aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/cbs.py
blob: 89614a3c96abec850f8d6510a1bdab741fd935b1 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
from __future__ import unicode_literals

from .common import InfoExtractor


class CBSIE(InfoExtractor):
    _VALID_URL = r'https?://(?:(?:www\.)?cbs\.com/shows/[^/]+/(?:video|artist)|colbertlateshow\.com/(?:video|podcasts))/(?P<id>[^/]+)/.*'

    _TESTS = [{
        'url': 'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
        'info_dict': {
            'id': '4JUVEwq3wUT7',
            'ext': 'flv',
            'title': 'Connect Chat feat. Garth Brooks',
            '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!',
            'duration': 1495,
        },
        'params': {
            # rtmp download
            'skip_download': True,
        },
        '_skip': 'Blocked outside the US',
    }, {
        'url': 'http://www.cbs.com/shows/liveonletterman/artist/221752/st-vincent/',
        'info_dict': {
            'id': 'WWF_5KqY3PK1',
            'ext': 'flv',
            'title': 'Live on Letterman - St. Vincent',
            'description': 'Live On Letterman: St. Vincent in concert from New York\'s Ed Sullivan Theater on Tuesday, July 16, 2014.',
            'duration': 3221,
        },
        'params': {
            # rtmp download
            'skip_download': True,
        },
        '_skip': 'Blocked outside the US',
    }, {
        'url': 'http://colbertlateshow.com/video/8GmB0oY0McANFvp2aEffk9jZZZ2YyXxy/the-colbeard/',
        'only_matching': True,
    }, {
        'url': 'http://colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        video_id = self._match_id(url)
        webpage = self._download_webpage(url, video_id)
        real_id = self._search_regex(
            [r"video\.settings\.pid\s*=\s*'([^']+)';", r"cbsplayer\.pid\s*=\s*'([^']+)';"],
            webpage, 'real video ID')
        return self.url_result('theplatform:%s' % real_id)