2 from __future__ import unicode_literals
6 from .common import InfoExtractor
7 from ..compat import compat_urllib_parse_urlparse
17 class CanalplusIE(InfoExtractor):
18 IE_DESC = 'canalplus.fr, piwiplus.fr and d8.tv'
23 (?:(?:www|m)\.)?canalplus\.fr|
24 (?:www\.)?piwiplus\.fr|
29 )/(?:(?:[^/]+/)*(?P<display_id>[^/?#&]+))?(?:\?.*\bvid=(?P<vid>\d+))?|
30 player\.canalplus\.fr/#/(?P<id>\d+)
34 _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s?format=json'
37 'piwiplus': 'teletoon',
45 'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1192814',
46 'md5': '41f438a4904f7664b91b4ed0dec969dc',
50 'title': "L'Année du Zapping 2014 - L'Année du Zapping 2014",
51 'description': "Toute l'année 2014 dans un Zapping exceptionnel !",
52 'upload_date': '20150105',
55 'url': 'http://www.piwiplus.fr/videos-piwi/pid1405-le-labyrinthe-boing-super-ranger.html?vid=1108190',
59 'title': 'Le labyrinthe - Boing super ranger',
60 'description': 'md5:4cea7a37153be42c1ba2c1d3064376ff',
61 'upload_date': '20140724',
63 'skip': 'Only works from France',
65 'url': 'http://www.d8.tv/d8-docs-mags/pid5198-d8-en-quete-d-actualite.html?vid=1390231',
69 'title': "Vacances pas chères : prix discount ou grosses dépenses ? - En quête d'actualité",
70 'description': 'md5:edb6cf1cb4a1e807b5dd089e1ac8bfc6',
71 'upload_date': '20160512',
74 'skip_download': True,
77 'url': 'http://www.itele.fr/chroniques/invite-bruce-toussaint/thierry-solere-nicolas-sarkozy-officialisera-sa-candidature-a-la-primaire-quand-il-le-voudra-167224',
81 'title': "L'invité de Bruce Toussaint du 07/06/2016 - ",
82 'description': 'md5:40ac7c9ad0feaeb6f605bad986f61324',
83 'upload_date': '20160607',
86 'skip_download': True,
89 'url': 'http://m.canalplus.fr/?vid=1398231',
90 'only_matching': True,
92 'url': 'http://www.d17.tv/emissions/pid8303-lolywood.html?vid=1397061',
93 'only_matching': True,
96 def _real_extract(self, url):
97 mobj = re.match(self._VALID_URL, url)
98 video_id = mobj.groupdict().get('id') or mobj.groupdict().get('vid')
100 site_id = self._SITE_ID_MAP[compat_urllib_parse_urlparse(url).netloc.rsplit('.', 2)[-2]]
102 # Beware, some subclasses do not define an id group
103 display_id = mobj.group('display_id') or video_id
106 webpage = self._download_webpage(url, display_id)
107 video_id = self._search_regex(
108 [r'<canal:player[^>]+?videoId=(["\'])(?P<id>\d+)', r'id=["\']canal_video_player(?P<id>\d+)'],
109 webpage, 'video id', group='id')
111 info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)
112 video_data = self._download_json(info_url, video_id, 'Downloading video JSON')
114 if isinstance(video_data, list):
115 video_data = [video for video in video_data if video.get('ID') == video_id][0]
116 media = video_data['MEDIA']
117 infos = video_data['INFOS']
119 preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD'])
121 fmt_url = next(iter(media.get('VIDEOS')))
122 if '/geo' in fmt_url.lower():
123 response = self._request_webpage(
124 HEADRequest(fmt_url), video_id,
125 'Checking if the video is georestricted')
126 if '/blocage' in response.geturl():
127 raise ExtractorError(
128 'The video is not available in your country',
132 for format_id, format_url in media['VIDEOS'].items():
135 if format_id == 'HLS':
136 formats.extend(self._extract_m3u8_formats(
137 format_url, video_id, 'mp4', 'm3u8_native', m3u8_id=format_id, fatal=False))
138 elif format_id == 'HDS':
139 formats.extend(self._extract_f4m_formats(
140 format_url + '?hdcore=2.11.3', video_id, f4m_id=format_id, fatal=False))
143 # the secret extracted ya function in http://player.canalplus.fr/common/js/canalPlayer.js
144 'url': format_url + '?secret=pqzerjlsmdkjfoiuerhsdlfknaes',
145 'format_id': format_id,
146 'preference': preference(format_id),
148 self._sort_formats(formats)
153 } for image_id, image_url in media.get('images', {}).items()]
155 titrage = infos['TITRAGE']
159 'display_id': display_id,
160 'title': '%s - %s' % (titrage['TITRE'],
161 titrage['SOUS_TITRE']),
162 'upload_date': unified_strdate(infos.get('PUBLICATION', {}).get('DATE')),
163 'thumbnails': thumbnails,
164 'description': infos.get('DESCRIPTION'),
165 'duration': int_or_none(infos.get('DURATION')),
166 'view_count': int_or_none(infos.get('NB_VUES')),
167 'like_count': int_or_none(infos.get('NB_LIKES')),
168 'comment_count': int_or_none(infos.get('NB_COMMENTS')),