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

[youtube] Fix subtitles only being extracted from the first client 

Closes #547
This commit is contained in:
pukkandan 2021-07-23 09:37:15 +05:30
parent ad34b2951e
commit 3944e7af92
No known key found for this signature in database
GPG Key ID: 0F00D95A001F4698
1 changed files with 15 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
yt_dlp/extractor/youtube.py
View File

@ -2845,7 +2845,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'release_timestamp': live_starttime, 'release_timestamp': live_starttime,
} }
pctr = get_first(player_responses, ('captions', 'playerCaptionsTracklistRenderer'), expected_type=dict) pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
# Converted into dicts to remove duplicates
captions = {
sub.get('baseUrl'): sub
for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
translation_languages = {
lang.get('languageCode'): lang.get('languageName')
for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
subtitles = {} subtitles = {}
if pctr: if pctr:
def process_language(container, base_url, lang_code, sub_name, query): def process_language(container, base_url, lang_code, sub_name, query):
@ -2860,8 +2867,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'name': sub_name, 'name': sub_name,
}) })
for caption_track in (pctr.get('captionTracks') or []): for base_url, caption_track in captions.items():
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':
@ -2872,18 +2878,17 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
continue continue
process_language( process_language(
subtitles, base_url, lang_code, subtitles, base_url, lang_code,
try_get(caption_track, lambda x: x['name']['simpleText']), traverse_obj(caption_track, ('name', 'simpleText')),
{}) {})
continue continue
automatic_captions = {} automatic_captions = {}
for translation_language in (pctr.get('translationLanguages') or []): for trans_code, trans_name in translation_languages.items():
translation_language_code = translation_language.get('languageCode') if not trans_code:
if not translation_language_code:
continue continue
process_language( process_language(
automatic_captions, base_url, translation_language_code, automatic_captions, base_url, trans_code,
self._get_text(translation_language.get('languageName'), max_runs=1), self._get_text(trans_name, max_runs=1),
{'tlang': translation_language_code}) {'tlang': trans_code})
info['automatic_captions'] = automatic_captions info['automatic_captions'] = automatic_captions
info['subtitles'] = subtitles info['subtitles'] = subtitles