youtube_dl/extractor/aljazeera.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4
   5
   6 class AlJazeeraIE(InfoExtractor):
   7     _VALID_URL = r'http://www\.aljazeera\.com/programmes/.*?/(?P<id>[^/]+)\.html'
   8
   9     _TEST = {
  10         'url': 'http://www.aljazeera.com/programmes/the-slum/2014/08/deliverance-201482883754237240.html',
  11         'info_dict': {
  12             'id': '3792260579001',
  13             'ext': 'mp4',
  14             'title': 'The Slum - Episode 1: Deliverance',
  15             'description': 'As a birth attendant advocating for family planning, Remy is on the frontline of Tondo\'s battle with overcrowding.',
  16             'uploader': 'Al Jazeera English',
  17         },
  18         'add_ie': ['Brightcove'],
  19     }
  20
  21     def _real_extract(self, url):
  22         program_name = self._match_id(url)
  23         webpage = self._download_webpage(url, program_name)
  24         brightcove_id = self._search_regex(
  25             r'RenderPagesVideo\(\'(.+?)\'', webpage, 'brightcove id')
  26
  27         return {
  28             '_type': 'url',
  29             'url': (
  30                 'brightcove:'
  31                 'playerKey=AQ~~%2CAAAAmtVJIFk~%2CTVGOQ5ZTwJbeMWnq5d_H4MOM57xfzApc'
  32                 '&%40videoPlayer={0}'.format(brightcove_id)
  33             ),
  34             'ie_key': 'Brightcove',
  35         }