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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6
   7
   8 class CBSSportsIE(InfoExtractor):
   9     _VALID_URL = r'http://www\.cbssports\.com/video/player/(?P<section>[^/]+)/(?P<id>[^/]+)'
  10
  11     _TEST = {
  12         'url': 'http://www.cbssports.com/video/player/tennis/318462531970/0/us-open-flashbacks-1990s',
  13         'info_dict': {
  14             'id': '_d5_GbO8p1sT',
  15             'ext': 'flv',
  16             'title': 'US Open flashbacks: 1990s',
  17             'description': 'Bill Macatee relives the best moments in US Open history from the 1990s.',
  18         },
  19     }
  20
  21     def _real_extract(self, url):
  22         mobj = re.match(self._VALID_URL, url)
  23         section = mobj.group('section')
  24         video_id = mobj.group('id')
  25         all_videos = self._download_json(
  26             'http://www.cbssports.com/data/video/player/getVideos/%s?as=json' % section,
  27             video_id)
  28         # The json file contains the info of all the videos in the section
  29         video_info = next(v for v in all_videos if v['pcid'] == video_id)
  30         return self.url_result('theplatform:%s' % video_info['pid'], 'ThePlatform')