[youtube] Fix extraction.
[youtube-dl] / youtube_dl / extractor / cbssports.py
1 from __future__ import unicode_literals
2
3 from .cbs import CBSBaseIE
4
5
6 class CBSSportsIE(CBSBaseIE):
7     _VALID_URL = r'https?://(?:www\.)?cbssports\.com/[^/]+/(?:video|news)/(?P<id>[^/?#&]+)'
8
9     _TESTS = [{
10         'url': 'https://www.cbssports.com/nba/video/donovan-mitchell-flashes-star-potential-in-game-2-victory-over-thunder/',
11         'info_dict': {
12             'id': '1214315075735',
13             'ext': 'mp4',
14             'title': 'Donovan Mitchell flashes star potential in Game 2 victory over Thunder',
15             'description': 'md5:df6f48622612c2d6bd2e295ddef58def',
16             'timestamp': 1524111457,
17             'upload_date': '20180419',
18             'uploader': 'CBSI-NEW',
19         },
20         'params': {
21             # m3u8 download
22             'skip_download': True,
23         }
24     }, {
25         'url': 'https://www.cbssports.com/nba/news/nba-playoffs-2018-watch-76ers-vs-heat-game-3-series-schedule-tv-channel-online-stream/',
26         'only_matching': True,
27     }]
28
29     def _extract_video_info(self, filter_query, video_id):
30         return self._extract_feed_info('dJ5BDC', 'VxxJg8Ymh8sE', filter_query, video_id)
31
32     def _real_extract(self, url):
33         display_id = self._match_id(url)
34         webpage = self._download_webpage(url, display_id)
35         video_id = self._search_regex(
36             [r'(?:=|%26)pcid%3D(\d+)', r'embedVideo(?:Container)?_(\d+)'],
37             webpage, 'video id')
38         return self._extract_video_info('byId=%s' % video_id, video_id)