Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/nrk.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_str,
   9     compat_urllib_parse_unquote,
  10 )
  11 from ..utils import (
  12     ExtractorError,
  13     int_or_none,
  14     JSON_LD_RE,
  15     js_to_json,
  16     NO_DEFAULT,
  17     parse_age_limit,
  18     parse_duration,
  19     try_get,
  20 )
  21
  22
  23 class NRKBaseIE(InfoExtractor):
  24     _GEO_COUNTRIES = ['NO']
  25
  26     _api_host = None
  27
  28     def _real_extract(self, url):
  29         video_id = self._match_id(url)
  30
  31         api_hosts = (self._api_host, ) if self._api_host else self._API_HOSTS
  32
  33         for api_host in api_hosts:
  34             data = self._download_json(
  35                 'http://%s/mediaelement/%s' % (api_host, video_id),
  36                 video_id, 'Downloading mediaelement JSON',
  37                 fatal=api_host == api_hosts[-1])
  38             if not data:
  39                 continue
  40             self._api_host = api_host
  41             break
  42
  43         title = data.get('fullTitle') or data.get('mainTitle') or data['title']
  44         video_id = data.get('id') or video_id
  45
  46         entries = []
  47
  48         conviva = data.get('convivaStatistics') or {}
  49         live = (data.get('mediaElementType') == 'Live'
  50                 or data.get('isLive') is True or conviva.get('isLive'))
  51
  52         def make_title(t):
  53             return self._live_title(t) if live else t
  54
  55         media_assets = data.get('mediaAssets')
  56         if media_assets and isinstance(media_assets, list):
  57             def video_id_and_title(idx):
  58                 return ((video_id, title) if len(media_assets) == 1
  59                         else ('%s-%d' % (video_id, idx), '%s (Part %d)' % (title, idx)))
  60             for num, asset in enumerate(media_assets, 1):
  61                 asset_url = asset.get('url')
  62                 if not asset_url:
  63                     continue
  64                 formats = self._extract_akamai_formats(asset_url, video_id)
  65                 if not formats:
  66                     continue
  67                 self._sort_formats(formats)
  68
  69                 # Some f4m streams may not work with hdcore in fragments' URLs
  70                 for f in formats:
  71                     extra_param = f.get('extra_param_to_segment_url')
  72                     if extra_param and 'hdcore' in extra_param:
  73                         del f['extra_param_to_segment_url']
  74
  75                 entry_id, entry_title = video_id_and_title(num)
  76                 duration = parse_duration(asset.get('duration'))
  77                 subtitles = {}
  78                 for subtitle in ('webVtt', 'timedText'):
  79                     subtitle_url = asset.get('%sSubtitlesUrl' % subtitle)
  80                     if subtitle_url:
  81                         subtitles.setdefault('no', []).append({
  82                             'url': compat_urllib_parse_unquote(subtitle_url)
  83                         })
  84                 entries.append({
  85                     'id': asset.get('carrierId') or entry_id,
  86                     'title': make_title(entry_title),
  87                     'duration': duration,
  88                     'subtitles': subtitles,
  89                     'formats': formats,
  90                 })
  91
  92         if not entries:
  93             media_url = data.get('mediaUrl')
  94             if media_url:
  95                 formats = self._extract_akamai_formats(media_url, video_id)
  96                 self._sort_formats(formats)
  97                 duration = parse_duration(data.get('duration'))
  98                 entries = [{
  99                     'id': video_id,
 100                     'title': make_title(title),
 101                     'duration': duration,
 102                     'formats': formats,
 103                 }]
 104
 105         if not entries:
 106             MESSAGES = {
 107                 'ProgramRightsAreNotReady': 'Du kan dessverre ikke se eller høre programmet',
