]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/nba.py
7e421610eb6f47054aa1ea1720fc4b2cb4404d49
[youtubedl] / youtube_dl / extractor / nba.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6
7
8 class NBAIE(InfoExtractor):
9 _VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*?)(?:/index\.html)?(?:\?.*)?$'
10 _TEST = {
11 'url': 'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html',
12 'file': u'0021200253-okc-bkn-recap.nba.mp4',
13 'md5': u'c0edcfc37607344e2ff8f13c378c88a4',
14 'info_dict': {
15 'description': 'Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.',
16 'title': 'Thunder vs. Nets',
17 },
18 }
19
20 def _real_extract(self, url):
21 mobj = re.match(self._VALID_URL, url)
22 video_id = mobj.group(1)
23
24 webpage = self._download_webpage(url, video_id)
25
26 video_url = 'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4'
27
28 shortened_video_id = video_id.rpartition('/')[2]
29 title = self._og_search_title(webpage, default=shortened_video_id).replace('NBA.com: ', '')
30
31 description = self._html_search_regex(r'<meta name="description" (?:content|value)="(.*?)" />', webpage, 'description', fatal=False)
32
33 return {
34 'id': shortened_video_id,
35 'url': video_url,
36 'ext': 'mp4',
37 'title': title,
38 'description': description,
39 }