/fake/prefix',
+            writer_info={'writer_id': 1},
+            max_file_size=1000,  # 1KB limit
+        )
+
+        mock_writer = AsyncMock()
+        current_file_sequence = 1
+        current_file_size = 700  # 700 bytes
+        added_byte_size = 300  # Adding 300 bytes, total would be exactly 1000
+
+        # Call rotate_files
+        result_writer, result_sequence, result_size = await warc_filter.rotate_files(
+            writer=mock_writer,
+            current_file_sequence=current_file_sequence,
+            current_file_size=current_file_size,
+            added_byte_size=added_byte_size,
+            writer_id=1,
+            output_path_prefix='/fake/output',
+            max_attempts=3,
+            base_backoff_seconds=1.0,
+            min_part_size=1024,
+            writer_info={'writer_id': 1},
+        )
+
+        # Should not rotate when exactly at limit (only rotate when > limit)
+        assert result_writer == mock_writer
+        assert result_sequence == current_file_sequence
+        assert result_size == current_file_size
+
+        # Writer should not be closed
+        mock_writer.close.assert_not_called()
+
+    asyncio.run(run_test())
+
+
+def test_rotate_files_edge_case_just_over_limit():
+    """Test rotate_files when the total size is just 1 byte over the limit."""
+
+    async def run_test():
+        warc_filter = WARCFilter(
+            index_paths=['/fake/path'],
+            prefix_path='/fake/prefix',
+            writer_info={'writer_id': 1},
+            max_file_size=1000,  # 1KB limit
+        )
+
+        mock_writer = AsyncMock()
+        mock_new_writer = AsyncMock()
+        current_file_sequence = 1
+        current_file_size = 700  # 700 bytes
+        added_byte_size = 301  # Adding 301 bytes, total would be 1001 (1 byte over)
+
+        # Mock create_new_writer_with_header
+        with patch('cdx_toolkit.filter_warc.warc_filter.create_new_writer_with_header') as mock_create:
+            mock_create.return_value = (mock_new_writer, 150, 'warcinfo-123')
+
+            # Call rotate_files
+            result_writer, result_sequence, result_size = await warc_filter.rotate_files(
+                writer=mock_writer,
+                current_file_sequence=current_file_sequence,
+                current_file_size=current_file_size,
+                added_byte_size=added_byte_size,
+                writer_id=1,
+                output_path_prefix='/fake/output',
+                max_attempts=3,
+                base_backoff_seconds=1.0,
+                min_part_size=1024,
+                writer_info={'writer_id': 1},
+            )
+
+            # Should rotate when just over limit
+            assert result_writer == mock_new_writer
+            assert result_sequence == current_file_sequence + 1
+            assert result_size == 150
+
+            # Old writer should be closed
+            mock_writer.close.assert_called_once()
+
+    asyncio.run(run_test())
+
+
+def test_rotate_files_kwargs_passed_through():
+    """Test that all kwargs are properly passed to create_new_writer_with_header."""
+
+    async def run_test():
+        warc_filter = WARCFilter(
+            index_paths=['/fake/path'], prefix_path='/fake/prefix', writer_info={'writer_id': 1}, max_file_size=1000
+        )
+
+        mock_writer = AsyncMock()
+        mock_new_writer = AsyncMock()
+
+        # Mock create_new_writer_with_header
+        with patch('cdx_toolkit.filter_warc.warc_filter.create_new_writer_with_header') as mock_create:
+            mock_create.return_value = (mock_new_writer, 150, 'warcinfo-123')
+
+            # Call rotate_files with various kwargs
+            await warc_filter.rotate_files(
+                writer=mock_writer,
+                current_file_sequence=1,
+                current_file_size=800,
+                added_byte_size=300,
+                writer_id=99,
+                output_path_prefix='/custom/output',
+                max_attempts=5,
+                base_backoff_seconds=2.5,
+                min_part_size=2048,
+                writer_info={'custom': 'info'},
+                warc_version='1.1',
+                gzip=True,
+                custom_param='custom_value',
+            )
+
+            # Verify all kwargs are passed through
+            mock_create.assert_called_once_with(
+                sequence=2,  # incremented from 1
+                writer_id=99,
+                output_path_prefix='/custom/output',
+                max_attempts=5,
+                base_backoff_seconds=2.5,
+                min_part_size=2048,
+                writer_info={'custom': 'info'},
+                warc_version='1.1',
+                gzip=True,
+                custom_param='custom_value',
+            )
+
+    asyncio.run(run_test())
+
+
+def test_rotate_files_logging(caplog):
+    """Test that rotation logs the appropriate message."""
+    import logging
+
+    async def run_test():
+        # Set log level to capture INFO messages
+        caplog.set_level(logging.INFO, logger='cdx_toolkit.filter_warc.warc_filter')
+
+        warc_filter = WARCFilter(
+            index_paths=['/fake/path'], prefix_path='/fake/prefix', writer_info={'writer_id': 1}, max_file_size=1000
+        )
+
+        mock_writer = AsyncMock()
+        mock_new_writer = AsyncMock()
+
+        # Mock create_new_writer_with_header
+        with patch('cdx_toolkit.filter_warc.warc_filter.create_new_writer_with_header') as mock_create:
+            mock_create.return_value = (mock_new_writer, 150, 'warcinfo-123')
+
+            # Call rotate_files to trigger rotation
+            await warc_filter.rotate_files(
+                writer=mock_writer,
+                current_file_sequence=5,
+                current_file_size=800,
+                added_byte_size=300,
+                writer_id=1,
+                output_path_prefix='/fake/output',
+                max_attempts=3,
+                base_backoff_seconds=1.0,
+                min_part_size=1024,
+                writer_info={'writer_id': 1},
+            )
+
+            # Check that the rotation log message was written
+            assert 'Rotated to new WARC file sequence 6 due to size limit' in caplog.text
+
+    asyncio.run(run_test())
+
+
+def test_log_writer(caplog):
+    """Test log writer."""
+
+    warc_filter = WARCFilter(
+        index_paths=['/fake/path'],
+        prefix_path='/fake/prefix',
+        writer_info={'writer_id': 1},
+        log_every_n=2,
     )
+    tracker = ThroughputTracker()
+    warc_filter.log_writer(1, 0, tracker)
+    warc_filter.log_writer(1, 1, tracker)
+    warc_filter.log_writer(1, 2, tracker)
+
+    assert caplog.text.count('WARC Writer 1') == 2
 
 
-@requires_aws_s3
-def test_cli_warc_by_cdx_over_s3_to_local_in_parallel_warc_filter(tmpdir, caplog):
-    assert_cli_warc_by_cdx(
-        's3://commoncrawl',
-        base_prefix=tmpdir,
-        caplog=caplog,
-        extra_args=[
-            '--parallel=3',
-        ],
+def test_log_reader(caplog):
+    """Test log reader."""
+
+    warc_filter = WARCFilter(
+        index_paths=['/fake/path'],
+        prefix_path='/fake/prefix',
+        writer_info={'writer_id': 1},
+        log_every_n=2,
     )
+    tracker = ThroughputTracker()
+    warc_filter.log_reader(1, 0, tracker)
+    warc_filter.log_reader(1, 1, tracker)
+    warc_filter.log_reader(1, 2, tracker)
+
+    assert caplog.text.count('WARC Reader 1') == 2
diff --git a/tests/filter_warc/test_warc_utils.py b/tests/filter_warc/test_warc_utils.py
index 23de5e1..9cda87b 100644
--- a/tests/filter_warc/test_warc_utils.py
+++ b/tests/filter_warc/test_warc_utils.py
@@ -5,27 +5,29 @@
 
 def test_get_resource_record_from_path():
     resource_path = TEST_DATA_PATH / 'filter_cdx/whitelist_10_urls.txt'
-    record = get_resource_record_from_path(resource_path)
+    record = get_resource_record_from_path(resource_path, warcinfo_id="abc123")
 
     assert record.content_type == 'text/plain'
 
     record_headers = dict(record.rec_headers.headers)
     assert record_headers['WARC-Target-URI'] == str(resource_path)
+    assert record_headers["WARC-Warcinfo-ID"] == "abc123"
 
 
 def test_get_resource_record_from_path_with_metadata():
     resource_path = TEST_DATA_PATH / 'warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.gz'
     metadata_path = TEST_DATA_PATH / 'warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.metadata.json'
 
-    record = get_resource_record_from_path(resource_path, metadata_path)
+    record = get_resource_record_from_path(resource_path, metadata_path=metadata_path, warcinfo_id="abc123")
 
     assert record.content_type == 'application/cdx'
 
     record_headers = dict(record.rec_headers.headers)
     assert record_headers['WARC-Target-URI'] == 'filter_cdx.cdx.gz'
+    assert record_headers["WARC-Warcinfo-ID"] == "abc123"
 
 
 def test_get_resource_record_from_path_with_invalid_metadata_path():
     with pytest.raises(ValueError):
         resource_path = TEST_DATA_PATH / 'filter_cdx/whitelist_10_urls.txt'
-        get_resource_record_from_path(resource_path, 'invalid_metadata.xy')
+        get_resource_record_from_path(resource_path, metadata_path='invalid_metadata.xy', warcinfo_id="abc123")

From a8e493ec202ad78e7fdfa691fcce2e279d5dff0b Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Thu, 9 Oct 2025 00:25:21 -0400
Subject: [PATCH 57/74] fix type hints

---
 cdx_toolkit/filter_cdx/path_utils.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/cdx_toolkit/filter_cdx/path_utils.py b/cdx_toolkit/filter_cdx/path_utils.py
index e77da72..08237b9 100644
--- a/cdx_toolkit/filter_cdx/path_utils.py
+++ b/cdx_toolkit/filter_cdx/path_utils.py
@@ -1,4 +1,5 @@
 import logging
+from typing import Optional
 
 import fsspec
 
@@ -10,7 +11,7 @@
 logger = logging.getLogger(__name__)
 
 
-def resolve_paths(input_base_path: str, input_glob: str | None, output_base_path: str):
+def resolve_paths(input_base_path: str, input_glob: Optional[str], output_base_path: str):
     """Resolve input paths from glob pattern and generate corresponding output paths."""
     # Use fsspec to handle local and remote file systems
     input_fs, input_fs_base_path = fsspec.url_to_fs(input_base_path)
@@ -32,7 +33,7 @@ def resolve_paths(input_base_path: str, input_glob: str | None, output_base_path
     input_file_paths = []
     for input_path in input_fs_file_paths:
         # Get relative path from input_base_path without last slash
-        rel_path = input_path[len(input_fs_base_path)+1:]
+        rel_path = input_path[len(input_fs_base_path) + 1 :]
 
         # Create corresponding full input and output path
         # Use forward slashes for URL paths (S3, HTTP, etc.) to ensure cross-platform compatibility

From f7011bde8d823ba484e32f9fd33ac616857f8a07 Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Thu, 9 Oct 2025 10:13:27 -0400
Subject: [PATCH 58/74] Adding settings via environment variables

---
 .github/workflows/ci.yaml | 17 ++++++++++
 cdx_toolkit/myrequests.py | 69 +++++++++++++++++++++++++--------------
 cdx_toolkit/settings.py   |  9 +++++
 3 files changed, 70 insertions(+), 25 deletions(-)
 create mode 100644 cdx_toolkit/settings.py

diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
index af07c13..4e134af 100644
--- a/.github/workflows/ci.yaml
+++ b/.github/workflows/ci.yaml
@@ -84,6 +84,23 @@ jobs:
           script: |
             core.exportVariable('CDXT_DISABLE_S3_TESTS', '1')
 
+      - name: Set environment variables for faster unit tests (requests are mocked)
+        uses: actions/github-script@v7
+        with:
+          script: |
+            core.exportVariable('CDXT_MAX_ERRORS', '2')
+            core.exportVariable('CDXT_WARNING_AFTER_N_ERRORS', '2')
+            core.exportVariable('CDXT_DEFAULT_MIN_RETRY_INTERVAL', '0.01')
+            core.exportVariable('CDXT_CC_INDEX_MIN_RETRY_INTERVAL', '0.01')
+            core.exportVariable('CDXT_CC_DATA_MIN_RETRY_INTERVAL', '0.01')
+            core.exportVariable('CDXT_IA_MIN_RETRY_INTERVAL', '0.01')
+
+      # - name: Run tests (only feature)
+      #   run: |
+      #     # make test_coverage
+      #     pytest -rA -s --doctest-modules --cov-report=xml --cov-append --cov cdx_toolkit tests/filter_warc tests/filter_cdx -v -v
+      #     coverage report
+
       - name: Run tests (only feature)
         run: |
           # make test_coverage
diff --git a/cdx_toolkit/myrequests.py b/cdx_toolkit/myrequests.py
index f34b856..6e8d684 100644
--- a/cdx_toolkit/myrequests.py
+++ b/cdx_toolkit/myrequests.py
@@ -1,9 +1,18 @@
+from typing import Optional
 import requests
 import logging
 import time
 from urllib.parse import urlparse
 
 from . import __version__
+from .settings import (
+    DEFAULT_MIN_RETRY_INTERVAL,
+    CC_DATA_MIN_RETRY_INTERVAL,
+    CC_INDEX_MIN_RETRY_INTERVAL,
+    IA_MIN_RETRY_INTERVAL,
+    MAX_ERRORS,
+    WARNING_AFTER_N_ERRORS,
+)
 
 LOGGER = logging.getLogger(__name__)
 
@@ -15,7 +24,7 @@
 
 
 def dns_fatal(hostname):
-    '''We have a dns error, should we fail immediately or not?'''
+    """We have a dns error, should we fail immediately or not?"""
     if hostname not in previously_seen_hostnames:
         return True
 
@@ -23,19 +32,19 @@ def dns_fatal(hostname):
 retry_info = {
     'default': {
         'next_fetch': 0,
-        'minimum_interval': 3.0,
+        'minimum_interval': DEFAULT_MIN_RETRY_INTERVAL,
     },
     'index.commoncrawl.org': {
         'next_fetch': 0,
-        'minimum_interval': 1.0,
+        'minimum_interval': CC_INDEX_MIN_RETRY_INTERVAL,
     },
     'data.commoncrawl.org': {
         'next_fetch': 0,
-        'minimum_interval': 0.55,
+        'minimum_interval': CC_DATA_MIN_RETRY_INTERVAL,
     },
     'web.archive.org': {
         'next_fetch': 0,
-        'minimum_interval': 6.0,
+        'minimum_interval': IA_MIN_RETRY_INTERVAL,
     },
 }
 
@@ -43,7 +52,7 @@ def dns_fatal(hostname):
 def get_retries(hostname):
     if hostname not in retry_info:
         retry_info[hostname] = retry_info['default'].copy()
-        LOGGER.debug('initializing retry info for new host '+hostname)
+        LOGGER.debug('initializing retry info for new host ' + hostname)
     entry = retry_info[hostname]
     if not entry['next_fetch']:
         entry['next_fetch'] = time.time()
@@ -55,17 +64,23 @@ def update_next_fetch(hostname, next_fetch):
 
 
 def myrequests_get(
-    url, 
-    params=None, 
-    headers=None, 
-    cdx=False, 
-    allow404=False, 
-    raise_error_after_n_errors: int = 100, 
-    raise_warning_after_n_errors: int = 10,
+    url,
+    params=None,
+    headers=None,
+    cdx=False,
+    allow404=False,
+    raise_error_after_n_errors: Optional[int] = None,
+    raise_warning_after_n_errors: Optional[int] = None,
     retry_max_sec: int = 60,
-    ):
+):
     t = time.time()
 
+    if raise_error_after_n_errors is None:
+        raise_error_after_n_errors = MAX_ERRORS
+
+    if raise_warning_after_n_errors is None:
+        raise_warning_after_n_errors = WARNING_AFTER_N_ERRORS
+
     hostname = urlparse(url).hostname
     next_fetch, minimum_interval = get_retries(hostname)
 
@@ -89,7 +104,7 @@ def myrequests_get(
     if headers is None:
         headers = {}
     if 'user-agent' not in headers:
-        headers['User-Agent'] = 'pypi_cdx_toolkit/'+__version__
+        headers['User-Agent'] = 'pypi_cdx_toolkit/' + __version__
 
     retry = True
     retry_sec = 2 * minimum_interval
@@ -98,8 +113,7 @@ def myrequests_get(
     while retry:
         try:
             LOGGER.debug('getting %s %r', url, params)
-            resp = requests.get(url, params=params, headers=headers,
-                                timeout=(30., 30.), allow_redirects=False)
+            resp = requests.get(url, params=params, headers=headers, timeout=(30.0, 30.0), allow_redirects=False)
             if cdx and resp.status_code in {400, 404}:
                 # 400: ia html error page -- probably page= is too big -- not an error
                 # 404: pywb {'error': 'No Captures found for: www.pbxxxxxxm.com/*'} -- not an error
@@ -120,7 +134,7 @@ def myrequests_get(
                 if resp.text:
                     LOGGER.log(level, 'response body is %s', resp.text)
                 time.sleep(retry_sec)
-                retry_sec = min(retry_sec*2, retry_max_sec)
+                retry_sec = min(retry_sec * 2, retry_max_sec)
                 continue
             if resp.status_code in {400, 404}:  # pragma: no cover
                 if resp.text:
@@ -128,26 +142,31 @@ def myrequests_get(
                 raise RuntimeError('invalid url of some sort, status={} {}'.format(resp.status_code, url))
             resp.raise_for_status()
             retry = False
-        except (requests.exceptions.ConnectionError, requests.exceptions.ChunkedEncodingError,
-                requests.exceptions.Timeout) as e:
+        except (
+            requests.exceptions.ConnectionError,
+            requests.exceptions.ChunkedEncodingError,
+            requests.exceptions.Timeout,
+        ) as e:
             connect_errors += 1
             string = '{} failures for url {} {!r}: {}'.format(connect_errors, url, params, str(e))
 
             # Check for DNS errors with different operating systems
-            if (('Name or service not known' in string)  # linux
+            if (
+                ('Name or service not known' in string)  # linux
                 or ('nodename nor servname provided, or not known' in string)  # macos
-                or ('getaddrinfo failed' in string)):  # windows
+                or ('getaddrinfo failed' in string)
+            ):  # windows
                 if dns_fatal(url):
-                    raise ValueError('invalid hostname in url '+url) from None
+                    raise ValueError('invalid hostname in url ' + url) from None
 
             if connect_errors > raise_error_after_n_errors:
                 LOGGER.error(string)
                 raise ValueError(string)
             if connect_errors > raise_warning_after_n_errors:
                 LOGGER.warning(string)
-            LOGGER.info('retrying after {:.2f}s for '.format(retry_max_sec)+str(e))
+            LOGGER.info('retrying after {:.2f}s for '.format(retry_max_sec) + str(e))
             time.sleep(retry_max_sec)  # notice the extra-long sleep
-            retry_sec = min(retry_sec*2, retry_max_sec)
+            retry_sec = min(retry_sec * 2, retry_max_sec)
         except requests.exceptions.RequestException as e:  # pragma: no cover
             LOGGER.warning('something unexpected happened, giving up after %s', str(e))
             raise
diff --git a/cdx_toolkit/settings.py b/cdx_toolkit/settings.py
new file mode 100644
index 0000000..505ada4
--- /dev/null
+++ b/cdx_toolkit/settings.py
@@ -0,0 +1,9 @@
+import os
+
+MAX_ERRORS = int(os.environ.get("CDXT_MAX_ERRORS", 100))
+WARNING_AFTER_N_ERRORS = int(os.environ.get("CDXT_WARNING_AFTER_N_ERRORS", 10))
+
+DEFAULT_MIN_RETRY_INTERVAL = float(os.environ.get("CDXT_DEFAULT_MIN_RETRY_INTERVAL", 3.0))
+CC_INDEX_MIN_RETRY_INTERVAL = float(os.environ.get("CDXT_CC_INDEX_MIN_RETRY_INTERVAL", 1.0))
+CC_DATA_MIN_RETRY_INTERVAL = float(os.environ.get("CDXT_CC_DATA_MIN_RETRY_INTERVAL", 0.55))
+IA_MIN_RETRY_INTERVAL = float(os.environ.get("CDXT_IA_MIN_RETRY_INTERVAL", 6.0))

From 1d8d3ffdb4df0116669dfd86d81967544486f3c6 Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Thu, 9 Oct 2025 10:21:14 -0400
Subject: [PATCH 59/74] Re-enabled all unit tests

---
 .github/workflows/ci.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
index 4e134af..a8f0d6c 100644
--- a/.github/workflows/ci.yaml
+++ b/.github/workflows/ci.yaml
@@ -104,7 +104,7 @@ jobs:
       - name: Run tests (only feature)
         run: |
           # make test_coverage
-          pytest -rA -s --doctest-modules --cov-report=xml --cov-append --cov cdx_toolkit tests/filter_warc tests/filter_cdx -v -v
+          pytest -rA -s --doctest-modules --cov-report=xml --cov-append --cov cdx_toolkit tests/ -v -v
           coverage report
 
       - name: Upload coverage to Codecov

From cc6b35e96bf7441f5117e40c6672c5ae2b782bc4 Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Thu, 9 Oct 2025 11:50:17 -0400
Subject: [PATCH 60/74] Adding MOCK_TIME env variable

---
 cdx_toolkit/commoncrawl.py | 12 ++++++++----
 cdx_toolkit/settings.py    |  2 ++
 tests/conftest.py          |  8 ++++++++
 3 files changed, 18 insertions(+), 4 deletions(-)

diff --git a/cdx_toolkit/commoncrawl.py b/cdx_toolkit/commoncrawl.py
index 6834217..7d3e035 100644
--- a/cdx_toolkit/commoncrawl.py
+++ b/cdx_toolkit/commoncrawl.py
@@ -11,6 +11,7 @@
 
 from .myrequests import myrequests_get
 from .timeutils import time_to_timestamp, timestamp_to_time, pad_timestamp, pad_timestamp_up, cc_index_to_time, cc_index_to_time_special
+from .settings import MOCK_TIME
 
 LOGGER = logging.getLogger(__name__)
 
