yt_dlp/extractor/dplay.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_HTTPError
   8 from ..utils import (
   9     determine_ext,
  10     ExtractorError,
  11     float_or_none,
  12     int_or_none,
  13     strip_or_none,
  14     unified_timestamp,
  15 )
  16
  17
  18 class DPlayIE(InfoExtractor):
  19     _PATH_REGEX = r'/(?P<id>[^/]+/[^/?#]+)'
  20     _VALID_URL = r'''(?x)https?://
  21         (?P<domain>
  22             (?:www\.)?(?P<host>d
  23                 (?:
  24                     play\.(?P<country>dk|fi|jp|se|no)|
  25                     iscoveryplus\.(?P<plus_country>dk|es|fi|it|se|no)
  26                 )
  27             )|
  28             (?P<subdomain_country>es|it)\.dplay\.com
  29         )/[^/]+''' + _PATH_REGEX
  30
  31     _TESTS = [{
  32         # non geo restricted, via secure api, unsigned download hls URL
  33         'url': 'https://www.dplay.se/videos/nugammalt-77-handelser-som-format-sverige/nugammalt-77-handelser-som-format-sverige-101',
  34         'info_dict': {
  35             'id': '13628',
  36             'display_id': 'nugammalt-77-handelser-som-format-sverige/nugammalt-77-handelser-som-format-sverige-101',
  37             'ext': 'mp4',
  38             'title': 'Svensken lär sig njuta av livet',
  39             'description': 'md5:d3819c9bccffd0fe458ca42451dd50d8',
  40             'duration': 2649.856,
  41             'timestamp': 1365453720,
  42             'upload_date': '20130408',
  43             'creator': 'Kanal 5',
  44             'series': 'Nugammalt - 77 händelser som format Sverige',
  45             'season_number': 1,
  46             'episode_number': 1,
  47         },
  48         'params': {
  49             'skip_download': True,
  50         },
  51     }, {
  52         # geo restricted, via secure api, unsigned download hls URL
  53         'url': 'http://www.dplay.dk/videoer/ted-bundy-mind-of-a-monster/ted-bundy-mind-of-a-monster',
  54         'info_dict': {
  55             'id': '104465',
  56             'display_id': 'ted-bundy-mind-of-a-monster/ted-bundy-mind-of-a-monster',
  57             'ext': 'mp4',
  58             'title': 'Ted Bundy: Mind Of A Monster',
  59             'description': 'md5:8b780f6f18de4dae631668b8a9637995',
  60             'duration': 5290.027,
  61             'timestamp': 1570694400,
  62             'upload_date': '20191010',
  63             'creator': 'ID - Investigation Discovery',
  64             'series': 'Ted Bundy: Mind Of A Monster',
  65             'season_number': 1,
  66             'episode_number': 1,
  67         },
  68         'params': {
  69             'skip_download': True,
  70         },
  71     }, {
  72         # disco-api
  73         'url': 'https://www.dplay.no/videoer/i-kongens-klr/sesong-1-episode-7',
  74         'info_dict': {
  75             'id': '40206',
  76             'display_id': 'i-kongens-klr/sesong-1-episode-7',
  77             'ext': 'mp4',
  78             'title': 'Episode 7',
  79             'description': 'md5:e3e1411b2b9aebeea36a6ec5d50c60cf',
  80             'duration': 2611.16,
  81             'timestamp': 1516726800,
  82             'upload_date': '20180123',
  83             'series': 'I kongens klær',
  84             'season_number': 1,
  85             'episode_number': 7,
  86         },
  87         'params': {
  88             'skip_download': True,
  89         },
  90         'skip': 'Available for Premium users',
  91     }, {
  92         'url': 'http://it.dplay.com/nove/biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij/',
  93         'md5': '2b808ffb00fc47b884a172ca5d13053c',
  94         'info_dict': {
  95             'id': '6918',
  96             'display_id': 'biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij',
  97             'ext': 'mp4',
  98             'title': 'Luigi Di Maio: la psicosi di Stanislawskij',
  99             'description': 'md5:3c7a4303aef85868f867a26f5cc14813',
 100             'thumbnail': r're:^https?://.*\.jpe?g',
 101             'upload_date': '20160524',
 102             'timestamp': 1464076800,
 103             'series': 'Biografie imbarazzanti',
 104             'season_number': 1,
 105             'episode': 'Episode 1',
 106             'episode_number': 1,
 107         },
 108     }, {
 109         'url': 'https://es.dplay.com/dmax/la-fiebre-del-oro/temporada-8-episodio-1/',
 110         'info_dict': {
 111             'id': '21652',
 112             'display_id': 'la-fiebre-del-oro/temporada-8-episodio-1',
 113             'ext': 'mp4',
 114             'title': 'Episodio 1',
 115             'description': 'md5:b9dcff2071086e003737485210675f69',
 116             'thumbnail': r're:^https?://.*\.png',
