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