@@ -70,7 +71,7 @@ def get_cc_endpoints(cc_mirror):
         url = cc_mirror.rstrip('/') + '/collinfo.json'
         r = myrequests_get(url)
         if r.status_code != 200:
-            raise RuntimeError('error {} getting list of cc indices from {}'.format(r.status_code, collinfo))  # pragma: no cover
+            raise RuntimeError('error {} getting list of cc indices from {}'.format(r.status_code, url))  # pragma: no cover
         set_collinfo_cache(cc_mirror, r.text)
         col = r.json()
 
@@ -119,9 +120,12 @@ def apply_cc_defaults(params, crawl_present=False, now=None):
                 LOGGER.info('to but no from_ts, setting from_ts=%s', params['from_ts'])
         else:
             if not now:
-                # now is passed in by tests. if not set, use actual now.
-                # XXX could be changed to mock
-                now = time.time()
+                # Check for test/override time first
+                if MOCK_TIME:
+                    now = float(MOCK_TIME)
+                else:
+                    # now is passed in by tests. if not set, use actual now.
+                    now = time.time()
             params['from_ts'] = time_to_timestamp(now - year)
             LOGGER.info('no from or to, setting default 1 year ago from_ts=%s', params['from_ts'])
     else:
diff --git a/cdx_toolkit/settings.py b/cdx_toolkit/settings.py
index 505ada4..42cdb83 100644
--- a/cdx_toolkit/settings.py
+++ b/cdx_toolkit/settings.py
@@ -7,3 +7,5 @@
 CC_INDEX_MIN_RETRY_INTERVAL = float(os.environ.get("CDXT_CC_INDEX_MIN_RETRY_INTERVAL", 1.0))
 CC_DATA_MIN_RETRY_INTERVAL = float(os.environ.get("CDXT_CC_DATA_MIN_RETRY_INTERVAL", 0.55))
 IA_MIN_RETRY_INTERVAL = float(os.environ.get("CDXT_IA_MIN_RETRY_INTERVAL", 6.0))
+
+MOCK_TIME = os.environ.get("CDXT_MOCK_TIME")
diff --git a/tests/conftest.py b/tests/conftest.py
index d7c6dc0..f15313e 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -31,6 +31,14 @@ def cleanup_cache():
         shutil.rmtree(cache_dir)
 
 
+@pytest.fixture(scope="session", autouse=True)
+def set_mock_time():
+    """Set CDXT_MOCK_TIME environment variable for consistent test results"""
+    # August 15, 2025 - ensures tests use CC-MAIN-2025-33 which exists in mock data
+    if 'CDXT_MOCK_TIME' not in os.environ:
+        os.environ['CDXT_MOCK_TIME'] = '1755259200'
+
+
 # Cache for AWS S3 access check to avoid repeated network calls
 _aws_s3_access_cache = None
 

From b0bb17fec5524771a707c225adfe319386e9742a Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Thu, 9 Oct 2025 16:19:16 -0400
Subject: [PATCH 61/74] Removed cdx fetcher from filter warc command

---
 .github/workflows/ci.yaml          |  3 +-
 cdx_toolkit/__init__.py            | 56 ++++++++++++++++++++----------
 cdx_toolkit/commoncrawl.py         |  7 ++--
 cdx_toolkit/filter_warc/args.py    |  1 +
 cdx_toolkit/filter_warc/command.py |  4 +--
 cdx_toolkit/settings.py            | 18 ++++++----
 tests/conftest.py                  | 55 ++++++++++++++++-------------
 tests/filter_warc/test_command.py  | 10 +-----
 8 files changed, 88 insertions(+), 66 deletions(-)

diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
index a8f0d6c..4b95f93 100644
--- a/.github/workflows/ci.yaml
+++ b/.github/workflows/ci.yaml
@@ -94,6 +94,7 @@ jobs:
             core.exportVariable('CDXT_CC_INDEX_MIN_RETRY_INTERVAL', '0.01')
             core.exportVariable('CDXT_CC_DATA_MIN_RETRY_INTERVAL', '0.01')
             core.exportVariable('CDXT_IA_MIN_RETRY_INTERVAL', '0.01')
+            core.exportVariable('LOGLEVEL', 'DEBUG')
 
       # - name: Run tests (only feature)
       #   run: |
@@ -101,7 +102,7 @@ jobs:
       #     pytest -rA -s --doctest-modules --cov-report=xml --cov-append --cov cdx_toolkit tests/filter_warc tests/filter_cdx -v -v
       #     coverage report
 
-      - name: Run tests (only feature)
+      - name: Run tests
         run: |
           # make test_coverage
           pytest -rA -s --doctest-modules --cov-report=xml --cov-append --cov cdx_toolkit tests/ -v -v
diff --git a/cdx_toolkit/__init__.py b/cdx_toolkit/__init__.py
index c27845a..086d235 100644
--- a/cdx_toolkit/__init__.py
+++ b/cdx_toolkit/__init__.py
@@ -2,7 +2,6 @@
 import json
 from pkg_resources import get_distribution, DistributionNotFound
 from collections.abc import MutableMapping
-import sys
 import warnings
 
 __version__ = 'installed-from-git'
@@ -32,7 +31,7 @@ def showNumPages(r):
     elif isinstance(j, int):  # ia always returns text, parsed as a json int
         pages = j
     else:
-        raise ValueError('surprised by showNumPages value of '+str(j))
+        raise ValueError('surprised by showNumPages value of ' + str(j))
     return pages
 
 
@@ -75,18 +74,19 @@ def cdx_to_captures(resp, wb=None, warc_download_prefix=None):
             lines = json.loads(text)
             fields = lines.pop(0)
         except (json.decoder.JSONDecodeError, KeyError, IndexError):  # pragma: no cover
-            raise ValueError('cannot decode response, first bytes are '+repr(text[:50]))
+            raise ValueError('cannot decode response, first bytes are ' + repr(text[:50]))
 
         ret = munge_fields(fields, lines)
         return [CaptureObject(r, wb=wb, warc_download_prefix=warc_download_prefix) for r in ret]
 
-    raise ValueError('cannot decode response, first bytes are '+repr(text[:50]))  # pragma: no cover
+    raise ValueError('cannot decode response, first bytes are ' + repr(text[:50]))  # pragma: no cover
 
 
 class CaptureObject(MutableMapping):
-    '''
+    """
     Represents a single capture of a webpage, plus less-visible info about how to fetch the content.
-    '''
+    """
+
     def __init__(self, data, wb=None, warc_download_prefix=None):
         self.data = data
         self.wb = wb
@@ -124,9 +124,9 @@ def content(self):
 
     @property
     def text(self):
-        '''
+        """
         Eventually this function will do something with the character set, but not yet.
-        '''
+        """
         return self.content.decode('utf-8', errors='replace')
 
     # the remaining code treats self.data like a dict
@@ -171,8 +171,9 @@ def get_more(self):
             if self.page == 0 and len(self.index_list) > 0 and self.endpoint < len(self.index_list):
                 LOGGER.info('get_more: fetching cdx from %s', self.index_list[self.endpoint])
 
-            status, objs = self.cdxfetcher.get_for_iter(self.endpoint, self.page,
-                                                        params=self.params, index_list=self.index_list)
+            status, objs = self.cdxfetcher.get_for_iter(
+                self.endpoint, self.page, params=self.params, index_list=self.index_list
+            )
             if status == 'last endpoint':
                 LOGGER.debug('get_more: I have reached the end')
                 return  # caller will raise StopIteration
@@ -202,7 +203,16 @@ def __next__(self):
 
 
 class CDXFetcher:
-    def __init__(self, source='cc', crawl=None, wb=None, warc_download_prefix=None, cc_mirror=None, cc_sort='mixed', loglevel=None):
+    def __init__(
+        self,
+        source='cc',
+        crawl=None,
+        wb=None,
+        warc_download_prefix=None,
+        cc_mirror=None,
+        cc_sort='mixed',
+        loglevel=None,
+    ):
         self.source = source
         self.crawl = crawl
         self.cc_sort = cc_sort
@@ -231,7 +241,14 @@ def __init__(self, source='cc', crawl=None, wb=None, warc_download_prefix=None,
             LOGGER.setLevel(level=loglevel)
 
     def customize_index_list(self, params):
-        if self.source == 'cc' and (self.crawl or 'crawl' in params or 'from' in params or 'from_ts' in params or 'to' in params or 'closest' in params):
+        if self.source == 'cc' and (
+            self.crawl
+            or 'crawl' in params
+            or 'from' in params
+            or 'from_ts' in params
+            or 'to' in params
+            or 'closest' in params
+        ):
             LOGGER.info('making a custom cc index list')
             if self.crawl and 'crawl' not in params:
                 params['crawl'] = self.crawl
@@ -264,7 +281,9 @@ def get(self, url, **kwargs):
         ret = []
         for endpoint in index_list:
             resp = myrequests_get(endpoint, params=params, cdx=True)
-            objs = cdx_to_captures(resp, wb=self.wb, warc_download_prefix=self.warc_download_prefix)  # turns 400 and 404 into []
+            objs = cdx_to_captures(
+                resp, wb=self.wb, warc_download_prefix=self.warc_download_prefix
+            )  # turns 400 and 404 into []
             ret.extend(objs)
             if 'limit' in params:
                 params['limit'] -= len(objs)
@@ -292,15 +311,14 @@ def iter(self, url, **kwargs):
 
     def items(self, url, **kwargs):  # pragma: no cover
         warnings.warn(
-            'cdx.items() has been renamed to cdx.iter() and will be removed in cdx_toolkit 1.0',
-            FutureWarning
+            'cdx.items() has been renamed to cdx.iter() and will be removed in cdx_toolkit 1.0', FutureWarning
         )
         return self.iter(url, **kwargs)
 
     def get_for_iter(self, endpoint, page, params={}, index_list=None):
-        '''
+        """
         Specalized get for the iterator
-        '''
+        """
         if endpoint >= len(index_list):
             return 'last endpoint', []
         if params.get('limit', -1) == 0:
@@ -320,12 +338,12 @@ def get_for_iter(self, endpoint, page, params={}, index_list=None):
         return 'ok', ret
 
     def get_size_estimate(self, url, as_pages=False, **kwargs):
-        '''
+        """
         Get the number of pages that match url
 
         useful additional args: matchType='host' pageSize=1
         or, url can end with * or start with *. to set the matchType
-        '''
+        """
         if 'details' in kwargs:
             details = True
             del kwargs['details']
diff --git a/cdx_toolkit/commoncrawl.py b/cdx_toolkit/commoncrawl.py
index 7d3e035..7d75690 100644
--- a/cdx_toolkit/commoncrawl.py
+++ b/cdx_toolkit/commoncrawl.py
@@ -11,7 +11,7 @@
 
 from .myrequests import myrequests_get
 from .timeutils import time_to_timestamp, timestamp_to_time, pad_timestamp, pad_timestamp_up, cc_index_to_time, cc_index_to_time_special
-from .settings import MOCK_TIME
+from .settings import get_mock_time
 
 LOGGER = logging.getLogger(__name__)
 
@@ -121,8 +121,9 @@ def apply_cc_defaults(params, crawl_present=False, now=None):
         else:
             if not now:
                 # Check for test/override time first
-                if MOCK_TIME:
-                    now = float(MOCK_TIME)
+                mock_time = get_mock_time()
+                if mock_time:
+                    now = mock_time
                 else:
                     # now is passed in by tests. if not set, use actual now.
                     now = time.time()
diff --git a/cdx_toolkit/filter_warc/args.py b/cdx_toolkit/filter_warc/args.py
index 72db4f9..bf86f7d 100644
--- a/cdx_toolkit/filter_warc/args.py
+++ b/cdx_toolkit/filter_warc/args.py
@@ -46,6 +46,7 @@ def add_warcer_by_cdx_args(parser: argparse.ArgumentParser):
         '--warc-download-prefix',
         action='store',
         help='prefix for downloading content, automatically set for CC',
+        default='https://data.commoncrawl.org',
     )
     parser.add_argument(
         '--write-paths-as-resource-records',  # --write-index-as-record
diff --git a/cdx_toolkit/filter_warc/command.py b/cdx_toolkit/filter_warc/command.py
index bd08c0e..b85724b 100644
--- a/cdx_toolkit/filter_warc/command.py
+++ b/cdx_toolkit/filter_warc/command.py
@@ -25,8 +25,6 @@ def run_warcer_by_cdx(args, cmdline):
     """
     logger.info('Filtering WARC files based on CDX')
 
-    cdx, kwargs = setup(args)
-
     # Start timing
     start_time = time.time()
 
@@ -86,7 +84,7 @@ def run_warcer_by_cdx(args, cmdline):
         write_paths_as_resource_records_metadata=write_paths_as_resource_records_metadata,
         record_limit=limit,
         log_every_n=log_every_n,
-        warc_download_prefix=cdx.warc_download_prefix,
+        warc_download_prefix=args.warc_download_prefix,
         n_parallel=n_parallel,
         max_file_size=args.size,
         # writer_kwargs=writer_kwargs,
diff --git a/cdx_toolkit/settings.py b/cdx_toolkit/settings.py
index 42cdb83..f223f65 100644
--- a/cdx_toolkit/settings.py
+++ b/cdx_toolkit/settings.py
@@ -1,11 +1,15 @@
 import os
 
-MAX_ERRORS = int(os.environ.get("CDXT_MAX_ERRORS", 100))
-WARNING_AFTER_N_ERRORS = int(os.environ.get("CDXT_WARNING_AFTER_N_ERRORS", 10))
+MAX_ERRORS = int(os.environ.get('CDXT_MAX_ERRORS', 100))
+WARNING_AFTER_N_ERRORS = int(os.environ.get('CDXT_WARNING_AFTER_N_ERRORS', 10))
 
-DEFAULT_MIN_RETRY_INTERVAL = float(os.environ.get("CDXT_DEFAULT_MIN_RETRY_INTERVAL", 3.0))
-CC_INDEX_MIN_RETRY_INTERVAL = float(os.environ.get("CDXT_CC_INDEX_MIN_RETRY_INTERVAL", 1.0))
-CC_DATA_MIN_RETRY_INTERVAL = float(os.environ.get("CDXT_CC_DATA_MIN_RETRY_INTERVAL", 0.55))
-IA_MIN_RETRY_INTERVAL = float(os.environ.get("CDXT_IA_MIN_RETRY_INTERVAL", 6.0))
+DEFAULT_MIN_RETRY_INTERVAL = float(os.environ.get('CDXT_DEFAULT_MIN_RETRY_INTERVAL', 3.0))
+CC_INDEX_MIN_RETRY_INTERVAL = float(os.environ.get('CDXT_CC_INDEX_MIN_RETRY_INTERVAL', 1.0))
+CC_DATA_MIN_RETRY_INTERVAL = float(os.environ.get('CDXT_CC_DATA_MIN_RETRY_INTERVAL', 0.55))
+IA_MIN_RETRY_INTERVAL = float(os.environ.get('CDXT_IA_MIN_RETRY_INTERVAL', 6.0))
 
-MOCK_TIME = os.environ.get("CDXT_MOCK_TIME")
+
+def get_mock_time():
+    """Get the mock time from environment variable, evaluated dynamically"""
+    mock_time = os.environ.get('CDXT_MOCK_TIME')
+    return float(mock_time) if mock_time else None
diff --git a/tests/conftest.py b/tests/conftest.py
index f15313e..fe39d25 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -23,15 +23,15 @@
 TEST_DATA_BASE_PATH = Path(__file__).parent / 'data'
 
 
-@pytest.fixture(scope="session", autouse=True)
+@pytest.fixture(scope='session', autouse=True)
 def cleanup_cache():
-    """Delete cache directory before test session starts"""
+    """Delete cache directory before each test to ensure clean state"""
     cache_dir = os.path.expanduser('~/.cache/cdx_toolkit/')
     if os.path.exists(cache_dir):
         shutil.rmtree(cache_dir)
 
 
-@pytest.fixture(scope="session", autouse=True)
+@pytest.fixture(scope='session', autouse=True)
 def set_mock_time():
     """Set CDXT_MOCK_TIME environment variable for consistent test results"""
     # August 15, 2025 - ensures tests use CC-MAIN-2025-33 which exists in mock data
@@ -51,12 +51,7 @@ def check_aws_s3_access():
         return _aws_s3_access_cache
 
     try:
-        config = Config(
-            retries={
-                'max_attempts': 1,
-                'mode': 'standard'
-            }
-        )
+        config = Config(retries={'max_attempts': 1, 'mode': 'standard'})
         s3_client = boto3.client('s3', config=config)
 
         # Try list objects on test bucket
@@ -205,28 +200,39 @@ def mock_response_from_jsonl(mock_data_name, mock_data_dir: Optional[str] = None
                 )
 
 
-def conditional_mock_responses(func):
+def conditional_mock_responses(func=None, *, auto_mock_data: bool = True):
     """Conditionally applies @responses.activate and auto-loads mock data based on DISABLE_MOCK_RESPONSES env var.
 
     The mock data is automatically loaded from JSONL file from the tests/data directory
     and dependinng on the test module and test function.
+
+    Args:
+        auto_mock_data: If True, auto-loads test-specific mock data. If False, only loads CC endpoints.
     """
 
-    # If the flag DISABLE_MOCK_RESPONSES is not detected, response mocking remains enabled
-    if not os.environ.get('DISABLE_MOCK_RESPONSES'):
-        # Add responses.activate
-        func = add_mock_responses(func)
+    def decorator(f):
+        # If the flag DISABLE_MOCK_RESPONSES is not detected, response mocking remains enabled
+        if not os.environ.get('DISABLE_MOCK_RESPONSES'):
+            # Add responses.activate
+            f = add_mock_responses(f, auto_mock_data=auto_mock_data)
+
+        if os.environ.get('SAVE_MOCK_RESPONSES'):
+            # Mock data is saved by capturing output from requests.get
+            @functools.wraps(f)
+            def wrapper(*args, **kwargs):
+                with patch('requests.get', side_effect=_custom_behavior_with_original(requests.get)):
+                    return f(*args, **kwargs)
 
-    if os.environ.get('SAVE_MOCK_RESPONSES'):
-        # Mock data is saved by capturing output from requests.get
-        @functools.wraps(func)
-        def wrapper(*args, **kwargs):
-            with patch('requests.get', side_effect=_custom_behavior_with_original(requests.get)):
-                return func(*args, **kwargs)
+            return wrapper
 
-        return wrapper
+        return f
 
-    return func
+    if func is None:
+        # Called with arguments: @conditional_mock_responses(auto_mock_data=False)
+        return decorator
+    else:
+        # Called without arguments: @conditional_mock_responses
+        return decorator(func)
 
 
 def save_response_as_mock_data(test_info: str, request_url: str, request_params: Dict, resp, output_base_dir: str):
@@ -293,14 +299,15 @@ def custom_behavior(*args, **kwargs):
     return custom_behavior
 
 
-def add_mock_responses(func):
+def add_mock_responses(func, auto_mock_data: bool = True):
     @functools.wraps(func)
     def wrapper(*args, **kwargs):
         # Load mock data for index calls (same for many test functions)
         mock_response_from_jsonl('test_get_cc_endpoints', 'test_cc')
 
         # Auto-load mock data based on function name
-        mock_response_from_jsonl(func.__name__, func.__module__.split('.')[-1])
+        if auto_mock_data:
+            mock_response_from_jsonl(func.__name__, func.__module__.split('.')[-1])
         return func(*args, **kwargs)
 
     return responses.activate(wrapper)
diff --git a/tests/filter_warc/test_command.py b/tests/filter_warc/test_command.py
index c3c5ed9..6ce5fee 100644
--- a/tests/filter_warc/test_command.py
+++ b/tests/filter_warc/test_command.py
@@ -33,7 +33,6 @@ def assert_cli_warc_by_cdx(
     main(
         args=[
             '-v',
-            '--cc',
             '--limit=10',
             'warc_by_cdx',
             str(index_path),
@@ -174,8 +173,6 @@ def test_warc_by_cdx_no_index_files_found_exits(tmpdir, caplog):
         main(
             args=[
                 '-v',
-                '--cc',
-                '--cc-mirror=https://index.commoncrawl.org/',
                 'warc_by_cdx',
                 f'{str(tmpdir)}',
                 f'--prefix={str(tmpdir)}/TEST',
@@ -194,8 +191,6 @@ def test_warc_by_cdx_subprefix_and_metadata(tmpdir):
     main(
         args=[
             '-v',
-            '--cc',
-            '--cc-mirror=https://index.commoncrawl.org/',
             '--limit=1',
             'warc_by_cdx',
             f'{str(index_path)}',
@@ -230,8 +225,6 @@ def test_warc_by_cdx_without_creator_operator(tmpdir):
     main(
         args=[
             '-v',
-            '--cc',
-            '--cc-mirror=https://index.commoncrawl.org/',
             '--limit=1',
             'warc_by_cdx',
             f'{str(index_path)}',
@@ -262,7 +255,6 @@ def test_resource_records_paths_mismatch():
         main(
             args=[
                 '-v',
-                '--cc',
                 'warc_by_cdx',
                 'foo/bar',
                 '--write-paths-as-resource-records',
@@ -278,5 +270,5 @@ def test_resource_records_paths_mismatch():
 def test_metadata_paths_without_resource_records_paths():
     # Test if error of missing resource records paths is raised.
     with pytest.raises(ValueError) as exc_info:
-        main(args=['-v', '--cc', 'warc_by_cdx', 'foo/bar', '--write-paths-as-resource-records-metadata', 'metadata2'])
+        main(args=['-v', 'warc_by_cdx', 'foo/bar', '--write-paths-as-resource-records-metadata', 'metadata2'])
     assert exc_info.match('Metadata paths are set but')

From 6020dffdad44019712e0b3eaf58237519ffe2ddf Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Thu, 9 Oct 2025 16:23:21 -0400
Subject: [PATCH 62/74] Adding float tol

---
 tests/filter_warc/test_s3_utils.py | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/tests/filter_warc/test_s3_utils.py b/tests/filter_warc/test_s3_utils.py
index fe4c53a..54c4188 100644
--- a/tests/filter_warc/test_s3_utils.py
+++ b/tests/filter_warc/test_s3_utils.py
@@ -15,23 +15,24 @@
 def test_backoff():
     """Test _backoff function with exponential backoff and jitter."""
     base_backoff = 1.0
+    tol_float = 0.001  # tolerance for float errors
 
