]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/ketnet.py
Prepare new release.
[youtubedl] / youtube_dl / extractor / ketnet.py
1 from __future__ import unicode_literals
2
3 from .common import InfoExtractor
4
5
6 class KetnetIE(InfoExtractor):
7 _VALID_URL = r'https?://(?:www\.)?ketnet\.be/(?:[^/]+/)*(?P<id>[^/?#&]+)'
8 _TESTS = [{
9 'url': 'https://www.ketnet.be/kijken/zomerse-filmpjes',
10 'md5': 'd907f7b1814ef0fa285c0475d9994ed7',
11 'info_dict': {
12 'id': 'zomerse-filmpjes',
13 'ext': 'mp4',
14 'title': 'Gluur mee op de filmset en op Pennenzakkenrock',
15 'description': 'Gluur mee met Ghost Rockers op de filmset',
16 'thumbnail': r're:^https?://.*\.jpg$',
17 }
18 }, {
19 'url': 'https://www.ketnet.be/kijken/karrewiet/uitzending-8-september-2016',
20 'only_matching': True,
21 }, {
22 'url': 'https://www.ketnet.be/achter-de-schermen/sien-repeteert-voor-stars-for-life',
23 'only_matching': True,
24 }, {
25 # mzsource, geo restricted to Belgium
26 'url': 'https://www.ketnet.be/kijken/nachtwacht/de-bermadoe',
27 'only_matching': True,
28 }]
29
30 def _real_extract(self, url):
31 video_id = self._match_id(url)
32
33 webpage = self._download_webpage(url, video_id)
34
35 config = self._parse_json(
36 self._search_regex(
37 r'(?s)playerConfig\s*=\s*({.+?})\s*;', webpage,
38 'player config'),
39 video_id)
40
41 title = config['title']
42
43 formats = []
44 for source_key in ('', 'mz'):
45 source = config.get('%ssource' % source_key)
46 if not isinstance(source, dict):
47 continue
48 for format_id, format_url in source.items():
49 if format_id == 'hls':
50 formats.extend(self._extract_m3u8_formats(
51 format_url, video_id, 'mp4',
52 entry_protocol='m3u8_native', m3u8_id=format_id,
53 fatal=False))
54 elif format_id == 'hds':
55 formats.extend(self._extract_f4m_formats(
56 format_url, video_id, f4m_id=format_id, fatal=False))
57 else:
58 formats.append({
59 'url': format_url,
60 'format_id': format_id,
61 })
62 self._sort_formats(formats)
63
64 return {
65 'id': video_id,
66 'title': title,
67 'description': config.get('description'),
68 'thumbnail': config.get('image'),
69 'series': config.get('program'),
70 'episode': config.get('episode'),
71 'formats': formats,
72 }