2 from __future__ import unicode_literals
6 from .common import InfoExtractor
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|itele\.fr)/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))'
19 _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s'
21 'canalplus.fr': 'cplus',
22 'piwiplus.fr': 'teletoon',
28 'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1263092',
32 'title': 'Le Zapping - 13/05/15',
33 'description': 'md5:09738c0d06be4b5d06a0940edb0da73f',
34 'upload_date': '20150513',
37 'url': 'http://www.piwiplus.fr/videos-piwi/pid1405-le-labyrinthe-boing-super-ranger.html?vid=1108190',
41 'title': 'Le labyrinthe - Boing super ranger',
42 'description': 'md5:4cea7a37153be42c1ba2c1d3064376ff',
43 'upload_date': '20140724',
45 'skip': 'Only works from France',
47 'url': 'http://www.d8.tv/d8-docs-mags/pid6589-d8-campagne-intime.html',
51 'title': 'Campagne intime - Documentaire exceptionnel',
52 'description': 'md5:d2643b799fb190846ae09c61e59a859f',
53 'upload_date': '20131108',
55 'skip': 'videos get deleted after a while',
57 'url': 'http://www.itele.fr/france/video/aubervilliers-un-lycee-en-colere-111559',
61 'title': 'Aubervilliers : un lycée en colère - Le 11/02/2015 à 06h45',
62 'description': 'md5:8216206ec53426ea6321321f3b3c16db',
63 'upload_date': '20150211',
67 def _real_extract(self, url):
68 mobj = re.match(self._VALID_URL, url)
69 video_id = mobj.groupdict().get('id')
71 site_id = self._SITE_ID_MAP[mobj.group('site') or 'canal']
73 # Beware, some subclasses do not define an id group
74 display_id = url_basename(mobj.group('path'))
77 webpage = self._download_webpage(url, display_id)
78 video_id = self._search_regex(
79 r'<canal:player[^>]+?videoId="(\d+)"', webpage, 'video id')
81 info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)
82 doc = self._download_xml(info_url, video_id, 'Downloading video XML')
84 video_info = [video for video in doc if video.find('ID').text == video_id][0]
85 media = video_info.find('MEDIA')
86 infos = video_info.find('INFOS')
88 preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD', 'HLS', 'HDS'])
90 fmt_url = next(iter(media.find('VIDEOS'))).text
91 if '/geo' in fmt_url.lower():
92 response = self._request_webpage(
93 HEADRequest(fmt_url), video_id,
94 'Checking if the video is georestricted')
95 if '/blocage' in response.geturl():
97 'The video is not available in your country',
101 for fmt in media.find('VIDEOS'):
102 format_url = fmt.text
106 if format_id == 'HLS':
107 hls_formats = self._extract_m3u8_formats(format_url, video_id, 'flv')
108 for fmt in hls_formats:
109 fmt['preference'] = preference(format_id)
110 formats.extend(hls_formats)
111 elif format_id == 'HDS':
112 hds_formats = self._extract_f4m_formats(format_url + '?hdcore=2.11.3', video_id)
113 for fmt in hds_formats:
114 fmt['preference'] = preference(format_id)
115 formats.extend(hds_formats)
119 'format_id': format_id,
120 'preference': preference(format_id),
122 self._sort_formats(formats)
126 'display_id': display_id,
127 'title': '%s - %s' % (infos.find('TITRAGE/TITRE').text,
128 infos.find('TITRAGE/SOUS_TITRE').text),
129 'upload_date': unified_strdate(infos.find('PUBLICATION/DATE').text),
130 'thumbnail': media.find('IMAGES/GRAND').text,
131 'description': infos.find('DESCRIPTION').text,
132 'view_count': int(infos.find('NB_VUES').text),
133 'like_count': int(infos.find('NB_LIKES').text),
134 'comment_count': int(infos.find('NB_COMMENTS').text),