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 from ..utils import (
   7     remove_end,
   8     parse_duration,
   9 )
  10
  11
  12 class NBAIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?:nba/)?video(?P<id>/[^?]*?)(?:/index\.html)?(?:\?.*)?$'
  14     _TEST = {
  15         'url': 'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html',
  16         'md5': 'c0edcfc37607344e2ff8f13c378c88a4',
  17         'info_dict': {
  18             'id': '0021200253-okc-bkn-recap.nba',
  19             'ext': 'mp4',
  20             'title': 'Thunder vs. Nets',
  21             'description': 'Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.',
  22             'duration': 181,
  23         },
  24     }
  25
  26     def _real_extract(self, url):
  27         mobj = re.match(self._VALID_URL, url)
  28         video_id = mobj.group('id')
  29
  30         webpage = self._download_webpage(url, video_id)
  31
  32         video_url = 'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4'
  33
  34         shortened_video_id = video_id.rpartition('/')[2]
  35         title = remove_end(
  36             self._og_search_title(webpage, default=shortened_video_id), ' : NBA.com')
  37
  38         description = self._og_search_description(webpage)
  39         duration = parse_duration(
  40             self._html_search_meta('duration', webpage, 'duration', fatal=False))
  41
  42
  43         return {
  44             'id': shortened_video_id,
  45             'url': video_url,
  46             'title': title,
  47             'description': description,
  48             'duration': duration,
  49         }