 108                 'ProgramRightsHasExpired': 'Programmet har gått ut',
 109                 'NoProgramRights': 'Ikke tilgjengelig',
 110                 'ProgramIsGeoBlocked': 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',
 111             }
 112             message_type = data.get('messageType', '')
 113             # Can be ProgramIsGeoBlocked or ChannelIsGeoBlocked*
 114             if 'IsGeoBlocked' in message_type:
 115                 self.raise_geo_restricted(
 116                     msg=MESSAGES.get('ProgramIsGeoBlocked'),
 117                     countries=self._GEO_COUNTRIES)
 118             raise ExtractorError(
 119                 '%s said: %s' % (self.IE_NAME, MESSAGES.get(
 120                     message_type, message_type)),
 121                 expected=True)
 122
 123         series = conviva.get('seriesName') or data.get('seriesTitle')
 124         episode = conviva.get('episodeName') or data.get('episodeNumberOrDate')
 125
 126         season_number = None
 127         episode_number = None
 128         if data.get('mediaElementType') == 'Episode':
 129             _season_episode = data.get('scoresStatistics', {}).get('springStreamStream') or \
 130                 data.get('relativeOriginUrl', '')
 131             EPISODENUM_RE = [
 132                 r'/s(?P<season>\d{,2})e(?P<episode>\d{,2})\.',
 133                 r'/sesong-(?P<season>\d{,2})/episode-(?P<episode>\d{,2})',
 134             ]
 135             season_number = int_or_none(self._search_regex(
 136                 EPISODENUM_RE, _season_episode, 'season number',
 137                 default=None, group='season'))
 138             episode_number = int_or_none(self._search_regex(
 139                 EPISODENUM_RE, _season_episode, 'episode number',
 140                 default=None, group='episode'))
 141
 142         thumbnails = None
 143         images = data.get('images')
 144         if images and isinstance(images, dict):
 145             web_images = images.get('webImages')
 146             if isinstance(web_images, list):
 147                 thumbnails = [{
 148                     'url': image['imageUrl'],
 149                     'width': int_or_none(image.get('width')),
 150                     'height': int_or_none(image.get('height')),
 151                 } for image in web_images if image.get('imageUrl')]
 152
 153         description = data.get('description')
 154         category = data.get('mediaAnalytics', {}).get('category')
 155
 156         common_info = {
 157             'description': description,
 158             'series': series,
 159             'episode': episode,
 160             'season_number': season_number,
 161             'episode_number': episode_number,
 162             'categories': [category] if category else None,
 163             'age_limit': parse_age_limit(data.get('legalAge')),
 164             'thumbnails': thumbnails,
 165         }
 166
 167         vcodec = 'none' if data.get('mediaType') == 'Audio' else None
 168
 169         for entry in entries:
 170             entry.update(common_info)
 171             for f in entry['formats']:
 172                 f['vcodec'] = vcodec
 173
 174         points = data.get('shortIndexPoints')
 175         if isinstance(points, list):
 176             chapters = []
 177             for next_num, point in enumerate(points, start=1):
 178                 if not isinstance(point, dict):
 179                     continue
 180                 start_time = parse_duration(point.get('startPoint'))
 181                 if start_time is None:
 182                     continue
 183                 end_time = parse_duration(
 184                     data.get('duration')
 185                     if next_num == len(points)
 186                     else points[next_num].get('startPoint'))
 187                 if end_time is None:
 188                     continue
 189                 chapters.append({
 190                     'start_time': start_time,
 191                     'end_time': end_time,
 192                     'title': point.get('title'),
 193                 })
