yt_dlp/extractor/nrk.py

   1 import itertools
   2 import random
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..networking.exceptions import HTTPError
   7 from ..utils import (
   8     ExtractorError,
   9     determine_ext,
  10     int_or_none,
  11     parse_duration,
  12     parse_iso8601,
  13     str_or_none,
  14     try_get,
  15     url_or_none,
  16     urljoin,
  17 )
  18
  19
  20 class NRKBaseIE(InfoExtractor):
  21     _GEO_COUNTRIES = ['NO']
  22     _CDN_REPL_REGEX = r'''(?x)://
  23         (?:
  24             nrkod\d{1,2}-httpcache0-47115-cacheod0\.dna\.ip-only\.net/47115-cacheod0|
  25             nrk-od-no\.telenorcdn\.net|
  26             minicdn-od\.nrk\.no/od/nrkhd-osl-rr\.netwerk\.no/no
  27         )/'''
  28
  29     def _extract_nrk_formats(self, asset_url, video_id):
  30         if re.match(r'https?://[^/]+\.akamaihd\.net/i/', asset_url):
  31             return self._extract_akamai_formats(asset_url, video_id)
  32         asset_url = re.sub(r'(?:bw_(?:low|high)=\d+|no_audio_only)&?', '', asset_url)
  33         formats = self._extract_m3u8_formats(
  34             asset_url, video_id, 'mp4', 'm3u8_native', fatal=False)
  35         if not formats and re.search(self._CDN_REPL_REGEX, asset_url):
  36             formats = self._extract_m3u8_formats(
  37                 re.sub(self._CDN_REPL_REGEX, '://nrk-od-%02d.akamaized.net/no/' % random.randint(0, 99), asset_url),
  38                 video_id, 'mp4', 'm3u8_native', fatal=False)
  39         return formats
  40
  41     def _raise_error(self, data):
  42         MESSAGES = {
  43             'ProgramRightsAreNotReady': 'Du kan dessverre ikke se eller høre programmet',
  44             'ProgramRightsHasExpired': 'Programmet har gått ut',
  45             'NoProgramRights': 'Ikke tilgjengelig',
  46             'ProgramIsGeoBlocked': 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',
  47         }
  48         message_type = data.get('messageType', '')
  49         # Can be ProgramIsGeoBlocked or ChannelIsGeoBlocked*
  50         if 'IsGeoBlocked' in message_type or try_get(data, lambda x: x['usageRights']['isGeoBlocked']) is True:
  51             self.raise_geo_restricted(
  52                 msg=MESSAGES.get('ProgramIsGeoBlocked'),
  53                 countries=self._GEO_COUNTRIES)
  54         message = data.get('endUserMessage') or MESSAGES.get(message_type, message_type)
  55         raise ExtractorError(f'{self.IE_NAME} said: {message}', expected=True)
  56
  57     def _call_api(self, path, video_id, item=None, note=None, fatal=True, query=None):
  58         return self._download_json(
  59             urljoin('https://psapi.nrk.no/', path),
  60             video_id, note or f'Downloading {item} JSON',
  61             fatal=fatal, query=query)
  62
  63
  64 class NRKIE(NRKBaseIE):
  65     _VALID_URL = r'''(?x)
  66                         (?:
  67                             nrk:|
  68                             https?://
  69                                 (?:
  70                                     (?:www\.)?nrk\.no/video/(?:PS\*|[^_]+_)|
  71                                     v8[-.]psapi\.nrk\.no/mediaelement/
  72                                 )
  73                             )
  74                             (?P<id>[^?\#&]+)
  75                         '''
  76
  77     _TESTS = [{
  78         # video
  79         'url': 'http://www.nrk.no/video/PS*150533',
  80         'md5': 'f46be075326e23ad0e524edfcb06aeb6',
  81         'info_dict': {
  82             'id': '150533',
  83             'ext': 'mp4',
  84             'title': 'Dompap og andre fugler i Piip-Show',
  85             'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f',
  86             'duration': 262,
  87         },
  88     }, {
  89         # audio
  90         'url': 'http://www.nrk.no/video/PS*154915',
  91         # MD5 is unstable
  92         'info_dict': {
  93             'id': '154915',
  94             'ext': 'mp4',
  95             'title': 'Slik høres internett ut når du er blind',
  96             'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
  97             'duration': 20,
  98         },
  99     }, {
 100         'url': 'nrk:ecc1b952-96dc-4a98-81b9-5296dc7a98d9',
 101         'only_matching': True,
 102     }, {
 103         'url': 'nrk:clip/7707d5a3-ebe7-434a-87d5-a3ebe7a34a70',
 104         'only_matching': True,
 105     }, {
 106         'url': 'https://v8-psapi.nrk.no/mediaelement/ecc1b952-96dc-4a98-81b9-5296dc7a98d9',