     # Test attempt 1: should be between 0.8 and 1.2 seconds (with jitter)
     result1 = _backoff(1, base_backoff)
-    assert 0.8 <= result1 <= 1.2
+    assert 0.8 <= result1 <= 1.2 + tol_float
 
     # Test attempt 2: should be between 1.6 and 2.41 seconds (2^1 * base * jitter)
     result2 = _backoff(2, base_backoff)
-    assert 1.6 <= result2 <= 2.41
+    assert 1.6 <= result2 <= 2.4 + tol_float
 
     # Test attempt 3: should be between 3.2 and 4.8 seconds (2^2 * base * jitter)
     result3 = _backoff(3, base_backoff)
-    assert 3.2 <= result3 <= 4.8
+    assert 3.2 <= result3 <= 4.8 + tol_float
 
     # Test with different base backoff
     base_backoff_small = 0.1
     result_small = _backoff(1, base_backoff_small)
-    assert 0.08 <= result_small <= 0.12
+    assert 0.08 <= result_small <= 0.12 + tol_float
 
     # Test minimum backoff (should never be less than 0.05)
     very_small_base = 0.001

From 77967965f4205775b8d31fa0c5da45f30dc389d3 Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Mon, 13 Oct 2025 16:09:18 +0200
Subject: [PATCH 63/74] WIP athena integration

---
 cdx_toolkit/filter_warc/args.py        |  17 +-
 cdx_toolkit/filter_warc/command.py     |  32 ++--
 cdx_toolkit/filter_warc/warc_filter.py | 216 ++++++++++++++++++-------
 tests/filter_warc/test_command.py      |  12 +-
 tests/filter_warc/test_warc_filter.py  |  22 +--
 5 files changed, 210 insertions(+), 89 deletions(-)

diff --git a/cdx_toolkit/filter_warc/args.py b/cdx_toolkit/filter_warc/args.py
index bf86f7d..020cc93 100644
--- a/cdx_toolkit/filter_warc/args.py
+++ b/cdx_toolkit/filter_warc/args.py
@@ -6,7 +6,12 @@
 
 
 def add_warcer_by_cdx_args(parser: argparse.ArgumentParser):
-    parser.add_argument('cdx_path', help='Path to CDX index file (local or remote, e.g. S3)')
+    parser.add_argument(
+        '--cdx-path',
+        type=str,
+        default=None,
+        help='Path to CDX index file (local or remote, e.g. S3). Required if target source is set to `cdx`.',
+    )
     parser.add_argument(
         '--cdx-glob',
         type=str,
@@ -50,12 +55,12 @@ def add_warcer_by_cdx_args(parser: argparse.ArgumentParser):
     )
     parser.add_argument(
         '--write-paths-as-resource-records',  # --write-index-as-record
-        nargs="*",
+        nargs='*',
         help='Paths to multiple files. File content is written to as a resource record to each the WARC file',
     )
     parser.add_argument(
         '--write-paths-as-resource-records-metadata',
-        nargs="*",
+        nargs='*',
         help='Paths to multiple metadata files (JSON) for resource records from `--write-paths-as-resource-records`',
     )
     parser.add_argument(
@@ -82,4 +87,10 @@ def add_warcer_by_cdx_args(parser: argparse.ArgumentParser):
         default=1000,
         help='Every N extracted record a log message is emitted (0 = no record logs)',
     )
+    parser.add_argument(
+        '--target-source',
+        action='store',
+        default='cdx',
+        help='Source from that the filter targets are loaded (available options: `cdx`, `athena`; defaults to `cdx`)',
+    )
     return parser
diff --git a/cdx_toolkit/filter_warc/command.py b/cdx_toolkit/filter_warc/command.py
index b85724b..c8439b4 100644
--- a/cdx_toolkit/filter_warc/command.py
+++ b/cdx_toolkit/filter_warc/command.py
@@ -33,10 +33,10 @@ def run_warcer_by_cdx(args, cmdline):
 
     if write_paths_as_resource_records and write_paths_as_resource_records_metadata:
         if len(write_paths_as_resource_records) != len(write_paths_as_resource_records_metadata):
-            raise ValueError("Number of paths to resource records must be equal to metadata paths.")
+            raise ValueError('Number of paths to resource records must be equal to metadata paths.')
 
     if not write_paths_as_resource_records and write_paths_as_resource_records_metadata:
-        raise ValueError("Metadata paths are set but resource records paths are missing.")
+        raise ValueError('Metadata paths are set but resource records paths are missing.')
 
     if args.is_part_of:
         ispartof = args.is_part_of
@@ -48,7 +48,9 @@ def run_warcer_by_cdx(args, cmdline):
     info = {
         'software': 'pypi_cdx_toolkit/' + get_version(),
         'isPartOf': ispartof,
-        'description': args.description if args.description else 'warc extraction based on CDX generated with: ' + cmdline,
+        'description': args.description
+        if args.description
+        else 'warc extraction based on CDX generated with: ' + cmdline,
         'format': 'WARC file version 1.0',
     }
     if args.creator:
@@ -69,14 +71,24 @@ def run_warcer_by_cdx(args, cmdline):
 
     # make sure the base dir exists
     prefix_fs.makedirs(prefix_fs._parent(prefix_fs_path), exist_ok=True)
-
-    cdx_paths = get_cdx_paths(
-        args.cdx_path,
-        args.cdx_glob,
-    )
+    
+    # target source handling
+    cdx_paths = None
+    athena_where_clause = None
+
+    if args.target_source == 'cdx':
+        cdx_paths = get_cdx_paths(
+            args.cdx_path,
+            args.cdx_glob,
+        )
+    elif args.target_source == "athena":
+        raise NotImplementedError
+    else:
+        raise ValueError(f'Invalid target source specified: {args.target_source} (available: cdx, athena)')
 
     warc_filter = WARCFilter(
-        index_paths=cdx_paths,
+        cdx_paths=cdx_paths,
+        athena_where_clause=athena_where_clause,
         prefix_path=prefix_path,
         writer_info=info,
         writer_subprefix=args.subprefix,
@@ -97,4 +109,4 @@ def run_warcer_by_cdx(args, cmdline):
     end_time = time.time()
     execution_time = end_time - start_time
 
-    logger.info(f'Script execution time: {execution_time:.3f} seconds')
\ No newline at end of file
+    logger.info(f'Script execution time: {execution_time:.3f} seconds')
diff --git a/cdx_toolkit/filter_warc/warc_filter.py b/cdx_toolkit/filter_warc/warc_filter.py
index 775de40..779fbab 100644
--- a/cdx_toolkit/filter_warc/warc_filter.py
+++ b/cdx_toolkit/filter_warc/warc_filter.py
@@ -29,7 +29,7 @@ class WARCFilter:
     The WARC filter uses a three stage listner-producer-consumer pattern.
 
     Filter targets:
-    - CDX index files from local or remote file system.
+    - CDX index files from local or remote file system, containing paths to WARC files and positions of target records.
 
     WARC reader:
     - HTTP range reads
@@ -42,9 +42,10 @@ class WARCFilter:
 
     def __init__(
         self,
-        index_paths: List[str],
         prefix_path: str,
         writer_info: Dict,
+        cdx_paths: Optional[List[str]] = None,
+        athena_where_clause: Optional[str] = None,
         writer_subprefix: Optional[str] = None,
         write_paths_as_resource_records: Optional[List[str]] = None,
         write_paths_as_resource_records_metadata: Optional[List[str]] = None,
@@ -69,7 +70,8 @@ def __init__(
         """Initialize the WARC filter.
 
         Args:
-            index_paths: List of paths to CDX index files.
+            cdx_paths: List of paths to CDX index files.
+            athena_where_clause: Where-clause for Athena query.
             prefix_path: Output path prefix for filtered WARC files.
             writer_info: Dictionary containing writer metadata.
             writer_subprefix: Optional subprefix for writer output paths.
@@ -93,7 +95,8 @@ def __init__(
             min_part_size: Minimum part byte size for multipart uploads (default: 5 MiB).
             max_file_size: Maximum byte size for individual WARC files (default: 1 GiB).
         """
-        self.index_paths = index_paths
+        self.cdx_paths = cdx_paths
+        self.athena_where_clause = athena_where_clause
         self.prefix_path = prefix_path
         self.writer_info = writer_info
         self.writer_subprefix = writer_subprefix
@@ -119,7 +122,7 @@ def __init__(
             else max(int(self.num_readers / self.fetcher_to_consumer_ratio), 1)
         )
 
-        self.gzip = self.index_paths[0].endswith('.gz') if self.index_paths else False
+        self.gzip = self.cdx_paths[0].endswith('.gz') if self.cdx_paths else False
         self.warc_version = warc_version
         self.content_type = content_type
         self.min_part_size = min_part_size
@@ -145,13 +148,31 @@ def needs_s3(self) -> bool:
             bool: True if S3 client is needed for any operation.
         """
         return (
-            (self.index_paths is not None and len(self.index_paths) > 0 and is_s3_url(self.index_paths[0]))  # stage 1
+            (self.cdx_paths is not None and len(self.cdx_paths) > 0 and is_s3_url(self.cdx_paths[0]))  # stage 1
             or is_s3_url(self.warc_download_prefix)  # stage 3
             or is_s3_url(self.prefix_path)  # stage 3
         )
 
-    def get_s3_client_context(self):
-        """Return s3 client context if needed.
+    def get_boto3_base_config(self) -> Dict:
+        """Get boto3 base configuration for S3 client.
+
+        Returns:
+            Dict: Boto3 base configuration object with retry and timeout settings.
+        """
+        # Calculate max connections based on parallelism
+        # Each reader + writer needs connections, plus some overhead for retries
+        # max_pool_connections = max(50, (self.num_readers + self.num_writers) * 2)
+
+        return dict(
+            region_name=self.aws_region_name,
+            retries={
+                'max_attempts': max(2, self.max_attempts),
+                'mode': 'adaptive',  # Better than 'standard' for variable workloads
+            },
+        )
+
+    async def get_s3_clients(self) -> Optional[Dict]:
+        """Return s3 clients for job/read/write if needed.
 
         Returns:
             Optional[aioboto3.Session.client]: S3 client context manager if S3 is needed, None otherwise.
@@ -168,7 +189,34 @@ def get_s3_client_context(self):
 
             session = aioboto3.Session()
 
-            return session.client('s3', config=self.get_boto3_config())
+            # Lightweight config for CDX index reads
+            job_config = Config(
+                max_pool_connections=5,
+                read_timeout=60,
+                **self.get_boto3_base_config(),
+            )
+
+            # High-throughput config for range reads
+            read_config = Config(
+                max_pool_connections=self.num_readers * 3,
+                read_timeout=300,
+                tcp_keepalive=True,
+                **self.get_boto3_base_config(),
+            )
+
+            # Optimized config for multipart uploads
+            write_config = Config(
+                max_pool_connections=self.num_writers * 4,
+                read_timeout=120,
+                connect_timeout=10,
+                **self.get_boto3_base_config(),
+            )
+
+            return {
+                'job': session.client('s3', config=job_config),
+                'read': session.client('s3', config=read_config),
+                'write': session.client('s3', config=write_config),
+            }
         else:
             return None
 
@@ -181,25 +229,43 @@ async def filter_async(self) -> int:
         range_jobs_queue: asyncio.Queue = asyncio.Queue(maxsize=self.range_jobs_queue_size)
         warc_records_queue: asyncio.Queue = asyncio.Queue(maxsize=self.warc_records_queue_size)
 
-        s3_client_context = self.get_s3_client_context()
-        if s3_client_context is not None:
-            async with s3_client_context as s3_client:
-                return await self._run_filter_pipeline(range_jobs_queue, warc_records_queue, s3_client)
+        if self.needs_s3():
+
+            clients = await self.get_s3_clients()
+
+            async with clients['job'] as job_s3_client, \
+                       clients['read'] as read_s3_client, \
+                       clients['write'] as write_s3_client:
+
+                return await self._run_filter_pipeline(
+                    range_jobs_queue=range_jobs_queue,
+                    warc_records_queue=warc_records_queue,
+                    job_s3_client=job_s3_client,
+                    read_s3_client=read_s3_client,
+                    write_s3_client=write_s3_client,
+                )
         else:
-            return await self._run_filter_pipeline(range_jobs_queue, warc_records_queue)
+            return await self._run_filter_pipeline(
+                range_jobs_queue=range_jobs_queue,
+                warc_records_queue=warc_records_queue,
+            )
 
     async def _run_filter_pipeline(
         self,
         range_jobs_queue: asyncio.Queue,
         warc_records_queue: asyncio.Queue,
-        s3_client=None,
+        job_s3_client=None,
+        read_s3_client=None,
+        write_s3_client=None,
     ) -> int:
         """Run the actual filter pipeline with or without S3 client.
 
         Args:
             range_jobs_queue: Queue for range jobs from CDX index.
             warc_records_queue: Queue for WARC record payloads.
-            s3_client: Optional S3 client for reading/writing to S3.
+            index_s3_client: Optional S3 client for jobs generation from S3.
+            read_s3_client: Optional S3 client for reads from S3.
+            write_s3_client: Optional S3 client for writes S3.
 
         Returns:
             int: Number of records written.
@@ -208,9 +274,9 @@ async def _run_filter_pipeline(
         logger.info('Starting lister, %d fetchers, %d consumers', self.num_readers, self.num_writers)
 
         job_generators = asyncio.create_task(
-            self.generate_range_jobs(
+            self.generate_range_jobs_from_cdx(
                 range_jobs_queue,
-                s3_client=s3_client,
+                s3_client=job_s3_client,
             )
         )
 
@@ -221,7 +287,7 @@ async def _run_filter_pipeline(
                     reader_id=i,
                     range_jobs_queue=range_jobs_queue,
                     warc_records_queue=warc_records_queue,
-                    s3_client=s3_client,
+                    s3_client=read_s3_client,
                 )
             )
             for i in range(self.num_readers)
@@ -233,16 +299,24 @@ async def _run_filter_pipeline(
                 self.write_warc_records(
                     writer_id=i,
                     warc_records_queue=warc_records_queue,
-                    s3_client=s3_client,
+                    s3_client=write_s3_client,
                 )
             )
             for i in range(self.num_writers)
         ]
 
+        # Start writer coordination task
+        writer_coordinator = asyncio.create_task(
+            self._coordinate_writer_shutdown(warc_readers, warc_records_queue)
+        )
+
         await job_generators
-        logger.info('Range jobs submitted, waiting for readers to finish')
+        logger.info('Range jobs submitted, monitoring readers and writers')
 
+        # Wait for all tasks to complete
         readers_results = await asyncio.gather(*warc_readers)
+        writers_results = await asyncio.gather(*warc_writers)
+        await writer_coordinator
 
         readers_records = sum([result['stats']['total_records'] for result in readers_results])
         readers_mb_per_sec = statistics.mean([result['stats']['mb_per_sec'] for result in readers_results])
@@ -251,12 +325,6 @@ async def _run_filter_pipeline(
         logger.info(f'All WARC readers completed: {readers_records} records')
         logger.info(f'Reader throughput: {readers_mb_per_sec:.2f} MB/s; {readers_records_per_sec:.2f} rec/s')
 
-        # Send stop signals to consumers
-        for _ in range(self.num_writers):
-            await warc_records_queue.put(_STOP)
-
-        writers_results = await asyncio.gather(*warc_writers)
-
         writers_records = sum([result['stats']['total_records'] for result in writers_results])
         writers_mb_per_sec = statistics.mean([result['stats']['mb_per_sec'] for result in writers_results])
         writers_records_per_sec = statistics.mean([result['stats']['records_per_sec'] for result in writers_results])
@@ -266,7 +334,60 @@ async def _run_filter_pipeline(
 
         return writers_records
 
-    async def generate_range_jobs(
+    async def _coordinate_writer_shutdown(
+        self,
+        warc_readers: List[asyncio.Task],
+        warc_records_queue: asyncio.Queue
+    ):
+        """Coordinate efficient shutdown of writers as readers complete.
+
+        This prevents writers from waiting unnecessarily when all readers are done
+        and the records queue is being drained.
+        """
+        completed_readers = 0
+
+        # Monitor reader completion
+        while completed_readers < len(warc_readers):
+            # Wait for any reader to complete
+            done, pending = await asyncio.wait(
+                warc_readers,
+                return_when=asyncio.FIRST_COMPLETED,
+                timeout=1.0  # Check periodically
+            )
+
+            if done:
+                completed_readers = len(warc_readers) - len(pending)
+                logger.debug(f'Readers completed: {completed_readers}/{len(warc_readers)}')
+
+        # All readers completed - signal writers to stop
+        logger.info('All readers completed, signaling writers to stop')
+
+        # Send stop signals to all writers
+        for _ in range(self.num_writers):
+            await warc_records_queue.put(_STOP)
+
+    async def generate_range_jobs_from_single_cdx(
+        self,
+        cdx_path: str,
+        range_jobs_queue: asyncio.Queue,
+        count: int = 0,
+    ) -> int:
+        """Read a CDX file and generate range jobs based on URLs and offsets."""
+        for warc_url, offset, length in iter_cdx_index_from_path(
+            cdx_path, warc_download_prefix=self.warc_download_prefix
+        ):
+            # Convert the CDX record back to a RangeJob
+            job = RangeJob(url=warc_url, offset=offset, length=length, records_count=1)
+            await range_jobs_queue.put(job)
+            count += 1
+
+            if self.record_limit > 0 and count >= self.record_limit:
+                logger.warning('Index limit reached at %i', count)
+                break
+
+        return count
+
+    async def generate_range_jobs_from_cdx(
         self,
         range_jobs_queue: asyncio.Queue,
         s3_client=None,
@@ -281,21 +402,16 @@ async def generate_range_jobs(
         logger.info('Range index limit: %i', self.record_limit)
         count = 0
 
-        # Iterate over index files
-        for index_path in self.index_paths:
+        # Iterate over index files 
+        # TODO this could be done in parallel
+        for index_path in self.cdx_paths:
             # Fetch range queries from index
             try:
-                for warc_url, offset, length in iter_cdx_index_from_path(
-                    index_path, warc_download_prefix=self.warc_download_prefix
-                ):
-                    # Convert the CDX record back to a RangeJob
-                    job = RangeJob(url=warc_url, offset=offset, length=length, records_count=1)
-                    await range_jobs_queue.put(job)
-                    count += 1
-
-                    if self.record_limit > 0 and count >= self.record_limit:
-                        logger.warning('Index limit reached at %i', count)
-                        break
+                count += await self.generate_range_jobs_from_single_cdx(
+                    cdx_path=index_path,
+                    range_jobs_queue=range_jobs_queue,
+                    count=count,
+                )
 
             except Exception as e:
                 logger.error('Failed to read CDX index from %s: %s', index_path, e)
@@ -548,21 +664,3 @@ async def rotate_files(
                 current_file_size += await self.write_resource_records(writer, warcinfo_id=warcinfo_id)
 
         return writer, current_file_sequence, current_file_size
-
-    def get_boto3_config(self):
-        """Get boto3 configuration for S3 client.
-
-        Returns:
-            Config: Boto3 configuration object with retry and timeout settings.
-        """
-        # Calculate max connections based on parallelism
-        # Each reader + writer needs connections, plus some overhead for retries
-        max_pool_connections = max(50, (self.num_readers + self.num_writers) * 2)
-
-        return Config(
-            region_name=self.aws_region_name,
-            retries={'max_attempts': max(2, self.max_attempts), 'mode': 'standard'},
-            connect_timeout=10,
-            read_timeout=120,
-            max_pool_connections=max_pool_connections,
-        )
diff --git a/tests/filter_warc/test_command.py b/tests/filter_warc/test_command.py
index 6ce5fee..e752203 100644
--- a/tests/filter_warc/test_command.py
+++ b/tests/filter_warc/test_command.py
@@ -35,7 +35,7 @@ def assert_cli_warc_by_cdx(
             '-v',
             '--limit=10',
             'warc_by_cdx',
-            str(index_path),
+            f'--cdx-path={str(index_path)}',
             '--write-paths-as-resource-records',
             str(resource_record_path),
             f'--prefix={base_prefix}/TEST_warc_by_index',
@@ -174,7 +174,7 @@ def test_warc_by_cdx_no_index_files_found_exits(tmpdir, caplog):
             args=[
                 '-v',
                 'warc_by_cdx',
-                f'{str(tmpdir)}',
+                f'--cdx-path={str(tmpdir)}',
                 f'--prefix={str(tmpdir)}/TEST',
                 '--cdx-glob=/nonexistent-pattern-*.gz',
             ]
@@ -193,7 +193,7 @@ def test_warc_by_cdx_subprefix_and_metadata(tmpdir):
             '-v',
             '--limit=1',
             'warc_by_cdx',
-            f'{str(index_path)}',
+            f'--cdx-path={str(index_path)}',
             f'--prefix={str(tmpdir)}/TEST',
             '--subprefix=SUB',
             '--creator=test_creator',
@@ -227,7 +227,7 @@ def test_warc_by_cdx_without_creator_operator(tmpdir):
             '-v',
             '--limit=1',
             'warc_by_cdx',
-            f'{str(index_path)}',
+            f'--cdx-path={str(index_path)}',
             f'--prefix={str(tmpdir)}/TEST_NO_META',
         ]
     )
@@ -256,7 +256,7 @@ def test_resource_records_paths_mismatch():
             args=[
                 '-v',
                 'warc_by_cdx',
-                'foo/bar',
+                '--cdx-path=foo/bar',
                 '--write-paths-as-resource-records',
                 'resource1',
                 'resource2',
@@ -270,5 +270,5 @@ def test_resource_records_paths_mismatch():
 def test_metadata_paths_without_resource_records_paths():
     # Test if error of missing resource records paths is raised.
     with pytest.raises(ValueError) as exc_info:
-        main(args=['-v', 'warc_by_cdx', 'foo/bar', '--write-paths-as-resource-records-metadata', 'metadata2'])
+        main(args=['-v', 'warc_by_cdx', '--cdx-path=foo/bar', '--write-paths-as-resource-records-metadata', 'metadata2'])
     assert exc_info.match('Metadata paths are set but')
diff --git a/tests/filter_warc/test_warc_filter.py b/tests/filter_warc/test_warc_filter.py
index 0c03063..937776e 100644
--- a/tests/filter_warc/test_warc_filter.py
+++ b/tests/filter_warc/test_warc_filter.py
@@ -16,7 +16,7 @@ def test_filter_keyboard_interrupt_handling(caplog):
     # Set log level to capture WARNING messages
     caplog.set_level(logging.WARNING, logger='cdx_toolkit.filter_warc.warc_filter')
 
