Miroirs/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp synced 2025-01-15 03:41:33 +01:00
Code Issues Projects Releases Packages Wiki Activity

[Zoom] add intepreter audio formats

Browse source 
Use the options `-f "best+mergeall[vcodec=none]" --audio-multistreams` to merge all intepreter tracks alongside the main video
This commit is contained in:
Lucas Rademaker 2024-10-08 17:39:47 +05:45
parent 983c58fb7a
commit b901e4fb8a
1 changed files with 17 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

20
yt_dlp/extractor/zoom.py
View file

@ -86,7 +86,6 @@ class ZoomIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
base_url, url_type, video_id = self._match_valid_url(url).group('base_url', 'type', 'id') base_url, url_type, video_id = self._match_valid_url(url).group('base_url', 'type', 'id')
query = {}
if url_type == 'share': if url_type == 'share':
webpage = self._get_real_webpage(url, base_url, video_id, 'share') webpage = self._get_real_webpage(url, base_url, video_id, 'share')
@ -95,7 +94,6 @@ class ZoomIE(InfoExtractor):
f'{base_url}nws/recording/1.0/play/share-info/{meeting_id}', f'{base_url}nws/recording/1.0/play/share-info/{meeting_id}',
video_id, note='Downloading share info JSON')['result']['redirectUrl'] video_id, note='Downloading share info JSON')['result']['redirectUrl']
url = urljoin(base_url, redirect_path) url = urljoin(base_url, redirect_path)
query['continueMode'] = 'true'
webpage = self._get_real_webpage(url, base_url, video_id, 'play') webpage = self._get_real_webpage(url, base_url, video_id, 'play')
file_id = self._get_page_data(webpage, video_id)['fileId'] file_id = self._get_page_data(webpage, video_id)['fileId']
@ -104,10 +102,13 @@ class ZoomIE(InfoExtractor):
raise ExtractorError('Unable to extract file ID') raise ExtractorError('Unable to extract file ID')
data = self._download_json( data = self._download_json(
f'{base_url}nws/recording/1.0/play/info/{file_id}', video_id, query=query, f'{base_url}nws/recording/1.0/play/info/{file_id}', video_id, query={
'continueMode': 'true', # Makes this return value include interpreter audio information
},
note='Downloading play info JSON')['result'] note='Downloading play info JSON')['result']
subtitles = {} subtitles = {}
# XXX: Would be more appropriate to parse chapters separate from subtitles
for _type in ('transcript', 'cc', 'chapter'): for _type in ('transcript', 'cc', 'chapter'):
if data.get(f'{_type}Url'): if data.get(f'{_type}Url'):
subtitles[_type] = [{ subtitles[_type] = [{
@ -117,6 +118,19 @@ class ZoomIE(InfoExtractor):
formats = [] formats = []
if data.get('interpreterAudioList'):
for audio in data.get('interpreterAudioList'):
formats.append({
'format_note': f'Intepreter: {audio["languageText"]}',
'url': audio['audioUrl'],
'format_id': f'interpreter-{ audio["icon"].lower()}',
'ext': 'm4a',
# There doesn't seem to be an explicit field for a standardized language code,
# sometimes the `language` field may be more accurate than `icon`
'language': audio['icon'].lower(),
'vcodec': 'none',
})
if data.get('viewMp4Url'): if data.get('viewMp4Url'):
formats.append({ formats.append({
'format_note': 'Camera stream', 'format_note': 'Camera stream',