 107         'only_matching': True,
 108     }, {
 109         'url': 'https://www.nrk.no/video/dompap-og-andre-fugler-i-piip-show_150533',
 110         'only_matching': True,
 111     }, {
 112         'url': 'https://www.nrk.no/video/humor/kommentatorboksen-reiser-til-sjos_d1fda11f-a4ad-437a-a374-0398bc84e999',
 113         'only_matching': True,
 114     }, {
 115         # podcast
 116         'url': 'nrk:l_96f4f1b0-de54-4e6a-b4f1-b0de54fe6af8',
 117         'only_matching': True,
 118     }, {
 119         'url': 'nrk:podcast/l_96f4f1b0-de54-4e6a-b4f1-b0de54fe6af8',
 120         'only_matching': True,
 121     }, {
 122         # clip
 123         'url': 'nrk:150533',
 124         'only_matching': True,
 125     }, {
 126         'url': 'nrk:clip/150533',
 127         'only_matching': True,
 128     }, {
 129         # program
 130         'url': 'nrk:MDDP12000117',
 131         'only_matching': True,
 132     }, {
 133         'url': 'nrk:program/ENRK10100318',
 134         'only_matching': True,
 135     }, {
 136         # direkte
 137         'url': 'nrk:nrk1',
 138         'only_matching': True,
 139     }, {
 140         'url': 'nrk:channel/nrk1',
 141         'only_matching': True,
 142     }]
 143
 144     def _real_extract(self, url):
 145         video_id = self._match_id(url).split('/')[-1]
 146
 147         def call_playback_api(item, query=None):
 148             try:
 149                 return self._call_api(f'playback/{item}/program/{video_id}', video_id, item, query=query)
 150             except ExtractorError as e:
 151                 if isinstance(e.cause, HTTPError) and e.cause.status == 400:
 152                     return self._call_api(f'playback/{item}/{video_id}', video_id, item, query=query)
 153                 raise
 154
 155         # known values for preferredCdn: akamai, iponly, minicdn and telenor
 156         manifest = call_playback_api('manifest', {'preferredCdn': 'akamai'})
 157
 158         video_id = try_get(manifest, lambda x: x['id'], str) or video_id
 159
 160         if manifest.get('playability') == 'nonPlayable':
 161             self._raise_error(manifest['nonPlayable'])
 162
 163         playable = manifest['playable']
 164
 165         formats = []
 166         for asset in playable['assets']:
 167             if not isinstance(asset, dict):
 168                 continue
 169             if asset.get('encrypted'):
 170                 continue
 171             format_url = url_or_none(asset.get('url'))
 172             if not format_url:
 173                 continue
 174             asset_format = (asset.get('format') or '').lower()
 175             if asset_format == 'hls' or determine_ext(format_url) == 'm3u8':
 176                 formats.extend(self._extract_nrk_formats(format_url, video_id))
 177             elif asset_format == 'mp3':
 178                 formats.append({
 179                     'url': format_url,
 180                     'format_id': asset_format,
 181                     'vcodec': 'none',
 182                 })
 183
 184         data = call_playback_api('metadata')
 185
 186         preplay = data['preplay']
 187         titles = preplay['titles']
 188         title = titles['title']
 189         alt_title = titles.get('subtitle')
 190
 191         description = try_get(preplay, lambda x: x['description'].replace('\r', '\n'))
 192         duration = parse_duration(playable.get('duration')) or parse_duration(data.get('duration'))
 193
 194         thumbnails = []
 195         for image in try_get(
 196                 preplay, lambda x: x['poster']['images'], list) or []:
 197             if not isinstance(image, dict):
 198                 continue
 199             image_url = url_or_none(image.get('url'))
 200             if not image_url:
 201                 continue
 202             thumbnails.append({
 203                 'url': image_url,
 204                 'width': int_or_none(image.get('pixelWidth')),
 205                 'height': int_or_none(image.get('pixelHeight')),
 206             })
 207
 208         subtitles = {}
 209         for sub in try_get(playable, lambda x: x['subtitles'], list) or []:
 210             if not isinstance(sub, dict):
 211                 continue
 212             sub_url = url_or_none(sub.get('webVtt'))
 213             if not sub_url:
 214                 continue
 215             sub_key = str_or_none(sub.get('language')) or 'nb'
 216             sub_type = str_or_none(sub.get('type'))
