yt_dlp/extractor/redbee.py

   1 import json
   2 import re
   3 import time
   4 import urllib.parse
   5 import uuid
   6
   7 from .common import InfoExtractor
   8 from ..utils import (
   9     ExtractorError,
  10     float_or_none,
  11     int_or_none,
  12     strip_or_none,
  13     traverse_obj,
  14     unified_timestamp,
  15 )
  16
  17
  18 class RedBeeBaseIE(InfoExtractor):
  19     _DEVICE_ID = str(uuid.uuid4())
  20
  21     @property
  22     def _API_URL(self):
  23         """
  24         Ref: https://apidocs.emp.ebsd.ericsson.net
  25         Subclasses must set _REDBEE_CUSTOMER, _REDBEE_BUSINESS_UNIT
  26         """
  27         return f'https://exposure.api.redbee.live/v2/customer/{self._REDBEE_CUSTOMER}/businessunit/{self._REDBEE_BUSINESS_UNIT}'
  28
  29     def _get_bearer_token(self, asset_id, jwt=None):
  30         request = {
  31             'deviceId': self._DEVICE_ID,
  32             'device': {
  33                 'deviceId': self._DEVICE_ID,
  34                 'name': 'Mozilla Firefox 102',
  35                 'type': 'WEB',
  36             },
  37         }
  38         if jwt:
  39             request['jwt'] = jwt
  40
  41         return self._download_json(
  42             f'{self._API_URL}/auth/{"gigyaLogin" if jwt else "anonymous"}',
  43             asset_id, data=json.dumps(request).encode('utf-8'), headers={
  44                 'Content-Type': 'application/json;charset=utf-8'
  45             })['sessionToken']
  46
  47     def _get_formats_and_subtitles(self, asset_id, **kwargs):
  48         bearer_token = self._get_bearer_token(asset_id, **kwargs)
  49         api_response = self._download_json(
  50             f'{self._API_URL}/entitlement/{asset_id}/play',
  51             asset_id, headers={
  52                 'Authorization': f'Bearer {bearer_token}',
  53                 'Accept': 'application/json, text/plain, */*'
  54             })
  55
  56         formats, subtitles = [], {}
  57         for format in api_response['formats']:
  58             if not format.get('mediaLocator'):
  59                 continue
  60
  61             fmts, subs = [], {}
  62             if format.get('format') == 'DASH':
  63                 fmts, subs = self._extract_mpd_formats_and_subtitles(
  64                     format['mediaLocator'], asset_id, fatal=False)
  65             elif format.get('format') == 'SMOOTHSTREAMING':
  66                 fmts, subs = self._extract_ism_formats_and_subtitles(
  67                     format['mediaLocator'], asset_id, fatal=False)
  68             elif format.get('format') == 'HLS':
  69                 fmts, subs = self._extract_m3u8_formats_and_subtitles(
  70                     format['mediaLocator'], asset_id, fatal=False)
  71
  72             formats.extend(fmts)
  73             self._merge_subtitles(subs, target=subtitles)
  74
  75         return formats, subtitles
  76
  77
  78 class ParliamentLiveUKIE(RedBeeBaseIE):
  79     IE_NAME = 'parliamentlive.tv'
  80     IE_DESC = 'UK parliament videos'
  81     _VALID_URL = r'(?i)https?://(?:www\.)?parliamentlive\.tv/Event/Index/(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
  82
  83     _REDBEE_CUSTOMER = 'UKParliament'
  84     _REDBEE_BUSINESS_UNIT = 'ParliamentLive'
  85
  86     _TESTS = [{
  87         'url': 'http://parliamentlive.tv/Event/Index/c1e9d44d-fd6c-4263-b50f-97ed26cc998b',
  88         'info_dict': {
  89             'id': 'c1e9d44d-fd6c-4263-b50f-97ed26cc998b',
  90             'ext': 'mp4',
  91             'title': 'Home Affairs Committee',
  92             'timestamp': 1395153872,
  93             'upload_date': '20140318',
  94             'thumbnail': r're:https?://[^?#]+c1e9d44d-fd6c-4263-b50f-97ed26cc998b[^/]*/thumbnail',
  95         },
  96     }, {
  97         'url': 'http://parliamentlive.tv/event/index/3f24936f-130f-40bf-9a5d-b3d6479da6a4',
  98         'only_matching': True,
  99     }, {
