[cbs] Add support for colbertlateshow (Closes #5888)
[youtube-dl] / youtube_dl / extractor / cbs.py
1 from __future__ import unicode_literals
2
3 from .common import InfoExtractor
4
5
6 class CBSIE(InfoExtractor):
7     _VALID_URL = r'https?://(?:(?:www\.)?cbs\.com/shows/[^/]+/(?:video|artist)|colbertlateshow\.com/(?:video|podcasts))/(?P<id>[^/]+)/.*'
8
9     _TESTS = [{
10         'url': 'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
11         'info_dict': {
12             'id': '4JUVEwq3wUT7',
13             'ext': 'flv',
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!',
16             'duration': 1495,
17         },
18         'params': {
19             # rtmp download
20             'skip_download': True,
21         },
22         '_skip': 'Blocked outside the US',
23     }, {
24         'url': 'http://www.cbs.com/shows/liveonletterman/artist/221752/st-vincent/',
25         'info_dict': {
26             'id': 'WWF_5KqY3PK1',
27             'ext': 'flv',
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.',
30             'duration': 3221,
31         },
32         'params': {
33             # rtmp download
34             'skip_download': True,
35         },
36         '_skip': 'Blocked outside the US',
37     }, {
38         'url': 'http://colbertlateshow.com/video/8GmB0oY0McANFvp2aEffk9jZZZ2YyXxy/the-colbeard/',
39         'only_matching': True,
40     }, {
41         'url': 'http://colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/',
42         'only_matching': True,
43     }]
44
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)