[youtube] Fix extraction.
[youtube-dl] / youtube_dl / extractor / radiode.py
1 from __future__ import unicode_literals
2
3 from .common import InfoExtractor
4
5
6 class RadioDeIE(InfoExtractor):
7     IE_NAME = 'radio.de'
8     _VALID_URL = r'https?://(?P<id>.+?)\.(?:radio\.(?:de|at|fr|pt|es|pl|it)|rad\.io)'
9     _TEST = {
10         'url': 'http://ndr2.radio.de/',
11         'info_dict': {
12             'id': 'ndr2',
13             'ext': 'mp3',
14             'title': 're:^NDR 2 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
15             'description': 'md5:591c49c702db1a33751625ebfb67f273',
16             'thumbnail': r're:^https?://.*\.png',
17             'is_live': True,
18         },
19         'params': {
20             'skip_download': True,
21         }
22     }
23
24     def _real_extract(self, url):
25         radio_id = self._match_id(url)
26         webpage = self._download_webpage(url, radio_id)
27         jscode = self._search_regex(
28             r"'components/station/stationService':\s*\{\s*'?station'?:\s*(\{.*?\s*\}),\n",
29             webpage, 'broadcast')
30
31         broadcast = self._parse_json(jscode, radio_id)
32         title = self._live_title(broadcast['name'])
33         description = broadcast.get('description') or broadcast.get('shortDescription')
34         thumbnail = broadcast.get('picture4Url') or broadcast.get('picture4TransUrl') or broadcast.get('logo100x100')
35
36         formats = [{
37             'url': stream['streamUrl'],
38             'ext': stream['streamContentFormat'].lower(),
39             'acodec': stream['streamContentFormat'],
40             'abr': stream['bitRate'],
41             'asr': stream['sampleRate']
42         } for stream in broadcast['streamUrls']]
43         self._sort_formats(formats)
44
45         return {
46             'id': radio_id,
47             'title': title,
48             'description': description,
49             'thumbnail': thumbnail,
50             'is_live': True,
51             'formats': formats,
52         }