youtube_dl/extractor/parliamentliveuk.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4
   5
   6 class ParliamentLiveUKIE(InfoExtractor):
   7     IE_NAME = 'parliamentlive.tv'
   8     IE_DESC = 'UK parliament videos'
   9     _VALID_URL = r'(?i)https?://(?:www\.)?parliamentlive\.tv/Event/Index/(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
  10
  11     _TESTS = [{
  12         'url': 'http://parliamentlive.tv/Event/Index/c1e9d44d-fd6c-4263-b50f-97ed26cc998b',
  13         'info_dict': {
  14             'id': '1_af9nv9ym',
  15             'ext': 'mp4',
  16             'title': 'Home Affairs Committee',
  17             'uploader_id': 'FFMPEG-01',
  18             'timestamp': 1422696664,
  19             'upload_date': '20150131',
  20         },
  21     }, {
  22         'url': 'http://parliamentlive.tv/event/index/3f24936f-130f-40bf-9a5d-b3d6479da6a4',
  23         'only_matching': True,
  24     }]
  25
  26     def _real_extract(self, url):
  27         video_id = self._match_id(url)
  28         webpage = self._download_webpage(
  29             'http://vodplayer.parliamentlive.tv/?mid=' + video_id, video_id)
  30         widget_config = self._parse_json(self._search_regex(
  31             r'(?s)kWidgetConfig\s*=\s*({.+});',
  32             webpage, 'kaltura widget config'), video_id)
  33         kaltura_url = 'kaltura:%s:%s' % (
  34             widget_config['wid'][1:], widget_config['entry_id'])
  35         event_title = self._download_json(
  36             'http://parliamentlive.tv/Event/GetShareVideo/' + video_id, video_id)['event']['title']
  37         return {
  38             '_type': 'url_transparent',
  39             'title': event_title,
  40             'description': '',
  41             'url': kaltura_url,
  42             'ie_key': 'Kaltura',
  43         }