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 ..utils import (
   8     # ExtractorError,
   9     # HEADRequest,
  10     int_or_none,
  11     qualities,
  12     unified_strdate,
  13 )
  14
  15
  16 class CanalplusIE(InfoExtractor):
  17     IE_DESC = 'mycanal.fr and piwiplus.fr'
  18     _VALID_URL = r'https?://(?:www\.)?(?P<site>mycanal|piwiplus)\.fr/(?:[^/]+/)*(?P<display_id>[^?/]+)(?:\.html\?.*\bvid=|/p/)(?P<id>\d+)'
  19     _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s?format=json'
  20     _SITE_ID_MAP = {
  21         'mycanal': 'cplus',
  22         'piwiplus': 'teletoon',
  23     }
  24
  25     # Only works for direct mp4 URLs
  26     _GEO_COUNTRIES = ['FR']
  27
  28     _TESTS = [{
  29         'url': 'https://www.mycanal.fr/d17-emissions/lolywood/p/1397061',
  30         'info_dict': {
  31             'id': '1397061',
  32             'display_id': 'lolywood',
  33             'ext': 'mp4',
  34             'title': 'Euro 2016 : Je préfère te prévenir - Lolywood - Episode 34',
  35             'description': 'md5:7d97039d455cb29cdba0d652a0efaa5e',
  36             'upload_date': '20160602',
  37         },
  38     }, {
  39         # geo restricted, bypassed
  40         'url': 'http://www.piwiplus.fr/videos-piwi/pid1405-le-labyrinthe-boing-super-ranger.html?vid=1108190',
  41         'info_dict': {
  42             'id': '1108190',
  43             'display_id': 'pid1405-le-labyrinthe-boing-super-ranger',
  44             'ext': 'mp4',
  45             'title': 'BOING SUPER RANGER - Ep : Le labyrinthe',
  46             'description': 'md5:4cea7a37153be42c1ba2c1d3064376ff',
  47             'upload_date': '20140724',
  48         },
  49         'expected_warnings': ['HTTP Error 403: Forbidden'],
  50     }]
  51
  52     def _real_extract(self, url):
  53         site, display_id, video_id = re.match(self._VALID_URL, url).groups()
  54
  55         site_id = self._SITE_ID_MAP[site]
  56
  57         info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)
  58         video_data = self._download_json(info_url, video_id, 'Downloading video JSON')
  59
  60         if isinstance(video_data, list):
  61             video_data = [video for video in video_data if video.get('ID') == video_id][0]
  62         media = video_data['MEDIA']
  63         infos = video_data['INFOS']
  64
  65         preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD'])
  66
  67         # _, fmt_url = next(iter(media['VIDEOS'].items()))
  68         # if '/geo' in fmt_url.lower():
  69         #     response = self._request_webpage(
  70         #         HEADRequest(fmt_url), video_id,
  71         #         'Checking if the video is georestricted')
  72         #     if '/blocage' in response.geturl():
  73         #         raise ExtractorError(
  74         #             'The video is not available in your country',
  75         #             expected=True)
  76
  77         formats = []
  78         for format_id, format_url in media['VIDEOS'].items():
  79             if not format_url:
  80                 continue
  81             if format_id == 'HLS':
  82                 formats.extend(self._extract_m3u8_formats(
  83                     format_url, video_id, 'mp4', 'm3u8_native', m3u8_id=format_id, fatal=False))
  84             elif format_id == 'HDS':
  85                 formats.extend(self._extract_f4m_formats(
  86                     format_url + '?hdcore=2.11.3', video_id, f4m_id=format_id, fatal=False))
  87             else:
  88                 formats.append({
  89                     # the secret extracted from ya function in http://player.canalplus.fr/common/js/canalPlayer.js
  90                     'url': format_url + '?secret=pqzerjlsmdkjfoiuerhsdlfknaes',
  91                     'format_id': format_id,
  92                     'preference': preference(format_id),
  93                 })
  94         self._sort_formats(formats)
  95
  96         thumbnails = [{
  97             'id': image_id,
  98             'url': image_url,
  99         } for image_id, image_url in media.get('images', {}).items()]
 100
 101         titrage = infos['TITRAGE']
 102
 103         return {
 104             'id': video_id,
 105             'display_id': display_id,
 106             'title': '%s - %s' % (titrage['TITRE'],
 107                                   titrage['SOUS_TITRE']),
 108             'upload_date': unified_strdate(infos.get('PUBLICATION', {}).get('DATE')),
 109             'thumbnails': thumbnails,
 110             'description': infos.get('DESCRIPTION'),
 111             'duration': int_or_none(infos.get('DURATION')),
 112             'view_count': int_or_none(infos.get('NB_VUES')),
 113             'like_count': int_or_none(infos.get('NB_LIKES')),
 114             'comment_count': int_or_none(infos.get('NB_COMMENTS')),
 115             'formats': formats,
 116         }