Merge pull request #18 from oleksis/master

Update youtube-dl 2020.12.12

Author: oleksis

youtube_dl/YoutubeDL.py

@@ -2410,7 +2410,7 @@ def _write_thumbnails(self, info_dict, filename):
             thumb_ext = determine_ext(t['url'], 'jpg')
             suffix = '_%s' % t['id'] if len(thumbnails) > 1 else ''
             thumb_display_id = '%s ' % t['id'] if len(thumbnails) > 1 else ''
-            t['filename'] = thumb_filename = os.path.splitext(filename)[0] + suffix + '.' + thumb_ext
+            t['filename'] = thumb_filename = replace_extension(filename + suffix, thumb_ext, info_dict.get('ext'))
 
             if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(thumb_filename)):
                 self.to_screen('[%s] %s: Thumbnail %sis already present' %

youtube_dl/extractor/amcnetworks.py

@@ -1,6 +1,8 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .theplatform import ThePlatformIE
 from ..utils import (
     int_or_none,
@@ -11,25 +13,22 @@
 
 
 class AMCNetworksIE(ThePlatformIE):
-    _VALID_URL = r'https?://(?:www\.)?(?:amc|bbcamerica|ifc|(?:we|sundance)tv)\.com/(?:movies|shows(?:/[^/]+)+)/(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://(?:www\.)?(?P<site>amc|bbcamerica|ifc|(?:we|sundance)tv)\.com/(?P<id>(?:movies|shows(?:/[^/]+)+)/[^/?#&]+)'
     _TESTS = [{
-        'url': 'http://www.ifc.com/shows/maron/season-04/episode-01/step-1',
-        'md5': '',
+        'url': 'https://www.bbcamerica.com/shows/the-graham-norton-show/videos/tina-feys-adorable-airline-themed-family-dinner--51631',
         'info_dict': {
-            'id': 's3MX01Nl4vPH',
+            'id': '4Lq1dzOnZGt0',
             'ext': 'mp4',
-            'title': 'Maron - Season 4 - Step 1',
-            'description': 'In denial about his current situation, Marc is reluctantly convinced by his friends to enter rehab. Starring Marc Maron and Constance Zimmer.',
-            'age_limit': 17,
-            'upload_date': '20160505',
-            'timestamp': 1462468831,
+            'title': "The Graham Norton Show - Season 28 - Tina Fey's Adorable Airline-Themed Family Dinner",
+            'description': "It turns out child stewardesses are very generous with the wine! All-new episodes of 'The Graham Norton Show' premiere Fridays at 11/10c on BBC America.",
+            'upload_date': '20201120',
+            'timestamp': 1605904350,
             'uploader': 'AMCN',
         },
         'params': {
             # m3u8 download
             'skip_download': True,
         },
-        'skip': 'Requires TV provider accounts',
     }, {
         'url': 'http://www.bbcamerica.com/shows/the-hunt/full-episodes/season-1/episode-01-the-hardest-challenge',
         'only_matching': True,
@@ -55,32 +54,33 @@ class AMCNetworksIE(ThePlatformIE):
         'url': 'https://www.sundancetv.com/shows/riviera/full-episodes/season-1/episode-01-episode-1',
         'only_matching': True,
     }]
+    _REQUESTOR_ID_MAP = {
+        'amc': 'AMC',
+        'bbcamerica': 'BBCA',
+        'ifc': 'IFC',
+        'sundancetv': 'SUNDANCE',
+        'wetv': 'WETV',
+    }
 
