Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/canalplus.py

   1 # coding: 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     dict_get,
  10     # ExtractorError,
  11     # HEADRequest,
  12     int_or_none,
  13     qualities,
  14     remove_end,
  15     unified_strdate,
  16 )
  17
  18
  19 class CanalplusIE(InfoExtractor):
  20     IE_DESC = 'canalplus.fr, piwiplus.fr and d8.tv'
  21     _VALID_URL = r'''(?x)
  22                         https?://
  23                             (?:
  24                                 (?:
  25                                     (?:(?:www|m)\.)?canalplus\.fr|
  26                                     (?:www\.)?piwiplus\.fr|
  27                                     (?:www\.)?d8\.tv|
  28                                     (?:www\.)?c8\.fr|
  29                                     (?:www\.)?d17\.tv|
  30                                     (?:(?:football|www)\.)?cstar\.fr|
  31                                     (?:www\.)?itele\.fr
  32                                 )/(?:(?:[^/]+/)*(?P<display_id>[^/?#&]+))?(?:\?.*\bvid=(?P<vid>\d+))?|
  33                                 player\.canalplus\.fr/#/(?P<id>\d+)
  34                             )
  35
  36                     '''
  37     _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s?format=json'
  38     _SITE_ID_MAP = {
  39         'canalplus': 'cplus',
  40         'piwiplus': 'teletoon',
  41         'd8': 'd8',
  42         'c8': 'd8',
  43         'd17': 'd17',
  44         'cstar': 'd17',
  45         'itele': 'itele',
  46     }
  47
  48     # Only works for direct mp4 URLs
  49     _GEO_COUNTRIES = ['FR']
  50
  51     _TESTS = [{
  52         'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1192814',
  53         'info_dict': {
  54             'id': '1405510',
  55             'display_id': 'pid1830-c-zapping',
  56             'ext': 'mp4',
  57             'title': 'Zapping - 02/07/2016',
  58             'description': 'Le meilleur de toutes les chaînes, tous les jours',
  59             'upload_date': '20160702',
  60         },
  61     }, {
  62         # geo restricted, bypassed
  63         'url': 'http://www.piwiplus.fr/videos-piwi/pid1405-le-labyrinthe-boing-super-ranger.html?vid=1108190',
  64         'info_dict': {
  65             'id': '1108190',
  66             'display_id': 'pid1405-le-labyrinthe-boing-super-ranger',
  67             'ext': 'mp4',
  68             'title': 'BOING SUPER RANGER - Ep : Le labyrinthe',
  69             'description': 'md5:4cea7a37153be42c1ba2c1d3064376ff',
  70             'upload_date': '20140724',
  71         },
  72         'expected_warnings': ['HTTP Error 403: Forbidden'],
  73     }, {
  74         # geo restricted, bypassed
  75         'url': 'http://www.c8.fr/c8-divertissement/ms-touche-pas-a-mon-poste/pid6318-videos-integrales.html?vid=1443684',
  76         'md5': 'bb6f9f343296ab7ebd88c97b660ecf8d',
  77         'info_dict': {
  78             'id': '1443684',
  79             'display_id': 'pid6318-videos-integrales',
  80             'ext': 'mp4',
  81             'title': 'Guess my iep ! - TPMP - 07/04/2017',
  82             'description': 'md5:6f005933f6e06760a9236d9b3b5f17fa',
  83             'upload_date': '20170407',
  84         },
  85         'expected_warnings': ['HTTP Error 403: Forbidden'],
  86     }, {
  87         'url': 'http://www.itele.fr/chroniques/invite-michael-darmon/rachida-dati-nicolas-sarkozy-est-le-plus-en-phase-avec-les-inquietudes-des-francais-171510',
  88         'info_dict': {
  89             'id': '1420176',
  90             'display_id': 'rachida-dati-nicolas-sarkozy-est-le-plus-en-phase-avec-les-inquietudes-des-francais-171510',
  91             'ext': 'mp4',
  92             'title': 'L\'invité de Michaël Darmon du 14/10/2016 - ',
  93             'description': 'Chaque matin du lundi au vendredi, Michaël Darmon reçoit un invité politique à 8h25.',
  94             'upload_date': '20161014',
  95         },
  96     }, {
  97         'url': 'http://football.cstar.fr/cstar-minisite-foot/pid7566-feminines-videos.html?vid=1416769',
  98         'info_dict': {
  99             'id': '1416769',
 100             'display_id': 'pid7566-feminines-videos',