 217             if sub_type:
 218                 sub_key += f'-{sub_type}'
 219             subtitles.setdefault(sub_key, []).append({
 220                 'url': sub_url,
 221             })
 222
 223         legal_age = try_get(
 224             data, lambda x: x['legalAge']['body']['rating']['code'], str)
 225         # https://en.wikipedia.org/wiki/Norwegian_Media_Authority
 226         age_limit = None
 227         if legal_age:
 228             if legal_age == 'A':
 229                 age_limit = 0
 230             elif legal_age.isdigit():
 231                 age_limit = int_or_none(legal_age)
 232
 233         is_series = try_get(data, lambda x: x['_links']['series']['name']) == 'series'
 234
 235         info = {
 236             'id': video_id,
 237             'title': title,
 238             'alt_title': alt_title,
 239             'description': description,
 240             'duration': duration,
 241             'thumbnails': thumbnails,
 242             'age_limit': age_limit,
 243             'formats': formats,
 244             'subtitles': subtitles,
 245             'timestamp': parse_iso8601(try_get(manifest, lambda x: x['availability']['onDemand']['from'], str)),
 246         }
 247
 248         if is_series:
 249             series = season_id = season_number = episode = episode_number = None
 250             programs = self._call_api(
 251                 f'programs/{video_id}', video_id, 'programs', fatal=False)
 252             if programs and isinstance(programs, dict):
 253                 series = str_or_none(programs.get('seriesTitle'))
 254                 season_id = str_or_none(programs.get('seasonId'))
 255                 season_number = int_or_none(programs.get('seasonNumber'))
 256                 episode = str_or_none(programs.get('episodeTitle'))
 257                 episode_number = int_or_none(programs.get('episodeNumber'))
 258             if not series:
 259                 series = title
 260             if alt_title:
 261                 title += f' - {alt_title}'
 262             if not season_number:
 263                 season_number = int_or_none(self._search_regex(
 264                     r'Sesong\s+(\d+)', description or '', 'season number',
 265                     default=None))
 266             if not episode:
 267                 episode = alt_title if is_series else None
 268             if not episode_number:
 269                 episode_number = int_or_none(self._search_regex(
 270                     r'^(\d+)\.', episode or '', 'episode number',
 271                     default=None))
 272             if not episode_number:
 273                 episode_number = int_or_none(self._search_regex(
 274                     r'\((\d+)\s*:\s*\d+\)', description or '',
 275                     'episode number', default=None))
 276             info.update({
 277                 'title': title,
 278                 'series': series,
 279                 'season_id': season_id,
 280                 'season_number': season_number,
 281                 'episode': episode,
 282                 'episode_number': episode_number,
 283             })
 284
 285         return info
 286
 287
 288 class NRKTVIE(InfoExtractor):
 289     IE_DESC = 'NRK TV and NRK Radio'
 290     _EPISODE_RE = r'(?P<id>[a-zA-Z]{4}\d{8})'
 291     _VALID_URL = rf'https?://(?:tv|radio)\.nrk(?:super)?\.no/(?:[^/]+/)*{_EPISODE_RE}'
 292     _TESTS = [{
 293         'url': 'https://tv.nrk.no/program/MDDP12000117',
 294         'md5': 'c4a5960f1b00b40d47db65c1064e0ab1',
 295         'info_dict': {
 296             'id': 'MDDP12000117',
 297             'ext': 'mp4',
 298             'title': 'Alarm Trolltunga',
 299             'description': 'md5:46923a6e6510eefcce23d5ef2a58f2ce',
 300             'duration': 2223.44,
 301             'age_limit': 6,
 302             'subtitles': {
 303                 'nb-nor': [{
 304                     'ext': 'vtt',
 305                 }],
 306                 'nb-ttv': [{
 307                     'ext': 'vtt',
 308                 }],
 309             },
 310         },
 311     }, {
 312         'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
 313         'md5': '8d40dab61cea8ab0114e090b029a0565',
 314         'info_dict': {
 315             'id': 'MUHH48000314',
 316             'ext': 'mp4',
 317             'title': '20 spørsmål - 23. mai 2014',
 318             'alt_title': '23. mai 2014',
 319             'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
