_ Git - youtube-dl/blob - youtube_dl/extractor/bfi.py

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