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                                     (?:www\.)?itele\.fr
  31                                 )/(?:(?:[^/]+/)*(?P<display_id>[^/?#&]+))?(?:\?.*\bvid=(?P<vid>\d+))?|
  32                                 player\.canalplus\.fr/#/(?P<id>\d+)
  33                             )
  34
  35                     '''
  36     _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s?format=json'
  37     _SITE_ID_MAP = {
  38         'canalplus': 'cplus',
  39         'piwiplus': 'teletoon',
  40         'd8': 'd8',
  41         'c8': 'd8',
  42         'd17': 'd17',
  43         'itele': 'itele',
  44     }
  45
  46     _TESTS = [{
  47         'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1192814',
  48         'info_dict': {
  49             'id': '1405510',
  50             'display_id': 'pid1830-c-zapping',
  51             'ext': 'mp4',
  52             'title': 'Zapping - 02/07/2016',
  53             'description': 'Le meilleur de toutes les chaînes, tous les jours',
  54             'upload_date': '20160702',
  55         },
  56     }, {
  57         'url': 'http://www.piwiplus.fr/videos-piwi/pid1405-le-labyrinthe-boing-super-ranger.html?vid=1108190',
  58         'info_dict': {
  59             'id': '1108190',
  60             'display_id': 'pid1405-le-labyrinthe-boing-super-ranger',
  61             'ext': 'mp4',
  62             'title': 'BOING SUPER RANGER - Ep : Le labyrinthe',
  63             'description': 'md5:4cea7a37153be42c1ba2c1d3064376ff',
  64             'upload_date': '20140724',
  65         },
  66         'skip': 'Only works from France',
  67     }, {
  68         'url': 'http://www.c8.fr/c8-divertissement/ms-touche-pas-a-mon-poste/pid6318-videos-integrales.html',
  69         'md5': '4b47b12b4ee43002626b97fad8fb1de5',
  70         'info_dict': {
  71             'id': '1420213',
  72             'display_id': 'pid6318-videos-integrales',
  73             'ext': 'mp4',
  74             'title': 'TPMP ! Même le matin - Les 35H de Baba - 14/10/2016',
  75             'description': 'md5:f96736c1b0ffaa96fd5b9e60ad871799',
  76             'upload_date': '20161014',
  77         },
  78         'skip': 'Only works from France',
  79     }, {
  80         'url': 'http://www.itele.fr/chroniques/invite-michael-darmon/rachida-dati-nicolas-sarkozy-est-le-plus-en-phase-avec-les-inquietudes-des-francais-171510',
  81         'info_dict': {
  82             'id': '1420176',
  83             'display_id': 'rachida-dati-nicolas-sarkozy-est-le-plus-en-phase-avec-les-inquietudes-des-francais-171510',
  84             'ext': 'mp4',
  85             'title': 'L\'invité de Michaël Darmon du 14/10/2016 - ',
  86             'description': 'Chaque matin du lundi au vendredi, Michaël Darmon reçoit un invité politique à 8h25.',
  87             'upload_date': '20161014',
  88         },
  89     }, {
  90         'url': 'http://m.canalplus.fr/?vid=1398231',
  91         'only_matching': True,
  92     }, {
  93         'url': 'http://www.d17.tv/emissions/pid8303-lolywood.html?vid=1397061',
  94         'only_matching': True,
  95     }]
  96
  97     def _real_extract(self, url):
  98         mobj = re.match(self._VALID_URL, url)
  99
 100         site_id = self._SITE_ID_MAP[compat_urllib_parse_urlparse(url).netloc.rsplit('.', 2)[-2]]
 101
 102         # Beware, some subclasses do not define an id group
 103         display_id = remove_end(dict_get(mobj.groupdict(), ('display_id', 'id', 'vid')), '.html')
 104
 105         webpage = self._download_webpage(url, display_id)
 106         video_id = self._search_regex(
 107             [r'<canal:player[^>]+?videoId=(["\'])(?P<id>\d+)',
 108              r'id=["\']canal_video_player(?P<id>\d+)'],
 109             webpage, 'video id', group='id')
 110
 111         info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)
 112         video_data = self._download_json(info_url, video_id, 'Downloading video JSON')
 113
 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']
 118
 119         preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD'])
 120
 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',
 129                     expected=True)
 130
 131         formats = []
 132         for format_id, format_url in media['VIDEOS'].items():
 133             if not format_url:
 134                 continue
 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))
 141             else:
 142                 formats.append({
 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),
 147                 })
 148         self._sort_formats(formats)
 149
 150         thumbnails = [{
 151             'id': image_id,
 152             'url': image_url,
 153         } for image_id, image_url in media.get('images', {}).items()]
 154
 155         titrage = infos['TITRAGE']
 156
 157         return {
 158             'id': video_id,
 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')),
 169             'formats': formats,
 170         }