 194             if chapters and len(entries) == 1:
 195                 entries[0]['chapters'] = chapters
 196
 197         return self.playlist_result(entries, video_id, title, description)
 198
 199
 200 class NRKIE(NRKBaseIE):
 201     _VALID_URL = r'''(?x)
 202                         (?:
 203                             nrk:|
 204                             https?://
 205                                 (?:
 206                                     (?:www\.)?nrk\.no/video/PS\*|
 207                                     v8[-.]psapi\.nrk\.no/mediaelement/
 208                                 )
 209                             )
 210                             (?P<id>[^?#&]+)
 211                         '''
 212     _API_HOSTS = ('psapi.nrk.no', 'v8-psapi.nrk.no')
 213     _TESTS = [{
 214         # video
 215         'url': 'http://www.nrk.no/video/PS*150533',
 216         'md5': '706f34cdf1322577589e369e522b50ef',
 217         'info_dict': {
 218             'id': '150533',
 219             'ext': 'mp4',
 220             'title': 'Dompap og andre fugler i Piip-Show',
 221             'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f',
 222             'duration': 262,
 223         }
 224     }, {
 225         # audio
 226         'url': 'http://www.nrk.no/video/PS*154915',
 227         # MD5 is unstable
 228         'info_dict': {
 229             'id': '154915',
 230             'ext': 'flv',
 231             'title': 'Slik høres internett ut når du er blind',
 232             'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
 233             'duration': 20,
 234         }
 235     }, {
 236         'url': 'nrk:ecc1b952-96dc-4a98-81b9-5296dc7a98d9',
 237         'only_matching': True,
 238     }, {
 239         'url': 'nrk:clip/7707d5a3-ebe7-434a-87d5-a3ebe7a34a70',
 240         'only_matching': True,
 241     }, {
 242         'url': 'https://v8-psapi.nrk.no/mediaelement/ecc1b952-96dc-4a98-81b9-5296dc7a98d9',
 243         'only_matching': True,
 244     }]
 245
 246
 247 class NRKTVIE(NRKBaseIE):
 248     IE_DESC = 'NRK TV and NRK Radio'
 249     _EPISODE_RE = r'(?P<id>[a-zA-Z]{4}\d{8})'
 250     _VALID_URL = r'''(?x)
 251                         https?://
 252                             (?:tv|radio)\.nrk(?:super)?\.no/
 253                             (?:serie(?:/[^/]+){1,2}|program)/
 254                             (?![Ee]pisodes)%s
 255                             (?:/\d{2}-\d{2}-\d{4})?
 256                             (?:\#del=(?P<part_id>\d+))?
 257                     ''' % _EPISODE_RE
 258     _API_HOSTS = ('psapi-ne.nrk.no', 'psapi-we.nrk.no')
 259     _TESTS = [{
 260         'url': 'https://tv.nrk.no/program/MDDP12000117',
 261         'md5': '8270824df46ec629b66aeaa5796b36fb',
 262         'info_dict': {
 263             'id': 'MDDP12000117AA',
 264             'ext': 'mp4',
 265             'title': 'Alarm Trolltunga',
 266             'description': 'md5:46923a6e6510eefcce23d5ef2a58f2ce',
 267             'duration': 2223,
 268             'age_limit': 6,
 269         },
 270     }, {
 271         'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
 272         'md5': '9a167e54d04671eb6317a37b7bc8a280',
 273         'info_dict': {
 274             'id': 'MUHH48000314AA',
 275             'ext': 'mp4',
 276             'title': '20 spørsmål 23.05.2014',
 277             'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
 278             'duration': 1741,
 279             'series': '20 spørsmål',
 280             'episode': '23.05.2014',
 281         },
 282         'skip': 'NoProgramRights',
 283     }, {
 284         'url': 'https://tv.nrk.no/program/mdfp15000514',
 285         'info_dict': {
 286             'id': 'MDFP15000514CA',
 287             'ext': 'mp4',
 288             'title': 'Grunnlovsjubiléet - Stor ståhei for ingenting 24.05.2014',
 289             'description': 'md5:89290c5ccde1b3a24bb8050ab67fe1db',
 290             'duration': 4605,
 291             'series': 'Kunnskapskanalen',
 292             'episode': '24.05.2014',
 293         },
 294         'params': {
 295             'skip_download': True,
 296         },
 297     }, {
