yt_dlp/extractor/breitbart.py

   1 from .common import InfoExtractor
   2
   3
   4 class BreitBartIE(InfoExtractor):
   5     _VALID_URL = r'https?://(?:www\.)?breitbart\.com/videos/v/(?P<id>[^/?#]+)'
   6     _TESTS = [{
   7         'url': 'https://www.breitbart.com/videos/v/5cOz1yup/?pl=Ij6NDOji',
   8         'md5': '0aa6d1d6e183ac5ca09207fe49f17ade',
   9         'info_dict': {
  10             'id': '5cOz1yup',
  11             'ext': 'mp4',
  12             'title': 'Watch \u2013 Clyburn: Statues in Congress Have to Go Because they Are Honoring Slavery',
  13             'description': 'md5:bac35eb0256d1cb17f517f54c79404d5',
  14             'thumbnail': 'https://cdn.jwplayer.com/thumbs/5cOz1yup-1920.jpg',
  15             'age_limit': 0,
  16         },
  17     }, {
  18         'url': 'https://www.breitbart.com/videos/v/eaiZjVOn/',
  19         'only_matching': True,
  20     }]
  21
  22     def _real_extract(self, url):
  23         video_id = self._match_id(url)
  24         webpage = self._download_webpage(url, video_id)
  25
  26         formats = self._extract_m3u8_formats(f'https://cdn.jwplayer.com/manifests/{video_id}.m3u8', video_id, ext='mp4')
  27         return {
  28             'id': video_id,
  29             'title': self._generic_title('', webpage),
  30             'description': self._og_search_description(webpage),
  31             'thumbnail': self._og_search_thumbnail(webpage),
  32             'age_limit': self._rta_search(webpage),
  33             'formats': formats,
  34         }