youtube_dl/extractor/dfb.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6
   7
   8 class DFBIE(InfoExtractor):
   9     IE_NAME = 'tv.dfb.de'
  10     _VALID_URL = r'https?://tv\.dfb\.de/video/[^/]+/(?P<id>\d+)'
  11
  12     _TEST = {
  13         'url': 'http://tv.dfb.de/video/highlights-des-empfangs-in-berlin/9070/',
  14         # The md5 is different each time
  15         'info_dict': {
  16             'id': '9070',
  17             'ext': 'flv',
  18             'title': 'Highlights des Empfangs in Berlin',
  19             'upload_date': '20140716',
  20         },
  21     }
  22
  23     def _real_extract(self, url):
  24         mobj = re.match(self._VALID_URL, url)
  25         video_id = mobj.group('id')
  26
  27         webpage = self._download_webpage(url, video_id)
  28         player_info = self._download_xml(
  29             'http://tv.dfb.de/server/hd_video.php?play=%s' % video_id,
  30             video_id)
  31         video_info = player_info.find('video')
  32
  33         f4m_info = self._download_xml(self._proto_relative_url(video_info.find('url').text.strip()), video_id)
  34         token_el = f4m_info.find('token')
  35         manifest_url = token_el.attrib['url'] + '?' + 'hdnea=' + token_el.attrib['auth'] + '&hdcore=3.2.0'
  36
  37         return {
  38             'id': video_id,
  39             'title': video_info.find('title').text,
  40             'url': manifest_url,
  41             'ext': 'flv',
  42             'thumbnail': self._og_search_thumbnail(webpage),
  43             'upload_date': ''.join(video_info.find('time_date').text.split('.')[::-1]),
  44         }