Add option to use email to get polite access

Openalex and crossref APIs provide polite access if email address is used along with API call
https://docs.openalex.org/how-to-use-the-api/rate-limits-and-authentication

Author: rohitgarud

asreviewcontrib/preprocess/update_data/base.py

@@ -45,6 +45,9 @@ def parse_metadata(retrieved_metadata):
 
         raise NotImplementedError
 
+    def _use_email(email):
+        """Use email to get polite access to updater API"""
+
 
 class BaseDOIUpdater(ABC):
     """Abstract class for doi updater finding missing dois"""
@@ -56,3 +59,6 @@ def retrieve_dois(input_data):
         """Retrieve missing dois"""
 
         raise NotImplementedError
+
+    def _use_email(email):
+        """Use email to get privileged access to updater API"""

asreviewcontrib/preprocess/update_data/crossref_doi_updater.py

@@ -13,6 +13,11 @@
 class CrossrefDOIUpdater(BaseDOIUpdater):
     def __init__(self):
         super(CrossrefDOIUpdater, self).__init__()
+        self.email = None
+
+    def _use_email(self, email):
+        self.email = email
+        # TODO: Make use of email in crossref API call
 
     def retrieve_dois(self, records_df: pd.DataFrame) -> pd.DataFrame:
         """Requests Crossref with title-year combination and returns DOI if

asreviewcontrib/preprocess/update_data/openalex_updater.py

@@ -1,4 +1,5 @@
 import pandas as pd
+import pyalex
 from asreviewcontrib.preprocess.config import OPENALEX_QUERY_LIMIT
 from asreviewcontrib.preprocess.update_data.base import BaseUpdater
 from pyalex import Works
@@ -14,6 +15,11 @@ class OpenAlexUpdater(BaseUpdater):
     def __init__(self):
         super(OpenAlexUpdater, self).__init__()
         self.db = None
+        self.email = None
+
+    def _use_email(self, email):
+        self.email = email
+        pyalex.config.email = email
 
     def retrieve_metadata(self, db, doi_list):
         """Retrive metadata for the records using doi
@@ -97,6 +103,3 @@ def parse_metadata(self, retrieved_metadata):
             parsed_data.append(metadata)
         parsed_data_df = pd.DataFrame(parsed_data)
         return parsed_data_df
-
-
-# TODO: Check if Lens.org api or database can be used freely