Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/nba.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     remove_end,
   6     parse_duration,
   7 )
   8
   9
  10 class NBAIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?:nba/)?video(?P<id>/[^?]*?)/?(?:/index\.html)?(?:\?.*)?$'
  12     _TESTS = [{
  13         'url': 'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html',
  14         'md5': 'c0edcfc37607344e2ff8f13c378c88a4',
  15         'info_dict': {
  16             'id': '0021200253-okc-bkn-recap.nba',
  17             'ext': 'mp4',
  18             'title': 'Thunder vs. Nets',
  19             'description': 'Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.',
  20             'duration': 181,
  21         },
  22     }, {
  23         'url': 'http://www.nba.com/video/games/hornets/2014/12/05/0021400276-nyk-cha-play5.nba/',
  24         'only_matching': True,
  25     }]
  26
  27     def _real_extract(self, url):
  28         video_id = self._match_id(url)
  29         webpage = self._download_webpage(url, video_id)
  30
  31         video_url = 'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4'
  32
  33         shortened_video_id = video_id.rpartition('/')[2]
  34         title = remove_end(
  35             self._og_search_title(webpage, default=shortened_video_id), ' : NBA.com')
  36
  37         description = self._og_search_description(webpage)
  38         duration = parse_duration(
  39             self._html_search_meta('duration', webpage, 'duration'))
  40
  41         return {
  42             'id': shortened_video_id,
  43             'url': video_url,
  44             'title': title,
  45             'description': description,
  46             'duration': duration,
  47         }