yt_dlp/extractor/radiocanada.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_HTTPError
   7 from ..utils import (
   8     determine_ext,
   9     ExtractorError,
  10     int_or_none,
  11     unified_strdate,
  12 )
  13
  14
  15 class RadioCanadaIE(InfoExtractor):
  16     IE_NAME = 'radiocanada'
  17     _VALID_URL = r'(?:radiocanada:|https?://ici\.radio-canada\.ca/widgets/mediaconsole/)(?P<app_code>[^:/]+)[:/](?P<id>[0-9]+)'
  18     _TESTS = [
  19         {
  20             'url': 'http://ici.radio-canada.ca/widgets/mediaconsole/medianet/7184272',
  21             'info_dict': {
  22                 'id': '7184272',
  23                 'ext': 'mp4',
  24                 'title': 'Le parcours du tireur capté sur vidéo',
  25                 'description': 'Images des caméras de surveillance fournies par la GRC montrant le parcours du tireur d\'Ottawa',
  26                 'upload_date': '20141023',
  27             },
  28             'params': {
  29                 # m3u8 download
  30                 'skip_download': True,
  31             }
  32         },
  33         {
  34             # empty Title
  35             'url': 'http://ici.radio-canada.ca/widgets/mediaconsole/medianet/7754998/',
  36             'info_dict': {
  37                 'id': '7754998',
  38                 'ext': 'mp4',
  39                 'title': 'letelejournal22h',
  40                 'description': 'INTEGRALE WEB 22H-TJ',
  41                 'upload_date': '20170720',
  42             },
  43             'params': {
  44                 # m3u8 download
  45                 'skip_download': True,
  46             },
  47         },
  48         {
  49             # with protectionType but not actually DRM protected
  50             'url': 'radiocanada:toutv:140872',
  51             'info_dict': {
  52                 'id': '140872',
  53                 'title': 'Épisode 1',
  54                 'series': 'District 31',
  55             },
  56             'only_matching': True,
  57         }
  58     ]
  59     _GEO_COUNTRIES = ['CA']
  60     _access_token = None
  61     _claims = None
  62
  63     def _call_api(self, path, video_id=None, app_code=None, query=None):
  64         if not query:
  65             query = {}
  66         query.update({
  67             'client_key': '773aea60-0e80-41bb-9c7f-e6d7c3ad17fb',
  68             'output': 'json',
  69         })
  70         if video_id:
  71             query.update({
  72                 'appCode': app_code,
  73                 'idMedia': video_id,
  74             })
  75         if self._access_token:
  76             query['access_token'] = self._access_token
  77         try:
  78             return self._download_json(
  79                 'https://services.radio-canada.ca/media/' + path, video_id, query=query)
  80         except ExtractorError as e:
  81             if isinstance(e.cause, compat_HTTPError) and e.cause.code in (401, 422):
  82                 data = self._parse_json(e.cause.read().decode(), None)
  83                 error = data.get('error_description') or data['errorMessage']['text']
  84                 raise ExtractorError(error, expected=True)
  85             raise
  86
  87     def _extract_info(self, app_code, video_id):
  88         metas = self._call_api('meta/v1/index.ashx', video_id, app_code)['Metas']
  89
  90         def get_meta(name):
  91             for meta in metas:
  92                 if meta.get('name') == name:
  93                     text = meta.get('text')
  94                     if text:
  95                         return text
  96
  97         # protectionType does not necessarily mean the video is DRM protected (see
  98         # https://github.com/ytdl-org/youtube-dl/pull/18609).
  99         if get_meta('protectionType'):
 100             self.report_warning('This video is probably DRM protected.')
 101
 102         query = {
 103             'connectionType': 'hd',
 104             'deviceType': 'ipad',
 105             'multibitrate': 'true',
 106         }
 107         if self._claims:
 108             query['claims'] = self._claims
 109         v_data = self._call_api('validation/v2/', video_id, app_code, query)
 110         v_url = v_data.get('url')
 111         if not v_url:
 112             error = v_data['message']
 113             if error == "Le contenu sélectionné n'est pas disponible dans votre pays":
 114                 raise self.raise_geo_restricted(error, self._GEO_COUNTRIES)
 115             if error == 'Le contenu sélectionné est disponible seulement en premium':
 116                 self.raise_login_required(error)
 117             raise ExtractorError(
 118                 '%s said: %s' % (self.IE_NAME, error), expected=True)
 119         formats = self._extract_m3u8_formats(v_url, video_id, 'mp4')
 120         self._sort_formats(formats)
 121
 122         subtitles = {}
 123         closed_caption_url = get_meta('closedCaption') or get_meta('closedCaptionHTML5')
 124         if closed_caption_url:
 125             subtitles['fr'] = [{
 126                 'url': closed_caption_url,
 127                 'ext': determine_ext(closed_caption_url, 'vtt'),
 128             }]
 129
 130         return {
 131             'id': video_id,
 132             'title': get_meta('Title') or get_meta('AV-nomEmission'),
 133             'description': get_meta('Description') or get_meta('ShortDescription'),
 134             'thumbnail': get_meta('imageHR') or get_meta('imageMR') or get_meta('imageBR'),
 135             'duration': int_or_none(get_meta('length')),
 136             'series': get_meta('Emission'),
 137             'season_number': int_or_none('SrcSaison'),
 138             'episode_number': int_or_none('SrcEpisode'),
 139             'upload_date': unified_strdate(get_meta('Date')),
 140             'subtitles': subtitles,
 141             'formats': formats,
 142         }
 143
 144     def _real_extract(self, url):
 145         return self._extract_info(*self._match_valid_url(url).groups())
 146
 147
 148 class RadioCanadaAudioVideoIE(InfoExtractor):
 149     IE_NAME = 'radiocanada:audiovideo'
 150     _VALID_URL = r'https?://ici\.radio-canada\.ca/([^/]+/)*media-(?P<id>[0-9]+)'
 151     _TESTS = [{
 152         'url': 'http://ici.radio-canada.ca/audio-video/media-7527184/barack-obama-au-vietnam',
 153         'info_dict': {
 154             'id': '7527184',
 155             'ext': 'mp4',
 156             'title': 'Barack Obama au Vietnam',
 157             'description': 'Les États-Unis lèvent l\'embargo sur la vente d\'armes qui datait de la guerre du Vietnam',
 158             'upload_date': '20160523',
 159         },
 160         'params': {
 161             # m3u8 download
 162             'skip_download': True,
 163         },
 164     }, {
 165         'url': 'https://ici.radio-canada.ca/info/videos/media-7527184/barack-obama-au-vietnam',
 166         'only_matching': True,
 167     }]
 168
 169     def _real_extract(self, url):
 170         return self.url_result('radiocanada:medianet:%s' % self._match_id(url))