]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/muenchentv.py
Fix extraction from youtube.
[youtubedl] / youtube_dl / extractor / muenchentv.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import json
5
6 from .common import InfoExtractor
7 from ..utils import (
8 determine_ext,
9 int_or_none,
10 js_to_json,
11 )
12
13
14 class MuenchenTVIE(InfoExtractor):
15 _VALID_URL = r'https?://(?:www\.)?muenchen\.tv/livestream'
16 IE_DESC = 'münchen.tv'
17 _TEST = {
18 'url': 'http://www.muenchen.tv/livestream/',
19 'info_dict': {
20 'id': '5334',
21 'display_id': 'live',
22 'ext': 'mp4',
23 'title': 're:^münchen.tv-Livestream [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
24 'is_live': True,
25 'thumbnail': r're:^https?://.*\.jpg$'
26 },
27 'params': {
28 'skip_download': True,
29 }
30 }
31
32 def _real_extract(self, url):
33 display_id = 'live'
34 webpage = self._download_webpage(url, display_id)
35
36 title = self._live_title(self._og_search_title(webpage))
37
38 data_js = self._search_regex(
39 r'(?s)\nplaylist:\s*(\[.*?}\]),',
40 webpage, 'playlist configuration')
41 data_json = js_to_json(data_js)
42 data = json.loads(data_json)[0]
43
44 video_id = data['mediaid']
45 thumbnail = data.get('image')
46
47 formats = []
48 for format_num, s in enumerate(data['sources']):
49 ext = determine_ext(s['file'], None)
50 label_str = s.get('label')
51 if label_str is None:
52 label_str = '_%d' % format_num
53
54 if ext is None:
55 format_id = label_str
56 else:
57 format_id = '%s-%s' % (ext, label_str)
58
59 formats.append({
60 'url': s['file'],
61 'tbr': int_or_none(s.get('label')),
62 'ext': 'mp4',
63 'format_id': format_id,
64 'preference': -100 if '.smil' in s['file'] else 0,
65 })
66 self._sort_formats(formats)
67
68 return {
69 'id': video_id,
70 'display_id': display_id,
71 'title': title,
72 'formats': formats,
73 'is_live': True,
74 'thumbnail': thumbnail,
75 }