]> git.bitcoin.ninja Git - youtube-dl/blob - youtube_dl/extractor/clubic.py
[dailymotion] Error spelling
[youtube-dl] / youtube_dl / extractor / clubic.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import json
5 import re
6
7 from .common import InfoExtractor
8 from ..utils import (
9     clean_html,
10     qualities,
11 )
12
13
14 class ClubicIE(InfoExtractor):
15     _VALID_URL = r'http://(?:www\.)?clubic\.com/video/(?:[^/]+/)*video.*-(?P<id>[0-9]+)\.html'
16
17     _TESTS = [{
18         'url': 'http://www.clubic.com/video/clubic-week/video-clubic-week-2-0-le-fbi-se-lance-dans-la-photo-d-identite-448474.html',
19         'md5': '1592b694ba586036efac1776b0b43cd3',
20         'info_dict': {
21             'id': '448474',
22             'ext': 'mp4',
23             'title': 'Clubic Week 2.0 : le FBI se lance dans la photo d\u0092identité',
24             'description': 're:Gueule de bois chez Nokia. Le constructeur a indiqué cette.*',
25             'thumbnail': 're:^http://img\.clubic\.com/.*\.jpg$',
26         }
27     }, {
28         'url': 'http://www.clubic.com/video/video-clubic-week-2-0-apple-iphone-6s-et-plus-mais-surtout-le-pencil-469792.html',
29         'only_matching': True,
30     }]
31
32     def _real_extract(self, url):
33         mobj = re.match(self._VALID_URL, url)
34         video_id = mobj.group('id')
35
36         player_url = 'http://player.m6web.fr/v1/player/clubic/%s.html' % video_id
37         player_page = self._download_webpage(player_url, video_id)
38
39         config_json = self._search_regex(
40             r'(?m)M6\.Player\.config\s*=\s*(\{.+?\});$', player_page,
41             'configuration')
42         config = json.loads(config_json)
43
44         video_info = config['videoInfo']
45         sources = config['sources']
46         quality_order = qualities(['sd', 'hq'])
47
48         formats = [{
49             'format_id': src['streamQuality'],
50             'url': src['src'],
51             'quality': quality_order(src['streamQuality']),
52         } for src in sources]
53         self._sort_formats(formats)
54
55         return {
56             'id': video_id,
57             'title': video_info['title'],
58             'formats': formats,
59             'description': clean_html(video_info.get('description')),
60             'thumbnail': config.get('poster'),
61         }