     def _real_extract(self, url):
-        display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
+        site, display_id = re.match(self._VALID_URL, url).groups()
+        requestor_id = self._REQUESTOR_ID_MAP[site]
+        properties = self._download_json(
+            'https://content-delivery-gw.svc.ds.amcn.com/api/v2/content/amcn/%s/url/%s' % (requestor_id.lower(), display_id),
+            display_id)['data']['properties']
         query = {
             'mbr': 'true',
             'manifest': 'm3u',
         }
-        media_url = self._search_regex(
-            r'window\.platformLinkURL\s*=\s*[\'"]([^\'"]+)',
-            webpage, 'media url')
-        theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
-            r'link\.theplatform\.com/s/([^?]+)',
-            media_url, 'theplatform_path'), display_id)
+        tp_path = 'M_UwQC/media/' + properties['videoPid']
+        media_url = 'https://link.theplatform.com/s/' + tp_path
+        theplatform_metadata = self._download_theplatform_metadata(tp_path, display_id)
         info = self._parse_theplatform_metadata(theplatform_metadata)
         video_id = theplatform_metadata['pid']
         title = theplatform_metadata['title']
         rating = try_get(
             theplatform_metadata, lambda x: x['ratings'][0]['rating'])
-        auth_required = self._search_regex(
-            r'window\.authRequired\s*=\s*(true|false);',
-            webpage, 'auth required')
-        if auth_required == 'true':
-            requestor_id = self._search_regex(
-                r'window\.requestor_id\s*=\s*[\'"]([^\'"]+)',
-                webpage, 'requestor id')
+        if properties.get('videoCategory') == 'TVE-Auth':
             resource = self._get_mvpd_resource(
                 requestor_id, title, video_id, rating)
             query['auth'] = self._extract_mvpd_auth(

youtube_dl/extractor/americastestkitchen.py

@@ -1,33 +1,33 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import (
     clean_html,
-    int_or_none,
-    js_to_json,
     try_get,
     unified_strdate,
 )
 
 
 class AmericasTestKitchenIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?americastestkitchen\.com/(?:episode|videos)/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:americastestkitchen|cooks(?:country|illustrated))\.com/(?P<resource_type>episode|videos)/(?P<id>\d+)'
     _TESTS = [{
         'url': 'https://www.americastestkitchen.com/episode/582-weeknight-japanese-suppers',
         'md5': 'b861c3e365ac38ad319cfd509c30577f',
         'info_dict': {
             'id': '5b400b9ee338f922cb06450c',
-            'title': 'Weeknight Japanese Suppers',
+            'title': 'Japanese Suppers',
             'ext': 'mp4',
-            'description': 'md5:3d0c1a44bb3b27607ce82652db25b4a8',
+            'description': 'md5:64e606bfee910627efc4b5f050de92b3',
             'thumbnail': r're:^https?://',
             'timestamp': 1523664000,
             'upload_date': '20180414',
-            'release_date': '20180414',
+            'release_date': '20180410',
             'series': "America's Test Kitchen",
             'season_number': 18,
-            'episode': 'Weeknight Japanese Suppers',
+            'episode': 'Japanese Suppers',
             'episode_number': 15,
         },
         'params': {
@@ -36,47 +36,31 @@ class AmericasTestKitchenIE(InfoExtractor):
     }, {
         'url': 'https://www.americastestkitchen.com/videos/3420-pan-seared-salmon',
         'only_matching': True,
+    }, {
+        'url': 'https://www.cookscountry.com/episode/564-when-only-chocolate-will-do',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.cooksillustrated.com/videos/4478-beef-wellington',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
+        resource_type, video_id = re.match(self._VALID_URL, url).groups()
+        is_episode = resource_type == 'episode'
+        if is_episode:
+            resource_type = 'episodes'
 