-    warc_filter = WARCFilter(index_paths=['/fake/path'], prefix_path='/fake/prefix', writer_info={'writer_id': 1})
+    warc_filter = WARCFilter(cdx_paths=['/fake/path'], prefix_path='/fake/prefix', writer_info={'writer_id': 1})
 
     # Mock filter_async to raise KeyboardInterrupt
     with patch.object(warc_filter, 'filter_async', side_effect=KeyboardInterrupt('Simulated user interrupt')):
@@ -35,7 +35,7 @@ def test_rotate_files_no_rotation_needed():
 
     async def run_test():
         warc_filter = WARCFilter(
-            index_paths=['/fake/path'],
+            cdx_paths=['/fake/path'],
             prefix_path='/fake/prefix',
             writer_info={'writer_id': 1},
             max_file_size=1000,  # 1KB limit
@@ -76,7 +76,7 @@ def test_rotate_files_rotation_needed_without_resource_records():
 
     async def run_test():
         warc_filter = WARCFilter(
-            index_paths=['/fake/path'],
+            cdx_paths=['/fake/path'],
             prefix_path='/fake/prefix',
             writer_info={'writer_id': 1},
             max_file_size=1000,  # 1KB limit
@@ -134,7 +134,7 @@ def test_rotate_files_rotation_needed_with_resource_records():
 
     async def run_test():
         warc_filter = WARCFilter(
-            index_paths=['/fake/path'],
+            cdx_paths=['/fake/path'],
             prefix_path='/fake/prefix',
             writer_info={'writer_id': 1},
             max_file_size=1000,  # 1KB limit
@@ -189,7 +189,7 @@ def test_rotate_files_no_max_file_size_set():
 
     async def run_test():
         warc_filter = WARCFilter(
-            index_paths=['/fake/path'],
+            cdx_paths=['/fake/path'],
             prefix_path='/fake/prefix',
             writer_info={'writer_id': 1},
             max_file_size=None,  # No limit
@@ -230,7 +230,7 @@ def test_rotate_files_edge_case_exact_limit():
 
     async def run_test():
         warc_filter = WARCFilter(
-            index_paths=['/fake/path'],
+            cdx_paths=['/fake/path'],
             prefix_path='/fake/prefix',
             writer_info={'writer_id': 1},
             max_file_size=1000,  # 1KB limit
@@ -271,7 +271,7 @@ def test_rotate_files_edge_case_just_over_limit():
 
     async def run_test():
         warc_filter = WARCFilter(
-            index_paths=['/fake/path'],
+            cdx_paths=['/fake/path'],
             prefix_path='/fake/prefix',
             writer_info={'writer_id': 1},
             max_file_size=1000,  # 1KB limit
@@ -317,7 +317,7 @@ def test_rotate_files_kwargs_passed_through():
 
     async def run_test():
         warc_filter = WARCFilter(
-            index_paths=['/fake/path'], prefix_path='/fake/prefix', writer_info={'writer_id': 1}, max_file_size=1000
+            cdx_paths=['/fake/path'], prefix_path='/fake/prefix', writer_info={'writer_id': 1}, max_file_size=1000
         )
 
         mock_writer = AsyncMock()
@@ -370,7 +370,7 @@ async def run_test():
         caplog.set_level(logging.INFO, logger='cdx_toolkit.filter_warc.warc_filter')
 
         warc_filter = WARCFilter(
-            index_paths=['/fake/path'], prefix_path='/fake/prefix', writer_info={'writer_id': 1}, max_file_size=1000
+            cdx_paths=['/fake/path'], prefix_path='/fake/prefix', writer_info={'writer_id': 1}, max_file_size=1000
         )
 
         mock_writer = AsyncMock()
@@ -404,7 +404,7 @@ def test_log_writer(caplog):
     """Test log writer."""
 
     warc_filter = WARCFilter(
-        index_paths=['/fake/path'],
+        cdx_paths=['/fake/path'],
         prefix_path='/fake/prefix',
         writer_info={'writer_id': 1},
         log_every_n=2,
@@ -421,7 +421,7 @@ def test_log_reader(caplog):
     """Test log reader."""
 
     warc_filter = WARCFilter(
-        index_paths=['/fake/path'],
+        cdx_paths=['/fake/path'],
         prefix_path='/fake/prefix',
         writer_info={'writer_id': 1},
         log_every_n=2,

From fac56ce678916229755da55c00a50ff382a2abe0 Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Wed, 15 Oct 2025 12:27:45 +0200
Subject: [PATCH 64/74] Adding Athena PoC

---
 cdx_toolkit/filter_warc/args.py               |  21 ++-
 .../filter_warc/athena_job_generator.py       | 137 +++++++++++++++++
 cdx_toolkit/filter_warc/command.py            |  15 +-
 cdx_toolkit/filter_warc/warc_filter.py        | 138 ++++++++++++------
 cdx_toolkit/filter_warc/warc_utils.py         |  40 +++--
 tests/conftest.py                             |  29 +++-
 .../filter_warc/test_athena_job_generator.py  |  69 +++++++++
 tests/filter_warc/test_command.py             |  74 +++++++++-
 8 files changed, 451 insertions(+), 72 deletions(-)
 create mode 100644 cdx_toolkit/filter_warc/athena_job_generator.py
 create mode 100644 tests/filter_warc/test_athena_job_generator.py

diff --git a/cdx_toolkit/filter_warc/args.py b/cdx_toolkit/filter_warc/args.py
index 020cc93..c1d87f5 100644
--- a/cdx_toolkit/filter_warc/args.py
+++ b/cdx_toolkit/filter_warc/args.py
@@ -18,7 +18,26 @@ def add_warcer_by_cdx_args(parser: argparse.ArgumentParser):
         default=None,
         help='a glob pattern for read from multiple CDX indices',
     )
-    parser.add_argument('--prefix', default='TEST', help='prefix for the warc filename')
+    parser.add_argument(
+        '--athena-hostnames',
+        type=str,
+        nargs="+",
+        default=None,
+        help='Hostnames to filter for via Athena (whitelist). Required if target source is set to `athena`.',
+    )
+    parser.add_argument(
+        '--athena-database',
+        type=str,
+        default=None,
+        help='Athena database. Required if target source is set to `athena`.',
+    )
+    parser.add_argument(
+        '--athena-s3-output',
+        type=str,
+        default=None,
+        help='Athena S3 output location. Required if target source is set to `athena`.',
+    )
+    parser.add_argument('--prefix', default='TEST', help='prefix for the output warc filename')
     parser.add_argument(
         '--subprefix',
         type=str,
diff --git a/cdx_toolkit/filter_warc/athena_job_generator.py b/cdx_toolkit/filter_warc/athena_job_generator.py
new file mode 100644
index 0000000..0d0e99a
--- /dev/null
+++ b/cdx_toolkit/filter_warc/athena_job_generator.py
@@ -0,0 +1,137 @@
+import asyncio
+import logging
+import time
+from typing import Any, Iterable
+
+from cdx_toolkit.filter_warc.data_classes import RangeJob
+
+
+logger = logging.getLogger(__name__)
+
+
+async def get_range_jobs_from_athena(
+    client,
+    database: str,
+    s3_output_location: str,
+    job_queue: asyncio.Queue,
+    queue_stop_object: Any,
+    url_host_names: list[str],
+    warc_download_prefix: str,
+    num_fetchers: int,
+    limit: int = 0,
+    max_wait_time: int = 300,
+):
+    """Generate range job based on an Athena query.
+
+    CommonCrawl provides an index via AWS Athena that we can use to
+    find the file names, offsets, and byte lengths for WARC filtering.
+
+    See https://commoncrawl.org/blog/index-to-warc-files-and-urls-in-columnar-format
+
+    This function queries Athena (AWS access required), puts a RangeJob
+    (WARC files and offets) for each result and pushed them to the
+    asyncio queue."""
+
+    logger.info('Range index limit: %i', limit)
+    count = 0
+
+    # Build query
+    tlds = set([url.split('.')[-1] for url in url_host_names])  # unique TLDs
+    query_tlds = ' OR '.join([f" url_host_tld = '{tld}'" for tld in tlds])
+    query_hostnames = ' OR '.join([f" url_host_name = '{host_name}'" for host_name in url_host_names])
+
+    # TODO there should be more filteres (dates/crawls/...)
+
+    query_limit = f'LIMIT {limit}' if limit > 0 else ''
+
+    query = f"""
+    SELECT
+        warc_filename, warc_record_offset, warc_record_length
+    FROM ccindex
+    WHERE subset = 'warc'
+        AND ({query_tlds}) -- help the query optimizer
+        AND ({query_hostnames})
+    {query_limit}"""
+
+    logger.info('Executing Athena query...')
+
+    # Start query execution
+    response = client.start_query_execution(
+        QueryString=query,
+        QueryExecutionContext={'Database': database},
+        ResultConfiguration={'OutputLocation': s3_output_location},
+    )
+
+    query_execution_id = response['QueryExecutionId']
+
+    logger.info(f'Query execution started. ID: {query_execution_id}')
+    status = _wait_for_query_completion(client, query_execution_id, max_wait_time)
+
+    if status == 'SUCCEEDED':
+        for range_job in _get_query_results(client, query_execution_id, warc_download_prefix):
+            await job_queue.put(range_job)
+            count += 1
+    else:
+        raise Exception(f'Query failed with status: {status}')
+
+    # Signal fetchers to stop
+    for _ in range(num_fetchers):
+        await job_queue.put(queue_stop_object)
+
+    logger.info('Athena query enqueued %d jobs', count)
+
+
+def _wait_for_query_completion(client, query_execution_id: str, max_wait_time: int) -> str:
+    """Wait for query to complete and return final status"""
+    start_time = time.time()
+
+    while time.time() - start_time < max_wait_time:
+        response = client.get_query_execution(QueryExecutionId=query_execution_id)
+
+        status = response['QueryExecution']['Status']['State']
+        logger.info(f'Query status: {status}')
+
+        if status in ['SUCCEEDED', 'FAILED', 'CANCELLED']:
+            if status == 'FAILED':
+                error_reason = response['QueryExecution']['Status'].get('StateChangeReason', 'Unknown error')
+                logger.info(f'Query failed: {error_reason}')
+            return status
+
+        time.sleep(2)
+
+    raise TimeoutError(f'Query did not complete within {max_wait_time} seconds')
+
+
+def _get_query_results(client, query_execution_id: str, warc_download_prefix: str) -> Iterable[RangeJob]:
+    """Retrieve query results and convert to pandas DataFrame"""
+    # Get query results
+    paginator = client.get_paginator('get_query_results')
+    page_iterator = paginator.paginate(QueryExecutionId=query_execution_id)
+    column_names = None
+
+    for page in page_iterator:
+        rows = page['ResultSet']['Rows']
+
+        # Get column names from first page
+        if column_names is None and rows:
+            column_names = [col['VarCharValue'] for col in rows[0]['Data']]
+            rows = rows[1:]  # Skip header row
+
+        # Process data rows
+        for row in rows:
+            row_data = []
+            for cell in row['Data']:
+                value = cell.get('VarCharValue', None)
+                row_data.append(value)
+
+            row = dict(zip(column_names, row_data))
+
+            warc_url = warc_download_prefix + "/" + row['warc_filename']
+
+            yield RangeJob(url=warc_url, offset=int(row['warc_record_offset']), length=int(row['warc_record_length']))
+
+
+def get_databases(client) -> list:
+    """Get list of available databases"""
+    response = client.list_databases(CatalogName='AwsDataCatalog')
+    return [db['Name'] for db in response['DatabaseList']]
diff --git a/cdx_toolkit/filter_warc/command.py b/cdx_toolkit/filter_warc/command.py
index c8439b4..614673f 100644
--- a/cdx_toolkit/filter_warc/command.py
+++ b/cdx_toolkit/filter_warc/command.py
@@ -1,6 +1,6 @@
 from cdx_toolkit.filter_warc.cdx_utils import get_cdx_paths
 from cdx_toolkit.filter_warc.warc_filter import WARCFilter
-from cdx_toolkit.utils import get_version, setup
+from cdx_toolkit.utils import get_version
 
 
 import fsspec
@@ -71,24 +71,25 @@ def run_warcer_by_cdx(args, cmdline):
 
     # make sure the base dir exists
     prefix_fs.makedirs(prefix_fs._parent(prefix_fs_path), exist_ok=True)
-    
-    # target source handling
-    cdx_paths = None
-    athena_where_clause = None
 
+    # target source handling
     if args.target_source == 'cdx':
         cdx_paths = get_cdx_paths(
             args.cdx_path,
             args.cdx_glob,
         )
     elif args.target_source == "athena":
-        raise NotImplementedError
+        # no extra handling required
+        cdx_paths = None
     else:
         raise ValueError(f'Invalid target source specified: {args.target_source} (available: cdx, athena)')
 
     warc_filter = WARCFilter(
+        target_source=args.target_source,
         cdx_paths=cdx_paths,
-        athena_where_clause=athena_where_clause,
+        athena_database=args.athena_database,
+        athena_s3_output_location=args.athena_s3_output,
+        athena_hostnames=args.athena_hostnames,
         prefix_path=prefix_path,
         writer_info=info,
         writer_subprefix=args.subprefix,
diff --git a/cdx_toolkit/filter_warc/warc_filter.py b/cdx_toolkit/filter_warc/warc_filter.py
index 779fbab..5f062bf 100644
--- a/cdx_toolkit/filter_warc/warc_filter.py
+++ b/cdx_toolkit/filter_warc/warc_filter.py
@@ -2,11 +2,12 @@
 import logging
 import statistics
 import sys
-from typing import List, Optional, Dict
+from typing import List, Literal, Optional, Dict
 
 
 from botocore.config import Config
 
+from cdx_toolkit.filter_warc.athena_job_generator import get_range_jobs_from_athena
 from cdx_toolkit.filter_warc.s3_utils import (
     is_s3_url,
 )
@@ -22,6 +23,8 @@
 
 logger = logging.getLogger(__name__)
 
+TargetSourceType = Literal['cdx', 'athena']
+
 
 class WARCFilter:
     """Filter or extract specific records from WARC files based on CDX indexes.
@@ -44,8 +47,11 @@ def __init__(
         self,
         prefix_path: str,
         writer_info: Dict,
+        target_source: TargetSourceType = 'cdx',
         cdx_paths: Optional[List[str]] = None,
-        athena_where_clause: Optional[str] = None,
+        athena_database: Optional[str] = None,
+        athena_hostnames: Optional[List[str]] = None,
+        athena_s3_output_location: Optional[str] = None,
         writer_subprefix: Optional[str] = None,
         write_paths_as_resource_records: Optional[List[str]] = None,
         write_paths_as_resource_records_metadata: Optional[List[str]] = None,
@@ -70,8 +76,11 @@ def __init__(
         """Initialize the WARC filter.
 
         Args:
+            target_source: Source of filter targets (Athena query or CDX files).
             cdx_paths: List of paths to CDX index files.
-            athena_where_clause: Where-clause for Athena query.
+            athena_database: Database for Athena query.
+            athena_hostnames: Hostnames for Athena query.
+            athena_s3_output_location: S3 output location for Athena query.            
             prefix_path: Output path prefix for filtered WARC files.
             writer_info: Dictionary containing writer metadata.
             writer_subprefix: Optional subprefix for writer output paths.
@@ -96,7 +105,10 @@ def __init__(
             max_file_size: Maximum byte size for individual WARC files (default: 1 GiB).
         """
         self.cdx_paths = cdx_paths
-        self.athena_where_clause = athena_where_clause
+        self.target_source: TargetSourceType = target_source
+        self.athena_database = athena_database
+        self.athena_s3_output_location = athena_s3_output_location
+        self.athena_hostnames = athena_hostnames
         self.prefix_path = prefix_path
         self.writer_info = writer_info
         self.writer_subprefix = writer_subprefix
@@ -122,7 +134,9 @@ def __init__(
             else max(int(self.num_readers / self.fetcher_to_consumer_ratio), 1)
         )
 
-        self.gzip = self.cdx_paths[0].endswith('.gz') if self.cdx_paths else False
+        # self.gzip = self.cdx_paths[0].endswith('.gz') if self.cdx_paths else False
+        self.gzip = True
+
         self.warc_version = warc_version
         self.content_type = content_type
         self.min_part_size = min_part_size
@@ -141,20 +155,21 @@ def filter(self) -> int:
 
         return -1
 
-    def needs_s3(self) -> bool:
-        """Returns true if S3 is needed at any stage.
+    def needs_aws(self) -> bool:
+        """Returns true if AWS (S3/Athena) is needed at any stage.
 
         Returns:
-            bool: True if S3 client is needed for any operation.
+            bool: True if AWS client is needed for any operation.
         """
         return (
-            (self.cdx_paths is not None and len(self.cdx_paths) > 0 and is_s3_url(self.cdx_paths[0]))  # stage 1
+            self.target_source == 'athena'  # stage 1
+            or (self.cdx_paths is not None and len(self.cdx_paths) > 0 and is_s3_url(self.cdx_paths[0]))  # stage 1
             or is_s3_url(self.warc_download_prefix)  # stage 3
             or is_s3_url(self.prefix_path)  # stage 3
         )
 
     def get_boto3_base_config(self) -> Dict:
-        """Get boto3 base configuration for S3 client.
+        """Get boto3 base configuration for AWS client.
 
         Returns:
             Dict: Boto3 base configuration object with retry and timeout settings.
@@ -171,21 +186,22 @@ def get_boto3_base_config(self) -> Dict:
             },
         )
 
-    async def get_s3_clients(self) -> Optional[Dict]:
-        """Return s3 clients for job/read/write if needed.
+    async def get_aws_clients(self) -> Optional[Dict]:
+        """Return S3/Athena clients for job/read/write if needed.
 
         Returns:
-            Optional[aioboto3.Session.client]: S3 client context manager if S3 is needed, None otherwise.
+            Optional[aioboto3.Session.client]: S3/Athena client context manager if S3/Athena is needed, None otherwise.
 
         Raises:
             SystemExit: If S3 is needed but Python version is < 3.9.
         """
-        if self.needs_s3():
+        if self.needs_aws():
             if sys.version_info.major < 3 or (sys.version_info.major >= 3 and sys.version_info.minor < 9):
                 logger.error('Reading and writing to S3 requires Python version >= 3.9')
                 sys.exit(1)
 
             import aioboto3
+            import boto3
 
             session = aioboto3.Session()
 
@@ -196,6 +212,12 @@ async def get_s3_clients(self) -> Optional[Dict]:
                 **self.get_boto3_base_config(),
             )
 
+            if self.target_source == 'athena':
+                # Athena does not need an async client
+                job_client = boto3.client('athena', config=job_config)
+            else:
+                job_client = session.client('s3', config=job_config)
+
             # High-throughput config for range reads
             read_config = Config(
                 max_pool_connections=self.num_readers * 3,
@@ -213,7 +235,7 @@ async def get_s3_clients(self) -> Optional[Dict]:
             )
 
             return {
-                'job': session.client('s3', config=job_config),
+                'job': job_client,
                 'read': session.client('s3', config=read_config),
                 'write': session.client('s3', config=write_config),
             }
@@ -229,21 +251,31 @@ async def filter_async(self) -> int:
         range_jobs_queue: asyncio.Queue = asyncio.Queue(maxsize=self.range_jobs_queue_size)
         warc_records_queue: asyncio.Queue = asyncio.Queue(maxsize=self.warc_records_queue_size)
 
-        if self.needs_s3():
-
-            clients = await self.get_s3_clients()
-
-            async with clients['job'] as job_s3_client, \
-                       clients['read'] as read_s3_client, \
-                       clients['write'] as write_s3_client:
-
-                return await self._run_filter_pipeline(
-                    range_jobs_queue=range_jobs_queue,
-                    warc_records_queue=warc_records_queue,
-                    job_s3_client=job_s3_client,
-                    read_s3_client=read_s3_client,
-                    write_s3_client=write_s3_client,
-                )
+        if self.needs_aws():
+            clients = await self.get_aws_clients()
+
+            # Handle mixed async/sync clients - Athena client is sync, S3 clients are async
+            if self.target_source == 'athena':
+                job_aws_client = clients['job']  # Sync client, no context manager needed
+                async with clients['read'] as read_aws_client, clients['write'] as write_aws_client:
+                    return await self._run_filter_pipeline(
+                        range_jobs_queue=range_jobs_queue,
+                        warc_records_queue=warc_records_queue,
+                        job_aws_client=job_aws_client,
+                        read_s3_client=read_aws_client,
+                        write_s3_client=write_aws_client,
+                    )
+            else:
+                async with clients['job'] as job_aws_client, clients['read'] as read_aws_client, clients[
+                    'write'
+                ] as write_aws_client:
+                    return await self._run_filter_pipeline(
+                        range_jobs_queue=range_jobs_queue,
+                        warc_records_queue=warc_records_queue,
+                        job_aws_client=job_aws_client,
+                        read_s3_client=read_aws_client,
+                        write_s3_client=write_aws_client,
+                    )
         else:
             return await self._run_filter_pipeline(
                 range_jobs_queue=range_jobs_queue,
@@ -254,7 +286,7 @@ async def _run_filter_pipeline(
         self,
         range_jobs_queue: asyncio.Queue,
         warc_records_queue: asyncio.Queue,
-        job_s3_client=None,
+        job_aws_client=None,
         read_s3_client=None,
         write_s3_client=None,
     ) -> int:
@@ -263,7 +295,7 @@ async def _run_filter_pipeline(
         Args:
             range_jobs_queue: Queue for range jobs from CDX index.
             warc_records_queue: Queue for WARC record payloads.
-            index_s3_client: Optional S3 client for jobs generation from S3.
+            job_aws_client: Optional AWS (S3/Athena) client for jobs generation.
             read_s3_client: Optional S3 client for reads from S3.
             write_s3_client: Optional S3 client for writes S3.
 