 320             'duration': 1741,
 321             'series': '20 spørsmål',
 322             'episode': '23. mai 2014',
 323             'age_limit': 0,
 324         },
 325     }, {
 326         'url': 'https://tv.nrk.no/program/mdfp15000514',
 327         'info_dict': {
 328             'id': 'MDFP15000514',
 329             'ext': 'mp4',
 330             'title': 'Kunnskapskanalen - Grunnlovsjubiléet - Stor ståhei for ingenting',
 331             'description': 'md5:89290c5ccde1b3a24bb8050ab67fe1db',
 332             'duration': 4605.08,
 333             'series': 'Kunnskapskanalen',
 334             'episode': 'Grunnlovsjubiléet - Stor ståhei for ingenting',
 335             'age_limit': 0,
 336         },
 337         'params': {
 338             'skip_download': True,
 339         },
 340     }, {
 341         # single playlist video
 342         'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
 343         'info_dict': {
 344             'id': 'MSPO40010515',
 345             'ext': 'mp4',
 346             'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015',
 347             'description': 'md5:c03aba1e917561eface5214020551b7a',
 348             'age_limit': 0,
 349         },
 350         'params': {
 351             'skip_download': True,
 352         },
 353         'expected_warnings': ['Failed to download m3u8 information'],
 354         'skip': 'particular part is not supported currently',
 355     }, {
 356         'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
 357         'info_dict': {
 358             'id': 'MSPO40010515',
 359             'ext': 'mp4',
 360             'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015',
 361             'description': 'md5:c03aba1e917561eface5214020551b7a',
 362             'age_limit': 0,
 363         },
 364         'expected_warnings': ['Failed to download m3u8 information'],
 365         'skip': 'Ikke tilgjengelig utenfor Norge',
 366     }, {
 367         'url': 'https://tv.nrk.no/serie/anno/KMTE50001317/sesong-3/episode-13',
 368         'info_dict': {
 369             'id': 'KMTE50001317',
 370             'ext': 'mp4',
 371             'title': 'Anno - 13. episode',
 372             'description': 'md5:11d9613661a8dbe6f9bef54e3a4cbbfa',
 373             'duration': 2340,
 374             'series': 'Anno',
 375             'episode': '13. episode',
 376             'season_number': 3,
 377             'episode_number': 13,
 378             'age_limit': 0,
 379         },
 380         'params': {
 381             'skip_download': True,
 382         },
 383     }, {
 384         'url': 'https://tv.nrk.no/serie/nytt-paa-nytt/MUHH46000317/27-01-2017',
 385         'info_dict': {
 386             'id': 'MUHH46000317',
 387             'ext': 'mp4',
 388             'title': 'Nytt på Nytt 27.01.2017',
 389             'description': 'md5:5358d6388fba0ea6f0b6d11c48b9eb4b',
 390             'duration': 1796,
 391             'series': 'Nytt på nytt',
 392             'episode': '27.01.2017',
 393             'age_limit': 0,
 394         },
 395         'params': {
 396             'skip_download': True,
 397         },
 398         'skip': 'ProgramRightsHasExpired',
 399     }, {
 400         'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#',
 401         'only_matching': True,
 402     }, {
 403         'url': 'https://tv.nrk.no/serie/lindmo/2018/MUHU11006318/avspiller',
 404         'only_matching': True,
 405     }, {
 406         'url': 'https://radio.nrk.no/serie/dagsnytt/sesong/201507/NPUB21019315',
 407         'only_matching': True,
 408     }]
 409
 410     def _real_extract(self, url):
 411         video_id = self._match_id(url)
 412         return self.url_result(
 413             f'nrk:{video_id}', ie=NRKIE.ie_key(), video_id=video_id)
 414
 415
 416 class NRKTVEpisodeIE(InfoExtractor):
 417     _VALID_URL = r'https?://tv\.nrk\.no/serie/(?P<id>[^/]+/sesong/(?P<season_number>\d+)/episode/(?P<episode_number>\d+))'
 418     _TESTS = [{
 419         'url': 'https://tv.nrk.no/serie/hellums-kro/sesong/1/episode/2',
 420         'info_dict': {
 421             'id': 'MUHH36005220',
 422             'ext': 'mp4',
 423             'title': 'Hellums kro - 2. Kro, krig og kjærlighet',
 424             'description': 'md5:ad92ddffc04cea8ce14b415deef81787',
 425             'duration': 1563.92,
 426             'series': 'Hellums kro',
 427             'season_number': 1,
 428             'episode_number': 2,
 429             'episode': '2. Kro, krig og kjærlighet',