 298         # single playlist video
 299         'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
 300         'info_dict': {
 301             'id': 'MSPO40010515-part2',
 302             'ext': 'flv',
 303             'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
 304             'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
 305         },
 306         'params': {
 307             'skip_download': True,
 308         },
 309         'expected_warnings': ['Video is geo restricted'],
 310         'skip': 'particular part is not supported currently',
 311     }, {
 312         'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
 313         'playlist': [{
 314             'info_dict': {
 315                 'id': 'MSPO40010515AH',
 316                 'ext': 'mp4',
 317                 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 1)',
 318                 'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',
 319                 'duration': 772,
 320                 'series': 'Tour de Ski',
 321                 'episode': '06.01.2015',
 322             },
 323             'params': {
 324                 'skip_download': True,
 325             },
 326         }, {
 327             'info_dict': {
 328                 'id': 'MSPO40010515BH',
 329                 'ext': 'mp4',
 330                 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 2)',
 331                 'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',
 332                 'duration': 6175,
 333                 'series': 'Tour de Ski',
 334                 'episode': '06.01.2015',
 335             },
 336             'params': {
 337                 'skip_download': True,
 338             },
 339         }],
 340         'info_dict': {
 341             'id': 'MSPO40010515',
 342             'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015',
 343             'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',
 344         },
 345         'expected_warnings': ['Video is geo restricted'],
 346     }, {
 347         'url': 'https://tv.nrk.no/serie/anno/KMTE50001317/sesong-3/episode-13',
 348         'info_dict': {
 349             'id': 'KMTE50001317AA',
 350             'ext': 'mp4',
 351             'title': 'Anno 13:30',
 352             'description': 'md5:11d9613661a8dbe6f9bef54e3a4cbbfa',
 353             'duration': 2340,
 354             'series': 'Anno',
 355             'episode': '13:30',
 356             'season_number': 3,
 357             'episode_number': 13,
 358         },
 359         'params': {
 360             'skip_download': True,
 361         },
 362     }, {
 363         'url': 'https://tv.nrk.no/serie/nytt-paa-nytt/MUHH46000317/27-01-2017',
 364         'info_dict': {
 365             'id': 'MUHH46000317AA',
 366             'ext': 'mp4',
 367             'title': 'Nytt på Nytt 27.01.2017',
 368             'description': 'md5:5358d6388fba0ea6f0b6d11c48b9eb4b',
 369             'duration': 1796,
 370             'series': 'Nytt på nytt',
 371             'episode': '27.01.2017',
 372         },
 373         'params': {
 374             'skip_download': True,
 375         },
 376     }, {
 377         'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#',
 378         'only_matching': True,
 379     }, {
 380         'url': 'https://tv.nrk.no/serie/lindmo/2018/MUHU11006318/avspiller',
 381         'only_matching': True,
 382     }]
 383
 384
 385 class NRKTVEpisodeIE(InfoExtractor):
 386     _VALID_URL = r'https?://tv\.nrk\.no/serie/(?P<id>[^/]+/sesong/\d+/episode/\d+)'
 387     _TESTS = [{
 388         'url': 'https://tv.nrk.no/serie/hellums-kro/sesong/1/episode/2',
 389         'info_dict': {
 390             'id': 'MUHH36005220BA',
 391             'ext': 'mp4',
 392             'title': 'Kro, krig og kjærlighet 2:6',
 393             'description': 'md5:b32a7dc0b1ed27c8064f58b97bda4350',
 394             'duration': 1563,
 395             'series': 'Hellums kro',
 396             'season_number': 1,
 397             'episode_number': 2,
 398             'episode': '2:6',
 399             'age_limit': 6,
 400         },
 401         'params': {
