youtube_dl/extractor/freespeech.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4 import json
   5
   6 from .common import InfoExtractor
   7
   8
   9 class FreespeechIE(InfoExtractor):
  10     IE_NAME = 'freespeech.org'
  11     _VALID_URL = r'https?://(?:www\.)?freespeech\.org/video/(?P<title>.+)'
  12     _TEST = {
  13         'add_ie': ['Youtube'],
  14         'url': 'https://www.freespeech.org/video/obama-romney-campaign-colorado-ahead-debate-0',
  15         'info_dict': {
  16             'id': 'poKsVCZ64uU',
  17             'ext': 'webm',
  18             'title': 'Obama, Romney Campaign in Colorado Ahead of Debate',
  19             'description': 'Obama, Romney Campaign in Colorado Ahead of Debate',
  20             'uploader': 'freespeechtv',
  21             'uploader_id': 'freespeechtv',
  22             'upload_date': '20121002',
  23         },
  24     }
  25
  26     def _real_extract(self, url):
  27         mobj = re.match(self._VALID_URL, url)
  28         title = mobj.group('title')
  29         webpage = self._download_webpage(url, title)
  30         info_json = self._search_regex(r'jQuery.extend\(Drupal.settings, ({.*?})\);', webpage, 'info')
  31         info = json.loads(info_json)
  32
  33         return {
  34             '_type': 'url',
  35             'url': info['jw_player']['basic_video_node_player']['file'],
  36             'ie_key': 'Youtube',
  37         }