 100         'url': 'https://parliamentlive.tv/Event/Index/27cf25e4-e77b-42a3-93c5-c815cd6d7377',
 101         'info_dict': {
 102             'id': '27cf25e4-e77b-42a3-93c5-c815cd6d7377',
 103             'ext': 'mp4',
 104             'title': 'House of Commons',
 105             'timestamp': 1658392447,
 106             'upload_date': '20220721',
 107             'thumbnail': r're:https?://[^?#]+27cf25e4-e77b-42a3-93c5-c815cd6d7377[^/]*/thumbnail',
 108         },
 109     }]
 110
 111     def _real_extract(self, url):
 112         video_id = self._match_id(url)
 113
 114         formats, subtitles = self._get_formats_and_subtitles(video_id)
 115         self._sort_formats(formats)
 116
 117         video_info = self._download_json(
 118             f'https://www.parliamentlive.tv/Event/GetShareVideo/{video_id}', video_id, fatal=False)
 119
 120         self._sort_formats(formats, ['res', 'proto'])
 121
 122         return {
 123             'id': video_id,
 124             'formats': formats,
 125             'subtitles': subtitles,
 126             'title': traverse_obj(video_info, ('event', 'title')),
 127             'thumbnail': traverse_obj(video_info, 'thumbnailUrl'),
 128             'timestamp': traverse_obj(
 129                 video_info, ('event', 'publishedStartTime'), expected_type=unified_timestamp),
 130         }
 131
 132
 133 class RTBFIE(RedBeeBaseIE):
 134     _VALID_URL = r'''(?x)
 135         https?://(?:www\.)?rtbf\.be/
 136         (?:
 137             video/[^?]+\?.*\bid=|
 138             ouftivi/(?:[^/]+/)*[^?]+\?.*\bvideoId=|
 139             auvio/[^/]+\?.*\b(?P<live>l)?id=
 140         )(?P<id>\d+)'''
 141     _NETRC_MACHINE = 'rtbf'
 142
 143     _REDBEE_CUSTOMER = 'RTBF'
 144     _REDBEE_BUSINESS_UNIT = 'Auvio'
 145
 146     _TESTS = [{
 147         'url': 'https://www.rtbf.be/video/detail_les-diables-au-coeur-episode-2?id=1921274',
 148         'md5': '8c876a1cceeb6cf31b476461ade72384',
 149         'info_dict': {
 150             'id': '1921274',
 151             'ext': 'mp4',
 152             'title': 'Les Diables au coeur (épisode 2)',
 153             'description': '(du 25/04/2014)',
 154             'duration': 3099.54,
 155             'upload_date': '20140425',
 156             'timestamp': 1398456300,
 157         },
 158         'skip': 'No longer available',
 159     }, {
 160         # geo restricted
 161         'url': 'http://www.rtbf.be/ouftivi/heros/detail_scooby-doo-mysteres-associes?id=1097&videoId=2057442',
 162         'only_matching': True,
 163     }, {
 164         'url': 'http://www.rtbf.be/ouftivi/niouzz?videoId=2055858',
 165         'only_matching': True,
 166     }, {
 167         'url': 'http://www.rtbf.be/auvio/detail_jeudi-en-prime-siegfried-bracke?id=2102996',
 168         'only_matching': True,
 169     }, {
 170         # Live
 171         'url': 'https://www.rtbf.be/auvio/direct_pure-fm?lid=134775',
 172         'only_matching': True,
 173     }, {
 174         # Audio
 175         'url': 'https://www.rtbf.be/auvio/detail_cinq-heures-cinema?id=2360811',
 176         'only_matching': True,
 177     }, {
 178         # With Subtitle
 179         'url': 'https://www.rtbf.be/auvio/detail_les-carnets-du-bourlingueur?id=2361588',
 180         'only_matching': True,
 181     }, {
 182         'url': 'https://www.rtbf.be/auvio/detail_investigation?id=2921926',
 183         'md5': 'd5d11bb62169fef38d7ce7ac531e034f',
 184         'info_dict': {
 185             'id': '2921926',
 186             'ext': 'mp4',
 187             'title': 'Le handicap un confinement perpétuel - Maladie de Lyme',
 188             'description': 'md5:dcbd5dcf6015488c9069b057c15ccc52',
 189             'duration': 5258.8,
 190             'upload_date': '20220727',
 191             'timestamp': 1658934000,
 192             'series': '#Investigation',
 193             'thumbnail': r're:^https?://[^?&]+\.jpg$',
 194         },
 195     }, {