 117             'upload_date': '20180709',
 118             'timestamp': 1531173540,
 119             'series': 'La fiebre del oro',
 120             'season_number': 8,
 121             'episode': 'Episode 1',
 122             'episode_number': 1,
 123         },
 124         'params': {
 125             'skip_download': True,
 126         },
 127     }, {
 128         'url': 'https://www.dplay.fi/videot/shifting-gears-with-aaron-kaufman/episode-16',
 129         'only_matching': True,
 130     }, {
 131         'url': 'https://www.dplay.jp/video/gold-rush/24086',
 132         'only_matching': True,
 133     }, {
 134         'url': 'https://www.discoveryplus.se/videos/nugammalt-77-handelser-som-format-sverige/nugammalt-77-handelser-som-format-sverige-101',
 135         'only_matching': True,
 136     }, {
 137         'url': 'https://www.discoveryplus.dk/videoer/ted-bundy-mind-of-a-monster/ted-bundy-mind-of-a-monster',
 138         'only_matching': True,
 139     }, {
 140         'url': 'https://www.discoveryplus.no/videoer/i-kongens-klr/sesong-1-episode-7',
 141         'only_matching': True,
 142     }, {
 143         'url': 'https://www.discoveryplus.it/videos/biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij',
 144         'only_matching': True,
 145     }, {
 146         'url': 'https://www.discoveryplus.es/videos/la-fiebre-del-oro/temporada-8-episodio-1',
 147         'only_matching': True,
 148     }, {
 149         'url': 'https://www.discoveryplus.fi/videot/shifting-gears-with-aaron-kaufman/episode-16',
 150         'only_matching': True,
 151     }]
 152
 153     def _process_errors(self, e, geo_countries):
 154         info = self._parse_json(e.cause.read().decode('utf-8'), None)
 155         error = info['errors'][0]
 156         error_code = error.get('code')
 157         if error_code == 'access.denied.geoblocked':
 158             self.raise_geo_restricted(countries=geo_countries)
 159         elif error_code in ('access.denied.missingpackage', 'invalid.token'):
 160             raise ExtractorError(
 161                 'This video is only available for registered users. You may want to use --cookies.', expected=True)
 162         raise ExtractorError(info['errors'][0]['detail'], expected=True)
 163
 164     def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
 165         headers['Authorization'] = 'Bearer ' + self._download_json(
 166             disco_base + 'token', display_id, 'Downloading token',
 167             query={
 168                 'realm': realm,
 169             })['data']['attributes']['token']
 170
 171     def _download_video_playback_info(self, disco_base, video_id, headers):
 172         streaming = self._download_json(
 173             disco_base + 'playback/videoPlaybackInfo/' + video_id,
 174             video_id, headers=headers)['data']['attributes']['streaming']
 175         streaming_list = []
 176         for format_id, format_dict in streaming.items():
 177             streaming_list.append({
 178                 'type': format_id,
 179                 'url': format_dict.get('url'),
 180             })
 181         return streaming_list
 182
 183     def _get_disco_api_info(self, url, display_id, disco_host, realm, country):
 184         geo_countries = [country.upper()]
 185         self._initialize_geo_bypass({
 186             'countries': geo_countries,
 187         })
 188         disco_base = 'https://%s/' % disco_host
 189         headers = {
 190             'Referer': url,
 191         }
 192         self._update_disco_api_headers(headers, disco_base, display_id, realm)
 193         try:
 194             video = self._download_json(
 195                 disco_base + 'content/videos/' + display_id, display_id,
 196                 headers=headers, query={
 197                     'fields[channel]': 'name',
 198                     'fields[image]': 'height,src,width',
 199                     'fields[show]': 'name',
 200                     'fields[tag]': 'name',
 201                     'fields[video]': 'description,episodeNumber,name,publishStart,seasonNumber,videoDuration',
 202                     'include': 'images,primaryChannel,show,tags'
 203                 })
 204         except ExtractorError as e:
 205             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
 206                 self._process_errors(e, geo_countries)
 207             raise
 208         video_id = video['data']['id']
 209         info = video['data']['attributes']
 210         title = info['name'].strip()
 211         formats = []
 212         try:
 213             streaming = self._download_video_playback_info(
 214                 disco_base, video_id, headers)
 215         except ExtractorError as e:
 216             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
 217                 self._process_errors(e, geo_countries)
 218             raise
 219         for format_dict in streaming:
 220             if not isinstance(format_dict, dict):
 221                 continue
 222             format_url = format_dict.get('url')
 223             if not format_url:
 224                 continue
 225             format_id = format_dict.get('type')
 226             ext = determine_ext(format_url)
 227             if format_id == 'dash' or ext == 'mpd':
 228                 formats.extend(self._extract_mpd_formats(
 229                     format_url, display_id, mpd_id='dash', fatal=False))
 230             elif format_id == 'hls' or ext == 'm3u8':
 231                 formats.extend(self._extract_m3u8_formats(
 232                     format_url, display_id, 'mp4',
 233                     entry_protocol='m3u8_native', m3u8_id='hls',
 234                     fatal=False))
 235             else:
 236                 formats.append({
 237                     'url': format_url,
 238                     'format_id': format_id,
 239                 })
 240         self._sort_formats(formats)
 241
 242         creator = series = None
 243         tags = []
 244         thumbnails = []
 245         included = video.get('included') or []
 246         if isinstance(included, list):
 247             for e in included:
 248                 attributes = e.get('attributes')
 249                 if not attributes:
 250                     continue
 251                 e_type = e.get('type')
 252                 if e_type == 'channel':
 253                     creator = attributes.get('name')
 254                 elif e_type == 'image':
 255                     src = attributes.get('src')
 256                     if src:
 257                         thumbnails.append({
 258                             'url': src,
 259                             'width': int_or_none(attributes.get('width')),
 260                             'height': int_or_none(attributes.get('height')),
 261                         })
 262                 if e_type == 'show':
 263                     series = attributes.get('name')
 264                 elif e_type == 'tag':
 265                     name = attributes.get('name')
 266                     if name:
 267                         tags.append(name)
 268
 269         return {
 270             'id': video_id,
 271             'display_id': display_id,
 272             'title': title,
 273             'description': strip_or_none(info.get('description')),
 274             'duration': float_or_none(info.get('videoDuration'), 1000),
 275             'timestamp': unified_timestamp(info.get('publishStart')),
 276             'series': series,
 277             'season_number': int_or_none(info.get('seasonNumber')),
 278             'episode_number': int_or_none(info.get('episodeNumber')),
 279             'creator': creator,
 280             'tags': tags,
 281             'thumbnails': thumbnails,
 282             'formats': formats,
 283         }
 284
 285     def _real_extract(self, url):
 286         mobj = self._match_valid_url(url)
 287         display_id = mobj.group('id')
 288         domain = mobj.group('domain').lstrip('www.')
 289         country = mobj.group('country') or mobj.group('subdomain_country') or mobj.group('plus_country')
 290         host = 'disco-api.' + domain if domain[0] == 'd' else 'eu2-prod.disco-api.com'
 291         return self._get_disco_api_info(
 292             url, display_id, host, 'dplay' + country, country)
 293
 294
 295 class HGTVDeIE(DPlayIE):
 296     _VALID_URL = r'https?://de\.hgtv\.com/sendungen' + DPlayIE._PATH_REGEX
 297     _TESTS = [{
 298         'url': 'https://de.hgtv.com/sendungen/tiny-house-klein-aber-oho/wer-braucht-schon-eine-toilette/',
 299         'info_dict': {
 300             'id': '151205',
 301             'display_id': 'tiny-house-klein-aber-oho/wer-braucht-schon-eine-toilette',
 302             'ext': 'mp4',
 303             'title': 'Wer braucht schon eine Toilette',
 304             'description': 'md5:05b40a27e7aed2c9172de34d459134e2',
 305             'duration': 1177.024,
 306             'timestamp': 1595705400,
 307             'upload_date': '20200725',
 308             'creator': 'HGTV',
 309             'series': 'Tiny House - klein, aber oho',
 310             'season_number': 3,
 311             'episode_number': 3,
 312         },
 313     }]
 314
 315     def _real_extract(self, url):
 316         display_id = self._match_id(url)
 317         return self._get_disco_api_info(
 318             url, display_id, 'eu1-prod.disco-api.com', 'hgtv', 'de')
 319
 320
