yt_dlp/extractor/drtv.py

   1 import json
   2 import uuid
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     ExtractorError,
   7     int_or_none,
   8     mimetype2ext,
   9     parse_iso8601,
  10     try_call,
  11     update_url_query,
  12     url_or_none,
  13 )
  14 from ..utils.traversal import traverse_obj
  15
  16 SERIES_API = 'https://production-cdn.dr-massive.com/api/page?device=web_browser&item_detail_expand=all&lang=da&max_list_prefetch=3&path=%s'
  17
  18
  19 class DRTVIE(InfoExtractor):
  20     _VALID_URL = r'''(?x)
  21                     https?://
  22                         (?:
  23                             (?:www\.)?dr\.dk/tv/se(?:/ondemand)?/(?:[^/?#]+/)*|
  24                             (?:www\.)?(?:dr\.dk|dr-massive\.com)/drtv/(?:se|episode|program)/
  25                         )
  26                         (?P<id>[\da-z_-]+)
  27                     '''
  28     _GEO_BYPASS = False
  29     _GEO_COUNTRIES = ['DK']
  30     IE_NAME = 'drtv'
  31     _TESTS = [{
  32         'url': 'https://www.dr.dk/tv/se/boern/ultra/klassen-ultra/klassen-darlig-taber-10',
  33         'md5': '25e659cccc9a2ed956110a299fdf5983',
  34         'info_dict': {
  35             'id': 'klassen-darlig-taber-10',
  36             'ext': 'mp4',
  37             'title': 'Klassen - Dårlig taber (10)',
  38             'description': 'md5:815fe1b7fa656ed80580f31e8b3c79aa',
  39             'timestamp': 1539085800,
  40             'upload_date': '20181009',
  41             'duration': 606.84,
  42             'series': 'Klassen',
  43             'season': 'Klassen I',
  44             'season_number': 1,
  45             'season_id': 'urn:dr:mu:bundle:57d7e8216187a4031cfd6f6b',
  46             'episode': 'Episode 10',
  47             'episode_number': 10,
  48             'release_year': 2016,
  49         },
  50         'expected_warnings': ['Unable to download f4m manifest'],
  51         'skip': 'this video has been removed',
  52     }, {
  53         # with SignLanguage formats
  54         'url': 'https://www.dr.dk/tv/se/historien-om-danmark/-/historien-om-danmark-stenalder',
  55         'info_dict': {
  56             'id': '00831690010',
  57             'ext': 'mp4',
  58             'title': 'Historien om Danmark: Stenalder',
  59             'description': 'md5:8c66dcbc1669bbc6f873879880f37f2a',
  60             'timestamp': 1546628400,
  61             'upload_date': '20190104',
  62             'duration': 3504.619,
  63             'formats': 'mincount:20',
  64             'release_year': 2017,
  65             'season_id': 'urn:dr:mu:bundle:5afc03ad6187a4065ca5fd35',
  66             'season_number': 1,
  67             'season': 'Historien om Danmark',
  68             'series': 'Historien om Danmark',
  69         },
  70         'skip': 'this video has been removed',
  71     }, {
  72         'url': 'https://www.dr.dk/drtv/se/frank-and-kastaniegaarden_71769',
  73         'info_dict': {
  74             'id': '00951930010',
  75             'ext': 'mp4',
  76             'title': 'Frank & Kastaniegaarden',
  77             'description': 'md5:974e1780934cf3275ef10280204bccb0',
  78             'release_timestamp': 1546545600,
  79             'release_date': '20190103',
  80             'duration': 2576,
  81             'season': 'Frank & Kastaniegaarden',
  82             'season_id': '67125',
  83             'release_year': 2019,
  84             'season_number': 2019,
  85             'series': 'Frank & Kastaniegaarden',
  86             'episode_number': 1,
  87             'episode': 'Frank & Kastaniegaarden',
  88             'thumbnail': r're:https?://.+',
  89         },
  90         'params': {
  91             'skip_download': True,
  92         },
  93     }, {
  94         # Foreign and Regular subtitle track
  95         'url': 'https://www.dr.dk/drtv/se/spise-med-price_-pasta-selv_397445',
  96         'info_dict': {
  97             'id': '00212301010',
  98             'ext': 'mp4',
  99             'episode_number': 1,
 100             'title': 'Spise med Price: Pasta Selv',
 101             'alt_title': '1. Pasta Selv',
 102             'release_date': '20230807',
 103             'description': 'md5:2da9060524fed707810d71080b3d0cd8',
 104             'duration': 1750,
 105             'season': 'Spise med Price',
 106             'release_timestamp': 1691438400,
 107             'season_id': '397440',
