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             'format': 'bestvideo',
  50             'skip_download': True,
  51         },
  52     }, {
  53         # geo restricted, via secure api, unsigned download hls URL
  54         'url': 'http://www.dplay.dk/videoer/ted-bundy-mind-of-a-monster/ted-bundy-mind-of-a-monster',
  55         'info_dict': {
  56             'id': '104465',
  57             'display_id': 'ted-bundy-mind-of-a-monster/ted-bundy-mind-of-a-monster',
  58             'ext': 'mp4',
  59             'title': 'Ted Bundy: Mind Of A Monster',
  60             'description': 'md5:8b780f6f18de4dae631668b8a9637995',
  61             'duration': 5290.027,
  62             'timestamp': 1570694400,
  63             'upload_date': '20191010',
  64             'creator': 'ID - Investigation Discovery',
  65             'series': 'Ted Bundy: Mind Of A Monster',
  66             'season_number': 1,
  67             'episode_number': 1,
  68         },
  69         'params': {
  70             'format': 'bestvideo',
  71             'skip_download': True,
  72         },
  73     }, {
  74         # disco-api
  75         'url': 'https://www.dplay.no/videoer/i-kongens-klr/sesong-1-episode-7',
  76         'info_dict': {
  77             'id': '40206',
  78             'display_id': 'i-kongens-klr/sesong-1-episode-7',
  79             'ext': 'mp4',
  80             'title': 'Episode 7',
  81             'description': 'md5:e3e1411b2b9aebeea36a6ec5d50c60cf',
  82             'duration': 2611.16,
  83             'timestamp': 1516726800,
  84             'upload_date': '20180123',
  85             'series': 'I kongens klær',
  86             'season_number': 1,
  87             'episode_number': 7,
  88         },
  89         'params': {
  90             'format': 'bestvideo',
  91             'skip_download': True,
  92         },
  93         'skip': 'Available for Premium users',
  94     }, {
  95         'url': 'http://it.dplay.com/nove/biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij/',
  96         'md5': '2b808ffb00fc47b884a172ca5d13053c',
  97         'info_dict': {
  98             'id': '6918',
  99             'display_id': 'biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij',
 100             'ext': 'mp4',
 101             'title': 'Luigi Di Maio: la psicosi di Stanislawskij',
 102             'description': 'md5:3c7a4303aef85868f867a26f5cc14813',
 103             'thumbnail': r're:^https?://.*\.jpe?g',
 104             'upload_date': '20160524',
 105             'timestamp': 1464076800,
 106             'series': 'Biografie imbarazzanti',
 107             'season_number': 1,
 108             'episode': 'Episode 1',
 109             'episode_number': 1,
 110         },
 111     }, {
 112         'url': 'https://es.dplay.com/dmax/la-fiebre-del-oro/temporada-8-episodio-1/',
 113         'info_dict': {
 114             'id': '21652',
 115             'display_id': 'la-fiebre-del-oro/temporada-8-episodio-1',
 116             'ext': 'mp4',
 117             'title': 'Episodio 1',
 118             'description': 'md5:b9dcff2071086e003737485210675f69',
 119             'thumbnail': r're:^https?://.*\.png',
 120             'upload_date': '20180709',
 121             'timestamp': 1531173540,
 122             'series': 'La fiebre del oro',
 123             'season_number': 8,
 124             'episode': 'Episode 1',
 125             'episode_number': 1,
 126         },
 127         'params': {
 128             'skip_download': True,
 129         },
 130     }, {
 131         'url': 'https://www.dplay.fi/videot/shifting-gears-with-aaron-kaufman/episode-16',
 132         'only_matching': True,
 133     }, {
 134         'url': 'https://www.dplay.jp/video/gold-rush/24086',
 135         'only_matching': True,
 136     }, {
 137         'url': 'https://www.discoveryplus.se/videos/nugammalt-77-handelser-som-format-sverige/nugammalt-77-handelser-som-format-sverige-101',
 138         'only_matching': True,
 139     }, {
 140         'url': 'https://www.discoveryplus.dk/videoer/ted-bundy-mind-of-a-monster/ted-bundy-mind-of-a-monster',
 141         'only_matching': True,
 142     }, {
 143         'url': 'https://www.discoveryplus.no/videoer/i-kongens-klr/sesong-1-episode-7',
 144         'only_matching': True,
 145     }, {