 430             'age_limit': 6,
 431         },
 432         'params': {
 433             'skip_download': True,
 434         },
 435     }, {
 436         'url': 'https://tv.nrk.no/serie/backstage/sesong/1/episode/8',
 437         'info_dict': {
 438             'id': 'MSUI14000816',
 439             'ext': 'mp4',
 440             'title': 'Backstage - 8. episode',
 441             'description': 'md5:de6ca5d5a2d56849e4021f2bf2850df4',
 442             'duration': 1320,
 443             'series': 'Backstage',
 444             'season_number': 1,
 445             'episode_number': 8,
 446             'episode': '8. episode',
 447             'age_limit': 0,
 448         },
 449         'params': {
 450             'skip_download': True,
 451         },
 452         'skip': 'ProgramRightsHasExpired',
 453     }]
 454
 455     def _real_extract(self, url):
 456         display_id, season_number, episode_number = self._match_valid_url(url).groups()
 457
 458         webpage = self._download_webpage(url, display_id)
 459
 460         info = self._search_json_ld(webpage, display_id, default={})
 461         nrk_id = info.get('@id') or self._html_search_meta(
 462             'nrk:program-id', webpage, default=None) or self._search_regex(
 463             rf'data-program-id=["\']({NRKTVIE._EPISODE_RE})', webpage,
 464             'nrk id')
 465         assert re.match(NRKTVIE._EPISODE_RE, nrk_id)
 466
 467         info.update({
 468             '_type': 'url',
 469             'id': nrk_id,
 470             'url': f'nrk:{nrk_id}',
 471             'ie_key': NRKIE.ie_key(),
 472             'season_number': int(season_number),
 473             'episode_number': int(episode_number),
 474         })
 475         return info
 476
 477
 478 class NRKTVSerieBaseIE(NRKBaseIE):
 479     def _extract_entries(self, entry_list):
 480         if not isinstance(entry_list, list):
 481             return []
 482         entries = []
 483         for episode in entry_list:
 484             nrk_id = episode.get('prfId') or episode.get('episodeId')
 485             if not nrk_id or not isinstance(nrk_id, str):
 486                 continue
 487             entries.append(self.url_result(
 488                 f'nrk:{nrk_id}', ie=NRKIE.ie_key(), video_id=nrk_id))
 489         return entries
 490
 491     _ASSETS_KEYS = ('episodes', 'instalments')
 492
 493     def _extract_assets_key(self, embedded):
 494         for asset_key in self._ASSETS_KEYS:
 495             if embedded.get(asset_key):
 496                 return asset_key
 497
 498     @staticmethod
 499     def _catalog_name(serie_kind):
 500         return 'podcast' if serie_kind in ('podcast', 'podkast') else 'series'
 501
 502     def _entries(self, data, display_id):
 503         for page_num in itertools.count(1):
 504             embedded = data.get('_embedded') or data
 505             if not isinstance(embedded, dict):
 506                 break
 507             assets_key = self._extract_assets_key(embedded)
 508             if not assets_key:
 509                 break
 510             # Extract entries
 511             entries = try_get(
 512                 embedded,
 513                 (lambda x: x[assets_key]['_embedded'][assets_key],
 514                  lambda x: x[assets_key]),
 515                 list)
 516             yield from self._extract_entries(entries)
 517             # Find next URL
 518             next_url_path = try_get(
 519                 data,
 520                 (lambda x: x['_links']['next']['href'],
 521                  lambda x: x['_embedded'][assets_key]['_links']['next']['href']),
 522                 str)
 523             if not next_url_path:
 524                 break
 525             data = self._call_api(
 526                 next_url_path, display_id,
 527                 note=f'Downloading {assets_key} JSON page {page_num}',
 528                 fatal=False)
 529             if not data:
 530                 break
 531
 532
 533 class NRKTVSeasonIE(NRKTVSerieBaseIE):
 534     _VALID_URL = r'''(?x)
 535                     https?://
 536                         (?P<domain>tv|radio)\.nrk\.no/
 537                         (?P<serie_kind>serie|pod[ck]ast)/
 538                         (?P<serie>[^/]+)/
 539                         (?:
 540                             (?:sesong/)?(?P<id>\d+)|
 541                             sesong/(?P<id_2>[^/?#&]+)
 542                         )
 543                     '''
 544     _TESTS = [{
