youtube_dl/extractor/charlierose.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import remove_end
   5
   6
   7 class CharlieRoseIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?charlierose\.com/(?:video|episode)(?:s|/player)/(?P<id>\d+)'
   9     _TESTS = [{
  10         'url': 'https://charlierose.com/videos/27996',
  11         'md5': 'fda41d49e67d4ce7c2411fd2c4702e09',
  12         'info_dict': {
  13             'id': '27996',
  14             'ext': 'mp4',
  15             'title': 'Remembering Zaha Hadid',
  16             'thumbnail': r're:^https?://.*\.jpg\?\d+',
  17             'description': 'We revisit past conversations with Zaha Hadid, in memory of the world renowned Iraqi architect.',
  18             'subtitles': {
  19                 'en': [{
  20                     'ext': 'vtt',
  21                 }],
  22             },
  23         },
  24     }, {
  25         'url': 'https://charlierose.com/videos/27996',
  26         'only_matching': True,
  27     }, {
  28         'url': 'https://charlierose.com/episodes/30887?autoplay=true',
  29         'only_matching': True,
  30     }]
  31
  32     _PLAYER_BASE = 'https://charlierose.com/video/player/%s'
  33
  34     def _real_extract(self, url):
  35         video_id = self._match_id(url)
  36         webpage = self._download_webpage(self._PLAYER_BASE % video_id, video_id)
  37
  38         title = remove_end(self._og_search_title(webpage), ' - Charlie Rose')
  39
  40         info_dict = self._parse_html5_media_entries(
  41             self._PLAYER_BASE % video_id, webpage, video_id,
  42             m3u8_entry_protocol='m3u8_native')[0]
  43
  44         self._sort_formats(info_dict['formats'])
  45         self._remove_duplicate_formats(info_dict['formats'])
  46
  47         info_dict.update({
  48             'id': video_id,
  49             'title': title,
  50             'thumbnail': self._og_search_thumbnail(webpage),
  51             'description': self._og_search_description(webpage),
  52         })
  53
  54         return info_dict