 146         'url': 'https://www.discoveryplus.it/videos/biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij',
 147         'only_matching': True,
 148     }, {
 149         'url': 'https://www.discoveryplus.es/videos/la-fiebre-del-oro/temporada-8-episodio-1',
 150         'only_matching': True,
 151     }, {
 152         'url': 'https://www.discoveryplus.fi/videot/shifting-gears-with-aaron-kaufman/episode-16',
 153         'only_matching': True,
 154     }]
 155
 156     def _process_errors(self, e, geo_countries):
 157         info = self._parse_json(e.cause.read().decode('utf-8'), None)
 158         error = info['errors'][0]
 159         error_code = error.get('code')
 160         if error_code == 'access.denied.geoblocked':
 161             self.raise_geo_restricted(countries=geo_countries)
 162         elif error_code in ('access.denied.missingpackage', 'invalid.token'):
 163             raise ExtractorError(
 164                 'This video is only available for registered users. You may want to use --cookies.', expected=True)
 165         raise ExtractorError(info['errors'][0]['detail'], expected=True)
 166
 167     def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
 168         headers['Authorization'] = 'Bearer ' + self._download_json(
 169             disco_base + 'token', display_id, 'Downloading token',
 170             query={
 171                 'realm': realm,
 172             })['data']['attributes']['token']
 173
 174     def _download_video_playback_info(self, disco_base, video_id, headers):
 175         streaming = self._download_json(
 176             disco_base + 'playback/videoPlaybackInfo/' + video_id,
 177             video_id, headers=headers)['data']['attributes']['streaming']
 178         streaming_list = []
 179         for format_id, format_dict in streaming.items():
 180             streaming_list.append({
 181                 'type': format_id,
 182                 'url': format_dict.get('url'),
 183             })
 184         return streaming_list
 185
 186     def _get_disco_api_info(self, url, display_id, disco_host, realm, country):
 187         geo_countries = [country.upper()]
 188         self._initialize_geo_bypass({
 189             'countries': geo_countries,
 190         })
 191         disco_base = 'https://%s/' % disco_host
 192         headers = {
 193             'Referer': url,
 194         }
 195         self._update_disco_api_headers(headers, disco_base, display_id, realm)
 196         try:
 197             video = self._download_json(
 198                 disco_base + 'content/videos/' + display_id, display_id,
 199                 headers=headers, query={
 200                     'fields[channel]': 'name',
 201                     'fields[image]': 'height,src,width',
 202                     'fields[show]': 'name',
 203                     'fields[tag]': 'name',
 204                     'fields[video]': 'description,episodeNumber,name,publishStart,seasonNumber,videoDuration',
 205                     'include': 'images,primaryChannel,show,tags'
 206                 })
 207         except ExtractorError as e:
 208             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
 209                 self._process_errors(e, geo_countries)
 210             raise
 211         video_id = video['data']['id']
 212         info = video['data']['attributes']
 213         title = info['name'].strip()
 214         formats = []
 215         try:
 216             streaming = self._download_video_playback_info(
 217                 disco_base, video_id, headers)
 218         except ExtractorError as e:
 219             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
 220                 self._process_errors(e, geo_countries)
 221             raise
 222         for format_dict in streaming:
 223             if not isinstance(format_dict, dict):
 224                 continue
 225             format_url = format_dict.get('url')
 226             if not format_url:
 227                 continue
 228             format_id = format_dict.get('type')
 229             ext = determine_ext(format_url)
 230             if format_id == 'dash' or ext == 'mpd':
 231                 formats.extend(self._extract_mpd_formats(
 232                     format_url, display_id, mpd_id='dash', fatal=False))
 233             elif format_id == 'hls' or ext == 'm3u8':
 234                 formats.extend(self._extract_m3u8_formats(