 402             'skip_download': True,
 403         },
 404     }, {
 405         'url': 'https://tv.nrk.no/serie/backstage/sesong/1/episode/8',
 406         'info_dict': {
 407             'id': 'MSUI14000816AA',
 408             'ext': 'mp4',
 409             'title': 'Backstage 8:30',
 410             'description': 'md5:de6ca5d5a2d56849e4021f2bf2850df4',
 411             'duration': 1320,
 412             'series': 'Backstage',
 413             'season_number': 1,
 414             'episode_number': 8,
 415             'episode': '8:30',
 416         },
 417         'params': {
 418             'skip_download': True,
 419         },
 420         'skip': 'ProgramRightsHasExpired',
 421     }]
 422
 423     def _real_extract(self, url):
 424         display_id = self._match_id(url)
 425
 426         webpage = self._download_webpage(url, display_id)
 427
 428         nrk_id = self._parse_json(
 429             self._search_regex(JSON_LD_RE, webpage, 'JSON-LD', group='json_ld'),
 430             display_id)['@id']
 431
 432         assert re.match(NRKTVIE._EPISODE_RE, nrk_id)
 433         return self.url_result(
 434             'nrk:%s' % nrk_id, ie=NRKIE.ie_key(), video_id=nrk_id)
 435
 436
 437 class NRKTVSerieBaseIE(InfoExtractor):
 438     def _extract_series(self, webpage, display_id, fatal=True):
 439         config = self._parse_json(
 440             self._search_regex(
 441                 (r'INITIAL_DATA(?:_V\d)?_*\s*=\s*({.+?})\s*;',
 442                  r'({.+?})\s*,\s*"[^"]+"\s*\)\s*</script>'),
 443                 webpage, 'config', default='{}' if not fatal else NO_DEFAULT),
 444             display_id, fatal=False, transform_source=js_to_json)
 445         if not config:
 446             return
 447         return try_get(
 448             config,
 449             (lambda x: x['initialState']['series'], lambda x: x['series']),
 450             dict)
 451
 452     def _extract_seasons(self, seasons):
 453         if not isinstance(seasons, list):
 454             return []
 455         entries = []
 456         for season in seasons:
 457             entries.extend(self._extract_episodes(season))
 458         return entries
 459
 460     def _extract_episodes(self, season):
 461         if not isinstance(season, dict):
 462             return []
 463         return self._extract_entries(season.get('episodes'))
 464
 465     def _extract_entries(self, entry_list):
 466         if not isinstance(entry_list, list):
 467             return []
 468         entries = []
 469         for episode in entry_list:
 470             nrk_id = episode.get('prfId')
 471             if not nrk_id or not isinstance(nrk_id, compat_str):
 472                 continue
 473             entries.append(self.url_result(
 474                 'nrk:%s' % nrk_id, ie=NRKIE.ie_key(), video_id=nrk_id))
 475         return entries
 476
 477
 478 class NRKTVSeasonIE(NRKTVSerieBaseIE):
 479     _VALID_URL = r'https?://tv\.nrk\.no/serie/[^/]+/sesong/(?P<id>\d+)'
 480     _TEST = {
 481         'url': 'https://tv.nrk.no/serie/backstage/sesong/1',
 482         'info_dict': {
 483             'id': '1',
 484             'title': 'Sesong 1',
 485         },
 486         'playlist_mincount': 30,
 487     }
 488
 489     @classmethod
 490     def suitable(cls, url):
 491         return (False if NRKTVIE.suitable(url) or NRKTVEpisodeIE.suitable(url)
 492                 else super(NRKTVSeasonIE, cls).suitable(url))
 493
 494     def _real_extract(self, url):
 495         display_id = self._match_id(url)
 496
 497         webpage = self._download_webpage(url, display_id)
 498
 499         series = self._extract_series(webpage, display_id)
 500
 501         season = next(
 502             s for s in series['seasons']
 503             if int(display_id) == s.get('seasonNumber'))
 504
 505         title = try_get(season, lambda x: x['titles']['title'], compat_str)
 506         return self.playlist_result(
 507             self._extract_episodes(season), display_id, title)
 508
 509
 510 class NRKTVSeriesIE(NRKTVSerieBaseIE):
 511     _VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/serie/(?P<id>[^/]+)'