 108             'episode': 'Spise med Price: Pasta Selv',
 109             'thumbnail': r're:https?://.+',
 110             'season_number': 15,
 111             'series': 'Spise med Price',
 112             'release_year': 2022,
 113             'subtitles': 'mincount:2',
 114         },
 115         'params': {
 116             'skip_download': 'm3u8',
 117         },
 118     }, {
 119         'url': 'https://www.dr.dk/drtv/episode/bonderoeven_71769',
 120         'only_matching': True,
 121     }, {
 122         'url': 'https://dr-massive.com/drtv/se/bonderoeven_71769',
 123         'only_matching': True,
 124     }, {
 125         'url': 'https://www.dr.dk/drtv/program/jagten_220924',
 126         'only_matching': True,
 127     }]
 128
 129     SUBTITLE_LANGS = {
 130         'DanishLanguageSubtitles': 'da',
 131         'ForeignLanguageSubtitles': 'da_foreign',
 132         'CombinedLanguageSubtitles': 'da_combined',
 133     }
 134
 135     _TOKEN = None
 136
 137     def _real_initialize(self):
 138         if self._TOKEN:
 139             return
 140
 141         token_response = self._download_json(
 142             'https://isl.dr-massive.com/api/authorization/anonymous-sso', None,
 143             note='Downloading anonymous token', headers={
 144                 'content-type': 'application/json',
 145             }, query={
 146                 'device': 'phone_android',
 147                 'lang': 'da',
 148                 'supportFallbackToken': 'true',
 149             }, data=json.dumps({
 150                 'deviceId': str(uuid.uuid4()),
 151                 'scopes': ['Catalog'],
 152                 'optout': True,
 153             }).encode())
 154
 155         self._TOKEN = traverse_obj(
 156             token_response, (lambda _, x: x['type'] == 'UserAccount', 'value', {str}), get_all=False)
 157         if not self._TOKEN:
 158             raise ExtractorError('Unable to get anonymous token')
 159
 160     def _real_extract(self, url):
 161         url_slug = self._match_id(url)
 162         webpage = self._download_webpage(url, url_slug)
 163
 164         json_data = self._search_json(
 165             r'window\.__data\s*=', webpage, 'data', url_slug, fatal=False) or {}
 166         item = traverse_obj(
 167             json_data, ('cache', 'page', ..., (None, ('entries', 0)), 'item', {dict}), get_all=False)
 168         if item:
 169             item_id = item.get('id')
 170         else:
 171             item_id = url_slug.rsplit('_', 1)[-1]
 172             item = self._download_json(
 173                 f'https://production-cdn.dr-massive.com/api/items/{item_id}', item_id,
 174                 note='Attempting to download backup item data', query={
 175                     'device': 'web_browser',
 176                     'expand': 'all',
 177                     'ff': 'idp,ldp,rpt',
 178                     'geoLocation': 'dk',
 179                     'isDeviceAbroad': 'false',
 180                     'lang': 'da',
 181                     'segments': 'drtv,optedout',
 182                     'sub': 'Anonymous',
 183                 })
 184
 185         video_id = try_call(lambda: item['customId'].rsplit(':', 1)[-1]) or item_id
 186         stream_data = self._download_json(
 187             f'https://production.dr-massive.com/api/account/items/{item_id}/videos', video_id,
 188             note='Downloading stream data', query={
 189                 'delivery': 'stream',
 190                 'device': 'web_browser',
 191                 'ff': 'idp,ldp,rpt',
 192                 'lang': 'da',
 193                 'resolution': 'HD-1080',
 194                 'sub': 'Anonymous',
 195             }, headers={'authorization': f'Bearer {self._TOKEN}'})
 196
 197         formats = []
 198         subtitles = {}
 199         for stream in traverse_obj(stream_data, (lambda _, x: x['url'])):
 200             format_id = stream.get('format', 'na')
 201             access_service = stream.get('accessService')
 202             preference = None
 203             subtitle_suffix = ''
 204             if access_service in ('SpokenSubtitles', 'SignLanguage', 'VisuallyInterpreted'):
 205                 preference = -1
 206                 format_id += f'-{access_service}'
 207                 subtitle_suffix = f'-{access_service}'
 208             elif access_service == 'StandardVideo':
 209                 preference = 1
 210             fmts, subs = self._extract_m3u8_formats_and_subtitles(
