Raphaël G. Git Repositories - youtubedl/blob - 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 ..compat import compat_urllib_parse_urlparse
   8 from ..utils import (
   9     ExtractorError,
  10     HEADRequest,
  11     unified_strdate,
  12     qualities,
  13     int_or_none,
  14 )
  15
  16
  17 class CanalplusIE(InfoExtractor):
  18     IE_DESC = 'canalplus.fr, piwiplus.fr and d8.tv'
  19     _VALID_URL = r'''(?x)
  20                         https?://
  21                             (?:
  22                                 (?:
  23                                     (?:(?:www|m)\.)?canalplus\.fr|
  24                                     (?:www\.)?piwiplus\.fr|
  25                                     (?:www\.)?d8\.tv|
  26                                     (?:www\.)?d17\.tv|
  27                                     (?:www\.)?itele\.fr
  28                                 )/(?:(?:[^/]+/)*(?P<display_id>[^/?#&]+))?(?:\?.*\bvid=(?P<vid>\d+))?|
  29                                 player\.canalplus\.fr/#/(?P<id>\d+)
  30                             )
  31
  32                     '''
  33     _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s?format=json'
  34     _SITE_ID_MAP = {
  35         'canalplus': 'cplus',
  36         'piwiplus': 'teletoon',
  37         'd8': 'd8',
  38         'd17': 'd17',
  39         'itele': 'itele',
  40     }
  41
  42     _TESTS = [{
  43         'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1192814',
  44         'md5': '41f438a4904f7664b91b4ed0dec969dc',
  45         'info_dict': {
  46             'id': '1192814',
  47             'ext': 'mp4',
  48             'title': "L'Année du Zapping 2014 - L'Année du Zapping 2014",
  49             'description': "Toute l'année 2014 dans un Zapping exceptionnel !",
  50             'upload_date': '20150105',
  51         },
  52     }, {
  53         'url': 'http://www.piwiplus.fr/videos-piwi/pid1405-le-labyrinthe-boing-super-ranger.html?vid=1108190',
  54         'info_dict': {
  55             'id': '1108190',
  56             'ext': 'flv',
  57             'title': 'Le labyrinthe - Boing super ranger',
  58             'description': 'md5:4cea7a37153be42c1ba2c1d3064376ff',
  59             'upload_date': '20140724',
  60         },
  61         'skip': 'Only works from France',
  62     }, {
  63         'url': 'http://www.d8.tv/d8-docs-mags/pid5198-d8-en-quete-d-actualite.html?vid=1390231',
  64         'info_dict': {
  65             'id': '1390231',
  66             'ext': 'mp4',
  67             'title': "Vacances pas chères : prix discount ou grosses dépenses ? - En quête d'actualité",
  68             'description': 'md5:edb6cf1cb4a1e807b5dd089e1ac8bfc6',
  69             'upload_date': '20160512',
  70         },
  71         'params': {
  72             'skip_download': True,
  73         },
  74     }, {
  75         'url': 'http://www.itele.fr/chroniques/invite-bruce-toussaint/thierry-solere-nicolas-sarkozy-officialisera-sa-candidature-a-la-primaire-quand-il-le-voudra-167224',
  76         'info_dict': {
  77             'id': '1398334',
  78             'ext': 'mp4',
  79             'title': "L'invité de Bruce Toussaint du 07/06/2016 - ",
  80             'description': 'md5:40ac7c9ad0feaeb6f605bad986f61324',
  81             'upload_date': '20160607',
  82         },
  83         'params': {
  84             'skip_download': True,
  85         },
  86     }, {
  87         'url': 'http://m.canalplus.fr/?vid=1398231',
  88         'only_matching': True,
  89     }, {
  90         'url': 'http://www.d17.tv/emissions/pid8303-lolywood.html?vid=1397061',
  91         'only_matching': True,
  92     }]
  93
  94     def _real_extract(self, url):
  95         mobj = re.match(self._VALID_URL, url)
  96         video_id = mobj.groupdict().get('id') or mobj.groupdict().get('vid')
  97
  98         site_id = self._SITE_ID_MAP[compat_urllib_parse_urlparse(url).netloc.rsplit('.', 2)[-2]]
  99
 100         # Beware, some subclasses do not define an id group
 101         display_id = mobj.group('display_id') or video_id
 102
 103         if video_id is None:
 104             webpage = self._download_webpage(url, display_id)
 105             video_id = self._search_regex(
 106                 [r'<canal:player[^>]+?videoId=(["\'])(?P<id>\d+)', r'id=["\']canal_video_player(?P<id>\d+)'],
 107                 webpage, 'video id', group='id')
 108
 109         info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)
 110         video_data = self._download_json(info_url, video_id, 'Downloading video JSON')
 111
 112         if isinstance(video_data, list):
 113             video_data = [video for video in video_data if video.get('ID') == video_id][0]
 114         media = video_data['MEDIA']
 115         infos = video_data['INFOS']
 116
 117         preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD'])
 118
 119         fmt_url = next(iter(media.get('VIDEOS')))
 120         if '/geo' in fmt_url.lower():
 121             response = self._request_webpage(
 122                 HEADRequest(fmt_url), video_id,
 123                 'Checking if the video is georestricted')
 124             if '/blocage' in response.geturl():
 125                 raise ExtractorError(
 126                     'The video is not available in your country',
 127                     expected=True)
 128
 129         formats = []
 130         for format_id, format_url in media['VIDEOS'].items():
 131             if not format_url:
 132                 continue
 133             if format_id == 'HLS':
 134                 formats.extend(self._extract_m3u8_formats(
 135                     format_url, video_id, 'mp4', 'm3u8_native', m3u8_id=format_id, fatal=False))
 136             elif format_id == 'HDS':
 137                 formats.extend(self._extract_f4m_formats(
 138                     format_url + '?hdcore=2.11.3', video_id, f4m_id=format_id, fatal=False))
 139             else:
 140                 formats.append({
 141                     # the secret extracted ya function in http://player.canalplus.fr/common/js/canalPlayer.js
 142                     'url': format_url + '?secret=pqzerjlsmdkjfoiuerhsdlfknaes',
 143                     'format_id': format_id,
 144                     'preference': preference(format_id),
 145                 })
 146         self._sort_formats(formats)
 147
 148         thumbnails = [{
 149             'id': image_id,
 150             'url': image_url,
 151         } for image_id, image_url in media.get('images', {}).items()]
 152
 153         titrage = infos['TITRAGE']
 154
 155         return {
 156             'id': video_id,
 157             'display_id': display_id,
 158             'title': '%s - %s' % (titrage['TITRE'],
 159                                   titrage['SOUS_TITRE']),
 160             'upload_date': unified_strdate(infos.get('PUBLICATION', {}).get('DATE')),
 161             'thumbnails': thumbnails,
 162             'description': infos.get('DESCRIPTION'),
 163             'duration': int_or_none(infos.get('DURATION')),
 164             'view_count': int_or_none(infos.get('NB_VUES')),
 165             'like_count': int_or_none(infos.get('NB_LIKES')),
 166             'comment_count': int_or_none(infos.get('NB_COMMENTS')),
 167             'formats': formats,
 168         }