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(?:s|/player)/(?P<id>\d+)'
   9     _TEST = {
  10         'url': 'https://charlierose.com/videos/27996',
  11         'info_dict': {
  12             'id': '27996',
  13             'ext': 'mp4',
  14             'title': 'Remembering Zaha Hadid',
  15             'thumbnail': 're:^https?://.*\.jpg\?\d+',
  16             'description': 'We revisit past conversations with Zaha Hadid, in memory of the world renowned Iraqi architect.',
  17         },
  18         'params': {
  19             # m3u8 download
  20             'skip_download': True,
  21         }
  22     }
  23
  24     _PLAYER_BASE = 'https://charlierose.com/video/player/%s'
  25
  26     def _real_extract(self, url):
  27         video_id = self._match_id(url)
  28         webpage = self._download_webpage(self._PLAYER_BASE % video_id, video_id)
  29
  30         title = remove_end(self._og_search_title(webpage), ' - Charlie Rose')
  31
  32         entries = self._parse_html5_media_entries(self._PLAYER_BASE % video_id, webpage, video_id)[0]
  33         formats = entries['formats']
  34
  35         self._sort_formats(formats)
  36         self._remove_duplicate_formats(formats)
  37
  38         return {
  39             'id': video_id,
  40             'title': title,
  41             'formats': formats,
  42             'thumbnail': self._og_search_thumbnail(webpage),
  43             'description': self._og_search_description(webpage),
  44             'subtitles': entries.get('subtitles'),
  45         }