 211                 stream.get('url'), video_id, ext='mp4', preference=preference, m3u8_id=format_id, fatal=False)
 212             formats.extend(fmts)
 213
 214             api_subtitles = traverse_obj(stream, ('subtitles', lambda _, v: url_or_none(v['link']), {dict}))
 215             if not api_subtitles:
 216                 self._merge_subtitles(subs, target=subtitles)
 217
 218             for sub_track in api_subtitles:
 219                 lang = sub_track.get('language') or 'da'
 220                 subtitles.setdefault(self.SUBTITLE_LANGS.get(lang, lang) + subtitle_suffix, []).append({
 221                     'url': sub_track['link'],
 222                     'ext': mimetype2ext(sub_track.get('format')) or 'vtt',
 223                 })
 224
 225         if not formats and traverse_obj(item, ('season', 'customFields', 'IsGeoRestricted')):
 226             self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
 227
 228         return {
 229             'id': video_id,
 230             'formats': formats,
 231             'subtitles': subtitles,
 232             **traverse_obj(item, {
 233                 'title': 'title',
 234                 'alt_title': 'contextualTitle',
 235                 'description': 'description',
 236                 'thumbnail': ('images', 'wallpaper'),
 237                 'release_timestamp': ('customFields', 'BroadcastTimeDK', {parse_iso8601}),
 238                 'duration': ('duration', {int_or_none}),
 239                 'series': ('season', 'show', 'title'),
 240                 'season': ('season', 'title'),
 241                 'season_number': ('season', 'seasonNumber', {int_or_none}),
 242                 'season_id': 'seasonId',
 243                 'episode': 'episodeName',
 244                 'episode_number': ('episodeNumber', {int_or_none}),
 245                 'release_year': ('releaseYear', {int_or_none}),
 246             }),
 247         }
 248
 249
 250 class DRTVLiveIE(InfoExtractor):
 251     IE_NAME = 'drtv:live'
 252     _VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv|TV)/live/(?P<id>[\da-z-]+)'
 253     _GEO_COUNTRIES = ['DK']
 254     _TEST = {
 255         'url': 'https://www.dr.dk/tv/live/dr1',
 256         'info_dict': {
 257             'id': 'dr1',
 258             'ext': 'mp4',
 259             'title': 're:^DR1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
 260         },
 261         'params': {
 262             # m3u8 download
 263             'skip_download': True,
 264         },
 265     }
 266
 267     def _real_extract(self, url):
 268         channel_id = self._match_id(url)
 269         channel_data = self._download_json(
 270             'https://www.dr.dk/mu-online/api/1.0/channel/' + channel_id,
 271             channel_id)
 272         title = channel_data['Title']
 273
 274         formats = []
 275         for streaming_server in channel_data.get('StreamingServers', []):
 276             server = streaming_server.get('Server')
 277             if not server:
 278                 continue
 279             link_type = streaming_server.get('LinkType')
 280             for quality in streaming_server.get('Qualities', []):
 281                 for stream in quality.get('Streams', []):
 282                     stream_path = stream.get('Stream')
 283                     if not stream_path:
 284                         continue
 285                     stream_url = update_url_query(
 286                         f'{server}/{stream_path}', {'b': ''})
 287                     if link_type == 'HLS':
 288                         formats.extend(self._extract_m3u8_formats(
 289                             stream_url, channel_id, 'mp4',
 290                             m3u8_id=link_type, fatal=False, live=True))
 291                     elif link_type == 'HDS':
 292                         formats.extend(self._extract_f4m_formats(update_url_query(
 293                             f'{server}/{stream_path}', {'hdcore': '3.7.0'}),
 294                             channel_id, f4m_id=link_type, fatal=False))
 295
 296         return {
 297             'id': channel_id,
 298             'title': title,
 299             'thumbnail': channel_data.get('PrimaryImageUri'),
 300             'formats': formats,
 301             'is_live': True,
 302         }
 303
 304
 305 class DRTVSeasonIE(InfoExtractor):
 306     IE_NAME = 'drtv:season'
