[zoom] Extract transcripts as subtitles

This commit is contained in:
pukkandan 2021-06-06 17:09:09 +05:30
parent d3d8d8184a
commit eb0f9d6838
No known key found for this signature in database
GPG Key ID: 0F00D95A001F4698
1 changed files with 10 additions and 0 deletions

View File

@ -10,6 +10,7 @@ from ..utils import (
js_to_json, js_to_json,
parse_filesize, parse_filesize,
urlencode_postdata, urlencode_postdata,
urljoin,
) )
@ -55,10 +56,19 @@ class ZoomIE(InfoExtractor):
r'(?s)window\.__data__\s*=\s*({.+?});', r'(?s)window\.__data__\s*=\s*({.+?});',
webpage, 'data'), play_id, js_to_json) webpage, 'data'), play_id, js_to_json)
subtitles = {}
for _type in ('transcript', 'cc'):
if data.get('%sUrl' % _type):
subtitles[_type] = [{
'url': urljoin(base_url, data['%sUrl' % _type]),
'ext': 'vtt',
}]
return { return {
'id': play_id, 'id': play_id,
'title': data['topic'], 'title': data['topic'],
'url': data['viewMp4Url'], 'url': data['viewMp4Url'],
'subtitles': subtitles,
'width': int_or_none(data.get('viewResolvtionsWidth')), 'width': int_or_none(data.get('viewResolvtionsWidth')),
'height': int_or_none(data.get('viewResolvtionsHeight')), 'height': int_or_none(data.get('viewResolvtionsHeight')),
'http_headers': { 'http_headers': {