[funk] Add extractor (closes #14464)
[ytdl] / youtube_dl / extractor / funk.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor
5 from .nexx import NexxIE
6 from ..utils import extract_attributes
7
8
9 class FunkIE(InfoExtractor):
10     _VALID_URL = r'https?://(?:www\.)?funk\.net/(?:mix|channel)/(?:[^/]+/)*(?P<id>[^?/#]+)'
11     _TESTS = [{
12         'url': 'https://www.funk.net/mix/59d65d935f8b160001828b5b/0/59d517e741dca10001252574/',
13         'md5': '4d40974481fa3475f8bccfd20c5361f8',
14         'info_dict': {
15             'id': '716599',
16             'ext': 'mp4',
17             'title': 'Neue Rechte Welle',
18             'description': 'md5:a30a53f740ffb6bfd535314c2cc5fb69',
19             'timestamp': 1501337639,
20             'upload_date': '20170729',
21         },
22         'params': {
23             'format': 'bestvideo',
24             'skip_download': True,
25         },
26     }, {
27         'url': 'https://www.funk.net/channel/59d5149841dca100012511e3/0/59d52049999264000182e79d/',
28         'only_matching': True,
29     }]
30
31     def _real_extract(self, url):
32         video_id = self._match_id(url)
33
34         webpage = self._download_webpage(url, video_id)
35
36         domain_id = NexxIE._extract_domain_id(webpage) or '741'
37         nexx_id = extract_attributes(self._search_regex(
38             r'(<div[^>]id=["\']mediaplayer-funk[^>]+>)',
39             webpage, 'media player'))['data-id']
40
41         return self.url_result(
42             'nexx:%s:%s' % (domain_id, nexx_id), ie=NexxIE.ie_key(),
43             video_id=nexx_id)