yt_dlp/extractor/mychannels.py

   1 from .common import InfoExtractor
   2
   3
   4 class MyChannelsIE(InfoExtractor):
   5     _VALID_URL = r'https?://(?:www\.)?mychannels\.com/.*(?P<id_type>video|production)_id=(?P<id>[0-9]+)'
   6     _TEST = {
   7         'url': 'https://mychannels.com/missholland/miss-holland?production_id=3416',
   8         'md5': 'b8993daad4262dd68d89d651c0c52c45',
   9         'info_dict': {
  10             'id': 'wUUDZZep6vQD',
  11             'ext': 'mp4',
  12             'title': 'Miss Holland joins VOTE LEAVE',
  13             'description': 'Miss Holland | #13 Not a potato',
  14             'uploader': 'Miss Holland',
  15         }
  16     }
  17
  18     def _real_extract(self, url):
  19         id_type, url_id = self._match_valid_url(url).groups()
  20         webpage = self._download_webpage(url, url_id)
  21         video_data = self._html_search_regex(r'<div([^>]+data-%s-id="%s"[^>]+)>' % (id_type, url_id), webpage, 'video data')
  22
  23         def extract_data_val(attr, fatal=False):
  24             return self._html_search_regex(r'data-%s\s*=\s*"([^"]+)"' % attr, video_data, attr, fatal=fatal)
  25         minoto_id = extract_data_val('minoto-id') or self._search_regex(r'/id/([a-zA-Z0-9]+)', extract_data_val('video-src', True), 'minoto id')
  26
  27         return {
  28             '_type': 'url_transparent',
  29             'url': 'minoto:%s' % minoto_id,
  30             'id': url_id,
  31             'title': extract_data_val('title', True),
  32             'description': extract_data_val('description'),
  33             'thumbnail': extract_data_val('image'),
  34             'uploader': extract_data_val('channel'),
  35         }