Merge pull request #257 from bellingcat/standardise_parsedates

Standardise parse dates to get_datetime_from_str

src/auto_archiver/modules/generic_extractor/generic_extractor.py

@@ -13,6 +13,7 @@ from loguru import logger
 
 from auto_archiver.core.extractor import Extractor
 from auto_archiver.core import Metadata, Media
+from auto_archiver.utils import get_datetime_from_str
 from .dropin import GenericDropin
 
 
@@ -223,7 +224,7 @@ class GenericExtractor(Extractor):
             timestamp = datetime.datetime.fromtimestamp(timestamp, tz=datetime.timezone.utc).isoformat()
             result.set_timestamp(timestamp)
         if upload_date := video_data.pop("upload_date", None) and not result.get("upload_date"):
-            upload_date = datetime.datetime.strptime(upload_date, "%Y%m%d").replace(tzinfo=datetime.timezone.utc)
+            upload_date = get_datetime_from_str(upload_date, "%Y%m%d").replace(tzinfo=datetime.timezone.utc)
             result.set("upload_date", upload_date)
 
         # then clean away any keys we don't want

src/auto_archiver/modules/generic_extractor/twitter.py

@@ -1,13 +1,12 @@
 import re
 import mimetypes
 import json
-from datetime import datetime
 
 from loguru import logger
 from slugify import slugify
 
 from auto_archiver.core.metadata import Metadata, Media
-from auto_archiver.utils import url as UrlUtil
+from auto_archiver.utils import url as UrlUtil, get_datetime_from_str
 from auto_archiver.core.extractor import Extractor
 
 from .dropin import GenericDropin, InfoExtractor
@@ -38,7 +37,7 @@ class Twitter(GenericDropin):
         try:
             if not tweet.get("user") or not tweet.get("created_at"):
                 raise ValueError("Error retreiving post. Are you sure it exists?")
-            timestamp = datetime.strptime(tweet["created_at"], "%a %b %d %H:%M:%S %z %Y")
+            timestamp = get_datetime_from_str(tweet["created_at"], "%a %b %d %H:%M:%S %z %Y")
         except (ValueError, KeyError) as ex:
             logger.warning(f"Unable to parse tweet: {str(ex)}\nRetreived tweet data: {tweet}")
             return False

src/auto_archiver/modules/twitter_api_extractor/twitter_api_extractor.py

@@ -2,7 +2,6 @@ import json
 import re
 import mimetypes
 import requests
-from datetime import datetime
 
 from loguru import logger
 from pytwitter import Api
@@ -10,6 +9,7 @@ from slugify import slugify
 
 from auto_archiver.core import Extractor
 from auto_archiver.core import Metadata, Media
+from auto_archiver.utils import get_datetime_from_str
 
 
 class TwitterApiExtractor(Extractor):
@@ -91,7 +91,7 @@ class TwitterApiExtractor(Extractor):
 
         result = Metadata()
         result.set_title(tweet.data.text)
-        result.set_timestamp(datetime.strptime(tweet.data.created_at, "%Y-%m-%dT%H:%M:%S.%fZ"))
+        result.set_timestamp(get_datetime_from_str(tweet.data.created_at, "%Y-%m-%dT%H:%M:%S.%fZ"))
 
         urls = []
         if tweet.includes: