fenix
/
yt-dlp
mirror of https://github.com/yt-dlp/yt-dlp.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

[youtube] multiple subtitles in same language 

Fixes: https://github.com/ytdl-org/youtube-dl/issues/21164
Related: #310, https://github.com/ytdl-org/youtube-dl/pull/26112
This commit is contained in:
pukkandan 2021-05-13 00:50:02 +05:30
parent fe346461ff
commit 120916dac2
No known key found for this signature in database
GPG Key ID: 0F00D95A001F4698
1 changed files with 9 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
yt_dlp/extractor/youtube.py
View File

@ -1308,6 +1308,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'url': 'WaOKSUlf4TM', 'url': 'WaOKSUlf4TM',
'only_matching': True 'only_matching': True
}, },
{
# multiple subtitles with same lang_code
'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
'only_matching': True,
},
] ]
@classmethod @classmethod
@ -2182,7 +2187,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
subtitles = {} subtitles = {}
if pctr: if pctr:
def process_language(container, base_url, lang_code, query): def process_language(container, base_url, lang_code, query):
lang_subs = [] lang_subs = container.setdefault(lang_code, [])
for fmt in self._SUBTITLE_FORMATS: for fmt in self._SUBTITLE_FORMATS:
query.update({ query.update({
'fmt': fmt, 'fmt': fmt,
@ -2191,14 +2196,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'ext': fmt, 'ext': fmt,
'url': update_url_query(base_url, query), 'url': update_url_query(base_url, query),
}) })
container[lang_code] = lang_subs
for caption_track in (pctr.get('captionTracks') or []): for caption_track in (pctr.get('captionTracks') or []):
base_url = caption_track.get('baseUrl') base_url = caption_track.get('baseUrl')
if not base_url: if not base_url:
continue continue
if caption_track.get('kind') != 'asr': if caption_track.get('kind') != 'asr':
lang_code = caption_track.get('languageCode') lang_code = (
remove_start(caption_track.get('vssId') or '', '.').replace('.', '-')
or caption_track.get('languageCode'))
if not lang_code: if not lang_code:
continue continue
process_language( process_language(