youtube_dl/extractor/thescene.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4
   5 from ..compat import compat_urlparse
   6
   7
   8 class TheSceneIE(InfoExtractor):
   9     _VALID_URL = r'https?://thescene\.com/watch/[^/]+/(?P<id>[^/#?]+)'
  10
  11     _TEST = {
  12         'url': 'https://thescene.com/watch/vogue/narciso-rodriguez-spring-2013-ready-to-wear',
  13         'info_dict': {
  14             'id': '520e8faac2b4c00e3c6e5f43',
  15             'ext': 'mp4',
  16             'title': 'Narciso Rodriguez: Spring 2013 Ready-to-Wear',
  17             'display_id': 'narciso-rodriguez-spring-2013-ready-to-wear',
  18             'duration': 127,
  19             'series': 'Style.com Fashion Shows',
  20             'season': 'Ready To Wear Spring 2013',
  21             'tags': list,
  22             'categories': list,
  23             'upload_date': '20120913',
  24             'timestamp': 1347512400,
  25             'uploader': 'vogue',
  26         },
  27     }
  28
  29     def _real_extract(self, url):
  30         display_id = self._match_id(url)
  31
  32         webpage = self._download_webpage(url, display_id)
  33
  34         player_url = compat_urlparse.urljoin(
  35             url,
  36             self._html_search_regex(
  37                 r'id=\'js-player-script\'[^>]+src=\'(.+?)\'', webpage, 'player url'))
  38
  39         return {
  40             '_type': 'url_transparent',
  41             'display_id': display_id,
  42             'url': player_url,
  43             'ie_key': 'CondeNast',
  44         }