 545         'url': 'https://tv.nrk.no/serie/backstage/sesong/1',
 546         'info_dict': {
 547             'id': 'backstage/1',
 548             'title': 'Sesong 1',
 549         },
 550         'playlist_mincount': 30,
 551     }, {
 552         # no /sesong/ in path
 553         'url': 'https://tv.nrk.no/serie/lindmo/2016',
 554         'info_dict': {
 555             'id': 'lindmo/2016',
 556             'title': '2016',
 557         },
 558         'playlist_mincount': 29,
 559     }, {
 560         # weird nested _embedded in catalog JSON response
 561         'url': 'https://radio.nrk.no/serie/dickie-dick-dickens/sesong/1',
 562         'info_dict': {
 563             'id': 'dickie-dick-dickens/1',
 564             'title': 'Sesong 1',
 565         },
 566         'playlist_mincount': 11,
 567     }, {
 568         # 841 entries, multi page
 569         'url': 'https://radio.nrk.no/serie/dagsnytt/sesong/201509',
 570         'info_dict': {
 571             'id': 'dagsnytt/201509',
 572             'title': 'September 2015',
 573         },
 574         'playlist_mincount': 841,
 575     }, {
 576         # 180 entries, single page
 577         'url': 'https://tv.nrk.no/serie/spangas/sesong/1',
 578         'only_matching': True,
 579     }, {
 580         'url': 'https://radio.nrk.no/podkast/hele_historien/sesong/diagnose-kverulant',
 581         'info_dict': {
 582             'id': 'hele_historien/diagnose-kverulant',
 583             'title': 'Diagnose kverulant',
 584         },
 585         'playlist_mincount': 3,
 586     }, {
 587         'url': 'https://radio.nrk.no/podkast/loerdagsraadet/sesong/202101',
 588         'only_matching': True,
 589     }]
 590
 591     @classmethod
 592     def suitable(cls, url):
 593         return (False if NRKTVIE.suitable(url) or NRKTVEpisodeIE.suitable(url) or NRKRadioPodkastIE.suitable(url)
 594                 else super().suitable(url))
 595
 596     def _real_extract(self, url):
 597         mobj = self._match_valid_url(url)
 598         domain = mobj.group('domain')
 599         serie_kind = mobj.group('serie_kind')
 600         serie = mobj.group('serie')
 601         season_id = mobj.group('id') or mobj.group('id_2')
 602         display_id = f'{serie}/{season_id}'
 603
 604         data = self._call_api(
 605             f'{domain}/catalog/{self._catalog_name(serie_kind)}/{serie}/seasons/{season_id}',
 606             display_id, 'season', query={'pageSize': 50})
 607
 608         title = try_get(data, lambda x: x['titles']['title'], str) or display_id
 609         return self.playlist_result(
 610             self._entries(data, display_id),
 611             display_id, title)
 612
 613
 614 class NRKTVSeriesIE(NRKTVSerieBaseIE):
 615     _VALID_URL = r'https?://(?P<domain>(?:tv|radio)\.nrk|(?:tv\.)?nrksuper)\.no/(?P<serie_kind>serie|pod[ck]ast)/(?P<id>[^/]+)'
 616     _TESTS = [{
 617         # new layout, instalments
 618         'url': 'https://tv.nrk.no/serie/groenn-glede',
 619         'info_dict': {
 620             'id': 'groenn-glede',
 621             'title': 'Grønn glede',
 622             'description': 'md5:7576e92ae7f65da6993cf90ee29e4608',
 623         },
 624         'playlist_mincount': 90,
 625     }, {
 626         # new layout, instalments, more entries
 627         'url': 'https://tv.nrk.no/serie/lindmo',
 628         'only_matching': True,
 629     }, {
 630         'url': 'https://tv.nrk.no/serie/blank',
 631         'info_dict': {
 632             'id': 'blank',
 633             'title': 'Blank',
 634             'description': 'md5:7664b4e7e77dc6810cd3bca367c25b6e',
 635         },
 636         'playlist_mincount': 30,
 637     }, {
 638         # new layout, seasons
 639         'url': 'https://tv.nrk.no/serie/backstage',
 640         'info_dict': {
 641             'id': 'backstage',
 642             'title': 'Backstage',
 643             'description': 'md5:63692ceb96813d9a207e9910483d948b',
 644         },
 645         'playlist_mincount': 60,
 646     }, {
 647         # old layout
 648         'url': 'https://tv.nrksuper.no/serie/labyrint',
 649         'info_dict': {
 650             'id': 'labyrint',
 651             'title': 'Labyrint',
 652             'description': 'I Daidalos sin undersjøiske Labyrint venter spennende oppgaver, skumle robotskapninger og slim.',
 653         },
 654         'playlist_mincount': 3,
 655     }, {
 656         'url': 'https://tv.nrk.no/serie/broedrene-dal-og-spektralsteinene',
 657         'only_matching': True,
