]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/canalplus.py
debian/control: Add recommends on aria2 | wget | curl to use external downloaders.
[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 ExtractorError,
9 HEADRequest,
10 unified_strdate,
11 url_basename,
12 qualities,
13 )
14
15
16 class CanalplusIE(InfoExtractor):
17 IE_DESC = 'canalplus.fr, piwiplus.fr and d8.tv'
18 _VALID_URL = r'https?://(?:www\.(?P<site>canalplus\.fr|piwiplus\.fr|d8\.tv)/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))'
19 _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s'
20 _SITE_ID_MAP = {
21 'canalplus.fr': 'cplus',
22 'piwiplus.fr': 'teletoon',
23 'd8.tv': 'd8',
24 }
25
26 _TESTS = [{
27 'url': 'http://www.canalplus.fr/c-infos-documentaires/pid1830-c-zapping.html?vid=922470',
28 'md5': '3db39fb48b9685438ecf33a1078023e4',
29 'info_dict': {
30 'id': '922470',
31 'ext': 'flv',
32 'title': 'Zapping - 26/08/13',
33 'description': 'Le meilleur de toutes les chaînes, tous les jours.\nEmission du 26 août 2013',
34 'upload_date': '20130826',
35 },
36 }, {
37 'url': 'http://www.piwiplus.fr/videos-piwi/pid1405-le-labyrinthe-boing-super-ranger.html?vid=1108190',
38 'info_dict': {
39 'id': '1108190',
40 'ext': 'flv',
41 'title': 'Le labyrinthe - Boing super ranger',
42 'description': 'md5:4cea7a37153be42c1ba2c1d3064376ff',
43 'upload_date': '20140724',
44 },
45 'skip': 'Only works from France',
46 }, {
47 'url': 'http://www.d8.tv/d8-docs-mags/pid6589-d8-campagne-intime.html',
48 'info_dict': {
49 'id': '966289',
50 'ext': 'flv',
51 'title': 'Campagne intime - Documentaire exceptionnel',
52 'description': 'md5:d2643b799fb190846ae09c61e59a859f',
53 'upload_date': '20131108',
54 },
55 'skip': 'videos get deleted after a while',
56 }]
57
58 def _real_extract(self, url):
59 mobj = re.match(self._VALID_URL, url)
60 video_id = mobj.groupdict().get('id')
61
62 site_id = self._SITE_ID_MAP[mobj.group('site') or 'canal']
63
64 # Beware, some subclasses do not define an id group
65 display_id = url_basename(mobj.group('path'))
66
67 if video_id is None:
68 webpage = self._download_webpage(url, display_id)
69 video_id = self._search_regex(
70 r'<canal:player[^>]+?videoId="(\d+)"', webpage, 'video id')
71
72 info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)
73 doc = self._download_xml(info_url, video_id, 'Downloading video XML')
74
75 video_info = [video for video in doc if video.find('ID').text == video_id][0]
76 media = video_info.find('MEDIA')
77 infos = video_info.find('INFOS')
78
79 preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD', 'HLS', 'HDS'])
80
81 fmt_url = next(iter(media.find('VIDEOS'))).text
82 if '/geo' in fmt_url.lower():
83 response = self._request_webpage(
84 HEADRequest(fmt_url), video_id,
85 'Checking if the video is georestricted')
86 if '/blocage' in response.geturl():
87 raise ExtractorError(
88 'The video is not available in your country',
89 expected=True)
90
91 formats = []
92 for fmt in media.find('VIDEOS'):
93 format_url = fmt.text
94 if not format_url:
95 continue
96 format_id = fmt.tag
97 if format_id == 'HLS':
98 hls_formats = self._extract_m3u8_formats(format_url, video_id, 'flv')
99 for fmt in hls_formats:
100 fmt['preference'] = preference(format_id)
101 formats.extend(hls_formats)
102 elif format_id == 'HDS':
103 hds_formats = self._extract_f4m_formats(format_url + '?hdcore=2.11.3', video_id)
104 for fmt in hds_formats:
105 fmt['preference'] = preference(format_id)
106 formats.extend(hds_formats)
107 else:
108 formats.append({
109 'url': format_url,
110 'format_id': format_id,
111 'preference': preference(format_id),
112 })
113 self._sort_formats(formats)
114
115 return {
116 'id': video_id,
117 'display_id': display_id,
118 'title': '%s - %s' % (infos.find('TITRAGE/TITRE').text,
119 infos.find('TITRAGE/SOUS_TITRE').text),
120 'upload_date': unified_strdate(infos.find('PUBLICATION/DATE').text),
121 'thumbnail': media.find('IMAGES/GRAND').text,
122 'description': infos.find('DESCRIPTION').text,
123 'view_count': int(infos.find('NB_VUES').text),
124 'like_count': int(infos.find('NB_LIKES').text),
125 'comment_count': int(infos.find('NB_COMMENTS').text),
126 'formats': formats,
127 }