youtube_dl/extractor/aljazeera.py

   1 from .common import InfoExtractor
   2
   3
   4 class AlJazeeraIE(InfoExtractor):
   5     _VALID_URL = r'http://www\.aljazeera\.com/programmes/.*?/(?P<id>[^/]+)\.html'
   6
   7     _TEST = {
   8         'url': 'http://www.aljazeera.com/programmes/the-slum/2014/08/deliverance-201482883754237240.html',
   9         'info_dict': {
  10             'id': '3792260579001',
  11             'ext': 'mp4',
  12             'title': 'The Slum - Episode 1: Deliverance',
  13             'description': 'As a birth attendant advocating for family planning, Remy is on the frontline of Tondo\'s battle with overcrowding.',
  14             'uploader': 'Al Jazeera English',
  15         },
  16         'add_ie': ['Brightcove'],
  17     }
  18
  19     def _real_extract(self, url):
  20         program_name = self._match_id(url)
  21         webpage = self._download_webpage(url, program_name)
  22         brightcove_id = self._search_regex(
  23             r'RenderPagesVideo\(\'(.+?)\'', webpage, 'brightcove id')
  24
  25         return {
  26             '_type': 'url',
  27             'url': (
  28                 'brightcove:'
  29                 'playerKey=AQ~~%2CAAAAmtVJIFk~%2CTVGOQ5ZTwJbeMWnq5d_H4MOM57xfzApc'
  30                 '&%40videoPlayer={0}'.format(brightcove_id)
  31             ),
  32             'ie_key': 'Brightcove',
  33         }