 658     }, {
 659         'url': 'https://tv.nrk.no/serie/saving-the-human-race',
 660         'only_matching': True,
 661     }, {
 662         'url': 'https://tv.nrk.no/serie/postmann-pat',
 663         'only_matching': True,
 664     }, {
 665         'url': 'https://radio.nrk.no/serie/dickie-dick-dickens',
 666         'info_dict': {
 667             'id': 'dickie-dick-dickens',
 668             'title': 'Dickie Dick Dickens',
 669             'description': 'md5:19e67411ffe57f7dce08a943d7a0b91f',
 670         },
 671         'playlist_mincount': 8,
 672     }, {
 673         'url': 'https://nrksuper.no/serie/labyrint',
 674         'only_matching': True,
 675     }, {
 676         'url': 'https://radio.nrk.no/podkast/ulrikkes_univers',
 677         'info_dict': {
 678             'id': 'ulrikkes_univers',
 679         },
 680         'playlist_mincount': 10,
 681     }, {
 682         'url': 'https://radio.nrk.no/podkast/ulrikkes_univers/nrkno-poddkast-26588-134079-05042018030000',
 683         'only_matching': True,
 684     }]
 685
 686     @classmethod
 687     def suitable(cls, url):
 688         return (
 689             False if any(ie.suitable(url)
 690                          for ie in (NRKTVIE, NRKTVEpisodeIE, NRKRadioPodkastIE, NRKTVSeasonIE))
 691             else super().suitable(url))
 692
 693     def _real_extract(self, url):
 694         site, serie_kind, series_id = self._match_valid_url(url).groups()
 695         is_radio = site == 'radio.nrk'
 696         domain = 'radio' if is_radio else 'tv'
 697
 698         size_prefix = 'p' if is_radio else 'embeddedInstalmentsP'
 699         series = self._call_api(
 700             f'{domain}/catalog/{self._catalog_name(serie_kind)}/{series_id}',
 701             series_id, 'serie', query={size_prefix + 'ageSize': 50})
 702         titles = try_get(series, [
 703             lambda x: x['titles'],
 704             lambda x: x[x['type']]['titles'],
 705             lambda x: x[x['seriesType']]['titles'],
 706         ]) or {}
 707
 708         entries = []
 709         entries.extend(self._entries(series, series_id))
 710         embedded = series.get('_embedded') or {}
 711         linked_seasons = try_get(series, lambda x: x['_links']['seasons']) or []
 712         embedded_seasons = embedded.get('seasons') or []
 713         if len(linked_seasons) > len(embedded_seasons):
 714             for season in linked_seasons:
 715                 season_url = urljoin(url, season.get('href'))
 716                 if not season_url:
 717                     season_name = season.get('name')
 718                     if season_name and isinstance(season_name, str):
 719                         season_url = f'https://{domain}.nrk.no/serie/{series_id}/sesong/{season_name}'
 720                 if season_url:
 721                     entries.append(self.url_result(
 722                         season_url, ie=NRKTVSeasonIE.ie_key(),
 723                         video_title=season.get('title')))
 724         else:
 725             for season in embedded_seasons:
 726                 entries.extend(self._entries(season, series_id))
 727         entries.extend(self._entries(
 728             embedded.get('extraMaterial') or {}, series_id))
 729
 730         return self.playlist_result(
 731             entries, series_id, titles.get('title'), titles.get('subtitle'))
 732
 733
 734 class NRKTVDirekteIE(NRKTVIE):  # XXX: Do not subclass from concrete IE
 735     IE_DESC = 'NRK TV Direkte and NRK Radio Direkte'
 736     _VALID_URL = r'https?://(?:tv|radio)\.nrk\.no/direkte/(?P<id>[^/?#&]+)'
 737
 738     _TESTS = [{
 739         'url': 'https://tv.nrk.no/direkte/nrk1',
 740         'only_matching': True,
 741     }, {
 742         'url': 'https://radio.nrk.no/direkte/p1_oslo_akershus',
 743         'only_matching': True,
 744     }]
 745
 746
 747 class NRKRadioPodkastIE(InfoExtractor):
 748     _VALID_URL = r'https?://radio\.nrk\.no/pod[ck]ast/(?:[^/]+/)+(?P<id>l_[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
 749
 750     _TESTS = [{
 751         'url': 'https://radio.nrk.no/podkast/ulrikkes_univers/l_96f4f1b0-de54-4e6a-b4f1-b0de54fe6af8',
 752         'md5': '8d40dab61cea8ab0114e090b029a0565',
 753         'info_dict': {
 754             'id': 'MUHH48000314AA',
 755             'ext': 'mp4',
 756             'title': '20 spørsmål 23.05.2014',
 757             'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
 758             'duration': 1741,
 759             'series': '20 spørsmål',
