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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6
   7
   8 class SyfyIE(InfoExtractor):
   9     _VALID_URL = r'https?://www\.syfy\.com/(?:videos/.+?vid:(?P<id>[0-9]+)|(?!videos)(?P<video_name>[^/]+)(?:$|[?#]))'
  10
  11     _TESTS = [{
  12         'url': 'http://www.syfy.com/videos/Robot%20Combat%20League/Behind%20the%20Scenes/vid:2631458',
  13         'info_dict': {
  14             'id': 'NmqMrGnXvmO1',
  15             'ext': 'flv',
  16             'title': 'George Lucas has Advice for his Daughter',
  17             'description': 'Listen to what insights George Lucas give his daughter Amanda.',
  18         },
  19         'add_ie': ['ThePlatform'],
  20     }, {
  21         'url': 'http://www.syfy.com/wilwheaton',
  22         'md5': '94dfa54ee3ccb63295b276da08c415f6',
  23         'info_dict': {
  24             'id': '4yoffOOXC767',
  25             'ext': 'flv',
  26             'title': 'The Wil Wheaton Project - Premiering May 27th at 10/9c.',
  27             'description': 'The Wil Wheaton Project premieres May 27th at 10/9c. Don\'t miss it.',
  28         },
  29         'add_ie': ['ThePlatform'],
  30         'skip': 'Blocked outside the US',
  31     }]
  32
  33     def _real_extract(self, url):
  34         mobj = re.match(self._VALID_URL, url)
  35         video_name = mobj.group('video_name')
  36         if video_name:
  37             generic_webpage = self._download_webpage(url, video_name)
  38             video_id = self._search_regex(
  39                 r'<iframe.*?class="video_iframe_page"\s+src="/_utils/video/thP_video_controller.php.*?_vid([0-9]+)">',
  40                 generic_webpage, 'video ID')
  41             url = 'http://www.syfy.com/videos/%s/%s/vid:%s' % (
  42                 video_name, video_name, video_id)
  43         else:
  44             video_id = mobj.group('id')
  45         webpage = self._download_webpage(url, video_id)
  46         return self.url_result(self._og_search_video_url(webpage))