-        video_data = self._parse_json(
-            self._search_regex(
-                r'window\.__INITIAL_STATE__\s*=\s*({.+?})\s*;\s*</script>',
-                webpage, 'initial context'),
-            video_id, js_to_json)
-
-        ep_data = try_get(
-            video_data,
-            (lambda x: x['episodeDetail']['content']['data'],
-             lambda x: x['videoDetail']['content']['data']), dict)
-        ep_meta = ep_data.get('full_video', {})
-
-        zype_id = ep_data.get('zype_id') or ep_meta['zype_id']
-
-        title = ep_data.get('title') or ep_meta.get('title')
-        description = clean_html(ep_meta.get('episode_description') or ep_data.get(
-            'description') or ep_meta.get('description'))
-        thumbnail = try_get(ep_meta, lambda x: x['photo']['image_url'])
-        release_date = unified_strdate(ep_data.get('aired_at'))
-
-        season_number = int_or_none(ep_meta.get('season_number'))
-        episode = ep_meta.get('title')
-        episode_number = int_or_none(ep_meta.get('episode_number'))
+        resource = self._download_json(
+            'https://www.americastestkitchen.com/api/v6/%s/%s' % (resource_type, video_id), video_id)
+        video = resource['video'] if is_episode else resource
+        episode = resource if is_episode else resource.get('episode') or {}
 
         return {
             '_type': 'url_transparent',
-            'url': 'https://player.zype.com/embed/%s.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ' % zype_id,
+            'url': 'https://player.zype.com/embed/%s.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ' % video['zypeId'],
             'ie_key': 'Zype',
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'release_date': release_date,
-            'series': "America's Test Kitchen",
-            'season_number': season_number,
-            'episode': episode,
-            'episode_number': episode_number,
+            'description': clean_html(video.get('description')),
+            'release_date': unified_strdate(video.get('publishDate')),
+            'series': try_get(episode, lambda x: x['show']['title']),
+            'episode': episode.get('title'),
         }

youtube_dl/extractor/common.py

@@ -2517,9 +2517,9 @@ def _media_formats(src, cur_media_type, type_info={}):
         # https://www.ampproject.org/docs/reference/components/amp-video)
         # For dl8-* tags see https://delight-vr.com/documentation/dl8-video/
         _MEDIA_TAG_NAME_RE = r'(?:(?:amp|dl8(?:-live)?)-)?(video|audio)'
-        media_tags = [(media_tag, media_type, '')
-                      for media_tag, media_type
-                      in re.findall(r'(?s)(<%s[^>]*/>)' % _MEDIA_TAG_NAME_RE, webpage)]
+        media_tags = [(media_tag, media_tag_name, media_type, '')
+                      for media_tag, media_tag_name, media_type
+                      in re.findall(r'(?s)(<(%s)[^>]*/>)' % _MEDIA_TAG_NAME_RE, webpage)]
         media_tags.extend(re.findall(
             # We only allow video|audio followed by a whitespace or '>'.
             # Allowing more characters may end up in significant slow down (see

youtube_dl/extractor/extractors.py

@@ -91,10 +91,6 @@
     BBCCoUkPlaylistIE,
     BBCIE,
 )
-from .beampro import (
-    BeamProLiveIE,
-    BeamProVodIE,
-)
 from .beeg import BeegIE
 from .behindkink import BehindKinkIE
 from .bellmedia import BellMediaIE
@@ -534,7 +530,10 @@
     EHFTVIE,
     ITTFIE,
 )
-from .lbry import LBRYIE
+from .lbry import (
+    LBRYIE,
+    LBRYChannelIE,
+)
 from .lci import LCIIE
 from .lcp import (
     LcpPlayIE,
@@ -1047,12 +1046,6 @@
 from .slideshare import SlideshareIE
 from .slideslive import SlidesLiveIE
 from .slutload import SlutloadIE
-from .smotri import (
-    SmotriIE,
-    SmotriCommunityIE,
-    SmotriUserIE,
-    SmotriBroadcastIE,
-)
 from .snotr import SnotrIE
 from .sohu import SohuIE
 from .sonyliv import SonyLIVIE
@@ -1157,6 +1150,7 @@
     TeleQuebecSquatIE,
     TeleQuebecEmissionIE,
     TeleQuebecLiveIE,
+    TeleQuebecVideoIE,
 )
 from .teletask import TeleTaskIE
 from .telewebion import TelewebionIE