[ign] improve extraction and extract uploader_id
[youtube-dl] / 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         'info_dict': {
12             'id': 'schalke-04-0-2-real-madrid-2015-02',
13             'title': 'Schalke 04 0 – 2 Real Madrid',
14         },
15         'playlist_count': 3,
16     }, {
17         'url': 'http://footyroom.com/georgia-0-2-germany-2015-03/',
18         'info_dict': {
19             'id': 'georgia-0-2-germany-2015-03',
20             'title': 'Georgia 0 – 2 Germany',
21         },
22         'playlist_count': 1,
23     }]
24
25     def _real_extract(self, url):
26         playlist_id = self._match_id(url)
27
28         webpage = self._download_webpage(url, playlist_id)
29
30         playlist = self._parse_json(
31             self._search_regex(
32                 r'VideoSelector\.load\((\[.+?\])\);', webpage, 'video selector'),
33             playlist_id)
34
35         playlist_title = self._og_search_title(webpage)
36
37         entries = []
38         for video in playlist:
39             payload = video.get('payload')
40             if not payload:
41                 continue
42             playwire_url = self._search_regex(
43                 r'data-config="([^"]+)"', payload,
44                 'playwire url', default=None)
45             if playwire_url:
46                 entries.append(self.url_result(self._proto_relative_url(
47                     playwire_url, 'http:'), 'Playwire'))
48
49         return self.playlist_result(entries, playlist_id, playlist_title)