diff options
| author | coletdjnz <colethedj@protonmail.com> | 2021-07-15 11:24:42 +1200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2021-07-14 23:24:42 +0000 |
| commit | 49bd8c66d3d7b6038b62d091e2dec1d599fdb90a (patch) | |
| tree | 66a7dae303f55023165d2286381c39b436348442 | |
| parent | 182b6ae8a6b12ad49f2fa880f8db436f9a79a8ba (diff) | |
| download | hypervideo-pre-49bd8c66d3d7b6038b62d091e2dec1d599fdb90a.tar.lz hypervideo-pre-49bd8c66d3d7b6038b62d091e2dec1d599fdb90a.tar.xz hypervideo-pre-49bd8c66d3d7b6038b62d091e2dec1d599fdb90a.zip | |
[youtube:comments] Improve comment vote count parsing (fixes #506) (#508)
Authored by: colethedj
| -rw-r--r-- | yt_dlp/extractor/youtube.py | 6 |
1 files changed, 4 insertions, 2 deletions
diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index 1b4f3960b..a2abdc503 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -40,6 +40,7 @@ from ..utils import ( intlist_to_bytes, mimetype2ext, parse_codecs, + parse_count, parse_duration, qualities, remove_start, @@ -1992,12 +1993,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor): text = self._join_text_entries(comment_text_runs) or '' comment_time_text = try_get(comment_renderer, lambda x: x['publishedTimeText']['runs']) or [] time_text = self._join_text_entries(comment_time_text) + # note: timestamp is an estimate calculated from the current time and time_text timestamp = calendar.timegm(self.parse_time_text(time_text).timetuple()) author = try_get(comment_renderer, lambda x: x['authorText']['simpleText'], compat_str) author_id = try_get(comment_renderer, lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str) - votes = str_to_int(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'], - lambda x: x['likeCount']), compat_str)) or 0 + votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'], + lambda x: x['likeCount']), compat_str)) or 0 author_thumbnail = try_get(comment_renderer, lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str) |