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     unified_strdate,
   9     url_basename,
  10     qualities,
  11 )
  12
  13
  14 class CanalplusIE(InfoExtractor):
  15     IE_DESC = 'canalplus.fr, piwiplus.fr and d8.tv'
  16     _VALID_URL = r'https?://(?:www\.(?P<site>canalplus\.fr|piwiplus\.fr|d8\.tv)/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))'
  17     _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s'
  18     _SITE_ID_MAP = {
  19         'canalplus.fr': 'cplus',
  20         'piwiplus.fr': 'teletoon',
  21         'd8.tv': 'd8',
  22     }
  23
  24     _TESTS = [{
  25         'url': 'http://www.canalplus.fr/c-infos-documentaires/pid1830-c-zapping.html?vid=922470',
  26         'md5': '3db39fb48b9685438ecf33a1078023e4',
  27         'info_dict': {
  28             'id': '922470',
  29             'ext': 'flv',
  30             'title': 'Zapping - 26/08/13',
  31             'description': 'Le meilleur de toutes les chaînes, tous les jours.\nEmission du 26 août 2013',
  32             'upload_date': '20130826',
  33         },
  34     }, {
  35         'url': 'http://www.piwiplus.fr/videos-piwi/pid1405-le-labyrinthe-boing-super-ranger.html?vid=1108190',
  36         'info_dict': {
  37             'id': '1108190',
  38             'ext': 'flv',
  39             'title': 'Le labyrinthe - Boing super ranger',
  40             'description': 'md5:4cea7a37153be42c1ba2c1d3064376ff',
  41             'upload_date': '20140724',
  42         },
  43         'skip': 'Only works from France',
  44     }, {
  45         'url': 'http://www.d8.tv/d8-docs-mags/pid6589-d8-campagne-intime.html',
  46         'info_dict': {
  47             'id': '966289',
  48             'ext': 'flv',
  49             'title': 'Campagne intime - Documentaire exceptionnel',
  50             'description': 'md5:d2643b799fb190846ae09c61e59a859f',
  51             'upload_date': '20131108',
  52         },
  53         'skip': 'videos get deleted after a while',
  54     }]
  55
  56     def _real_extract(self, url):
  57         mobj = re.match(self._VALID_URL, url)
  58         video_id = mobj.groupdict().get('id')
  59
  60         site_id = self._SITE_ID_MAP[mobj.group('site') or 'canal']
  61
  62         # Beware, some subclasses do not define an id group
  63         display_id = url_basename(mobj.group('path'))
  64
  65         if video_id is None:
  66             webpage = self._download_webpage(url, display_id)
  67             video_id = self._search_regex(
  68                 r'<canal:player[^>]+?videoId="(\d+)"', webpage, 'video id')
  69
  70         info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)
  71         doc = self._download_xml(info_url, video_id, 'Downloading video XML')
  72
  73         video_info = [video for video in doc if video.find('ID').text == video_id][0]
  74         media = video_info.find('MEDIA')
  75         infos = video_info.find('INFOS')
  76
  77         preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD', 'HLS', 'HDS'])
  78
  79         formats = []
  80         for fmt in media.find('VIDEOS'):
  81             format_url = fmt.text
  82             if not format_url:
  83                 continue
  84             format_id = fmt.tag
  85             if format_id == 'HLS':
  86                 hls_formats = self._extract_m3u8_formats(format_url, video_id, 'flv')
  87                 for fmt in hls_formats:
  88                     fmt['preference'] = preference(format_id)
  89                 formats.extend(hls_formats)
  90             elif format_id == 'HDS':
  91                 hds_formats = self._extract_f4m_formats(format_url + '?hdcore=2.11.3', video_id)
  92                 for fmt in hds_formats:
  93                     fmt['preference'] = preference(format_id)
  94                 formats.extend(hds_formats)
  95             else:
  96                 formats.append({
  97                     'url': format_url,
  98                     'format_id': format_id,
  99                     'preference': preference(format_id),
 100                 })
 101         self._sort_formats(formats)
 102
 103         return {
 104             'id': video_id,
 105             'display_id': display_id,
 106             'title': '%s - %s' % (infos.find('TITRAGE/TITRE').text,
 107                                   infos.find('TITRAGE/SOUS_TITRE').text),
 108             'upload_date': unified_strdate(infos.find('PUBLICATION/DATE').text),
 109             'thumbnail': media.find('IMAGES/GRAND').text,
 110             'description': infos.find('DESCRIPTION').text,
 111             'view_count': int(infos.find('NB_VUES').text),
 112             'like_count': int(infos.find('NB_LIKES').text),
 113             'comment_count': int(infos.find('NB_COMMENTS').text),
 114             'formats': formats,
 115         }