 101             'ext': 'mp4',
 102             'title': 'France - Albanie : les temps forts de la soirée - 20/09/2016',
 103             'description': 'md5:c3f30f2aaac294c1c969b3294de6904e',
 104             'upload_date': '20160921',
 105         },
 106         'params': {
 107             'skip_download': True,
 108         },
 109     }, {
 110         'url': 'http://m.canalplus.fr/?vid=1398231',
 111         'only_matching': True,
 112     }, {
 113         'url': 'http://www.d17.tv/emissions/pid8303-lolywood.html?vid=1397061',
 114         'only_matching': True,
 115     }]
 116
 117     def _real_extract(self, url):
 118         mobj = re.match(self._VALID_URL, url)
 119
 120         site_id = self._SITE_ID_MAP[compat_urllib_parse_urlparse(url).netloc.rsplit('.', 2)[-2]]
 121
 122         # Beware, some subclasses do not define an id group
 123         display_id = remove_end(dict_get(mobj.groupdict(), ('display_id', 'id', 'vid')), '.html')
 124
 125         webpage = self._download_webpage(url, display_id)
 126         video_id = self._search_regex(
 127             [r'<canal:player[^>]+?videoId=(["\'])(?P<id>\d+)',
 128              r'id=["\']canal_video_player(?P<id>\d+)',
 129              r'data-video=["\'](?P<id>\d+)'],
 130             webpage, 'video id', default=mobj.group('vid'), group='id')
 131
 132         info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)
 133         video_data = self._download_json(info_url, video_id, 'Downloading video JSON')
 134
 135         if isinstance(video_data, list):
 136             video_data = [video for video in video_data if video.get('ID') == video_id][0]
 137         media = video_data['MEDIA']
 138         infos = video_data['INFOS']
 139
 140         preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD'])
 141
 142         # _, fmt_url = next(iter(media['VIDEOS'].items()))
 143         # if '/geo' in fmt_url.lower():
 144         #     response = self._request_webpage(
 145         #         HEADRequest(fmt_url), video_id,
 146         #         'Checking if the video is georestricted')
 147         #     if '/blocage' in response.geturl():
 148         #         raise ExtractorError(
 149         #             'The video is not available in your country',
 150         #             expected=True)
 151
 152         formats = []
 153         for format_id, format_url in media['VIDEOS'].items():
 154             if not format_url:
 155                 continue
 156             if format_id == 'HLS':
 157                 formats.extend(self._extract_m3u8_formats(
 158                     format_url, video_id, 'mp4', 'm3u8_native', m3u8_id=format_id, fatal=False))
 159             elif format_id == 'HDS':
 160                 formats.extend(self._extract_f4m_formats(
 161                     format_url + '?hdcore=2.11.3', video_id, f4m_id=format_id, fatal=False))
 162             else:
 163                 formats.append({
 164                     # the secret extracted ya function in http://player.canalplus.fr/common/js/canalPlayer.js
 165                     'url': format_url + '?secret=pqzerjlsmdkjfoiuerhsdlfknaes',
 166                     'format_id': format_id,
 167                     'preference': preference(format_id),
 168                 })
 169         self._sort_formats(formats)
 170
 171         thumbnails = [{
 172             'id': image_id,
 173             'url': image_url,
 174         } for image_id, image_url in media.get('images', {}).items()]
 175
 176         titrage = infos['TITRAGE']
 177
 178         return {
 179             'id': video_id,
 180             'display_id': display_id,
 181             'title': '%s - %s' % (titrage['TITRE'],
 182                                   titrage['SOUS_TITRE']),
 183             'upload_date': unified_strdate(infos.get('PUBLICATION', {}).get('DATE')),
 184             'thumbnails': thumbnails,
 185             'description': infos.get('DESCRIPTION'),
 186             'duration': int_or_none(infos.get('DURATION')),
 187             'view_count': int_or_none(infos.get('NB_VUES')),
 188             'like_count': int_or_none(infos.get('NB_LIKES')),
 189             'comment_count': int_or_none(infos.get('NB_COMMENTS')),
 190             'formats': formats,
 191         }