yt_dlp/extractor/masters.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     traverse_obj,
   4     unified_strdate,
   5 )
   6
   7
   8 class MastersIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?masters\.com/en_US/watch/(?P<date>\d{4}-\d{2}-\d{2})/(?P<id>\d+)'
  10     _TESTS = [{
  11         'url': 'https://www.masters.com/en_US/watch/2022-04-07/16493755593805191/sungjae_im_thursday_interview_2022.html',
  12         'info_dict': {
  13             'id': '16493755593805191',
  14             'ext': 'mp4',
  15             'title': 'Sungjae Im: Thursday Interview 2022',
  16             'upload_date': '20220407',
  17             'thumbnail': r're:^https?://.*\.jpg$',
  18         },
  19     }]
  20
  21     def _real_extract(self, url):
  22         video_id, upload_date = self._match_valid_url(url).group('id', 'date')
  23         content_resp = self._download_json(
  24             f'https://www.masters.com/relatedcontent/rest/v2/masters_v1/en/content/masters_v1_{video_id}_en',
  25             video_id)
  26         formats, subtitles = self._extract_m3u8_formats_and_subtitles(traverse_obj(content_resp, ('media', 'm3u8')), video_id, 'mp4')
  27
  28         thumbnails = [{'id': name, 'url': url} for name, url in traverse_obj(content_resp, ('images', 0), default={}).items()]
  29
  30         return {
  31             'id': video_id,
  32             'title': content_resp.get('title'),
  33             'formats': formats,
  34             'subtitles': subtitles,
  35             'upload_date': unified_strdate(upload_date),
  36             'thumbnails': thumbnails,
  37         }