kumi/yt-dlp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[extractor/youtube] Ignore incomplete data error for comment replies (#5490)

Browse source 
When --ignore-errors is used.
Closes https://github.com/yt-dlp/yt-dlp/issues/4669
Authored by: coletdjnz
This commit is contained in:
Matthew 2022-11-10 19:35:22 +13:00 committed by GitHub
parent 0cf643b234
commit e72e48c53f
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 15 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
yt_dlp/extractor/youtube.py
View file

@ -3237,11 +3237,21 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
note_prefix = '%sDownloading comment%s API JSON page %d %s' % ( note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
' ' if parent else '', ' replies' if parent else '', ' ' if parent else '', ' replies' if parent else '',
page_num, comment_prog_str) page_num, comment_prog_str)
try:
response = self._extract_response( response = self._extract_response(
item_id=None, query=continuation, item_id=None, query=continuation,
ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix, ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None) check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
except ExtractorError as e:
# Ignore incomplete data error for replies if retries didn't work.
# This is to allow any other parent comments and comment threads to be downloaded.
# See: https://github.com/yt-dlp/yt-dlp/issues/4669
if 'incomplete data' in str(e).lower() and parent and self.get_param('ignoreerrors') is True:
self.report_warning(
'Received incomplete data for a comment reply thread and retrying did not help. '
'Ignoring to let other comments be downloaded.')
else:
raise
is_forced_continuation = False is_forced_continuation = False
continuation_contents = traverse_obj( continuation_contents = traverse_obj(
response, 'onResponseReceivedEndpoints', expected_type=list, default=[]) response, 'onResponseReceivedEndpoints', expected_type=list, default=[])