 235                     format_url, display_id, 'mp4',
 236                     entry_protocol='m3u8_native', m3u8_id='hls',
 237                     fatal=False))
 238             else:
 239                 formats.append({
 240                     'url': format_url,
 241                     'format_id': format_id,
 242                 })
 243         self._sort_formats(formats)
 244
 245         creator = series = None
 246         tags = []
 247         thumbnails = []
 248         included = video.get('included') or []
 249         if isinstance(included, list):
 250             for e in included:
 251                 attributes = e.get('attributes')
 252                 if not attributes:
 253                     continue
 254                 e_type = e.get('type')
 255                 if e_type == 'channel':
 256                     creator = attributes.get('name')
 257                 elif e_type == 'image':
 258                     src = attributes.get('src')
 259                     if src:
 260                         thumbnails.append({
 261                             'url': src,
 262                             'width': int_or_none(attributes.get('width')),
 263                             'height': int_or_none(attributes.get('height')),
 264                         })
 265                 if e_type == 'show':
 266                     series = attributes.get('name')
 267                 elif e_type == 'tag':
 268                     name = attributes.get('name')
 269                     if name:
 270                         tags.append(name)
 271
 272         return {
 273             'id': video_id,
 274             'display_id': display_id,
 275             'title': title,
 276             'description': strip_or_none(info.get('description')),
 277             'duration': float_or_none(info.get('videoDuration'), 1000),
 278             'timestamp': unified_timestamp(info.get('publishStart')),
 279             'series': series,
 280             'season_number': int_or_none(info.get('seasonNumber')),
 281             'episode_number': int_or_none(info.get('episodeNumber')),
 282             'creator': creator,
 283             'tags': tags,
 284             'thumbnails': thumbnails,
 285             'formats': formats,
 286         }
 287
 288     def _real_extract(self, url):
 289         mobj = self._match_valid_url(url)
 290         display_id = mobj.group('id')
 291         domain = mobj.group('domain').lstrip('www.')
 292         country = mobj.group('country') or mobj.group('subdomain_country') or mobj.group('plus_country')
 293         host = 'disco-api.' + domain if domain[0] == 'd' else 'eu2-prod.disco-api.com'
 294         return self._get_disco_api_info(
 295             url, display_id, host, 'dplay' + country, country)
 296
 297
 298 class HGTVDeIE(DPlayIE):
 299     _VALID_URL = r'https?://de\.hgtv\.com/sendungen' + DPlayIE._PATH_REGEX
 300     _TESTS = [{
 301         'url': 'https://de.hgtv.com/sendungen/tiny-house-klein-aber-oho/wer-braucht-schon-eine-toilette/',
 302         'info_dict': {
 303             'id': '151205',
 304             'display_id': 'tiny-house-klein-aber-oho/wer-braucht-schon-eine-toilette',
 305             'ext': 'mp4',
 306             'title': 'Wer braucht schon eine Toilette',
 307             'description': 'md5:05b40a27e7aed2c9172de34d459134e2',
 308             'duration': 1177.024,
 309             'timestamp': 1595705400,
 310             'upload_date': '20200725',
 311             'creator': 'HGTV',
 312             'series': 'Tiny House - klein, aber oho',
 313             'season_number': 3,
 314             'episode_number': 3,
 315         },
 316         'params': {
 317             'format': 'bestvideo',
 318         },
 319     }]
 320
 321     def _real_extract(self, url):
 322         display_id = self._match_id(url)
 323         return self._get_disco_api_info(
 324             url, display_id, 'eu1-prod.disco-api.com', 'hgtv', 'de')
 325
 326
 327 class DiscoveryPlusIE(DPlayIE):
 328     _VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/(?:\w{2}/)?video' + DPlayIE._PATH_REGEX
 329     _TESTS = [{
 330         'url': 'https://www.discoveryplus.com/video/property-brothers-forever-home/food-and-family',
 331         'info_dict': {
 332             'id': '1140794',
 333             'display_id': 'property-brothers-forever-home/food-and-family',
