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 ..utils import (
   8     ExtractorError,
   9     HEADRequest,
  10     unified_strdate,
  11     url_basename,
  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'https?://(?:www\.(?P<site>canalplus\.fr|piwiplus\.fr|d8\.tv|itele\.fr)/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))'
  20     _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s?format=json'
  21     _SITE_ID_MAP = {
  22         'canalplus.fr': 'cplus',
  23         'piwiplus.fr': 'teletoon',
  24         'd8.tv': 'd8',
  25         'itele.fr': 'itele',
  26     }
  27
  28     _TESTS = [{
  29         'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1263092',
  30         'md5': '12164a6f14ff6df8bd628e8ba9b10b78',
  31         'info_dict': {
  32             'id': '1263092',
  33             'ext': 'mp4',
  34             'title': 'Le Zapping - 13/05/15',
  35             'description': 'md5:09738c0d06be4b5d06a0940edb0da73f',
  36             'upload_date': '20150513',
  37         },
  38     }, {
  39         'url': 'http://www.piwiplus.fr/videos-piwi/pid1405-le-labyrinthe-boing-super-ranger.html?vid=1108190',
  40         'info_dict': {
  41             'id': '1108190',
  42             'ext': 'flv',
  43             'title': 'Le labyrinthe - Boing super ranger',
  44             'description': 'md5:4cea7a37153be42c1ba2c1d3064376ff',
  45             'upload_date': '20140724',
  46         },
  47         'skip': 'Only works from France',
  48     }, {
  49         'url': 'http://www.d8.tv/d8-docs-mags/pid6589-d8-campagne-intime.html',
  50         'info_dict': {
  51             'id': '966289',
  52             'ext': 'flv',
  53             'title': 'Campagne intime - Documentaire exceptionnel',
  54             'description': 'md5:d2643b799fb190846ae09c61e59a859f',
  55             'upload_date': '20131108',
  56         },
  57         'skip': 'videos get deleted after a while',
  58     }, {
  59         'url': 'http://www.itele.fr/france/video/aubervilliers-un-lycee-en-colere-111559',
  60         'md5': '38b8f7934def74f0d6f3ba6c036a5f82',
  61         'info_dict': {
  62             'id': '1213714',
  63             'ext': 'mp4',
  64             'title': 'Aubervilliers : un lycée en colère - Le 11/02/2015 à 06h45',
  65             'description': 'md5:8216206ec53426ea6321321f3b3c16db',
  66             'upload_date': '20150211',
  67         },
  68     }]
  69
  70     def _real_extract(self, url):
  71         mobj = re.match(self._VALID_URL, url)
  72         video_id = mobj.groupdict().get('id')
  73
  74         site_id = self._SITE_ID_MAP[mobj.group('site') or 'canal']
  75
  76         # Beware, some subclasses do not define an id group
  77         display_id = url_basename(mobj.group('path'))
  78
  79         if video_id is None:
  80             webpage = self._download_webpage(url, display_id)
  81             video_id = self._search_regex(
  82                 [r'<canal:player[^>]+?videoId=(["\'])(?P<id>\d+)', r'id=["\']canal_video_player(?P<id>\d+)'],
  83                 webpage, 'video id', group='id')
  84
  85         info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)
  86         video_data = self._download_json(info_url, video_id, 'Downloading video JSON')
  87
  88         if isinstance(video_data, list):
  89             video_data = [video for video in video_data if video.get('ID') == video_id][0]
  90         media = video_data['MEDIA']
  91         infos = video_data['INFOS']
  92
  93         preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD'])
  94
  95         fmt_url = next(iter(media.get('VIDEOS')))
  96         if '/geo' in fmt_url.lower():
  97             response = self._request_webpage(
  98                 HEADRequest(fmt_url), video_id,
  99                 'Checking if the video is georestricted')
 100             if '/blocage' in response.geturl():
 101                 raise ExtractorError(
 102                     'The video is not available in your country',
 103                     expected=True)
 104
 105         formats = []
 106         for format_id, format_url in media['VIDEOS'].items():
 107             if not format_url:
 108                 continue
 109             if format_id == 'HLS':
 110                 formats.extend(self._extract_m3u8_formats(
 111                     format_url, video_id, 'mp4', 'm3u8_native', m3u8_id=format_id, fatal=False))
 112             elif format_id == 'HDS':
 113                 formats.extend(self._extract_f4m_formats(
 114                     format_url + '?hdcore=2.11.3', video_id, f4m_id=format_id, fatal=False))
 115             else:
 116                 formats.append({
 117                     # the secret extracted ya function in http://player.canalplus.fr/common/js/canalPlayer.js
 118                     'url': format_url + '?secret=pqzerjlsmdkjfoiuerhsdlfknaes',
 119                     'format_id': format_id,
 120                     'preference': preference(format_id),
 121                 })
 122         self._sort_formats(formats)
 123
 124         thumbnails = [{
 125             'id': image_id,
 126             'url': image_url,
 127         } for image_id, image_url in media.get('images', {}).items()]
 128
 129         titrage = infos['TITRAGE']
 130
 131         return {
 132             'id': video_id,
 133             'display_id': display_id,
 134             'title': '%s - %s' % (titrage['TITRE'],
 135                                   titrage['SOUS_TITRE']),
 136             'upload_date': unified_strdate(infos.get('PUBLICATION', {}).get('DATE')),
 137             'thumbnails': thumbnails,
 138             'description': infos.get('DESCRIPTION'),
 139             'duration': int_or_none(infos.get('DURATION')),
 140             'view_count': int_or_none(infos.get('NB_VUES')),
 141             'like_count': int_or_none(infos.get('NB_LIKES')),
 142             'comment_count': int_or_none(infos.get('NB_COMMENTS')),
 143             'formats': formats,
 144         }