yt_dlp/extractor/charlierose.py

   1 from .common import InfoExtractor
   2 from ..utils import remove_end
   3
   4
   5 class CharlieRoseIE(InfoExtractor):
   6     _VALID_URL = r'https?://(?:www\.)?charlierose\.com/(?:video|episode)(?:s|/player)/(?P<id>\d+)'
   7     _TESTS = [{
   8         'url': 'https://charlierose.com/videos/27996',
   9         'md5': 'fda41d49e67d4ce7c2411fd2c4702e09',
  10         'info_dict': {
  11             'id': '27996',
  12             'ext': 'mp4',
  13             'title': 'Remembering Zaha Hadid',
  14             'thumbnail': r're:^https?://.*\.jpg\?\d+',
  15             'description': 'We revisit past conversations with Zaha Hadid, in memory of the world renowned Iraqi architect.',
  16             'subtitles': {
  17                 'en': [{
  18                     'ext': 'vtt',
  19                 }],
  20             },
  21         },
  22     }, {
  23         'url': 'https://charlierose.com/videos/27996',
  24         'only_matching': True,
  25     }, {
  26         'url': 'https://charlierose.com/episodes/30887?autoplay=true',
  27         'only_matching': True,
  28     }]
  29
  30     _PLAYER_BASE = 'https://charlierose.com/video/player/%s'
  31
  32     def _real_extract(self, url):
  33         video_id = self._match_id(url)
  34         webpage = self._download_webpage(self._PLAYER_BASE % video_id, video_id)
  35
  36         title = remove_end(self._og_search_title(webpage), ' - Charlie Rose')
  37
  38         info_dict = self._parse_html5_media_entries(
  39             self._PLAYER_BASE % video_id, webpage, video_id,
  40             m3u8_entry_protocol='m3u8_native')[0]
  41         self._remove_duplicate_formats(info_dict['formats'])
  42
  43         info_dict.update({
  44             'id': video_id,
  45             'title': title,
  46             'thumbnail': self._og_search_thumbnail(webpage),
  47             'description': self._og_search_description(webpage),
  48         })
  49
  50         return info_dict