nhyatt/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2025-04-04 14:10:13 -05:00
Code Issues Projects Releases Wiki Activity

[YouTube] Get subtitles/automatic captions from both web and API responses

Browse Source
This commit is contained in:
dirkf 2025-03-25 21:39:31 +00:00
parent da7223d4aa
commit 2239ee7965
1 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
youtube_dl/extractor/youtube.py
View File

@ -2136,7 +2136,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
video_details = merge_dicts(*traverse_obj( video_details = merge_dicts(*traverse_obj(
(player_response, api_player_response), (player_response, api_player_response),
(Ellipsis, 'videoDetails', T(dict)))) (Ellipsis, 'videoDetails', T(dict))))
player_response.update(api_player_response or {}) player_response.update(filter_dict(
api_player_response or {}, cndn=lambda k, _: k != 'captions'))
player_response['videoDetails'] = video_details player_response['videoDetails'] = video_details
def is_agegated(playability): def is_agegated(playability):
@ -2566,8 +2567,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
} }
pctr = traverse_obj( pctr = traverse_obj(
player_response, (player_response, api_player_response),
('captions', 'playerCaptionsTracklistRenderer', T(dict))) (Ellipsis, 'captions', 'playerCaptionsTracklistRenderer', T(dict)))
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 = []
@ -2584,20 +2585,19 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
def process_subtitles(): def process_subtitles():
subtitles = {} subtitles = {}
for caption_track in traverse_obj(pctr, ( for caption_track in traverse_obj(pctr, (
'captionTracks', lambda _, v: v.get('baseUrl'))): Ellipsis, 'captionTracks', lambda _, v: (
v.get('baseUrl') and v.get('languageCode')))):
base_url = self._yt_urljoin(caption_track['baseUrl']) base_url = self._yt_urljoin(caption_track['baseUrl'])
if not base_url: if not base_url:
continue continue
lang_code = caption_track['languageCode']
if caption_track.get('kind') != 'asr': if caption_track.get('kind') != 'asr':
lang_code = caption_track.get('languageCode')
if not lang_code:
continue
process_language( process_language(
subtitles, base_url, lang_code, {}) subtitles, base_url, lang_code, {})
continue continue
automatic_captions = {} automatic_captions = {}
for translation_language in traverse_obj(pctr, ( for translation_language in traverse_obj(pctr, (
'translationLanguages', lambda _, v: v.get('languageCode'))): Ellipsis, 'translationLanguages', lambda _, v: v.get('languageCode'))):
translation_language_code = translation_language['languageCode'] translation_language_code = translation_language['languageCode']
process_language( process_language(
automatic_captions, base_url, translation_language_code, automatic_captions, base_url, translation_language_code,