 512     _ITEM_RE = r'(?:data-season=["\']|id=["\']season-)(?P<id>\d+)'
 513     _TESTS = [{
 514         'url': 'https://tv.nrk.no/serie/blank',
 515         'info_dict': {
 516             'id': 'blank',
 517             'title': 'Blank',
 518             'description': 'md5:7664b4e7e77dc6810cd3bca367c25b6e',
 519         },
 520         'playlist_mincount': 30,
 521     }, {
 522         # new layout, seasons
 523         'url': 'https://tv.nrk.no/serie/backstage',
 524         'info_dict': {
 525             'id': 'backstage',
 526             'title': 'Backstage',
 527             'description': 'md5:c3ec3a35736fca0f9e1207b5511143d3',
 528         },
 529         'playlist_mincount': 60,
 530     }, {
 531         # new layout, instalments
 532         'url': 'https://tv.nrk.no/serie/groenn-glede',
 533         'info_dict': {
 534             'id': 'groenn-glede',
 535             'title': 'Grønn glede',
 536             'description': 'md5:7576e92ae7f65da6993cf90ee29e4608',
 537         },
 538         'playlist_mincount': 10,
 539     }, {
 540         # old layout
 541         'url': 'https://tv.nrksuper.no/serie/labyrint',
 542         'info_dict': {
 543             'id': 'labyrint',
 544             'title': 'Labyrint',
 545             'description': 'md5:318b597330fdac5959247c9b69fdb1ec',
 546         },
 547         'playlist_mincount': 3,
 548     }, {
 549         'url': 'https://tv.nrk.no/serie/broedrene-dal-og-spektralsteinene',
 550         'only_matching': True,
 551     }, {
 552         'url': 'https://tv.nrk.no/serie/saving-the-human-race',
 553         'only_matching': True,
 554     }, {
 555         'url': 'https://tv.nrk.no/serie/postmann-pat',
 556         'only_matching': True,
 557     }]
 558
 559     @classmethod
 560     def suitable(cls, url):
 561         return (
 562             False if any(ie.suitable(url)
 563                          for ie in (NRKTVIE, NRKTVEpisodeIE, NRKTVSeasonIE))
 564             else super(NRKTVSeriesIE, cls).suitable(url))
 565
 566     def _real_extract(self, url):
 567         series_id = self._match_id(url)
 568
 569         webpage = self._download_webpage(url, series_id)
 570
 571         # New layout (e.g. https://tv.nrk.no/serie/backstage)
 572         series = self._extract_series(webpage, series_id, fatal=False)
 573         if series:
 574             title = try_get(series, lambda x: x['titles']['title'], compat_str)
 575             description = try_get(
 576                 series, lambda x: x['titles']['subtitle'], compat_str)
 577             entries = []
 578             entries.extend(self._extract_seasons(series.get('seasons')))
 579             entries.extend(self._extract_entries(series.get('instalments')))
 580             entries.extend(self._extract_episodes(series.get('extraMaterial')))
 581             return self.playlist_result(entries, series_id, title, description)
 582
 583         # Old layout (e.g. https://tv.nrksuper.no/serie/labyrint)
 584         entries = [
 585             self.url_result(
 586                 'https://tv.nrk.no/program/Episodes/{series}/{season}'.format(
 587                     series=series_id, season=season_id))
 588             for season_id in re.findall(self._ITEM_RE, webpage)
 589         ]
 590
 591         title = self._html_search_meta(
 592             'seriestitle', webpage,
 593             'title', default=None) or self._og_search_title(
 594             webpage, fatal=False)
 595         if title:
 596             title = self._search_regex(
 597                 r'NRK (?:Super )?TV\s*[-–]\s*(.+)', title, 'title', default=title)
 598
 599         description = self._html_search_meta(
 600             'series_description', webpage,
 601             'description', default=None) or self._og_search_description(webpage)
 602
 603         return self.playlist_result(entries, series_id, title, description)
 604
 605
 606 class NRKTVDirekteIE(NRKTVIE):
 607     IE_DESC = 'NRK TV Direkte and NRK Radio Direkte'
 608     _VALID_URL = r'https?://(?:tv|radio)\.nrk\.no/direkte/(?P<id>[^/?#&]+)'
 609
 610     _TESTS = [{
 611         'url': 'https://tv.nrk.no/direkte/nrk1',
