Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/radiocanada.py

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