1 from __future__ import unicode_literals
3 from .common import InfoExtractor
6 class CBSIE(InfoExtractor):
7 _VALID_URL = r'https?://(?:(?:www\.)?cbs\.com/shows/[^/]+/(?:video|artist)|colbertlateshow\.com/(?:video|podcasts))/(?P<id>[^/]+)/.*'
10 'url': 'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
14 'title': 'Connect Chat feat. Garth Brooks',
15 'description': 'Connect with country music singer Garth Brooks, as he chats with fans on Wednesday November 27, 2013. Be sure to tune in to Garth Brooks: Live from Las Vegas, Friday November 29, at 9/8c on CBS!',
20 'skip_download': True,
22 '_skip': 'Blocked outside the US',
24 'url': 'http://www.cbs.com/shows/liveonletterman/artist/221752/st-vincent/',
28 'title': 'Live on Letterman - St. Vincent',
29 'description': 'Live On Letterman: St. Vincent in concert from New York\'s Ed Sullivan Theater on Tuesday, July 16, 2014.',
34 'skip_download': True,
36 '_skip': 'Blocked outside the US',
38 'url': 'http://colbertlateshow.com/video/8GmB0oY0McANFvp2aEffk9jZZZ2YyXxy/the-colbeard/',
39 'only_matching': True,
41 'url': 'http://colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/',
42 'only_matching': True,
45 def _real_extract(self, url):
46 video_id = self._match_id(url)
47 webpage = self._download_webpage(url, video_id)
48 real_id = self._search_regex(
49 [r"video\.settings\.pid\s*=\s*'([^']+)';", r"cbsplayer\.pid\s*=\s*'([^']+)';"],
50 webpage, 'real video ID')
51 return self.url_result('theplatform:%s' % real_id)