youtube_dl/extractor/footyroom.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6
   7 class FootyRoomIE(InfoExtractor):
   8     _VALID_URL = r'http://footyroom\.com/(?P<id>[^/]+)'
   9     _TESTS = [{
  10         'url': 'http://footyroom.com/schalke-04-0-2-real-madrid-2015-02/',
  11         'md5': 'f38d400d32f19724570040d5ce3a505f',
  12         'info_dict': {
  13             'id': 'schalke-04-0-2-real-madrid-2015-02',
  14             'title': 'Schalke 04 0 – 2 Real Madrid',
  15         },
  16         'playlist_count': 3,
  17     },
  18     {
  19         'url': 'http://footyroom.com/georgia-0-2-germany-2015-03/',
  20         'info_dict': {
  21             'id': 'georgia-0-2-germany-2015-03',
  22             'title': 'Georgia 0 – 2 Germany',
  23         },
  24         'playlist_count': 1,
  25     },
  26
  27     ]
  28
  29     def _real_extract(self, url):
  30         playlist_id = self._match_id(url)
  31
  32         webpage = self._download_webpage(url, playlist_id)
  33
  34         playlist = self._parse_json(
  35             self._search_regex(
  36                 r'VideoSelector\.load\((\[.+?\])\);', webpage, 'video selector'),
  37             playlist_id)
  38
  39         playlist_title = self._og_search_title(webpage)
  40
  41         entries = []
  42         for video in playlist:
  43             payload = video.get('payload')
  44             if not payload:
  45                 continue
  46             playwire_url = self._search_regex(
  47                 r'data-config="([^"]+)"', payload,
  48                 'playwire url', default=None)
  49             if not playwire_url.startswith("http:"):
  50                 playwire_url = "http:" + playwire_url
  51             if playwire_url:
  52                 entries.append(self.url_result(playwire_url, 'Playwire'))
  53
  54         return self.playlist_result(entries, playlist_id, playlist_title)