]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/canalplus.py
debian/changelog: Start new release.
[youtubedl] / youtube_dl / extractor / canalplus.py
1 # encoding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..utils import (
8 unified_strdate,
9 url_basename,
10 )
11
12
13 class CanalplusIE(InfoExtractor):
14 _VALID_URL = r'https?://(?:www\.canalplus\.fr/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))'
15 _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/cplus/%s'
16 IE_NAME = 'canalplus.fr'
17
18 _TEST = {
19 'url': 'http://www.canalplus.fr/c-infos-documentaires/pid1830-c-zapping.html?vid=922470',
20 'md5': '3db39fb48b9685438ecf33a1078023e4',
21 'info_dict': {
22 'id': '922470',
23 'ext': 'flv',
24 'title': 'Zapping - 26/08/13',
25 'description': 'Le meilleur de toutes les chaînes, tous les jours.\nEmission du 26 août 2013',
26 'upload_date': '20130826',
27 },
28 }
29
30 def _real_extract(self, url):
31 mobj = re.match(self._VALID_URL, url)
32 video_id = mobj.groupdict().get('id')
33
34 # Beware, some subclasses do not define an id group
35 display_id = url_basename(mobj.group('path'))
36
37 if video_id is None:
38 webpage = self._download_webpage(url, display_id)
39 video_id = self._search_regex(r'<canal:player videoId="(\d+)"', webpage, 'video id')
40
41 info_url = self._VIDEO_INFO_TEMPLATE % video_id
42 doc = self._download_xml(info_url, video_id, 'Downloading video XML')
43
44 video_info = [video for video in doc if video.find('ID').text == video_id][0]
45 media = video_info.find('MEDIA')
46 infos = video_info.find('INFOS')
47
48 preferences = ['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD', 'HLS', 'HDS']
49
50 formats = [
51 {
52 'url': fmt.text + '?hdcore=2.11.3' if fmt.tag == 'HDS' else fmt.text,
53 'format_id': fmt.tag,
54 'ext': 'mp4' if fmt.tag == 'HLS' else 'flv',
55 'preference': preferences.index(fmt.tag) if fmt.tag in preferences else -1,
56 } for fmt in media.find('VIDEOS') if fmt.text
57 ]
58 self._sort_formats(formats)
59
60 return {
61 'id': video_id,
62 'display_id': display_id,
63 'title': '%s - %s' % (infos.find('TITRAGE/TITRE').text,
64 infos.find('TITRAGE/SOUS_TITRE').text),
65 'upload_date': unified_strdate(infos.find('PUBLICATION/DATE').text),
66 'thumbnail': media.find('IMAGES/GRAND').text,
67 'description': infos.find('DESCRIPTION').text,
68 'view_count': int(infos.find('NB_VUES').text),
69 'like_count': int(infos.find('NB_LIKES').text),
70 'comment_count': int(infos.find('NB_COMMENTS').text),
71 'formats': formats,
72 }