yt_dlp/extractor/canalplus.py

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