yt_dlp/extractor/canalplus.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     # ExtractorError,
   8     # HEADRequest,
   9     int_or_none,
  10     qualities,
  11     unified_strdate,
  12 )
  13
  14
  15 class CanalplusIE(InfoExtractor):
  16     IE_DESC = 'mycanal.fr and piwiplus.fr'
  17     _VALID_URL = r'https?://(?:www\.)?(?P<site>mycanal|piwiplus)\.fr/(?:[^/]+/)*(?P<display_id>[^?/]+)(?:\.html\?.*\bvid=|/p/)(?P<id>\d+)'
  18     _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s?format=json'
  19     _SITE_ID_MAP = {
  20         'mycanal': 'cplus',
  21         'piwiplus': 'teletoon',
  22     }
  23
  24     # Only works for direct mp4 URLs
  25     _GEO_COUNTRIES = ['FR']
  26
  27     _TESTS = [{
  28         'url': 'https://www.mycanal.fr/d17-emissions/lolywood/p/1397061',
  29         'info_dict': {
  30             'id': '1397061',
  31             'display_id': 'lolywood',
  32             'ext': 'mp4',
  33             'title': 'Euro 2016 : Je préfère te prévenir - Lolywood - Episode 34',
  34             'description': 'md5:7d97039d455cb29cdba0d652a0efaa5e',
  35             'upload_date': '20160602',
  36         },
  37     }, {
  38         # geo restricted, bypassed
  39         'url': 'http://www.piwiplus.fr/videos-piwi/pid1405-le-labyrinthe-boing-super-ranger.html?vid=1108190',
  40         'info_dict': {
  41             'id': '1108190',
  42             'display_id': 'pid1405-le-labyrinthe-boing-super-ranger',
  43             'ext': 'mp4',
  44             'title': 'BOING SUPER RANGER - Ep : Le labyrinthe',
  45             'description': 'md5:4cea7a37153be42c1ba2c1d3064376ff',
  46             'upload_date': '20140724',
  47         },
  48         'expected_warnings': ['HTTP Error 403: Forbidden'],
  49     }]
  50
  51     def _real_extract(self, url):
  52         site, display_id, video_id = self._match_valid_url(url).groups()
  53
  54         site_id = self._SITE_ID_MAP[site]
  55
  56         info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)
  57         video_data = self._download_json(info_url, video_id, 'Downloading video JSON')
  58
  59         if isinstance(video_data, list):
  60             video_data = [video for video in video_data if video.get('ID') == video_id][0]
  61         media = video_data['MEDIA']
  62         infos = video_data['INFOS']
  63
  64         preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD'])
  65
  66         # _, fmt_url = next(iter(media['VIDEOS'].items()))
  67         # if '/geo' in fmt_url.lower():
  68         #     response = self._request_webpage(
  69         #         HEADRequest(fmt_url), video_id,
  70         #         'Checking if the video is georestricted')
  71         #     if '/blocage' in response.geturl():
  72         #         raise ExtractorError(
  73         #             'The video is not available in your country',
  74         #             expected=True)
  75
  76         formats = []
  77         for format_id, format_url in media['VIDEOS'].items():
  78             if not format_url:
  79                 continue
  80             if format_id == 'HLS':
  81                 formats.extend(self._extract_m3u8_formats(
  82                     format_url, video_id, 'mp4', 'm3u8_native', m3u8_id=format_id, fatal=False))
  83             elif format_id == 'HDS':
  84                 formats.extend(self._extract_f4m_formats(
  85                     format_url + '?hdcore=2.11.3', video_id, f4m_id=format_id, fatal=False))
  86             else:
  87                 formats.append({
  88                     # the secret extracted from ya function in http://player.canalplus.fr/common/js/canalPlayer.js
  89                     'url': format_url + '?secret=pqzerjlsmdkjfoiuerhsdlfknaes',
  90                     'format_id': format_id,
  91                     'quality': preference(format_id),
  92                 })
  93         self._sort_formats(formats)
  94
  95         thumbnails = [{
  96             'id': image_id,
  97             'url': image_url,
  98         } for image_id, image_url in media.get('images', {}).items()]
  99
 100         titrage = infos['TITRAGE']
 101
 102         return {
 103             'id': video_id,
 104             'display_id': display_id,
 105             'title': '%s - %s' % (titrage['TITRE'],
 106                                   titrage['SOUS_TITRE']),
 107             'upload_date': unified_strdate(infos.get('PUBLICATION', {}).get('DATE')),
 108             'thumbnails': thumbnails,
 109             'description': infos.get('DESCRIPTION'),
 110             'duration': int_or_none(infos.get('DURATION')),
 111             'view_count': int_or_none(infos.get('NB_VUES')),
 112             'like_count': int_or_none(infos.get('NB_LIKES')),
 113             'comment_count': int_or_none(infos.get('NB_COMMENTS')),
 114             'formats': formats,
 115         }