youtube_dl/extractor/tvp.py

   1 import json
   2 import re
   3
   4 from .common import InfoExtractor
   5
   6
   7 class TvpIE(InfoExtractor):
   8     IE_NAME = u'tvp.pl'
   9     _VALID_URL = r'https?://www\.tvp\.pl/.*?wideo/(?P<date>\d+)/(?P<id>\d+)'
  10
  11     _TEST = {
  12         u'url': u'http://www.tvp.pl/warszawa/magazyny/campusnews/wideo/31102013/12878238',
  13         u'md5': u'148408967a6a468953c0a75cbdaf0d7a',
  14         u'file': u'12878238.wmv',
  15         u'info_dict': {
  16             u'title': u'31.10.2013 - Odcinek 2',
  17             u'description': u'31.10.2013 - Odcinek 2',
  18         },
  19         u'skip': u'Download has to use same server IP as extraction. Therefore, a good (load-balancing) DNS resolver will make the download fail.'
  20     }
  21
  22     def _real_extract(self, url):
  23         mobj = re.match(self._VALID_URL, url)
  24         video_id = mobj.group('id')
  25         webpage = self._download_webpage(url, video_id)
  26         json_url = 'http://www.tvp.pl/pub/stat/videofileinfo?video_id=%s' % video_id
  27         json_params = self._download_webpage(
  28             json_url, video_id, u"Downloading video metadata")
  29
  30         params = json.loads(json_params)
  31         self.report_extraction(video_id)
  32         video_url = params['video_url']
  33
  34         title = self._og_search_title(webpage, fatal=True)
  35         return {
  36             'id': video_id,
  37             'title': title,
  38             'ext': 'wmv',
  39             'url': video_url,
  40             'description': self._og_search_description(webpage),
  41             'thumbnail': self._og_search_thumbnail(webpage),
  42         }