 307     _VALID_URL = r'https?://(?:www\.)?(?:dr\.dk|dr-massive\.com)/drtv/saeson/(?P<display_id>[\w-]+)_(?P<id>\d+)'
 308     _GEO_COUNTRIES = ['DK']
 309     _TESTS = [{
 310         'url': 'https://www.dr.dk/drtv/saeson/frank-and-kastaniegaarden_9008',
 311         'info_dict': {
 312             'id': '9008',
 313             'display_id': 'frank-and-kastaniegaarden',
 314             'title': 'Frank & Kastaniegaarden',
 315             'series': 'Frank & Kastaniegaarden',
 316             'season_number': 2008,
 317             'alt_title': 'Season 2008',
 318         },
 319         'playlist_mincount': 8,
 320     }, {
 321         'url': 'https://www.dr.dk/drtv/saeson/frank-and-kastaniegaarden_8761',
 322         'info_dict': {
 323             'id': '8761',
 324             'display_id': 'frank-and-kastaniegaarden',
 325             'title': 'Frank & Kastaniegaarden',
 326             'series': 'Frank & Kastaniegaarden',
 327             'season_number': 2009,
 328             'alt_title': 'Season 2009',
 329         },
 330         'playlist_mincount': 19,
 331     }]
 332
 333     def _real_extract(self, url):
 334         display_id, season_id = self._match_valid_url(url).group('display_id', 'id')
 335         data = self._download_json(SERIES_API % f'/saeson/{display_id}_{season_id}', display_id)
 336
 337         entries = [{
 338             '_type': 'url',
 339             'url': f'https://www.dr.dk/drtv{episode["path"]}',
 340             'ie_key': DRTVIE.ie_key(),
 341             'title': episode.get('title'),
 342             'alt_title': episode.get('contextualTitle'),
 343             'episode': episode.get('episodeName'),
 344             'description': episode.get('shortDescription'),
 345             'series': traverse_obj(data, ('entries', 0, 'item', 'title')),
 346             'season_number': traverse_obj(data, ('entries', 0, 'item', 'seasonNumber')),
 347             'episode_number': episode.get('episodeNumber'),
 348         } for episode in traverse_obj(data, ('entries', 0, 'item', 'episodes', 'items'))]
 349
 350         return {
 351             '_type': 'playlist',
 352             'id': season_id,
 353             'display_id': display_id,
 354             'title': traverse_obj(data, ('entries', 0, 'item', 'title')),
 355             'alt_title': traverse_obj(data, ('entries', 0, 'item', 'contextualTitle')),
 356             'series': traverse_obj(data, ('entries', 0, 'item', 'title')),
 357             'entries': entries,
 358             'season_number': traverse_obj(data, ('entries', 0, 'item', 'seasonNumber')),
 359         }
 360
 361
 362 class DRTVSeriesIE(InfoExtractor):
 363     IE_NAME = 'drtv:series'
 364     _VALID_URL = r'https?://(?:www\.)?(?:dr\.dk|dr-massive\.com)/drtv/serie/(?P<display_id>[\w-]+)_(?P<id>\d+)'
 365     _GEO_COUNTRIES = ['DK']
 366     _TESTS = [{
 367         'url': 'https://www.dr.dk/drtv/serie/frank-and-kastaniegaarden_6954',
 368         'info_dict': {
 369             'id': '6954',
 370             'display_id': 'frank-and-kastaniegaarden',
 371             'title': 'Frank & Kastaniegaarden',
 372             'series': 'Frank & Kastaniegaarden',
 373             'alt_title': '',
 374         },
 375         'playlist_mincount': 15,
 376     }]
 377
 378     def _real_extract(self, url):
 379         display_id, series_id = self._match_valid_url(url).group('display_id', 'id')
 380         data = self._download_json(SERIES_API % f'/serie/{display_id}_{series_id}', display_id)
 381
 382         entries = [{
 383             '_type': 'url',
 384             'url': f'https://www.dr.dk/drtv{season.get("path")}',
 385             'ie_key': DRTVSeasonIE.ie_key(),
 386             'title': season.get('title'),
 387             'alt_title': season.get('contextualTitle'),
 388             'series': traverse_obj(data, ('entries', 0, 'item', 'title')),
 389             'season_number': traverse_obj(data, ('entries', 0, 'item', 'seasonNumber')),
 390         } for season in traverse_obj(data, ('entries', 0, 'item', 'show', 'seasons', 'items'))]
 391
 392         return {
 393             '_type': 'playlist',
 394             'id': series_id,
 395             'display_id': display_id,
 396             'title': traverse_obj(data, ('entries', 0, 'item', 'title')),
 397             'alt_title': traverse_obj(data, ('entries', 0, 'item', 'contextualTitle')),
 398             'series': traverse_obj(data, ('entries', 0, 'item', 'title')),
 399             'entries': entries,
 400         }