@@ -273,12 +305,30 @@ async def _run_filter_pipeline(
         # Fetch file paths and ranges (offset, length) from index files
         logger.info('Starting lister, %d fetchers, %d consumers', self.num_readers, self.num_writers)
 
-        job_generators = asyncio.create_task(
-            self.generate_range_jobs_from_cdx(
-                range_jobs_queue,
-                s3_client=job_s3_client,
+        # Generate range jobs from different target sources
+        if self.target_source == 'cdx':
+            job_generators = asyncio.create_task(
+                self.generate_range_jobs_from_cdx(
+                    range_jobs_queue,
+                    s3_client=job_aws_client,
+                )
             )
-        )
+        elif self.target_source == 'athena':
+            job_generators = asyncio.create_task(
+                get_range_jobs_from_athena(
+                    client=job_aws_client,
+                    database=self.athena_database,
+                    s3_output_location=self.athena_s3_output_location,
+                    job_queue=range_jobs_queue,
+                    queue_stop_object=_STOP,
+                    url_host_names=self.athena_hostnames,
+                    warc_download_prefix=self.warc_download_prefix,
+                    num_fetchers=self.num_readers,
+                    limit=self.record_limit,
+                )
+            )
+        else:
+            raise ValueError(f'Invalid target source: {self.target_source}')
 
         # Read WARC records based on file paths and ranges
         warc_readers = [
@@ -306,9 +356,7 @@ async def _run_filter_pipeline(
         ]
 
         # Start writer coordination task
-        writer_coordinator = asyncio.create_task(
-            self._coordinate_writer_shutdown(warc_readers, warc_records_queue)
-        )
+        writer_coordinator = asyncio.create_task(self._coordinate_writer_shutdown(warc_readers, warc_records_queue))
 
         await job_generators
         logger.info('Range jobs submitted, monitoring readers and writers')
@@ -334,11 +382,7 @@ async def _run_filter_pipeline(
 
         return writers_records
 
-    async def _coordinate_writer_shutdown(
-        self,
-        warc_readers: List[asyncio.Task],
-        warc_records_queue: asyncio.Queue
-    ):
+    async def _coordinate_writer_shutdown(self, warc_readers: List[asyncio.Task], warc_records_queue: asyncio.Queue):
         """Coordinate efficient shutdown of writers as readers complete.
 
         This prevents writers from waiting unnecessarily when all readers are done
@@ -352,7 +396,7 @@ async def _coordinate_writer_shutdown(
             done, pending = await asyncio.wait(
                 warc_readers,
                 return_when=asyncio.FIRST_COMPLETED,
-                timeout=1.0  # Check periodically
+                timeout=1.0,  # Check periodically
             )
 
             if done:
@@ -402,7 +446,7 @@ async def generate_range_jobs_from_cdx(
         logger.info('Range index limit: %i', self.record_limit)
         count = 0
 
-        # Iterate over index files 
+        # Iterate over index files
         # TODO this could be done in parallel
         for index_path in self.cdx_paths:
             # Fetch range queries from index
diff --git a/cdx_toolkit/filter_warc/warc_utils.py b/cdx_toolkit/filter_warc/warc_utils.py
index 99642af..e7d4b80 100644
--- a/cdx_toolkit/filter_warc/warc_utils.py
+++ b/cdx_toolkit/filter_warc/warc_utils.py
@@ -1,5 +1,6 @@
 from io import BytesIO
 import json
+import logging
 from pathlib import Path
 import fsspec
 from warcio.recordloader import ArcWarcRecord
@@ -13,24 +14,29 @@
 from cdx_toolkit.filter_warc.local_writer import LocalFileWriter
 from cdx_toolkit.filter_warc.s3_writer import S3ShardWriter
 
+logger = logging.getLogger(__name__)
+
+
 def get_bytes_from_warc_record(
-    record, 
+    record,
     warc_version: str = '1.0',
     gzip: bool = False,
-    ):
+):
+    """Get byte representation of WARC record."""
     buffer = BytesIO()
     warc_writer = WARCWriter(buffer, gzip=gzip, warc_version=warc_version)
     warc_writer.write_record(record)
 
     return buffer.getvalue()
 
+
 def get_resource_record_from_path(
     file_path: Union[str, Path],
     warcinfo_id: str,
     metadata_path: Optional[Union[str, Path]] = None,
-    ) -> ArcWarcRecord:
+) -> ArcWarcRecord:
     """Build WARC resource record for file path and metdata path.
-    
+
     The metadata file must be a valid JSON and can have the following fields:
     - warc_content_type: str
     - uri: str
@@ -42,24 +48,24 @@ def get_resource_record_from_path(
     """
     # Cast to string
     file_path = str(file_path)
-    
-    with fsspec.open(file_path, "rb") as f:
+
+    with fsspec.open(file_path, 'rb') as f:
         file_bytes = BytesIO(f.read())
 
     if metadata_path:
         # Load metadata from path
         metadata_path = str(metadata_path)
 
-        if not metadata_path.endswith(".json"):
-            raise ValueError("Metadata must be provided JSON (file path ends with *.json)")
-        
+        if not metadata_path.endswith('.json'):
+            raise ValueError('Metadata must be provided JSON (file path ends with *.json)')
+
         with fsspec.open(metadata_path) as f:
             metadata = json.load(f)
 
-            warc_content_type = metadata.get("warc_content_type", None)
-            uri = metadata.get("uri", None)
-            http_headers = metadata.get("http_headers", None)
-            warc_headers_dict = metadata.get("warc_headers_dict", {})
+            warc_content_type = metadata.get('warc_content_type', None)
+            uri = metadata.get('uri', None)
+            http_headers = metadata.get('http_headers', None)
+            warc_headers_dict = metadata.get('warc_headers_dict', {})
     else:
         # Without metdata
         warc_content_type = None
@@ -74,7 +80,7 @@ def get_resource_record_from_path(
         uri = file_path
 
     # Set WARC-Warcinfo-ID
-    warc_headers_dict["WARC-Warcinfo-ID"] = warcinfo_id
+    warc_headers_dict['WARC-Warcinfo-ID'] = warcinfo_id
 
     return WARCWriter(None).create_warc_record(
         uri=uri,
@@ -93,6 +99,7 @@ def generate_warc_filename(
     writer_subprefix: Optional[str] = None,
     gzip: bool = False,
 ) -> str:
+    """Generate a WARC file name."""
     file_name = dest_prefix + '-'
     if writer_subprefix is not None:
         file_name += writer_subprefix + '-'
@@ -117,6 +124,7 @@ async def create_new_writer_with_header(
     content_type: Optional[str] = None,
     s3_client=None,
 ) -> Tuple[Union[S3ShardWriter, LocalFileWriter], int, str]:
+    """Create a new WARC writer (local or S3) including file header."""
     if is_s3_url(output_path_prefix):
         dest_bucket, dest_prefix = parse_s3_uri(output_path_prefix)
 
@@ -152,6 +160,8 @@ async def create_new_writer_with_header(
             file_path=filename,
         )
 
+    logger.debug('Initialzing new WARC writer for {filename}')
+
     # Initialize writer
     await new_writer.start()
 
@@ -164,6 +174,6 @@ async def create_new_writer_with_header(
     await new_writer.write(header_data)
 
     # WARC-Warcinfo-ID indicates the WARC-Record-ID of the associated ‘warcinfo’ record
-    warcinfo_id = warcinfo.rec_headers.get("WARC-Record-ID")
+    warcinfo_id = warcinfo.rec_headers.get('WARC-Record-ID')
 
     return new_writer, len(header_data), warcinfo_id
diff --git a/tests/conftest.py b/tests/conftest.py
index fe39d25..935db85 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -39,8 +39,9 @@ def set_mock_time():
         os.environ['CDXT_MOCK_TIME'] = '1755259200'
 
 
-# Cache for AWS S3 access check to avoid repeated network calls
+# Cache for AWS S3/Athena access check to avoid repeated network calls
 _aws_s3_access_cache = None
+_aws_athena_access_cache = None
 
 
 def check_aws_s3_access():
@@ -72,6 +73,32 @@ def requires_aws_s3(func):
     )
 
 
+def check_aws_athena_access():
+    """Check if AWS Athena access is available."""
+    global _aws_athena_access_cache
+
+    if _aws_athena_access_cache is not None:
+        return _aws_athena_access_cache
+
+    try:
+        client = boto3.client('athena')
+
+        # Try list databasets
+        client.list_databases(CatalogName='AwsDataCatalog')
+        _aws_athena_access_cache = True
+    except (NoCredentialsError, ClientError):
+        _aws_athena_access_cache = False
+
+    return _aws_athena_access_cache
+
+
+def requires_aws_athena(func):
+    """Pytest decorator that skips test if AWS Athena access is not available."""
+    return pytest.mark.skipif(
+        not check_aws_s3_access(), reason='AWS S3 access not available (no credentials or permissions)'
+    )(func)
+
+
 @pytest.fixture
 def s3_tmpdir():
     """S3 equivalent of tmpdir - provides a temporary S3 path and handles cleanup."""
diff --git a/tests/filter_warc/test_athena_job_generator.py b/tests/filter_warc/test_athena_job_generator.py
new file mode 100644
index 0000000..1ddb32c
--- /dev/null
+++ b/tests/filter_warc/test_athena_job_generator.py
@@ -0,0 +1,69 @@
+import asyncio
+from cdx_toolkit.filter_warc.warc_filter import _STOP
+from cdx_toolkit.filter_warc.athena_job_generator import get_databases, get_range_jobs_from_athena
+from tests.conftest import requires_aws_athena
+
+import boto3
+
+
+@requires_aws_athena
+def test_get_databases():
+    from botocore.config import Config
+    import boto3
+
+    boto_cfg = Config(
+        region_name='us-east-1',
+    )
+    athena_client = boto3.client('athena', config=boto_cfg)
+    dbs = get_databases(client=athena_client)
+    assert 'ccindex' in dbs
+
+
+@requires_aws_athena
+def test_get_range_jobs_from_athena():
+    async def run_test():
+        # Setup test data
+        warc_download_prefix = 's3://commoncrawl'
+
+        # Create asyncio queues
+        key_queue = asyncio.Queue()
+
+        # Setup S3 client
+        from botocore.config import Config
+
+        boto_cfg = Config(
+            region_name='us-east-1',
+            retries={'max_attempts': 3, 'mode': 'standard'},
+            connect_timeout=10,
+            read_timeout=120,
+        )
+
+        athena_client = boto3.client('athena', config=boto_cfg)
+
+        # Generate range jobs from Athena query
+        await get_range_jobs_from_athena(
+            client=athena_client,
+            database="ccindex",
+            s3_output_location="s3://commoncrawl-ci-temp/athena-results/",
+            url_host_names=[
+                'oceancolor.sci.gsfc.nasa.gov',
+            ],
+            job_queue=key_queue,
+            warc_download_prefix=warc_download_prefix,
+            num_fetchers=1,
+            limit=10,  # Use 10 records to ensure we have enough data
+            queue_stop_object=_STOP,
+        )
+
+        # Collect all range jobs
+        range_jobs = []
+        while not key_queue.empty():
+            job = await key_queue.get()
+            if job is not _STOP:
+                range_jobs.append(job)
+            key_queue.task_done()
+
+        assert len(range_jobs) == 10, "Invalid range jobs count"
+
+    # Run the async test
+    asyncio.run(run_test())
diff --git a/tests/filter_warc/test_command.py b/tests/filter_warc/test_command.py
index e752203..10e3b8b 100644
--- a/tests/filter_warc/test_command.py
+++ b/tests/filter_warc/test_command.py
@@ -270,5 +270,77 @@ def test_resource_records_paths_mismatch():
 def test_metadata_paths_without_resource_records_paths():
     # Test if error of missing resource records paths is raised.
     with pytest.raises(ValueError) as exc_info:
-        main(args=['-v', 'warc_by_cdx', '--cdx-path=foo/bar', '--write-paths-as-resource-records-metadata', 'metadata2'])
+        main(
+            args=['-v', 'warc_by_cdx', '--cdx-path=foo/bar', '--write-paths-as-resource-records-metadata', 'metadata2']
+        )
     assert exc_info.match('Metadata paths are set but')
+
+
+def test_cli_warc_by_athena(
+    tmpdir,
+    caplog,
+):
+    base_prefix = tmpdir
+    warc_download_prefix = 's3://commoncrawl'
+    extra_args: Optional[List[str]] = None
+    warc_filename: str = 'TEST_warc_by_index-000000-001.extracted.warc.gz'  # due to parallel writer
+    base_prefix = str(base_prefix)
+
+    if extra_args is None:
+        extra_args = []
+
+    main(
+        args=[
+            '-v',
+            '--limit=10',
+            'warc_by_cdx',
+            '--target-source=athena',
+            '--athena-database=ccindex',
+            '--athena-s3-output=s3://commoncrawl-ci-temp/athena-results/',
+            '--athena-hostnames',
+            'oceancolor.sci.gsfc.nasa.gov',
+            'example.com',
+            f'--prefix={base_prefix}/TEST_warc_by_index',
+            '--creator=foo',
+            '--operator=bob',
+            f'--warc-download-prefix={warc_download_prefix}',
+        ]
+        + extra_args
+    )
+
+    # Check log
+    assert 'WARC records extracted: 10' in caplog.text
+
+    # Validate extracted WARC
+    if 's3:' in base_prefix:
+        warc_path = base_prefix + '/' + warc_filename
+    else:
+        warc_path = os.path.join(base_prefix, warc_filename)
+
+    info_record = None
+    response_records = []
+    response_contents = []
+
+    # resource_record = None
+    # resource_record_content = None
+
+    with fsspec.open(warc_path, 'rb') as stream:
+        for record in ArchiveIterator(stream):
+            if record.rec_type == 'warcinfo':
+                info_record = record.content_stream().read().decode('utf-8')
+
+            if record.rec_type == 'response':
+                response_records.append(record)
+                response_contents.append(record.content_stream().read().decode('utf-8', errors='ignore'))
+
+            # if record.rec_type == 'resource':
+            #     resource_record = record
+            #     resource_record_content = record.content_stream().read().decode('utf-8')
+
+    assert len(response_records) == 10, 'Invalid record count'
+
+    assert info_record is not None, 'Invalid info record'
+    assert 'operator: bob' in info_record, 'Invalid info record'
+
+    assert '<h1>Example Domain</h1>' in response_contents[0], 'Invalid response content'
+    assert '<h1>Example Domain</h1>' in response_contents[9], 'Invalid response content'

From e58da4821a653ffe73a9cba03cf2534fe1107aed Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Wed, 15 Oct 2025 14:11:43 +0200
Subject: [PATCH 65/74] Fix type hints for py38

---
 cdx_toolkit/filter_warc/athena_job_generator.py | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/cdx_toolkit/filter_warc/athena_job_generator.py b/cdx_toolkit/filter_warc/athena_job_generator.py
index 0d0e99a..2911125 100644
--- a/cdx_toolkit/filter_warc/athena_job_generator.py
+++ b/cdx_toolkit/filter_warc/athena_job_generator.py
@@ -1,7 +1,7 @@
 import asyncio
 import logging
 import time
-from typing import Any, Iterable
+from typing import Any, Iterable, List
 
 from cdx_toolkit.filter_warc.data_classes import RangeJob
 
@@ -15,12 +15,12 @@ async def get_range_jobs_from_athena(
     s3_output_location: str,
     job_queue: asyncio.Queue,
     queue_stop_object: Any,
-    url_host_names: list[str],
+    url_host_names: List[str],
     warc_download_prefix: str,
     num_fetchers: int,
     limit: int = 0,
     max_wait_time: int = 300,
-):
+) -> int:
     """Generate range job based on an Athena query.
 
     CommonCrawl provides an index via AWS Athena that we can use to
@@ -80,6 +80,8 @@ async def get_range_jobs_from_athena(
 
     logger.info('Athena query enqueued %d jobs', count)
 
+    return count
+
 
 def _wait_for_query_completion(client, query_execution_id: str, max_wait_time: int) -> str:
     """Wait for query to complete and return final status"""

From 1f17ecf343f29c7337c609ff2cdda8dc1bae6417 Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Wed, 15 Oct 2025 14:47:16 +0200
Subject: [PATCH 66/74] Fixed stats

---
 cdx_toolkit/filter_warc/warc_filter.py | 24 ++++++++++++++++--------
 1 file changed, 16 insertions(+), 8 deletions(-)

diff --git a/cdx_toolkit/filter_warc/warc_filter.py b/cdx_toolkit/filter_warc/warc_filter.py
index 5f062bf..b5781e6 100644
--- a/cdx_toolkit/filter_warc/warc_filter.py
+++ b/cdx_toolkit/filter_warc/warc_filter.py
@@ -80,7 +80,7 @@ def __init__(
             cdx_paths: List of paths to CDX index files.
             athena_database: Database for Athena query.
             athena_hostnames: Hostnames for Athena query.
-            athena_s3_output_location: S3 output location for Athena query.            
+            athena_s3_output_location: S3 output location for Athena query.
             prefix_path: Output path prefix for filtered WARC files.
             writer_info: Dictionary containing writer metadata.
             writer_subprefix: Optional subprefix for writer output paths.
@@ -303,7 +303,7 @@ async def _run_filter_pipeline(
             int: Number of records written.
         """
         # Fetch file paths and ranges (offset, length) from index files
-        logger.info('Starting lister, %d fetchers, %d consumers', self.num_readers, self.num_writers)
+        logger.info('Starting job generator, %d WARC readers, %d WARC writers', self.num_readers, self.num_writers)
 
         # Generate range jobs from different target sources
         if self.target_source == 'cdx':
@@ -367,18 +367,26 @@ async def _run_filter_pipeline(
         await writer_coordinator
 
         readers_records = sum([result['stats']['total_records'] for result in readers_results])
-        readers_mb_per_sec = statistics.mean([result['stats']['mb_per_sec'] for result in readers_results])
-        readers_records_per_sec = statistics.mean([result['stats']['records_per_sec'] for result in readers_results])
+        readers_mb_per_sec = self.num_readers * statistics.mean(
+            [result['stats']['mb_per_sec'] for result in readers_results]
+        )
+        readers_records_per_sec = self.num_readers * statistics.mean(
+            [result['stats']['records_per_sec'] for result in readers_results]
+        )
 
         logger.info(f'All WARC readers completed: {readers_records} records')
-        logger.info(f'Reader throughput: {readers_mb_per_sec:.2f} MB/s; {readers_records_per_sec:.2f} rec/s')
+        logger.info(f'Total reader throughput: {readers_mb_per_sec:.2f} MB/s; {readers_records_per_sec:.2f} rec/s')
 
         writers_records = sum([result['stats']['total_records'] for result in writers_results])
-        writers_mb_per_sec = statistics.mean([result['stats']['mb_per_sec'] for result in writers_results])
-        writers_records_per_sec = statistics.mean([result['stats']['records_per_sec'] for result in writers_results])
+        writers_mb_per_sec = self.num_writers * statistics.mean(
+            [result['stats']['mb_per_sec'] for result in writers_results]
+        )
+        writers_records_per_sec = self.num_writers * statistics.mean(
+            [result['stats']['records_per_sec'] for result in writers_results]
+        )
 
         logger.info(f'All WARC writers completed: {writers_records} records')
-        logger.info(f'Writer throughput: {writers_mb_per_sec:.2f} MB/s; {writers_records_per_sec:.2f} rec/s')
+        logger.info(f'Total writer throughput: {writers_mb_per_sec:.2f} MB/s; {writers_records_per_sec:.2f} rec/s')
 
         return writers_records
 

From ed7046f13eeac38dfb74a87c0b5363ee5bb99cb6 Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Wed, 15 Oct 2025 17:13:40 +0200
Subject: [PATCH 67/74] Fixed Athena check

---
 tests/conftest.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/conftest.py b/tests/conftest.py
index 935db85..4185719 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -95,7 +95,7 @@ def check_aws_athena_access():
 def requires_aws_athena(func):
     """Pytest decorator that skips test if AWS Athena access is not available."""
     return pytest.mark.skipif(
-        not check_aws_s3_access(), reason='AWS S3 access not available (no credentials or permissions)'
+        not check_aws_athena_access(), reason='AWS Athena access not available (no credentials or permissions)'
     )(func)
 
 

From 3e85de9972122c255ad53b6b19cd6873107c17e3 Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Mon, 27 Oct 2025 10:50:07 +0100
Subject: [PATCH 68/74] Fixed doc string

---
 cdx_toolkit/filter_warc/athena_job_generator.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/cdx_toolkit/filter_warc/athena_job_generator.py b/cdx_toolkit/filter_warc/athena_job_generator.py
index 2911125..59b29d8 100644
--- a/cdx_toolkit/filter_warc/athena_job_generator.py
+++ b/cdx_toolkit/filter_warc/athena_job_generator.py
@@ -105,7 +105,7 @@ def _wait_for_query_completion(client, query_execution_id: str, max_wait_time: i
 
 
 def _get_query_results(client, query_execution_id: str, warc_download_prefix: str) -> Iterable[RangeJob]:
-    """Retrieve query results and convert to pandas DataFrame"""
+    """Retrieve query results and convert to RangeJob"""
     # Get query results
     paginator = client.get_paginator('get_query_results')
     page_iterator = paginator.paginate(QueryExecutionId=query_execution_id)

From 95cd3f1af75886a5a605c544bcd6f30809ca34e2 Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Mon, 27 Oct 2025 11:13:57 +0100
Subject: [PATCH 69/74] Fixed lint check

