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

   1 import re
   2
   3 from .common import InfoExtractor
   4
   5
   6 class CBSIE(InfoExtractor):
   7     _VALID_URL = r'https?://(?:www\.)?cbs\.com/shows/[^/]+/video/(?P<id>[^/]+)/.*'
   8
   9     _TEST = {
  10         u'url': u'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
  11         u'file': u'4JUVEwq3wUT7.flv',
  12         u'info_dict': {
  13             u'title': u'Connect Chat feat. Garth Brooks',
  14             u'description': u'Connect with country music singer Garth Brooks, as he chats with fans on Wednesday November 27, 2013. Be sure to tune in to Garth Brooks: Live from Las Vegas, Friday November 29, at 9/8c on CBS!',
  15             u'duration': 1495,
  16         },
  17         u'params': {
  18             # rtmp download
  19             u'skip_download': True,
  20         },
  21     }
  22
  23     def _real_extract(self, url):
  24         mobj = re.match(self._VALID_URL, url)
  25         video_id = mobj.group('id')
  26         webpage = self._download_webpage(url, video_id)
  27         real_id = self._search_regex(
  28             r"video\.settings\.pid\s*=\s*'([^']+)';",
  29             webpage, u'real video ID')
  30         return self.url_result(u'theplatform:%s' % real_id)