 612         'only_matching': True,
 613     }, {
 614         'url': 'https://radio.nrk.no/direkte/p1_oslo_akershus',
 615         'only_matching': True,
 616     }]
 617
 618
 619 class NRKPlaylistBaseIE(InfoExtractor):
 620     def _extract_description(self, webpage):
 621         pass
 622
 623     def _real_extract(self, url):
 624         playlist_id = self._match_id(url)
 625
 626         webpage = self._download_webpage(url, playlist_id)
 627
 628         entries = [
 629             self.url_result('nrk:%s' % video_id, NRKIE.ie_key())
 630             for video_id in re.findall(self._ITEM_RE, webpage)
 631         ]
 632
 633         playlist_title = self. _extract_title(webpage)
 634         playlist_description = self._extract_description(webpage)
 635
 636         return self.playlist_result(
 637             entries, playlist_id, playlist_title, playlist_description)
 638
 639
 640 class NRKPlaylistIE(NRKPlaylistBaseIE):
 641     _VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video|skole)(?:[^/]+/)+(?P<id>[^/]+)'
 642     _ITEM_RE = r'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"'
 643     _TESTS = [{
 644         'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',
 645         'info_dict': {
 646             'id': 'gjenopplev-den-historiske-solformorkelsen-1.12270763',
 647             'title': 'Gjenopplev den historiske solformørkelsen',
 648             'description': 'md5:c2df8ea3bac5654a26fc2834a542feed',
 649         },
 650         'playlist_count': 2,
 651     }, {
 652         'url': 'http://www.nrk.no/kultur/bok/rivertonprisen-til-karin-fossum-1.12266449',
 653         'info_dict': {
 654             'id': 'rivertonprisen-til-karin-fossum-1.12266449',
 655             'title': 'Rivertonprisen til Karin Fossum',
 656             'description': 'Første kvinne på 15 år til å vinne krimlitteraturprisen.',
 657         },
 658         'playlist_count': 2,
 659     }]
 660
 661     def _extract_title(self, webpage):
 662         return self._og_search_title(webpage, fatal=False)
 663
 664     def _extract_description(self, webpage):
 665         return self._og_search_description(webpage)
 666
 667
 668 class NRKTVEpisodesIE(NRKPlaylistBaseIE):
 669     _VALID_URL = r'https?://tv\.nrk\.no/program/[Ee]pisodes/[^/]+/(?P<id>\d+)'
 670     _ITEM_RE = r'data-episode=["\']%s' % NRKTVIE._EPISODE_RE
 671     _TESTS = [{
 672         'url': 'https://tv.nrk.no/program/episodes/nytt-paa-nytt/69031',
 673         'info_dict': {
 674             'id': '69031',
 675             'title': 'Nytt på nytt, sesong: 201210',
 676         },
 677         'playlist_count': 4,
 678     }]
 679
 680     def _extract_title(self, webpage):
 681         return self._html_search_regex(
 682             r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False)
 683
 684
 685 class NRKSkoleIE(InfoExtractor):
 686     IE_DESC = 'NRK Skole'
 687     _VALID_URL = r'https?://(?:www\.)?nrk\.no/skole/?\?.*\bmediaId=(?P<id>\d+)'
 688
 689     _TESTS = [{
 690         'url': 'https://www.nrk.no/skole/?page=search&q=&mediaId=14099',
 691         'md5': '18c12c3d071953c3bf8d54ef6b2587b7',
 692         'info_dict': {
 693             'id': '6021',
 694             'ext': 'mp4',
 695             'title': 'Genetikk og eneggede tvillinger',
 696             'description': 'md5:3aca25dcf38ec30f0363428d2b265f8d',
 697             'duration': 399,
 698         },
 699     }, {
 700         'url': 'https://www.nrk.no/skole/?page=objectives&subject=naturfag&objective=K15114&mediaId=19355',
 701         'only_matching': True,
 702     }]
 703
 704     def _real_extract(self, url):
 705         video_id = self._match_id(url)
 706
 707         webpage = self._download_webpage(
 708             'https://mimir.nrk.no/plugin/1.0/static?mediaId=%s' % video_id,
 709             video_id)
 710
 711         nrk_id = self._parse_json(
 712             self._search_regex(
 713                 r'<script[^>]+type=["\']application/json["\'][^>]*>({.+?})</script>',
 714                 webpage, 'application json'),
 715             video_id)['activeMedia']['psId']
 716
 717         return self.url_result('nrk:%s' % nrk_id)