---
 cdx_toolkit/cli.py                           |   6 +-
 cdx_toolkit/commoncrawl.py                   |   2 +
 cdx_toolkit/filter_cdx/args.py               |   2 +-
 cdx_toolkit/filter_cdx/cdx_filter.py         |  17 ++-
 cdx_toolkit/filter_cdx/command.py            |   2 +-
 cdx_toolkit/filter_cdx/path_utils.py         |   2 +-
 cdx_toolkit/filter_warc/cdx_utils.py         |   4 +-
 cdx_toolkit/filter_warc/local_writer.py      |   9 +-
 cdx_toolkit/filter_warc/s3_writer.py         |   2 -
 cdx_toolkit/warc.py                          |  42 +++---
 tests/filter_cdx/test_filter_cdx.py          |   2 +-
 tests/filter_cdx/test_path_utils.py          |  14 +-
 tests/filter_warc/test_cdx_utils.py          |   2 +-
 tests/filter_warc/test_grouped_range_jobs.py |  15 +-
 tests/filter_warc/test_local_writer.py       | 142 +++++++++++--------
 tests/filter_warc/test_warc_filter.py        |   2 +-
 tests/filter_warc/test_warc_from_fs.py       |   4 +-
 tests/unit/test_warc.py                      |   1 +
 18 files changed, 139 insertions(+), 131 deletions(-)

diff --git a/cdx_toolkit/cli.py b/cdx_toolkit/cli.py
index 4141a6c..ed78bc8 100644
--- a/cdx_toolkit/cli.py
+++ b/cdx_toolkit/cli.py
@@ -124,7 +124,10 @@ def main(args=None):
     warc.add_argument('url')
     warc.set_defaults(func=warcer)
 
-    warc_by_cdx = subparsers.add_parser('warc_by_cdx', help='iterate over capture content based on an CDX index file, creating a warc')
+    warc_by_cdx = subparsers.add_parser(
+        'warc_by_cdx',
+        help='iterate over capture content based on an CDX index file, creating a warc'
+    )
     add_warcer_by_cdx_args(warc_by_cdx)
     warc_by_cdx.set_defaults(func=run_warcer_by_cdx)
 
@@ -167,7 +170,6 @@ def set_loglevel(cmd):
     LOGGER.info('set loglevel to %s', str(loglevel))
 
 
-
 def winnow_fields(cmd, fields, obj):
     if cmd.all_fields:
         printme = obj
diff --git a/cdx_toolkit/commoncrawl.py b/cdx_toolkit/commoncrawl.py
index 32bdb28..7c38c24 100644
--- a/cdx_toolkit/commoncrawl.py
+++ b/cdx_toolkit/commoncrawl.py
@@ -9,6 +9,8 @@
 import json
 import logging
 
+from cdx_toolkit.settings import get_mock_time
+
 from .myrequests import myrequests_get
 from .timeutils import (
     time_to_timestamp,
diff --git a/cdx_toolkit/filter_cdx/args.py b/cdx_toolkit/filter_cdx/args.py
index 03d6f9e..7cbe448 100644
--- a/cdx_toolkit/filter_cdx/args.py
+++ b/cdx_toolkit/filter_cdx/args.py
@@ -5,7 +5,7 @@ def add_filter_cdx_args(parser: argparse.ArgumentParser):
     """Add command line arguments."""
     parser.add_argument(
         'input_base_path',
-        help='Base directory path on the local file system or remote URL for one or multiple CDX files (e.g., URL to S3 bucket)',
+        help='Base directory path on the local file system or remote URL for one or multiple CDX files (e.g., URL to S3 bucket)',  # noqa: E501
     )
     parser.add_argument(
         'filter_file',
diff --git a/cdx_toolkit/filter_cdx/cdx_filter.py b/cdx_toolkit/filter_cdx/cdx_filter.py
index 245b87b..ec69878 100644
--- a/cdx_toolkit/filter_cdx/cdx_filter.py
+++ b/cdx_toolkit/filter_cdx/cdx_filter.py
@@ -26,7 +26,6 @@ def _filter_single_cdx_file(
     logger.info('Writing filter output to %s', output_path)
 
     try:
-
         # Input/output from local or remote file system
         input_fs, input_fs_path = fsspec.url_to_fs(input_path)
         output_fs, output_fs_path = fsspec.url_to_fs(output_path)
@@ -61,7 +60,7 @@ def _filter_single_cdx_file(
                             logger.info(f'Lines completed: {i:,} (matched: {included_n:,}) from {input_path}')
 
                     except Exception as e:
-                        logger.error(f"Line processing error: {e}")
+                        logger.error(f'Line processing error: {e}')
                         errors_n += 1
 
         # Delete file if empty
@@ -70,7 +69,7 @@ def _filter_single_cdx_file(
             output_fs.rm(output_fs_path)
 
     except Exception as e:
-        logger.error(f"File processing error: {e}")
+        logger.error(f'File processing error: {e}')
         errors_n += 1
 
     return input_path, output_path, lines_n, included_n, errors_n
@@ -99,10 +98,10 @@ def filter_cdx(
     logger.info('Filtering with %i processes in parallel (limit: %i)', n_parallel, limit)
 
     # Prepare arguments for each task (input_path, output_path, matcher, limit)
-    task_args = [dict(
-                    input_path=input_path, 
-                    output_path=output_path, matcher=matcher, limit=limit, log_every_n=log_every_n)
-                 for input_path, output_path in zip(input_paths, output_paths)]
+    task_args = [
+        dict(input_path=input_path, output_path=output_path, matcher=matcher, limit=limit, log_every_n=log_every_n)
+        for input_path, output_path in zip(input_paths, output_paths)
+    ]
 
     pool = None
     try:
@@ -129,6 +128,6 @@ def filter_cdx(
             pool.close()
             pool.join()
 
-    logger.warning(f"Filter CDX errors: {total_errors_n}")
+    logger.warning(f'Filter CDX errors: {total_errors_n}')
 
-    return total_lines_n, total_included_n, total_errors_n
\ No newline at end of file
+    return total_lines_n, total_included_n, total_errors_n
diff --git a/cdx_toolkit/filter_cdx/command.py b/cdx_toolkit/filter_cdx/command.py
index 0ca10ce..80a0fc1 100644
--- a/cdx_toolkit/filter_cdx/command.py
+++ b/cdx_toolkit/filter_cdx/command.py
@@ -80,4 +80,4 @@ def run_filter_cdx(args, cmdline: str):
     end_time = time.time()
     execution_time = end_time - start_time
 
-    logger.info(f'Script execution time: {execution_time:.3f} seconds')
\ No newline at end of file
+    logger.info(f'Script execution time: {execution_time:.3f} seconds')
diff --git a/cdx_toolkit/filter_cdx/path_utils.py b/cdx_toolkit/filter_cdx/path_utils.py
index 08237b9..834c8f0 100644
--- a/cdx_toolkit/filter_cdx/path_utils.py
+++ b/cdx_toolkit/filter_cdx/path_utils.py
@@ -33,7 +33,7 @@ def resolve_paths(input_base_path: str, input_glob: Optional[str], output_base_p
     input_file_paths = []
     for input_path in input_fs_file_paths:
         # Get relative path from input_base_path without last slash
-        rel_path = input_path[len(input_fs_base_path) + 1 :]
+        rel_path = input_path[len(input_fs_base_path)+1:]
 
         # Create corresponding full input and output path
         # Use forward slashes for URL paths (S3, HTTP, etc.) to ensure cross-platform compatibility
diff --git a/cdx_toolkit/filter_warc/cdx_utils.py b/cdx_toolkit/filter_warc/cdx_utils.py
index 2a0c4ec..d061be2 100644
--- a/cdx_toolkit/filter_warc/cdx_utils.py
+++ b/cdx_toolkit/filter_warc/cdx_utils.py
@@ -33,7 +33,9 @@ def read_cdx_line(line: str, warc_download_prefix: str) -> Tuple[str, int, int]:
     if len(cols) == 3:
         # NOTE: We assume the following format (CC-CDX format): <surt> <timestamp> <json_data>
         #
-        # IA follows a different CDX specification from https://iipc.github.io/warc-specifications/specifications/cdx-format/cdx-2015/
+        # IA follows a different CDX specification:
+        # https://iipc.github.io/warc-specifications/specifications/cdx-format/cdx-2015/
+        #
         # > The default first line of a CDX file is:
         # > CDX A b e a m s c k r V v D d g M n
         data = json.loads(cols[2])
diff --git a/cdx_toolkit/filter_warc/local_writer.py b/cdx_toolkit/filter_warc/local_writer.py
index e85b052..8fd9e48 100644
--- a/cdx_toolkit/filter_warc/local_writer.py
+++ b/cdx_toolkit/filter_warc/local_writer.py
@@ -3,13 +3,8 @@
 
 class LocalFileWriter:
     """Async writer for local file system using aiofiles."""
-    
-    def __init__(
-        self,
-        file_path: str,
-        buffer_size: int = 8192,
-        mode: str = 'wb'
-    ):
+
+    def __init__(self, file_path: str, buffer_size: int = 8192, mode: str = 'wb'):
         self.file_path = file_path
         self.buffer_size = buffer_size
         self.mode = mode
diff --git a/cdx_toolkit/filter_warc/s3_writer.py b/cdx_toolkit/filter_warc/s3_writer.py
index b67e646..395f391 100644
--- a/cdx_toolkit/filter_warc/s3_writer.py
+++ b/cdx_toolkit/filter_warc/s3_writer.py
@@ -170,5 +170,3 @@ async def close(self):
             if self.upload_id:
                 await mpu_abort(self.s3_client, self.dest_bucket, self.shard_key, self.upload_id)
             raise
-
-
diff --git a/cdx_toolkit/warc.py b/cdx_toolkit/warc.py
index 9aa1ba1..657b2c0 100644
--- a/cdx_toolkit/warc.py
+++ b/cdx_toolkit/warc.py
@@ -1,6 +1,5 @@
 from urllib.parse import quote
 from io import BytesIO
-import os.path
 import datetime
 import logging
 import sys
@@ -33,9 +32,9 @@ def wb_redir_to_original(location):
 
 
 def fake_wb_warc(url, wb_url, resp, capture):
-    '''
+    """
     Given a playback from a wayback, fake up a warc response record
-    '''
+    """
     status_code = resp.status_code
     status_reason = resp.reason
 
@@ -43,19 +42,18 @@ def fake_wb_warc(url, wb_url, resp, capture):
         url = capture['url']
         timestamp = capture['timestamp']
         if status_code == 200 and capture['status'] == '-':
-            LOGGER.warning('revisit record vivified by wayback for %s %s',
-                           url, timestamp)
+            LOGGER.warning('revisit record vivified by wayback for %s %s', url, timestamp)
         elif status_code == 200 and capture['status'].startswith('3'):
-            LOGGER.warning('redirect capture came back 200, same-surt same-timestamp capture? %s %s',
-                           url, timestamp)
+            LOGGER.warning('redirect capture came back 200, same-surt same-timestamp capture? %s %s', url, timestamp)
         elif status_code == 302 and capture['status'].startswith('3'):
             # this is OK, wayback always sends a temporary redir
             status_code = int(capture['status'])
             if status_code != resp.status_code and status_code in http_status_text:
                 status_reason = http_status_text[status_code]
         else:  # pragma: no cover
-            LOGGER.warning('surprised that status code is now=%d orig=%s %s %s',
-                           status_code, capture['status'], url, timestamp)
+            LOGGER.warning(
+                'surprised that status code is now=%d orig=%s %s %s', status_code, capture['status'], url, timestamp
+            )
 
     http_headers = []
     http_date = None
@@ -90,16 +88,15 @@ def fake_wb_warc(url, wb_url, resp, capture):
     content_bytes = resp.content
 
     writer = WARCWriter(None)  # needs warc_version here?
-    return writer.create_warc_record(url, 'response',
-                                     payload=BytesIO(content_bytes),
-                                     http_headers=http_headers,
-                                     warc_headers_dict=warc_headers_dict)
+    return writer.create_warc_record(
+        url, 'response', payload=BytesIO(content_bytes), http_headers=http_headers, warc_headers_dict=warc_headers_dict
+    )
 
 
 def fetch_wb_warc(capture, wb, modifier='id_'):
     for field in ('url', 'timestamp', 'status'):
         if field not in capture:  # pragma: no cover
-            raise ValueError('capture must contain '+field)
+            raise ValueError('capture must contain ' + field)
 
     if wb is None:  # pragma: no cover
         raise ValueError('No wayback configured')
@@ -124,7 +121,7 @@ def fetch_wb_warc(capture, wb, modifier='id_'):
 def fetch_warc_record(capture, warc_download_prefix):
     for field in ('url', 'filename', 'offset', 'length'):
         if field not in capture:  # pragma: no cover
-            raise ValueError('capture must contain '+field)
+            raise ValueError('capture must contain ' + field)
 
     url = capture['url']
     filename = capture['filename']
@@ -133,14 +130,14 @@ def fetch_warc_record(capture, warc_download_prefix):
 
     warc_url = warc_download_prefix + '/' + filename
 
-    if warc_url.startswith("s3:"):
+    if warc_url.startswith('s3:'):
         # fetch from S3
         with fsspec.open(warc_url, 'rb') as f:
             f.seek(offset)
             record_bytes = f.read(length)
     else:
         # fetch over HTTP
-        headers = {'Range': 'bytes={}-{}'.format(offset, offset+length-1)}
+        headers = {'Range': 'bytes={}-{}'.format(offset, offset + length - 1)}
 
         resp = myrequests_get(warc_url, headers=headers)
         record_bytes = resp.content
@@ -155,21 +152,20 @@ def fetch_warc_record(capture, warc_download_prefix):
     warc_target_uri = record.rec_headers.get_header('WARC-Target-URI')
     if url != warc_target_uri:  # pragma: no cover
         print(
-            "Surprised that WARC-Target-URI {} is not the capture url {}".format(
-                warc_target_uri, url
-            ),
+            'Surprised that WARC-Target-URI {} is not the capture url {}'.format(warc_target_uri, url),
             file=sys.stderr,
         )
 
     record.rec_headers.replace_header('WARC-Source-URI', warc_url)
-    record.rec_headers.replace_header('WARC-Source-Range', 'bytes={}-{}'.format(offset, offset+length-1))
+    record.rec_headers.replace_header('WARC-Source-Range', 'bytes={}-{}'.format(offset, offset + length - 1))
     return record
 
 
 class CDXToolkitWARCWriter:
-    """Writer for WARC files. 
-    
+    """Writer for WARC files.
+
     The fsspec package is used for writting to local or remote file system, e.g., S3."""
+
     def __init__(self, prefix, subprefix, info, size=1000000000, gzip=True, warc_version=None):
         self.prefix = prefix
         self.subprefix = subprefix
diff --git a/tests/filter_cdx/test_filter_cdx.py b/tests/filter_cdx/test_filter_cdx.py
index c2c4ed2..406eb59 100644
--- a/tests/filter_cdx/test_filter_cdx.py
+++ b/tests/filter_cdx/test_filter_cdx.py
@@ -1,5 +1,5 @@
 import multiprocessing
-import signal
+
 import time
 
 from unittest.mock import patch, MagicMock
diff --git a/tests/filter_cdx/test_path_utils.py b/tests/filter_cdx/test_path_utils.py
index f1fddc7..d140937 100644
--- a/tests/filter_cdx/test_path_utils.py
+++ b/tests/filter_cdx/test_path_utils.py
@@ -8,9 +8,9 @@
 
 def test_resolve_s3_paths_without_glob():
     input_files, output_files = resolve_paths(
-        input_base_path="s3://commoncraw/cc-index/collections/CC-MAIN-2016-30/indexes/cdx-00001.gz", 
-        input_glob=None, 
-        output_base_path=f"s3://{TEST_S3_BUCKET}/output",
+        input_base_path='s3://commoncraw/cc-index/collections/CC-MAIN-2016-30/indexes/cdx-00001.gz',
+        input_glob=None,
+        output_base_path=f's3://{TEST_S3_BUCKET}/output',
     )
     assert len(input_files) == 1
     assert len(output_files) == len(input_files)
@@ -20,10 +20,10 @@ def test_validate_resolved_paths_with_makedirs():
     with tempfile.TemporaryDirectory() as tmpdir:
         validate_resolved_paths(
             output_paths=[
-                os.path.join(tmpdir, "1"),
-                os.path.join(tmpdir, "2"),
+                os.path.join(tmpdir, '1'),
+                os.path.join(tmpdir, '2'),
             ],
-            overwrite=False
+            overwrite=False,
         )
 
 
@@ -81,4 +81,4 @@ def test_validate_resolved_paths_existing_file_exits(tmpdir, caplog):
 
     assert exc_info.value.code == 1
     assert f'Output file already exists: {str(existing_file)}' in caplog.text
-    assert 'Use --overwrite to overwrite existing files' in caplog.text
\ No newline at end of file
+    assert 'Use --overwrite to overwrite existing files' in caplog.text
diff --git a/tests/filter_warc/test_cdx_utils.py b/tests/filter_warc/test_cdx_utils.py
index 378bf85..5ca7035 100644
--- a/tests/filter_warc/test_cdx_utils.py
+++ b/tests/filter_warc/test_cdx_utils.py
@@ -42,7 +42,7 @@ def test_iter_cdx_index_from_path_with_error():
 org,test)/ 20240102130000 {"url": "http://test.org/", "filename": "test2.warc.gz", "offset": "600", "length": "300"}
 another_bad_line
 org,valid)/ 20240103140000 {"url": "http://valid.org/", "filename": "test3.warc.gz", "offset": "900", "length": "200"}
-""".strip()
+""".strip()  # noqa: E501
 
     fd, tmp_file_path = tempfile.mkstemp(suffix='.cdx.gz')
     try:
diff --git a/tests/filter_warc/test_grouped_range_jobs.py b/tests/filter_warc/test_grouped_range_jobs.py
index adf9a07..b046709 100644
--- a/tests/filter_warc/test_grouped_range_jobs.py
+++ b/tests/filter_warc/test_grouped_range_jobs.py
@@ -1,14 +1,6 @@
-import fsspec
-import pytest
-from cdx_toolkit.filter_warc.cdx_utils import get_index_as_string_from_path, read_cdx_line, iter_cdx_index_from_path
+from cdx_toolkit.filter_warc.cdx_utils import iter_cdx_index_from_path
 from tests.conftest import TEST_DATA_PATH
 
-import tempfile
-import gzip
-import os
-from unittest.mock import patch
-
-
 
 def test_iter_cdx_index_from_test_data():
     cdx_path = TEST_DATA_PATH / 'warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.gz'
@@ -28,7 +20,7 @@ def group_neighbor_chunks(items):
         current_chunk = [items[0]]
 
         for i in range(1, len(items)):
-            prev_url, prev_offset, prev_length = items[i-1]
+            prev_url, prev_offset, prev_length = items[i - 1]
             curr_url, curr_offset, curr_length = items[i]
 
             # Check if current item is a neighbor (same URL and contiguous)
@@ -48,4 +40,5 @@ def group_neighbor_chunks(items):
 
 
 def test_grouped_ranges():
-    cdx_path = ""
\ No newline at end of file
+    # cdx_path = ''
+    pass
diff --git a/tests/filter_warc/test_local_writer.py b/tests/filter_warc/test_local_writer.py
index 36a88c5..fa15740 100644
--- a/tests/filter_warc/test_local_writer.py
+++ b/tests/filter_warc/test_local_writer.py
@@ -7,8 +7,8 @@
 
 def test_init_default_values():
     """Test initialization with default values."""
-    writer = LocalFileWriter("/tmp/test.txt")
-    assert writer.file_path == "/tmp/test.txt"
+    writer = LocalFileWriter('/tmp/test.txt')
+    assert writer.file_path == '/tmp/test.txt'
     assert writer.buffer_size == 8192
     assert writer.mode == 'wb'
     assert writer.file_handle is None
@@ -18,8 +18,8 @@ def test_init_default_values():
 
 def test_init_custom_values():
     """Test initialization with custom values."""
-    writer = LocalFileWriter("/tmp/test.txt", buffer_size=4096, mode='ab')
-    assert writer.file_path == "/tmp/test.txt"
+    writer = LocalFileWriter('/tmp/test.txt', buffer_size=4096, mode='ab')
+    assert writer.file_path == '/tmp/test.txt'
     assert writer.buffer_size == 4096
     assert writer.mode == 'ab'
     assert writer.file_handle is None
@@ -29,8 +29,9 @@ def test_init_custom_values():
 
 def test_start_opens_file(tmp_path):
     """Test that start() opens the file correctly."""
+
     async def run_test():
-        temp_file = tmp_path / "test.txt"
+        temp_file = tmp_path / 'test.txt'
         writer = LocalFileWriter(str(temp_file))
         await writer.start()
 
@@ -42,8 +43,9 @@ async def run_test():
 
 def test_start_with_different_modes(tmp_path):
     """Test start() with different file modes."""
+
     async def run_test():
-        temp_file = tmp_path / "test.txt"
+        temp_file = tmp_path / 'test.txt'
 
         # Test binary write mode
         writer = LocalFileWriter(str(temp_file), mode='wb')
@@ -62,10 +64,11 @@ async def run_test():
 
 def test_start_creates_directory_if_needed(tmp_path):
     """Test that start() works when parent directory exists."""
+
     async def run_test():
-        subdir = tmp_path / "subdir"
+        subdir = tmp_path / 'subdir'
         subdir.mkdir()
-        temp_file = subdir / "test.txt"
+        temp_file = subdir / 'test.txt'
 
         writer = LocalFileWriter(str(temp_file))
         await writer.start()
@@ -77,12 +80,13 @@ async def run_test():
 
 def test_write_small_data_buffers(tmp_path):
     """Test writing data that doesn't exceed buffer size."""
+
     async def run_test():
-        temp_file = tmp_path / "test.txt"
+        temp_file = tmp_path / 'test.txt'
         writer = LocalFileWriter(str(temp_file), buffer_size=100)
         await writer.start()
 
-        test_data = b"Hello, World!"
+        test_data = b'Hello, World!'
         await writer.write(test_data)
 
         # Data should be in buffer, not yet written to file
@@ -99,14 +103,15 @@ async def run_test():
 
 def test_write_large_data_triggers_flush(tmp_path):
     """Test writing data that exceeds buffer size triggers flush."""
+
     async def run_test():
-        temp_file = tmp_path / "test.txt"
+        temp_file = tmp_path / 'test.txt'
         buffer_size = 50
         writer = LocalFileWriter(str(temp_file), buffer_size=buffer_size)
         await writer.start()
 
         # Write data larger than buffer size
-        test_data = b"x" * (buffer_size + 10)
+        test_data = b'x' * (buffer_size + 10)
         await writer.write(test_data)
 
