diff options
| author | coletdjnz <coletdjnz@protonmail.com> | 2023-07-03 10:47:10 +0000 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-07-03 10:47:10 +0000 |
| commit | 4dc4d8473c085900edc841c87c20041233d25b1f (patch) | |
| tree | a89683b6d0bb40792266b97dc2d5e34d892e403c | |
| parent | 8776349ef6b1f644584a92dfa00a05208a48edc4 (diff) | |
| download | hypervideo-pre-4dc4d8473c085900edc841c87c20041233d25b1f.tar.lz hypervideo-pre-4dc4d8473c085900edc841c87c20041233d25b1f.tar.xz hypervideo-pre-4dc4d8473c085900edc841c87c20041233d25b1f.zip | |
[extractor/youtube] Ignore incomplete data for comment threads by default (#7475)
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
| -rw-r--r-- | yt_dlp/extractor/youtube.py | 22 |
1 files changed, 15 insertions, 7 deletions
diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index 967914c0f..2c64f8e84 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -3426,7 +3426,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor): # Pinned comments may appear a second time in newest first sort # See: https://github.com/yt-dlp/yt-dlp/issues/6712 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 else: tracker['seen_comment_ids'].add(comment['id']) @@ -3517,12 +3519,18 @@ class YoutubeIE(YoutubeBaseInfoExtractor): # 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 + if 'incomplete data' in str(e).lower() and parent: + if self.get_param('ignoreerrors') in (True, 'only_download'): + self.report_warning( + 'Received incomplete data for a comment reply thread and retrying did not help. ' + 'Ignoring to let other comments be downloaded. Pass --no-ignore-errors to not ignore.') + 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 continuation = None for continuation_items in traverse_obj(response, continuation_items_path, expected_type=list, default=[]): |