yt_dlp/extractor/bfi.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import extract_attributes
   5
   6
   7 class BFIPlayerIE(InfoExtractor):
   8     IE_NAME = 'bfi:player'
   9     _VALID_URL = r'https?://player\.bfi\.org\.uk/[^/]+/film/watch-(?P<id>[\w-]+)-online'
  10     _TEST = {
  11         'url': 'https://player.bfi.org.uk/free/film/watch-computer-doctor-1974-online',
  12         'md5': 'e8783ebd8e061ec4bc6e9501ed547de8',
  13         'info_dict': {
  14             'id': 'htNnhlZjE60C9VySkQEIBtU-cNV1Xx63',
  15             'ext': 'mp4',
  16             'title': 'Computer Doctor',
  17             'description': 'md5:fb6c240d40c4dbe40428bdd62f78203b',
  18         },
  19         'skip': 'BFI Player films cannot be played outside of the UK',
  20     }
  21
  22     def _real_extract(self, url):
  23         video_id = self._match_id(url)
  24         webpage = self._download_webpage(url, video_id)
  25         entries = []
  26         for player_el in re.findall(r'(?s)<[^>]+class="player"[^>]*>', webpage):
  27             player_attr = extract_attributes(player_el)
  28             ooyala_id = player_attr.get('data-video-id')
  29             if not ooyala_id:
  30                 continue
  31             entries.append(self.url_result(
  32                 'ooyala:' + ooyala_id, 'Ooyala',
  33                 ooyala_id, player_attr.get('data-label')))
  34         return self.playlist_result(entries)