         # Buffer should be empty after automatic flush
@@ -122,14 +127,15 @@ async def run_test():
 
 def test_write_multiple_small_chunks(tmp_path):
     """Test writing multiple small chunks that eventually trigger flush."""
+
     async def run_test():
-        temp_file = tmp_path / "test.txt"
+        temp_file = tmp_path / 'test.txt'
         buffer_size = 50
         writer = LocalFileWriter(str(temp_file), buffer_size=buffer_size)
         await writer.start()
 
-        chunk1 = b"a" * 30
-        chunk2 = b"b" * 25  # Total: 55 bytes, exceeds buffer
+        chunk1 = b'a' * 30
+        chunk2 = b'b' * 25  # Total: 55 bytes, exceeds buffer
 
         await writer.write(chunk1)
         assert len(writer.buffer) == 30
@@ -147,37 +153,39 @@ async def run_test():
 
 def test_write_empty_data(tmp_path):
     """Test writing empty data."""
+
     async def run_test():
-        temp_file = tmp_path / "test.txt"
+        temp_file = tmp_path / 'test.txt'
         writer = LocalFileWriter(str(temp_file))
         await writer.start()
 
-        await writer.write(b"")
+        await writer.write(b'')
         assert len(writer.buffer) == 0
 
         await writer.close()
 
-        assert temp_file.read_bytes() == b""
+        assert temp_file.read_bytes() == b''
 
     asyncio.run(run_test())
 
 
 def test_write_without_start_graceful_handling(tmp_path):
     """Test that writing without calling start() is handled gracefully."""
+
     async def run_test():
-        temp_file = tmp_path / "test.txt"
+        temp_file = tmp_path / 'test.txt'
         writer = LocalFileWriter(str(temp_file), buffer_size=10)  # Small buffer to force flush
 
         # This should work fine as long as we don't exceed buffer size
-        await writer.write(b"small")
+        await writer.write(b'small')
         assert len(writer.buffer) == 5
 
         # When buffer exceeds size, flush is called but does nothing since file_handle is None
         # The data stays in buffer instead of being written
-        await writer.write(b"data that exceeds buffer size")
+        await writer.write(b'data that exceeds buffer size')
 
         # Buffer should contain all the data since flush did nothing
-        expected_data = b"small" + b"data that exceeds buffer size"
+        expected_data = b'small' + b'data that exceeds buffer size'
         assert writer.buffer == expected_data
 
     asyncio.run(run_test())
@@ -185,8 +193,9 @@ async def run_test():
 
 def test_flush_empty_buffer(tmp_path):
     """Test flushing when buffer is empty."""
+
     async def run_test():
-        temp_file = tmp_path / "test.txt"
+        temp_file = tmp_path / 'test.txt'
         writer = LocalFileWriter(str(temp_file))
         await writer.start()
 
@@ -201,26 +210,28 @@ async def run_test():
 
 def test_flush_without_file_handle(tmp_path):
     """Test flushing without file handle."""
+
     async def run_test():
-        temp_file = tmp_path / "test.txt"
+        temp_file = tmp_path / 'test.txt'
         writer = LocalFileWriter(str(temp_file))
-        writer.buffer.extend(b"test data")
+        writer.buffer.extend(b'test data')
 
         # Should not raise error, just do nothing
         await writer._flush()
-        assert len(writer.buffer) == len(b"test data")  # Buffer unchanged
+        assert len(writer.buffer) == len(b'test data')  # Buffer unchanged
 
     asyncio.run(run_test())
 
 
 def test_close_flushes_remaining_data(tmp_path):
     """Test that close() flushes any remaining buffered data."""
+
     async def run_test():
-        temp_file = tmp_path / "test.txt"
+        temp_file = tmp_path / 'test.txt'
         writer = LocalFileWriter(str(temp_file), buffer_size=100)
         await writer.start()
 
-        test_data = b"This data should be flushed on close"
+        test_data = b'This data should be flushed on close'
         await writer.write(test_data)
 
         # Data should still be in buffer
@@ -236,8 +247,9 @@ async def run_test():
 
 def test_close_without_start(tmp_path):
     """Test closing without calling start()."""
+
     async def run_test():
-        temp_file = tmp_path / "test.txt"
+        temp_file = tmp_path / 'test.txt'
         writer = LocalFileWriter(str(temp_file))
 
         # Should not raise error
@@ -248,8 +260,9 @@ async def run_test():
 
 def test_close_twice(tmp_path):
     """Test calling close() multiple times."""
+
     async def run_test():
-        temp_file = tmp_path / "test.txt"
+        temp_file = tmp_path / 'test.txt'
         writer = LocalFileWriter(str(temp_file))
         await writer.start()
 
@@ -263,17 +276,18 @@ async def run_test():
 
 def test_close_handles_flush_exception(tmp_path):
     """Test that close() handles exceptions during flush properly."""
+
     async def run_test():
-        temp_file = tmp_path / "test.txt"
+        temp_file = tmp_path / 'test.txt'
         writer = LocalFileWriter(str(temp_file))
         await writer.start()
 
         # Add some data to buffer
-        await writer.write(b"test data")
+        await writer.write(b'test data')
 
         # Mock flush to raise an exception
-        with patch.object(writer, '_flush', side_effect=Exception("Flush error")):
-            with pytest.raises(Exception, match="Flush error"):
+        with patch.object(writer, '_flush', side_effect=Exception('Flush error')):
+            with pytest.raises(Exception, match='Flush error'):
                 await writer.close()
 
     asyncio.run(run_test())
@@ -281,14 +295,15 @@ async def run_test():
 
 def test_close_handles_file_close_exception(tmp_path):
     """Test that close() handles exceptions during file close."""
+
     async def run_test():
-        temp_file = tmp_path / "test.txt"
+        temp_file = tmp_path / 'test.txt'
         writer = LocalFileWriter(str(temp_file))
         await writer.start()
 
         # Mock file handle close to raise an exception
-        with patch.object(writer.file_handle, 'close', side_effect=Exception("Close error")):
-            with pytest.raises(Exception, match="Close error"):
+        with patch.object(writer.file_handle, 'close', side_effect=Exception('Close error')):
+            with pytest.raises(Exception, match='Close error'):
                 await writer.close()
 
     asyncio.run(run_test())
@@ -296,15 +311,16 @@ async def run_test():
 
 def test_large_file_write(tmp_path):
     """Test writing a large amount of data."""
+
     async def run_test():
-        temp_file = tmp_path / "test.txt"
+        temp_file = tmp_path / 'test.txt'
         writer = LocalFileWriter(str(temp_file), buffer_size=1024)
         await writer.start()
 
         # Write 1MB of data in chunks
         chunk_size = 1024  # Make chunk size same as buffer for exact division
         total_size = 1024 * 1024  # 1MB
-        chunk_data = b"x" * chunk_size
+        chunk_data = b'x' * chunk_size
 
         for _ in range(total_size // chunk_size):
             await writer.write(chunk_data)
@@ -319,8 +335,9 @@ async def run_test():
 
 def test_binary_data_integrity(tmp_path):
     """Test that binary data is written correctly."""
+
     async def run_test():
-        temp_file = tmp_path / "test.txt"
+        temp_file = tmp_path / 'test.txt'
         writer = LocalFileWriter(str(temp_file))
         await writer.start()
 
@@ -337,8 +354,9 @@ async def run_test():
 
 def test_concurrent_writes(tmp_path):
     """Test concurrent write operations."""
+
     async def run_test():
-        temp_file = tmp_path / "test.txt"
+        temp_file = tmp_path / 'test.txt'
         writer = LocalFileWriter(str(temp_file), buffer_size=100)
         await writer.start()
 
@@ -346,10 +364,7 @@ async def run_test():
         async def write_chunk(data):
             await writer.write(data)
 
-        tasks = [
-            write_chunk(f"chunk{i}".encode() * 10)
-            for i in range(10)
-        ]
+        tasks = [write_chunk(f'chunk{i}'.encode() * 10) for i in range(10)]
 
         await asyncio.gather(*tasks)
         await writer.close()
@@ -363,12 +378,13 @@ async def write_chunk(data):
 
 def test_file_permissions_error(tmp_path):
     """Test handling of file permission errors."""
+
     async def run_test():
         # Create a file path in a directory we can't write to
-        readonly_file = tmp_path / "readonly.txt"
+        readonly_file = tmp_path / 'readonly.txt'
 
         # Create the file first
-        readonly_file.write_text("test")
+        readonly_file.write_text('test')
 
         # Make the file read-only
         readonly_file.chmod(0o444)
@@ -383,8 +399,9 @@ async def run_test():
 
 def test_nonexistent_directory():
     """Test writing to a file in a nonexistent directory."""
+
     async def run_test():
-        nonexistent_path = "/nonexistent/directory/file.txt"
+        nonexistent_path = '/nonexistent/directory/file.txt'
         writer = LocalFileWriter(nonexistent_path)
 
         with pytest.raises(FileNotFoundError):
@@ -395,60 +412,63 @@ async def run_test():
 
 def test_context_manager_like_usage(tmp_path):
     """Test typical usage pattern similar to context manager."""
+
     async def run_test():
-        temp_file = tmp_path / "test.txt"
+        temp_file = tmp_path / 'test.txt'
         writer = LocalFileWriter(str(temp_file))
 
         try:
             await writer.start()
-            await writer.write(b"Hello, World!")
-            await writer.write(b" How are you?")
+            await writer.write(b'Hello, World!')
+            await writer.write(b' How are you?')
         finally:
             await writer.close()
 
-        assert temp_file.read_bytes() == b"Hello, World! How are you?"
+        assert temp_file.read_bytes() == b'Hello, World! How are you?'
 
     asyncio.run(run_test())
 
 
 def test_buffer_size_edge_cases(tmp_path):
     """Test edge cases with different buffer sizes."""
+
     async def run_test():
-        temp_file = tmp_path / "test.txt"
+        temp_file = tmp_path / 'test.txt'
         # Test with buffer size of 1
         writer = LocalFileWriter(str(temp_file), buffer_size=1)
         await writer.start()
 
-        await writer.write(b"a")  # Should trigger flush immediately
+        await writer.write(b'a')  # Should trigger flush immediately
         assert len(writer.buffer) == 0
 
-        await writer.write(b"bc")  # Should trigger flush after 'b', leaving 'c'
+        await writer.write(b'bc')  # Should trigger flush after 'b', leaving 'c'
         assert len(writer.buffer) == 0
 
         await writer.close()
 
-        assert temp_file.read_bytes() == b"abc"
+        assert temp_file.read_bytes() == b'abc'
 
     asyncio.run(run_test())
 
 
 def test_append_mode(tmp_path):
     """Test append mode functionality."""
+
     async def run_test():
-        temp_file = tmp_path / "test.txt"
+        temp_file = tmp_path / 'test.txt'
 
         # First, write some initial data
-        temp_file.write_bytes(b"Initial data\n")
+        temp_file.write_bytes(b'Initial data\n')
 
         # Now append using LocalFileWriter
         writer = LocalFileWriter(str(temp_file), mode='ab')
         await writer.start()
 
-        await writer.write(b"Appended data\n")
+        await writer.write(b'Appended data\n')
         await writer.close()
 
         # Verify both pieces of data are present
         content = temp_file.read_bytes()
-        assert content == b"Initial data\nAppended data\n"
+        assert content == b'Initial data\nAppended data\n'
 
-    asyncio.run(run_test())
\ No newline at end of file
+    asyncio.run(run_test())
diff --git a/tests/filter_warc/test_warc_filter.py b/tests/filter_warc/test_warc_filter.py
index 937776e..5f5a833 100644
--- a/tests/filter_warc/test_warc_filter.py
+++ b/tests/filter_warc/test_warc_filter.py
@@ -1,5 +1,5 @@
 import asyncio
-import pytest
+
 from unittest.mock import AsyncMock, patch
 from cdx_toolkit.filter_warc.data_classes import ThroughputTracker
 from tests.conftest import TEST_DATA_PATH
diff --git a/tests/filter_warc/test_warc_from_fs.py b/tests/filter_warc/test_warc_from_fs.py
index ccceaf0..aa23249 100644
--- a/tests/filter_warc/test_warc_from_fs.py
+++ b/tests/filter_warc/test_warc_from_fs.py
@@ -12,7 +12,7 @@ def test_fetch_warc_record_from_http():
         'digest': 'D5K3FUWDRAOMMTJC2CTWV7L2ABFIJ5BP',
         'length': '9754',
         'offset': '111440525',
-        'filename': 'crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00337.warc.gz',
+        'filename': 'crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00337.warc.gz',  # noqa: E501
         'charset': 'UTF-8',
         'languages': 'fra',
         'timestamp': '20240716153155',
@@ -38,7 +38,7 @@ def test_fetch_warc_record_from_s3():
         'digest': 'D5K3FUWDRAOMMTJC2CTWV7L2ABFIJ5BP',
         'length': '9754',
         'offset': '111440525',
-        'filename': 'crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00337.warc.gz',
+        'filename': 'crawl-data/CC-MAIN-2024-30/segments/1720763514759.37/warc/CC-MAIN-20240716142214-20240716172214-00337.warc.gz',  # noqa: E501
         'charset': 'UTF-8',
         'languages': 'fra',
         'timestamp': '20240716153155',
diff --git a/tests/unit/test_warc.py b/tests/unit/test_warc.py
index e2474ff..e5df43f 100644
--- a/tests/unit/test_warc.py
+++ b/tests/unit/test_warc.py
@@ -1,5 +1,6 @@
 import cdx_toolkit.warc
 
+
 def test_wb_redir_to_original():
     location = 'https://web.archive.org/web/20110209062054id_/http://commoncrawl.org/'
     ret = 'http://commoncrawl.org/'

From 166a0a926b21ca1638bb17ed695035c6eed34396 Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Mon, 27 Oct 2025 11:24:56 +0100
Subject: [PATCH 70/74] Add athena query check

---
 tests/conftest.py                             | 24 ++++++++++++++++++-
 .../filter_warc/test_athena_job_generator.py  |  6 ++---
 2 files changed, 26 insertions(+), 4 deletions(-)

diff --git a/tests/conftest.py b/tests/conftest.py
index 4185719..7ca16f2 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -18,6 +18,8 @@
 
 TEST_DATA_PATH = Path(__file__).parent / 'data'
 TEST_S3_BUCKET = os.environ.get('CDXT_TEST_S3_BUCKET', 'commoncrawl-ci-temp')
+TEST_ATHENA_S3_LOCATION = 's3://commoncrawl-ci-temp/athena-results/'
+TEST_ATHENA_DATABASE = 'ccindex'
 DISABLE_S3_TESTS = bool(os.environ.get('CDXT_DISABLE_S3_TESTS', False))
 
 TEST_DATA_BASE_PATH = Path(__file__).parent / 'data'
@@ -73,6 +75,24 @@ def requires_aws_s3(func):
     )
 
 
+def check_aws_athena_query_execution_access():
+    """Check if AWS Athena StartQueryExecution permission is available."""
+    try:
+        # Use IAM simulation instead of actual query execution
+        iam_client = boto3.client('iam')
+        response = iam_client.simulate_principal_policy(
+            PolicySourceArn=f'arn:aws:sts::{boto3.client("sts").get_caller_identity()["Account"]}:assumed-role/your-role/session',  # noqa: E501
+            ActionNames=['athena:StartQueryExecution'],
+            ResourceArns=['*'],
+        )
+
+        # Check if access is allowed
+        return response['EvaluationResults'][0]['EvalDecision'] == 'allowed'
+
+    except (ClientError, NoCredentialsError):
+        return False
+
+
 def check_aws_athena_access():
     """Check if AWS Athena access is available."""
     global _aws_athena_access_cache
@@ -85,7 +105,9 @@ def check_aws_athena_access():
 
         # Try list databasets
         client.list_databases(CatalogName='AwsDataCatalog')
-        _aws_athena_access_cache = True
+
+        # Try query access
+        _aws_athena_access_cache = check_aws_athena_query_execution_access()
     except (NoCredentialsError, ClientError):
         _aws_athena_access_cache = False
 
diff --git a/tests/filter_warc/test_athena_job_generator.py b/tests/filter_warc/test_athena_job_generator.py
index 1ddb32c..e270261 100644
--- a/tests/filter_warc/test_athena_job_generator.py
+++ b/tests/filter_warc/test_athena_job_generator.py
@@ -1,7 +1,7 @@
 import asyncio
 from cdx_toolkit.filter_warc.warc_filter import _STOP
 from cdx_toolkit.filter_warc.athena_job_generator import get_databases, get_range_jobs_from_athena
-from tests.conftest import requires_aws_athena
+from tests.conftest import TEST_ATHENA_DATABASE, TEST_ATHENA_S3_LOCATION, requires_aws_athena
 
 import boto3
 
@@ -43,8 +43,8 @@ async def run_test():
         # Generate range jobs from Athena query
         await get_range_jobs_from_athena(
             client=athena_client,
-            database="ccindex",
-            s3_output_location="s3://commoncrawl-ci-temp/athena-results/",
+            database=TEST_ATHENA_DATABASE,
+            s3_output_location=TEST_ATHENA_S3_LOCATION,
             url_host_names=[
                 'oceancolor.sci.gsfc.nasa.gov',
             ],

From 36f9f88257772f68544550cd52a1d66bc8f0dd92 Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Mon, 27 Oct 2025 11:30:07 +0100
Subject: [PATCH 71/74] disable athena unit tests

---
 .github/workflows/ci.yaml | 3 ++-
 tests/conftest.py         | 9 ++++++---
 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
index 112c654..140e19d 100644
--- a/.github/workflows/ci.yaml
+++ b/.github/workflows/ci.yaml
@@ -66,7 +66,7 @@ jobs:
         run: pip install .[test]
 
       - name: Configure AWS credentials from OIDC (disabled for forks)
-        if: github.event.pull_request.head.repo.full_name == github.repository || github.event_name == 'push'        
+        if: github.event.pull_request.head.repo.full_name == github.repository || github.event_name == 'push'
         uses: aws-actions/configure-aws-credentials@v4
         with:
           role-to-assume: arn:aws:iam::837454214164:role/GitHubActions-Role
@@ -89,6 +89,7 @@ jobs:
             core.exportVariable('CDXT_CC_INDEX_MIN_RETRY_INTERVAL', '0.01')
             core.exportVariable('CDXT_CC_DATA_MIN_RETRY_INTERVAL', '0.01')
             core.exportVariable('CDXT_IA_MIN_RETRY_INTERVAL', '0.01')
+            core.exportVariable('DISABLE_ATHENA_TESTS', '1')
             core.exportVariable('LOGLEVEL', 'DEBUG')
 
       - name: Lint code
diff --git a/tests/conftest.py b/tests/conftest.py
index 7ca16f2..ff92d5a 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -20,6 +20,7 @@
 TEST_S3_BUCKET = os.environ.get('CDXT_TEST_S3_BUCKET', 'commoncrawl-ci-temp')
 TEST_ATHENA_S3_LOCATION = 's3://commoncrawl-ci-temp/athena-results/'
 TEST_ATHENA_DATABASE = 'ccindex'
+DISABLE_ATHENA_TESTS = bool(os.environ.get('CDXT_DISABLE_ATHENA_TESTS', False))
 DISABLE_S3_TESTS = bool(os.environ.get('CDXT_DISABLE_S3_TESTS', False))
 
 TEST_DATA_BASE_PATH = Path(__file__).parent / 'data'
@@ -116,9 +117,11 @@ def check_aws_athena_access():
 
 def requires_aws_athena(func):
     """Pytest decorator that skips test if AWS Athena access is not available."""
-    return pytest.mark.skipif(
-        not check_aws_athena_access(), reason='AWS Athena access not available (no credentials or permissions)'
-    )(func)
+    return pytest.mark.skipif(DISABLE_ATHENA_TESTS, reason='AWS Athena access is disabled via environment variable.')(
+        pytest.mark.skipif(
+            not check_aws_athena_access(), reason='AWS Athena access not available (no credentials or permissions)'
+        )(func)
+    )
 
 
 @pytest.fixture

From 0a577d31a7804479e5e7af91b66828ab1f179f96 Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Mon, 27 Oct 2025 11:35:52 +0100
Subject: [PATCH 72/74] Added test decorator

---
 tests/filter_warc/test_command.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tests/filter_warc/test_command.py b/tests/filter_warc/test_command.py
index 10e3b8b..df5a2ea 100644
--- a/tests/filter_warc/test_command.py
+++ b/tests/filter_warc/test_command.py
@@ -7,7 +7,7 @@
 import pytest
 from warcio.archiveiterator import ArchiveIterator
 
-from tests.conftest import requires_aws_s3, TEST_DATA_PATH
+from tests.conftest import requires_aws_athena, requires_aws_s3, TEST_DATA_PATH
 
 
 fixture_path = TEST_DATA_PATH / 'warc_by_cdx'
@@ -276,6 +276,7 @@ def test_metadata_paths_without_resource_records_paths():
     assert exc_info.match('Metadata paths are set but')
 
 
+@requires_aws_athena
 def test_cli_warc_by_athena(
     tmpdir,
     caplog,

From 6c316f7afc82734984e10f54f0eea59eb2841507 Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Mon, 27 Oct 2025 12:02:20 +0100
Subject: [PATCH 73/74] Refactored resource to metadata records