 334             'ext': 'mp4',
 335             'title': 'Food and Family',
 336             'description': 'The brothers help a Richmond family expand their single-level home.',
 337             'duration': 2583.113,
 338             'timestamp': 1609304400,
 339             'upload_date': '20201230',
 340             'creator': 'HGTV',
 341             'series': 'Property Brothers: Forever Home',
 342             'season_number': 1,
 343             'episode_number': 1,
 344         },
 345         'skip': 'Available for Premium users',
 346     }, {
 347         'url': 'https://discoveryplus.com/ca/video/bering-sea-gold-discovery-ca/goldslingers',
 348         'only_matching': True,
 349     }]
 350
 351     _PRODUCT = 'dplus_us'
 352     _API_URL = 'us1-prod-direct.discoveryplus.com'
 353
 354     def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
 355         headers['x-disco-client'] = f'WEB:UNKNOWN:{self._PRODUCT}:25.2.6'
 356
 357     def _download_video_playback_info(self, disco_base, video_id, headers):
 358         return self._download_json(
 359             disco_base + 'playback/v3/videoPlaybackInfo',
 360             video_id, headers=headers, data=json.dumps({
 361                 'deviceInfo': {
 362                     'adBlocker': False,
 363                 },
 364                 'videoId': video_id,
 365                 'wisteriaProperties': {
 366                     'platform': 'desktop',
 367                     'product': self._PRODUCT,
 368                 },
 369             }).encode('utf-8'))['data']['attributes']['streaming']
 370
 371     def _real_extract(self, url):
 372         display_id = self._match_id(url)
 373         return self._get_disco_api_info(
 374             url, display_id, self._API_URL, 'go', 'us')
 375
 376
 377 class ScienceChannelIE(DiscoveryPlusIE):
 378     _VALID_URL = r'https?://(?:www\.)?sciencechannel\.com/video' + DPlayIE._PATH_REGEX
 379     _TESTS = [{
 380         'url': 'https://www.sciencechannel.com/video/strangest-things-science-atve-us/nazi-mystery-machine',
 381         'info_dict': {
 382             'id': '2842849',
 383             'display_id': 'strangest-things-science-atve-us/nazi-mystery-machine',
 384             'ext': 'mp4',
 385             'title': 'Nazi Mystery Machine',
 386             'description': 'Experts investigate the secrets of a revolutionary encryption machine.',
 387             'season_number': 1,
 388             'episode_number': 1,
 389         },
 390         'skip': 'Available for Premium users',
 391     }]
 392
 393     _PRODUCT = 'sci'
 394     _API_URL = 'us1-prod-direct.sciencechannel.com'
 395
 396
 397 class DIYNetworkIE(DiscoveryPlusIE):
 398     _VALID_URL = r'https?://(?:watch\.)?diynetwork\.com/video' + DPlayIE._PATH_REGEX
 399     _TESTS = [{
 400         'url': 'https://watch.diynetwork.com/video/pool-kings-diy-network/bringing-beach-life-to-texas',
 401         'info_dict': {
 402             'id': '2309730',
 403             'display_id': 'pool-kings-diy-network/bringing-beach-life-to-texas',
 404             'ext': 'mp4',
 405             'title': 'Bringing Beach Life to Texas',
 406             'description': 'The Pool Kings give a family a day at the beach in their own backyard.',
 407             'season_number': 10,
 408             'episode_number': 2,
 409         },
 410         'skip': 'Available for Premium users',
 411     }]
 412
 413     _PRODUCT = 'diy'
 414     _API_URL = 'us1-prod-direct.watch.diynetwork.com'
 415
 416
 417 class AnimalPlanetIE(DiscoveryPlusIE):
 418     _VALID_URL = r'https?://(?:www\.)?animalplanet\.com/video' + DPlayIE._PATH_REGEX
 419     _TESTS = [{
 420         'url': 'https://www.animalplanet.com/video/north-woods-law-animal-planet/squirrel-showdown',
 421         'info_dict': {
 422             'id': '3338923',
 423             'display_id': 'north-woods-law-animal-planet/squirrel-showdown',
 424             'ext': 'mp4',
 425             'title': 'Squirrel Showdown',
 426             'description': 'A woman is suspected of being in possession of flying squirrel kits.',
 427             'season_number': 16,
 428             'episode_number': 11,
 429         },
 430         'skip': 'Available for Premium users',
 431     }]
 432
 433     _PRODUCT = 'apl'
 434     _API_URL = 'us1-prod-direct.animalplanet.com'