 196         'url': 'https://www.rtbf.be/auvio/detail_la-belgique-criminelle?id=2920492',
 197         'md5': '054f9f143bc79c89647c35e5a7d35fa8',
 198         'info_dict': {
 199             'id': '2920492',
 200             'ext': 'mp4',
 201             'title': '04 - Le crime de la rue Royale',
 202             'description': 'md5:0c3da1efab286df83f2ab3f8f96bd7a6',
 203             'duration': 1574.6,
 204             'upload_date': '20220723',
 205             'timestamp': 1658596887,
 206             'series': 'La Belgique criminelle - TV',
 207             'thumbnail': r're:^https?://[^?&]+\.jpg$',
 208         },
 209     }]
 210
 211     _IMAGE_HOST = 'http://ds1.ds.static.rtbf.be'
 212     _PROVIDERS = {
 213         'YOUTUBE': 'Youtube',
 214         'DAILYMOTION': 'Dailymotion',
 215         'VIMEO': 'Vimeo',
 216     }
 217     _QUALITIES = [
 218         ('mobile', 'SD'),
 219         ('web', 'MD'),
 220         ('high', 'HD'),
 221     ]
 222     _LOGIN_URL = 'https://login.rtbf.be/accounts.login'
 223     _GIGYA_API_KEY = '3_kWKuPgcdAybqnqxq_MvHVk0-6PN8Zk8pIIkJM_yXOu-qLPDDsGOtIDFfpGivtbeO'
 224     _LOGIN_COOKIE_ID = f'glt_{_GIGYA_API_KEY}'
 225
 226     def _perform_login(self, username, password):
 227         if self._get_cookies(self._LOGIN_URL).get(self._LOGIN_COOKIE_ID):
 228             return
 229
 230         self._set_cookie('.rtbf.be', 'gmid', 'gmid.ver4', secure=True, expire_time=time.time() + 3600)
 231
 232         login_response = self._download_json(
 233             self._LOGIN_URL, None, data=urllib.parse.urlencode({
 234                 'loginID': username,
 235                 'password': password,
 236                 'APIKey': self._GIGYA_API_KEY,
 237                 'targetEnv': 'jssdk',
 238                 'sessionExpiration': '-2',
 239             }).encode('utf-8'), headers={
 240                 'Content-Type': 'application/x-www-form-urlencoded',
 241             })
 242
 243         if login_response['statusCode'] != 200:
 244             raise ExtractorError('Login failed. Server message: %s' % login_response['errorMessage'], expected=True)
 245
 246         self._set_cookie('.rtbf.be', self._LOGIN_COOKIE_ID, login_response['sessionInfo']['login_token'],
 247                          secure=True, expire_time=time.time() + 3600)
 248
 249     def _get_formats_and_subtitles(self, url, media_id):
 250         login_token = self._get_cookies(url).get(self._LOGIN_COOKIE_ID)
 251         if not login_token:
 252             self.raise_login_required()
 253
 254         session_jwt = self._download_json(
 255             'https://login.rtbf.be/accounts.getJWT', media_id, query={
 256                 'login_token': login_token.value,
 257                 'APIKey': self._GIGYA_API_KEY,
 258                 'sdk': 'js_latest',
 259                 'authMode': 'cookie',
 260                 'pageURL': url,
 261                 'sdkBuild': '13273',
 262                 'format': 'json',
 263             })['id_token']
 264
 265         return super()._get_formats_and_subtitles(media_id, jwt=session_jwt)
 266
 267     def _real_extract(self, url):
 268         live, media_id = self._match_valid_url(url).groups()
 269         embed_page = self._download_webpage(
 270             'https://www.rtbf.be/auvio/embed/' + ('direct' if live else 'media'),
 271             media_id, query={'id': media_id})
 272         data = self._parse_json(self._html_search_regex(
 273             r'data-media="([^"]+)"', embed_page, 'media data'), media_id)
 274
 275         error = data.get('error')
 276         if error:
 277             raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True)
 278
 279         provider = data.get('provider')
 280         if provider in self._PROVIDERS:
 281             return self.url_result(data['url'], self._PROVIDERS[provider])
 282
 283         title = data['subtitle']
 284         is_live = data.get('isLive')
 285         height_re = r'-(\d+)p\.'