---
 .codecov.yml                           |  3 ++
 cdx_toolkit/filter_warc/args.py        |  9 +----
 cdx_toolkit/filter_warc/command.py     | 22 ++---------
 cdx_toolkit/filter_warc/warc_filter.py | 50 +++++++++++------------
 cdx_toolkit/filter_warc/warc_utils.py  | 50 +++++------------------
 tests/filter_warc/test_command.py      | 55 +++++++-------------------
 tests/filter_warc/test_warc_filter.py  | 12 +++---
 tests/filter_warc/test_warc_utils.py   | 28 ++-----------
 8 files changed, 64 insertions(+), 165 deletions(-)
 create mode 100644 .codecov.yml

diff --git a/.codecov.yml b/.codecov.yml
new file mode 100644
index 0000000..b3ffdf1
--- /dev/null
+++ b/.codecov.yml
@@ -0,0 +1,3 @@
+coverage:
+  ignore:
+    - "cdx_toolkit/filter_warc/athena_job_generator.py"  # Athena is disabled in CI
diff --git a/cdx_toolkit/filter_warc/args.py b/cdx_toolkit/filter_warc/args.py
index c1d87f5..7234d74 100644
--- a/cdx_toolkit/filter_warc/args.py
+++ b/cdx_toolkit/filter_warc/args.py
@@ -73,14 +73,9 @@ def add_warcer_by_cdx_args(parser: argparse.ArgumentParser):
         default='https://data.commoncrawl.org',
     )
     parser.add_argument(
-        '--write-paths-as-resource-records',  # --write-index-as-record
+        '--write-paths-as-metadata-records',
         nargs='*',
-        help='Paths to multiple files. File content is written to as a resource record to each the WARC file',
-    )
-    parser.add_argument(
-        '--write-paths-as-resource-records-metadata',
-        nargs='*',
-        help='Paths to multiple metadata files (JSON) for resource records from `--write-paths-as-resource-records`',
+        help='Paths to multiple files. File content is written to as a metadata record to each the WARC file',
     )
     parser.add_argument(
         '--parallel',
diff --git a/cdx_toolkit/filter_warc/command.py b/cdx_toolkit/filter_warc/command.py
index 614673f..1fd590e 100644
--- a/cdx_toolkit/filter_warc/command.py
+++ b/cdx_toolkit/filter_warc/command.py
@@ -20,23 +20,15 @@ def run_warcer_by_cdx(args, cmdline):
     Approach:
     - Iterate over one or more CDX files to extract capture object (file, offset, length)
     - Fetch WARC record based on capture object
-    - Write to new WARC file with metadata including resource record with index.
-    - The CDX resource record is written to the WARC directly before for response records that matches to the CDX.
+    - Write to new WARC file including metadata records with index.
+    - The CDX metadata record is written to the WARC directly before for response records that matches to the CDX.
     """
     logger.info('Filtering WARC files based on CDX')
 
     # Start timing
     start_time = time.time()
 
-    write_paths_as_resource_records = args.write_paths_as_resource_records
-    write_paths_as_resource_records_metadata = args.write_paths_as_resource_records_metadata
-
-    if write_paths_as_resource_records and write_paths_as_resource_records_metadata:
-        if len(write_paths_as_resource_records) != len(write_paths_as_resource_records_metadata):
-            raise ValueError('Number of paths to resource records must be equal to metadata paths.')
-
-    if not write_paths_as_resource_records and write_paths_as_resource_records_metadata:
-        raise ValueError('Metadata paths are set but resource records paths are missing.')
+    write_paths_as_metadata_records = args.write_paths_as_metadata_records
 
     if args.is_part_of:
         ispartof = args.is_part_of
@@ -58,11 +50,6 @@ def run_warcer_by_cdx(args, cmdline):
     if args.operator:
         info['operator'] = args.operator
 
-    # writer_kwargs = {}
-    # if 'size' in kwargs:
-    #     writer_kwargs['size'] = kwargs['size']
-    #     del kwargs['size']
-
     n_parallel = args.parallel
     log_every_n = args.log_every_n
     limit = 0 if args.limit is None else args.limit
@@ -93,8 +80,7 @@ def run_warcer_by_cdx(args, cmdline):
         prefix_path=prefix_path,
         writer_info=info,
         writer_subprefix=args.subprefix,
-        write_paths_as_resource_records=write_paths_as_resource_records,
-        write_paths_as_resource_records_metadata=write_paths_as_resource_records_metadata,
+        write_paths_as_metadata_records=write_paths_as_metadata_records,
         record_limit=limit,
         log_every_n=log_every_n,
         warc_download_prefix=args.warc_download_prefix,
diff --git a/cdx_toolkit/filter_warc/warc_filter.py b/cdx_toolkit/filter_warc/warc_filter.py
index b5781e6..c87601e 100644
--- a/cdx_toolkit/filter_warc/warc_filter.py
+++ b/cdx_toolkit/filter_warc/warc_filter.py
@@ -16,7 +16,7 @@
 from cdx_toolkit.filter_warc.cdx_utils import (
     iter_cdx_index_from_path,
 )
-from cdx_toolkit.filter_warc.warc_utils import get_bytes_from_warc_record, get_resource_record_from_path
+from cdx_toolkit.filter_warc.warc_utils import get_bytes_from_warc_record, get_metadata_record_from_path
 
 
 _STOP = object()
@@ -53,8 +53,7 @@ def __init__(
         athena_hostnames: Optional[List[str]] = None,
         athena_s3_output_location: Optional[str] = None,
         writer_subprefix: Optional[str] = None,
-        write_paths_as_resource_records: Optional[List[str]] = None,
-        write_paths_as_resource_records_metadata: Optional[List[str]] = None,
+        write_paths_as_metadata_records: Optional[List[str]] = None,
         record_limit: int = 0,
         log_every_n: int = 1000,
         warc_download_prefix: Optional[str] = None,
@@ -84,8 +83,7 @@ def __init__(
             prefix_path: Output path prefix for filtered WARC files.
             writer_info: Dictionary containing writer metadata.
             writer_subprefix: Optional subprefix for writer output paths.
-            write_paths_as_resource_records: Optional list of file paths to write as resource records.
-            write_paths_as_resource_records_metadata: Optional list of metadata paths for resource records.
+            write_paths_as_metadata_records: Optional list of file paths to write as metadata records.
             record_limit: Maximum number of records to process (0 for unlimited).
             log_every_n: Log progress every N records.
             warc_download_prefix: Optional prefix to prepend to WARC URLs.
@@ -112,8 +110,7 @@ def __init__(
         self.prefix_path = prefix_path
         self.writer_info = writer_info
         self.writer_subprefix = writer_subprefix
-        self.write_paths_as_resource_records = write_paths_as_resource_records
-        self.write_paths_as_resource_records_metadata = write_paths_as_resource_records_metadata
+        self.write_paths_as_metadata_records = write_paths_as_metadata_records
         self.record_limit = record_limit
         self.log_every_n = log_every_n
         self.warc_download_prefix = warc_download_prefix
@@ -542,33 +539,30 @@ async def read_warc_records(
 
         return {'reader_id': reader_id, 'stats': tracker.get_stats()}
 
-    async def write_resource_records(self, writer, warcinfo_id: str) -> int:
-        """Write WARC resource records based on paths"""
-        resource_records_size = 0
+    async def write_metadata_records(self, writer, warcinfo_id: str) -> int:
+        """Write WARC metadata records based on paths"""
+        records_size = 0
+        records_count = 0
 
-        logger.info(f'Writing {len(self.write_paths_as_resource_records)} resource records to WARC ... ')
+        logger.info(f'Writing {len(self.write_paths_as_metadata_records)} metadata records to WARC ... ')
 
-        # Resource records are written at the beginning the WARC file.
-        for i, resource_record_path in enumerate(self.write_paths_as_resource_records):
-            logger.info(f'Writing resource record from {resource_record_path} ...')
-            resource_record = get_resource_record_from_path(
+        # Metadata records are written at the beginning each WARC file.
+        for i, resource_record_path in enumerate(self.write_paths_as_metadata_records):
+            logger.info(f'Writing metadata record from {resource_record_path} ...')
+            record = get_metadata_record_from_path(
                 file_path=resource_record_path,
-                metadata_path=(
-                    self.write_paths_as_resource_records_metadata[i]
-                    if self.write_paths_as_resource_records_metadata
-                    else None
-                ),
                 warcinfo_id=warcinfo_id,
             )
-            record_data = get_bytes_from_warc_record(resource_record, warc_version=self.warc_version, gzip=self.gzip)
+            record_data = get_bytes_from_warc_record(record, warc_version=self.warc_version, gzip=self.gzip)
             await writer.write(record_data)
 
             # Keep track but do not rotate resource records
-            resource_records_size += len(record_data)
+            records_size += len(record_data)
+            records_count += 1
 
-        logger.info(f'Resource records added: {len(self.write_paths_as_resource_records)}')
+        logger.info(f'Metadata records added: {records_count}')
 
-        return resource_records_size
+        return records_size
 
     async def write_warc_records(
         self,
@@ -616,8 +610,8 @@ async def write_warc_records(
         counter = 0
 
         # Resource records
-        if self.write_paths_as_resource_records:
-            current_file_size += await self.write_resource_records(writer, warcinfo_id=warcinfo_id)
+        if self.write_paths_as_metadata_records:
+            current_file_size += await self.write_metadata_records(writer, warcinfo_id=warcinfo_id)
 
         # Response records
         try:
@@ -712,7 +706,7 @@ async def rotate_files(
             logger.info(f'Rotated to new WARC file sequence {current_file_sequence} due to size limit')
 
             # Resource records also to new files
-            if self.write_paths_as_resource_records:
-                current_file_size += await self.write_resource_records(writer, warcinfo_id=warcinfo_id)
+            if self.write_paths_as_metadata_records:
+                current_file_size += await self.write_metadata_records(writer, warcinfo_id=warcinfo_id)
 
         return writer, current_file_sequence, current_file_size
diff --git a/cdx_toolkit/filter_warc/warc_utils.py b/cdx_toolkit/filter_warc/warc_utils.py
index e7d4b80..3c76c3b 100644
--- a/cdx_toolkit/filter_warc/warc_utils.py
+++ b/cdx_toolkit/filter_warc/warc_utils.py
@@ -1,5 +1,4 @@
 from io import BytesIO
-import json
 import logging
 from pathlib import Path
 import fsspec
@@ -30,21 +29,13 @@ def get_bytes_from_warc_record(
     return buffer.getvalue()
 
 
-def get_resource_record_from_path(
+def get_metadata_record_from_path(
     file_path: Union[str, Path],
     warcinfo_id: str,
-    metadata_path: Optional[Union[str, Path]] = None,
 ) -> ArcWarcRecord:
-    """Build WARC resource record for file path and metdata path.
+    """Build WARC metadata record for file path.
 
-    The metadata file must be a valid JSON and can have the following fields:
-    - warc_content_type: str
-    - uri: str
-    - http_headers: dict
-    - warc_headers_dict: str
-
-    If uri is not provided as metadata, the file_path is used.
-    If warc_content_type is not provided as metadata, the type is guessed.
+    The `Content-Type` header is guessed.
     """
     # Cast to string
     file_path = str(file_path)
@@ -52,41 +43,18 @@ def get_resource_record_from_path(
     with fsspec.open(file_path, 'rb') as f:
         file_bytes = BytesIO(f.read())
 
-    if metadata_path:
-        # Load metadata from path
-        metadata_path = str(metadata_path)
-
-        if not metadata_path.endswith('.json'):
-            raise ValueError('Metadata must be provided JSON (file path ends with *.json)')
-
-        with fsspec.open(metadata_path) as f:
-            metadata = json.load(f)
-
-            warc_content_type = metadata.get('warc_content_type', None)
-            uri = metadata.get('uri', None)
-            http_headers = metadata.get('http_headers', None)
-            warc_headers_dict = metadata.get('warc_headers_dict', {})
-    else:
-        # Without metdata
-        warc_content_type = None
-        uri = None
-        http_headers = None
-        warc_headers_dict = {}
-
-    if warc_content_type is None:
-        warc_content_type = mimetypes.guess_type(file_path)[0]
-
-    if uri is None:
-        uri = file_path
+    warc_content_type = mimetypes.guess_type(file_path)[0]
+    warc_headers_dict = {
+    }
 
     # Set WARC-Warcinfo-ID
     warc_headers_dict['WARC-Warcinfo-ID'] = warcinfo_id
 
     return WARCWriter(None).create_warc_record(
-        uri=uri,
-        record_type='resource',
+        uri=None,
+        record_type='metadata',
         payload=file_bytes,
-        http_headers=http_headers,
+        http_headers=None,
         warc_content_type=warc_content_type,
         warc_headers_dict=warc_headers_dict,
     )
diff --git a/tests/filter_warc/test_command.py b/tests/filter_warc/test_command.py
index df5a2ea..fe96d9b 100644
--- a/tests/filter_warc/test_command.py
+++ b/tests/filter_warc/test_command.py
@@ -23,7 +23,7 @@ def assert_cli_warc_by_cdx(
 ):
     # test cli and check output
     index_path = fixture_path / 'filtered_CC-MAIN-2024-30_cdx-00187.gz'
-    resource_record_path = TEST_DATA_PATH / 'filter_cdx/whitelist_10_urls.txt'
+    metadata_record_path = TEST_DATA_PATH / 'filter_cdx/whitelist_10_urls.txt'
 
     base_prefix = str(base_prefix)
 
@@ -36,8 +36,8 @@ def assert_cli_warc_by_cdx(
             '--limit=10',
             'warc_by_cdx',
             f'--cdx-path={str(index_path)}',
-            '--write-paths-as-resource-records',
-            str(resource_record_path),
+            '--write-paths-as-metadata-records',
+            str(metadata_record_path),
             f'--prefix={base_prefix}/TEST_warc_by_index',
             '--creator=foo',
             '--operator=bob',
@@ -59,8 +59,8 @@ def assert_cli_warc_by_cdx(
     response_records = []
     response_contents = []
 
-    resource_record = None
-    resource_record_content = None
+    metadata_record = None
+    metadata_record_content = None
 
     with fsspec.open(warc_path, 'rb') as stream:
         for record in ArchiveIterator(stream):
@@ -71,9 +71,9 @@ def assert_cli_warc_by_cdx(
                 response_records.append(record)
                 response_contents.append(record.content_stream().read().decode('utf-8', errors='ignore'))
 
-            if record.rec_type == 'resource':
-                resource_record = record
-                resource_record_content = record.content_stream().read().decode('utf-8')
+            if record.rec_type == 'metadata':
+                metadata_record = record
+                metadata_record_content = record.content_stream().read().decode('utf-8')
 
     assert len(response_records) == 10, 'Invalid record count'
 
@@ -83,20 +83,20 @@ def assert_cli_warc_by_cdx(
     assert 'Catalogue en ligne Mission de France' in response_contents[0], 'Invalid response content'
     assert 'dojo/dijit/themes/tundra/tundra' in response_contents[9], 'Invalid response content'
 
-    assert resource_record is not None, 'Resource record not set'
+    assert metadata_record is not None, 'Metadata record not set'
 
-    assert resource_record_content[:10] == 'example.co', 'Invalid resource record'
+    assert metadata_record_content[:10] == 'example.co', 'Invalid metdata record'
 
     # Disabled due to OS-specific line endings
     # assert resource_record_content[-20:-1] == 'hr.fr/produit/t-837', 'Invalid resource record'
 
     # Calculate expected length based on the actual source file on current OS
-    with open(resource_record_path, 'rb') as f:
+    with open(metadata_record_path, 'rb') as f:
         expected_length = len(f.read())
 
-    assert resource_record.length == expected_length, (
-        f'Invalid resource record length {resource_record.length}, expected {expected_length} '
-        f'(computed from {resource_record_path} on current OS)'
+    assert metadata_record.length == expected_length, (
+        f'Invalid metadata record length {metadata_record.length}, expected {expected_length} '
+        f'(computed from {metadata_record_path} on current OS)'
     )
 
 
@@ -249,33 +249,6 @@ def test_warc_by_cdx_without_creator_operator(tmpdir):
     assert 'operator:' not in info_record
 
 
-def test_resource_records_paths_mismatch():
-    # Test if mismatch of number of paths for resource records and their metdata is raised.
-    with pytest.raises(ValueError) as exc_info:
-        main(
-            args=[
-                '-v',
-                'warc_by_cdx',
-                '--cdx-path=foo/bar',
-                '--write-paths-as-resource-records',
-                'resource1',
-                'resource2',
-                '--write-paths-as-resource-records-metadata',
-                'metadata2',
-            ]
-        )
-    assert exc_info.match('Number of paths to resource records')
-
-
-def test_metadata_paths_without_resource_records_paths():
-    # Test if error of missing resource records paths is raised.
-    with pytest.raises(ValueError) as exc_info:
-        main(
-            args=['-v', 'warc_by_cdx', '--cdx-path=foo/bar', '--write-paths-as-resource-records-metadata', 'metadata2']
-        )
-    assert exc_info.match('Metadata paths are set but')
-
-
 @requires_aws_athena
 def test_cli_warc_by_athena(
     tmpdir,
diff --git a/tests/filter_warc/test_warc_filter.py b/tests/filter_warc/test_warc_filter.py
index 5f5a833..7d8307b 100644
--- a/tests/filter_warc/test_warc_filter.py
+++ b/tests/filter_warc/test_warc_filter.py
@@ -80,7 +80,7 @@ async def run_test():
             prefix_path='/fake/prefix',
             writer_info={'writer_id': 1},
             max_file_size=1000,  # 1KB limit
-            write_paths_as_resource_records=None,  # No resource records
+            write_paths_as_metadata_records=None,  # No resource records
         )
 
         mock_writer = AsyncMock()
@@ -129,8 +129,8 @@ async def run_test():
     asyncio.run(run_test())
 
 
-def test_rotate_files_rotation_needed_with_resource_records():
-    """Test rotate_files when rotation is needed and resource records need to be written."""
+def test_rotate_files_rotation_needed_with_metadata_records():
+    """Test rotate_files when rotation is needed and metadata records need to be written."""
 
     async def run_test():
         warc_filter = WARCFilter(
@@ -138,7 +138,7 @@ async def run_test():
             prefix_path='/fake/prefix',
             writer_info={'writer_id': 1},
             max_file_size=1000,  # 1KB limit
-            write_paths_as_resource_records=['/fake/resource1.txt', '/fake/resource2.txt'],
+            write_paths_as_metadata_records=['/fake/resource1.txt', '/fake/resource2.txt'],
         )
 
         mock_writer = AsyncMock()
@@ -151,8 +151,8 @@ async def run_test():
         with patch('cdx_toolkit.filter_warc.warc_filter.create_new_writer_with_header') as mock_create:
             mock_create.return_value = (mock_new_writer, 150, 'warcinfo-123')
 
-            # Mock write_resource_records
-            with patch.object(warc_filter, 'write_resource_records', return_value=75) as mock_write_resources:
+            # Mock write_metadata_records
+            with patch.object(warc_filter, 'write_metadata_records', return_value=75) as mock_write_resources:
                 # Call rotate_files
                 result_writer, result_sequence, result_size = await warc_filter.rotate_files(
                     writer=mock_writer,
diff --git a/tests/filter_warc/test_warc_utils.py b/tests/filter_warc/test_warc_utils.py
index 9cda87b..827713d 100644
--- a/tests/filter_warc/test_warc_utils.py
+++ b/tests/filter_warc/test_warc_utils.py
@@ -1,33 +1,13 @@
-import pytest
-from cdx_toolkit.filter_warc.warc_utils import get_resource_record_from_path
+from cdx_toolkit.filter_warc.warc_utils import get_metadata_record_from_path
 from tests.conftest import TEST_DATA_PATH
 
 
-def test_get_resource_record_from_path():
-    resource_path = TEST_DATA_PATH / 'filter_cdx/whitelist_10_urls.txt'
-    record = get_resource_record_from_path(resource_path, warcinfo_id="abc123")
+def test_get_metadata_record_from_path():
+    file_path = TEST_DATA_PATH / 'filter_cdx/whitelist_10_urls.txt'
+    record = get_metadata_record_from_path(file_path, warcinfo_id="abc123")
 
     assert record.content_type == 'text/plain'
 
     record_headers = dict(record.rec_headers.headers)
-    assert record_headers['WARC-Target-URI'] == str(resource_path)
-    assert record_headers["WARC-Warcinfo-ID"] == "abc123"
-
-
-def test_get_resource_record_from_path_with_metadata():
-    resource_path = TEST_DATA_PATH / 'warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.gz'
-    metadata_path = TEST_DATA_PATH / 'warc_by_cdx/filtered_CC-MAIN-2024-30_cdx-00187.metadata.json'
-
-    record = get_resource_record_from_path(resource_path, metadata_path=metadata_path, warcinfo_id="abc123")
 
-    assert record.content_type == 'application/cdx'
-
-    record_headers = dict(record.rec_headers.headers)
-    assert record_headers['WARC-Target-URI'] == 'filter_cdx.cdx.gz'
     assert record_headers["WARC-Warcinfo-ID"] == "abc123"
-
-
-def test_get_resource_record_from_path_with_invalid_metadata_path():
-    with pytest.raises(ValueError):
-        resource_path = TEST_DATA_PATH / 'filter_cdx/whitelist_10_urls.txt'
-        get_resource_record_from_path(resource_path, metadata_path='invalid_metadata.xy', warcinfo_id="abc123")

From fa5dfaabc8f45da6e49c27e030f27b6b0e5ff513 Mon Sep 17 00:00:00 2001
From: malteos <git@i.mieo.de>
Date: Wed, 29 Oct 2025 14:47:49 +0100
Subject: [PATCH 74/74] fixed CDX paths resolution from S3

---
 cdx_toolkit/filter_warc/cdx_utils.py | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/cdx_toolkit/filter_warc/cdx_utils.py b/cdx_toolkit/filter_warc/cdx_utils.py
index d061be2..6b0c584 100644
--- a/cdx_toolkit/filter_warc/cdx_utils.py
+++ b/cdx_toolkit/filter_warc/cdx_utils.py
@@ -81,10 +81,17 @@ def get_cdx_paths(index_path: str, index_glob: Optional[str] = None) -> List[str
 
         # Fetch multiple indicies via glob
         full_glob = index_fs_path + index_glob
+        index_paths = sorted(index_fs.glob(full_glob))
 
-        logger.info('glob pattern from %s (%s)', full_glob, index_fs.protocol)
+        # Get the protocol - might be a string or list
+        protocol = index_fs.protocol
+        if isinstance(protocol, (list, tuple)):
+            protocol = protocol[0]  # Use the first protocol if multiple
 
-        index_paths = sorted(index_fs.glob(full_glob))
+        logger.info('glob pattern from %s (%s)', full_glob, protocol)
+
+        # Add protocol prefix
+        index_paths = [f"{protocol}://{path}" for path in index_paths]
 
         logger.info('glob pattern found %i index files in %s', len(index_paths), index_fs_path)