 760             'episode': '23.05.2014',
 761         },
 762     }, {
 763         'url': 'https://radio.nrk.no/podcast/ulrikkes_univers/l_96f4f1b0-de54-4e6a-b4f1-b0de54fe6af8',
 764         'only_matching': True,
 765     }, {
 766         'url': 'https://radio.nrk.no/podkast/ulrikkes_univers/sesong/1/l_96f4f1b0-de54-4e6a-b4f1-b0de54fe6af8',
 767         'only_matching': True,
 768     }, {
 769         'url': 'https://radio.nrk.no/podkast/hele_historien/sesong/bortfoert-i-bergen/l_774d1a2c-7aa7-4965-8d1a-2c7aa7d9652c',
 770         'only_matching': True,
 771     }]
 772
 773     def _real_extract(self, url):
 774         video_id = self._match_id(url)
 775         return self.url_result(
 776             f'nrk:{video_id}', ie=NRKIE.ie_key(), video_id=video_id)
 777
 778
 779 class NRKPlaylistBaseIE(InfoExtractor):
 780     def _extract_description(self, webpage):
 781         pass
 782
 783     def _real_extract(self, url):
 784         playlist_id = self._match_id(url)
 785
 786         webpage = self._download_webpage(url, playlist_id)
 787
 788         entries = [
 789             self.url_result(f'nrk:{video_id}', NRKIE.ie_key())
 790             for video_id in re.findall(self._ITEM_RE, webpage)
 791         ]
 792
 793         playlist_title = self._extract_title(webpage)
 794         playlist_description = self._extract_description(webpage)
 795
 796         return self.playlist_result(
 797             entries, playlist_id, playlist_title, playlist_description)
 798
 799
 800 class NRKPlaylistIE(NRKPlaylistBaseIE):
 801     _VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video|skole)(?:[^/]+/)+(?P<id>[^/]+)'
 802     _ITEM_RE = r'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"'
 803     _TESTS = [{
 804         'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',
 805         'info_dict': {
 806             'id': 'gjenopplev-den-historiske-solformorkelsen-1.12270763',
 807             'title': 'Gjenopplev den historiske solformørkelsen',
 808             'description': 'md5:c2df8ea3bac5654a26fc2834a542feed',
 809         },
 810         'playlist_count': 2,
 811     }, {
 812         'url': 'http://www.nrk.no/kultur/bok/rivertonprisen-til-karin-fossum-1.12266449',
 813         'info_dict': {
 814             'id': 'rivertonprisen-til-karin-fossum-1.12266449',
 815             'title': 'Rivertonprisen til Karin Fossum',
 816             'description': 'Første kvinne på 15 år til å vinne krimlitteraturprisen.',
 817         },
 818         'playlist_count': 2,
 819     }]
 820
 821     def _extract_title(self, webpage):
 822         return self._og_search_title(webpage, fatal=False)
 823
 824     def _extract_description(self, webpage):
 825         return self._og_search_description(webpage)
 826
 827
 828 class NRKTVEpisodesIE(NRKPlaylistBaseIE):
 829     _VALID_URL = r'https?://tv\.nrk\.no/program/[Ee]pisodes/[^/]+/(?P<id>\d+)'
 830     _ITEM_RE = rf'data-episode=["\']{NRKTVIE._EPISODE_RE}'
 831     _TESTS = [{
 832         'url': 'https://tv.nrk.no/program/episodes/nytt-paa-nytt/69031',
 833         'info_dict': {
 834             'id': '69031',
 835             'title': 'Nytt på nytt, sesong: 201210',
 836         },
 837         'playlist_count': 4,
 838     }]
 839
 840     def _extract_title(self, webpage):
 841         return self._html_search_regex(
 842             r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False)
 843
 844
 845 class NRKSkoleIE(InfoExtractor):
 846     IE_DESC = 'NRK Skole'
 847     _VALID_URL = r'https?://(?:www\.)?nrk\.no/skole/?\?.*\bmediaId=(?P<id>\d+)'
 848
 849     _TESTS = [{
 850         'url': 'https://www.nrk.no/skole/?page=search&q=&mediaId=14099',
 851         'md5': '18c12c3d071953c3bf8d54ef6b2587b7',
 852         'info_dict': {
 853             'id': '6021',
 854             'ext': 'mp4',
 855             'title': 'Genetikk og eneggede tvillinger',
 856             'description': 'md5:3aca25dcf38ec30f0363428d2b265f8d',
 857             'duration': 399,
 858         },
 859     }, {
 860         'url': 'https://www.nrk.no/skole/?page=objectives&subject=naturfag&objective=K15114&mediaId=19355',
 861         'only_matching': True,
 862     }]
 863
 864     def _real_extract(self, url):
 865         video_id = self._match_id(url)
 866
 867         nrk_id = self._download_json(
 868             f'https://nrkno-skole-prod.kube.nrk.no/skole/api/media/{video_id}',
 869             video_id)['psId']
 870
 871         return self.url_result(f'nrk:{nrk_id}')