 321 class DiscoveryPlusIE(DPlayIE):
 322     _VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/(?:\w{2}/)?video' + DPlayIE._PATH_REGEX
 323     _TESTS = [{
 324         'url': 'https://www.discoveryplus.com/video/property-brothers-forever-home/food-and-family',
 325         'info_dict': {
 326             'id': '1140794',
 327             'display_id': 'property-brothers-forever-home/food-and-family',
 328             'ext': 'mp4',
 329             'title': 'Food and Family',
 330             'description': 'The brothers help a Richmond family expand their single-level home.',
 331             'duration': 2583.113,
 332             'timestamp': 1609304400,
 333             'upload_date': '20201230',
 334             'creator': 'HGTV',
 335             'series': 'Property Brothers: Forever Home',
 336             'season_number': 1,
 337             'episode_number': 1,
 338         },
 339         'skip': 'Available for Premium users',
 340     }, {
 341         'url': 'https://discoveryplus.com/ca/video/bering-sea-gold-discovery-ca/goldslingers',
 342         'only_matching': True,
 343     }]
 344
 345     _PRODUCT = 'dplus_us'
 346     _API_URL = 'us1-prod-direct.discoveryplus.com'
 347
 348     def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
 349         headers['x-disco-client'] = f'WEB:UNKNOWN:{self._PRODUCT}:25.2.6'
 350
 351     def _download_video_playback_info(self, disco_base, video_id, headers):
 352         return self._download_json(
 353             disco_base + 'playback/v3/videoPlaybackInfo',
 354             video_id, headers=headers, data=json.dumps({
 355                 'deviceInfo': {
 356                     'adBlocker': False,
 357                 },
 358                 'videoId': video_id,
 359                 'wisteriaProperties': {
 360                     'platform': 'desktop',
 361                     'product': self._PRODUCT,
 362                 },
 363             }).encode('utf-8'))['data']['attributes']['streaming']
 364
 365     def _real_extract(self, url):
 366         display_id = self._match_id(url)
 367         return self._get_disco_api_info(
 368             url, display_id, self._API_URL, 'go', 'us')
 369
 370
 371 class ScienceChannelIE(DiscoveryPlusIE):
 372     _VALID_URL = r'https?://(?:www\.)?sciencechannel\.com/video' + DPlayIE._PATH_REGEX
 373     _TESTS = [{
 374         'url': 'https://www.sciencechannel.com/video/strangest-things-science-atve-us/nazi-mystery-machine',
 375         'info_dict': {
 376             'id': '2842849',
 377             'display_id': 'strangest-things-science-atve-us/nazi-mystery-machine',
 378             'ext': 'mp4',
 379             'title': 'Nazi Mystery Machine',
 380             'description': 'Experts investigate the secrets of a revolutionary encryption machine.',
 381             'season_number': 1,
 382             'episode_number': 1,
 383         },
 384         'skip': 'Available for Premium users',
 385     }]
 386
 387     _PRODUCT = 'sci'
 388     _API_URL = 'us1-prod-direct.sciencechannel.com'
 389
 390
 391 class DIYNetworkIE(DiscoveryPlusIE):
 392     _VALID_URL = r'https?://(?:watch\.)?diynetwork\.com/video' + DPlayIE._PATH_REGEX
 393     _TESTS = [{
 394         'url': 'https://watch.diynetwork.com/video/pool-kings-diy-network/bringing-beach-life-to-texas',
 395         'info_dict': {
 396             'id': '2309730',
 397             'display_id': 'pool-kings-diy-network/bringing-beach-life-to-texas',
 398             'ext': 'mp4',
 399             'title': 'Bringing Beach Life to Texas',
 400             'description': 'The Pool Kings give a family a day at the beach in their own backyard.',
 401             'season_number': 10,
 402             'episode_number': 2,
 403         },
 404         'skip': 'Available for Premium users',
 405     }]
 406
 407     _PRODUCT = 'diy'
 408     _API_URL = 'us1-prod-direct.watch.diynetwork.com'
 409
 410
 411 class AnimalPlanetIE(DiscoveryPlusIE):
 412     _VALID_URL = r'https?://(?:www\.)?animalplanet\.com/video' + DPlayIE._PATH_REGEX
 413     _TESTS = [{
 414         'url': 'https://www.animalplanet.com/video/north-woods-law-animal-planet/squirrel-showdown',
 415         'info_dict': {
 416             'id': '3338923',
 417             'display_id': 'north-woods-law-animal-planet/squirrel-showdown',
 418             'ext': 'mp4',
 419             'title': 'Squirrel Showdown',
 420             'description': 'A woman is suspected of being in possession of flying squirrel kits.',
 421             'season_number': 16,
 422             'episode_number': 11,
 423         },
 424         'skip': 'Available for Premium users',
 425     }]
 426
 427     _PRODUCT = 'apl'
 428     _API_URL = 'us1-prod-direct.animalplanet.com'