github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[extractor/youtube] Ignore incomplete data for comment threads by default (#7475)

Browse source 
For both `--ignore-errors` and `--ignore-errors only_download`. Pass `--no-ignore-errors` to not ignore.

Closes https://github.com/yt-dlp/yt-dlp/issues/7474

Authored by: coletdjnz
This commit is contained in:
coletdjnz 2023-07-03 10:47:10 +00:00 committed by GitHub
parent 8776349ef6
commit 4dc4d8473c
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 15 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

22
yt_dlp/extractor/youtube.py
View file

@ -3426,7 +3426,9 @@ def extract_thread(contents):
# Pinned comments may appear a second time in newest first sort # Pinned comments may appear a second time in newest first sort
# See: https://github.com/yt-dlp/yt-dlp/issues/6712 # See: https://github.com/yt-dlp/yt-dlp/issues/6712
continue continue
self.report_warning('Detected YouTube comments looping. Stopping comment extraction as we probably cannot get any more.') self.report_warning(
'Detected YouTube comments looping. Stopping comment extraction '
f'{"for this thread" if parent else ""} as we probably cannot get any more.')
yield yield
else: else:
tracker['seen_comment_ids'].add(comment['id']) tracker['seen_comment_ids'].add(comment['id'])
@ -3517,12 +3519,18 @@ def extract_thread(contents):
# Ignore incomplete data error for replies if retries didn't work. # 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. # This is to allow any other parent comments and comment threads to be downloaded.
# See: https://github.com/yt-dlp/yt-dlp/issues/4669 # 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: if 'incomplete data' in str(e).lower() and parent:
self.report_warning( if self.get_param('ignoreerrors') in (True, 'only_download'):
'Received incomplete data for a comment reply thread and retrying did not help. ' self.report_warning(
'Ignoring to let other comments be downloaded.') 'Received incomplete data for a comment reply thread and retrying did not help. '
else: 'Ignoring to let other comments be downloaded. Pass --no-ignore-errors to not ignore.')
raise return
else:
raise ExtractorError(
'Incomplete data received for comment reply thread. '
'Pass --ignore-errors to ignore and allow rest of comments to download.',
expected=True)
raise
is_forced_continuation = False is_forced_continuation = False
continuation = None continuation = None
for continuation_items in traverse_obj(response, continuation_items_path, expected_type=list, default=[]): for continuation_items in traverse_obj(response, continuation_items_path, expected_type=list, default=[]):