yt_dlp/extractor/toutv.py

   1 import json
   2
   3 from .radiocanada import RadioCanadaIE
   4 from ..networking.exceptions import HTTPError
   5 from ..utils import (
   6     ExtractorError,
   7     int_or_none,
   8     merge_dicts,
   9 )
  10
  11
  12 class TouTvIE(RadioCanadaIE):  # XXX: Do not subclass from concrete IE
  13     _NETRC_MACHINE = 'toutv'
  14     IE_NAME = 'tou.tv'
  15     _VALID_URL = r'https?://ici\.tou\.tv/(?P<id>[a-zA-Z0-9_-]+(?:/S[0-9]+[EC][0-9]+)?)'
  16
  17     _TESTS = [{
  18         'url': 'http://ici.tou.tv/garfield-tout-court/S2015E17',
  19         'info_dict': {
  20             'id': '122017',
  21             'ext': 'mp4',
  22             'title': 'Saison 2015 Épisode 17',
  23             'description': 'La photo de famille 2',
  24             'upload_date': '20100717',
  25         },
  26         'params': {
  27             # m3u8 download
  28             'skip_download': True,
  29         },
  30         'skip': '404 Not Found',
  31     }, {
  32         'url': 'http://ici.tou.tv/hackers',
  33         'only_matching': True,
  34     }, {
  35         'url': 'https://ici.tou.tv/l-age-adulte/S01C501',
  36         'only_matching': True,
  37     }]
  38     _CLIENT_KEY = '90505c8d-9c34-4f34-8da1-3a85bdc6d4f4'
  39
  40     def _perform_login(self, username, password):
  41         try:
  42             self._access_token = self._download_json(
  43                 'https://services.radio-canada.ca/toutv/profiling/accounts/login',
  44                 None, 'Logging in', data=json.dumps({
  45                     'ClientId': self._CLIENT_KEY,
  46                     'ClientSecret': '34026772-244b-49b6-8b06-317b30ac9a20',
  47                     'Email': username,
  48                     'Password': password,
  49                     'Scope': 'id.write media-validation.read',
  50                 }).encode(), headers={
  51                     'Authorization': 'client-key ' + self._CLIENT_KEY,
  52                     'Content-Type': 'application/json;charset=utf-8',
  53                 })['access_token']
  54         except ExtractorError as e:
  55             if isinstance(e.cause, HTTPError) and e.cause.status == 401:
  56                 error = self._parse_json(e.cause.response.read().decode(), None)['Message']
  57                 raise ExtractorError(error, expected=True)
  58             raise
  59         self._claims = self._call_api('validation/v2/getClaims')['claims']
  60
  61     def _real_extract(self, url):
  62         path = self._match_id(url)
  63         metadata = self._download_json(
  64             'https://services.radio-canada.ca/toutv/presentation/%s' % path, path, query={
  65                 'client_key': self._CLIENT_KEY,
  66                 'device': 'web',
  67                 'version': 4,
  68             })
  69         # IsDrm does not necessarily mean the video is DRM protected (see
  70         # https://github.com/ytdl-org/youtube-dl/issues/13994).
  71         if not self.get_param('allow_unplayable_formats') and metadata.get('IsDrm'):
  72             self.report_warning('This video is probably DRM protected.', path)
  73         video_id = metadata['IdMedia']
  74         details = metadata['Details']
  75
  76         return merge_dicts({
  77             'id': video_id,
  78             'title': details.get('OriginalTitle'),
  79             'description': details.get('Description'),
  80             'thumbnail': details.get('ImageUrl'),
  81             'duration': int_or_none(details.get('LengthInSeconds')),
  82             'series': metadata.get('ProgramTitle'),
  83             'season_number': int_or_none(metadata.get('SeasonNumber')),
  84             'season': metadata.get('SeasonTitle'),
  85             'episode_number': int_or_none(metadata.get('EpisodeNumber')),
  86             'episode': metadata.get('EpisodeTitle'),
  87         }, self._extract_info(metadata.get('AppCode', 'toutv'), video_id))