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'https?://(?:www\.)?aljazeera\.com/(?:programmes|video)/.*?/(?P<id>[^/]+)\.html'
   8
   9     _TESTS = [{
  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_id': '665003303001',
  17             'timestamp': 1411116829,
  18             'upload_date': '20140919',
  19         },
  20         'add_ie': ['BrightcoveNew'],
  21         'skip': 'Not accessible from Travis CI server',
  22     }, {
  23         'url': 'http://www.aljazeera.com/video/news/2017/05/sierra-leone-709-carat-diamond-auctioned-170511100111930.html',
  24         'only_matching': True,
  25     }]
  26     BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/665003303001/default_default/index.html?videoId=%s'
  27
  28     def _real_extract(self, url):
  29         program_name = self._match_id(url)
  30         webpage = self._download_webpage(url, program_name)
  31         brightcove_id = self._search_regex(
  32             r'RenderPagesVideo\(\'(.+?)\'', webpage, 'brightcove id')
  33         return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id)