 286         formats = []
 287
 288         m3u8_url = data.get('urlHlsAes128') or data.get('urlHls')
 289         if m3u8_url:
 290             formats.extend(self._extract_m3u8_formats(
 291                 m3u8_url, media_id, 'mp4', m3u8_id='hls', fatal=False))
 292
 293         fix_url = lambda x: x.replace('//rtbf-vod.', '//rtbf.') if '/geo/drm/' in x else x
 294         http_url = data.get('url')
 295         if formats and http_url and re.search(height_re, http_url):
 296             http_url = fix_url(http_url)
 297             for m3u8_f in formats[:]:
 298                 height = m3u8_f.get('height')
 299                 if not height:
 300                     continue
 301                 f = m3u8_f.copy()
 302                 del f['protocol']
 303                 f.update({
 304                     'format_id': m3u8_f['format_id'].replace('hls-', 'http-'),
 305                     'url': re.sub(height_re, '-%dp.' % height, http_url),
 306                 })
 307                 formats.append(f)
 308         else:
 309             sources = data.get('sources') or {}
 310             for key, format_id in self._QUALITIES:
 311                 format_url = sources.get(key)
 312                 if not format_url:
 313                     continue
 314                 height = int_or_none(self._search_regex(
 315                     height_re, format_url, 'height', default=None))
 316                 formats.append({
 317                     'format_id': format_id,
 318                     'url': fix_url(format_url),
 319                     'height': height,
 320                 })
 321
 322         mpd_url = data.get('urlDash')
 323         if mpd_url and (self.get_param('allow_unplayable_formats') or not data.get('drm')):
 324             formats.extend(self._extract_mpd_formats(
 325                 mpd_url, media_id, mpd_id='dash', fatal=False))
 326
 327         audio_url = data.get('urlAudio')
 328         if audio_url:
 329             formats.append({
 330                 'format_id': 'audio',
 331                 'url': audio_url,
 332                 'vcodec': 'none',
 333             })
 334
 335         subtitles = {}
 336         for track in (data.get('tracks') or {}).values():
 337             sub_url = track.get('url')
 338             if not sub_url:
 339                 continue
 340             subtitles.setdefault(track.get('lang') or 'fr', []).append({
 341                 'url': sub_url,
 342             })
 343
 344         if not formats:
 345             fmts, subs = self._get_formats_and_subtitles(url, media_id)
 346             formats.extend(fmts)
 347             self._merge_subtitles(subs, target=subtitles)
 348
 349         self._sort_formats(formats, ['res', 'proto'])
 350         return {
 351             'id': media_id,
 352             'formats': formats,
 353             'title': title,
 354             'description': strip_or_none(data.get('description')),
 355             'thumbnail': data.get('thumbnail'),
 356             'duration': float_or_none(data.get('realDuration')),
 357             'timestamp': int_or_none(data.get('liveFrom')),
 358             'series': data.get('programLabel'),
 359             'subtitles': subtitles,
 360             'is_live': is_live,
 361         }