nrk.py (31884B)
1 # coding: utf-8 2 from __future__ import unicode_literals 3 4 import itertools 5 import random 6 import re 7 8 from .common import InfoExtractor 9 from ..compat import compat_str 10 from ..utils import ( 11 determine_ext, 12 ExtractorError, 13 int_or_none, 14 parse_duration, 15 str_or_none, 16 try_get, 17 urljoin, 18 url_or_none, 19 ) 20 21 22 class NRKBaseIE(InfoExtractor): 23 _GEO_COUNTRIES = ['NO'] 24 _CDN_REPL_REGEX = r'''(?x):// 25 (?: 26 nrkod\d{1,2}-httpcache0-47115-cacheod0\.dna\.ip-only\.net/47115-cacheod0| 27 nrk-od-no\.telenorcdn\.net| 28 minicdn-od\.nrk\.no/od/nrkhd-osl-rr\.netwerk\.no/no 29 )/''' 30 31 def _extract_nrk_formats(self, asset_url, video_id): 32 if re.match(r'https?://[^/]+\.akamaihd\.net/i/', asset_url): 33 return self._extract_akamai_formats(asset_url, video_id) 34 asset_url = re.sub(r'(?:bw_(?:low|high)=\d+|no_audio_only)&?', '', asset_url) 35 formats = self._extract_m3u8_formats( 36 asset_url, video_id, 'mp4', 'm3u8_native', fatal=False) 37 if not formats and re.search(self._CDN_REPL_REGEX, asset_url): 38 formats = self._extract_m3u8_formats( 39 re.sub(self._CDN_REPL_REGEX, '://nrk-od-%02d.akamaized.net/no/' % random.randint(0, 99), asset_url), 40 video_id, 'mp4', 'm3u8_native', fatal=False) 41 return formats 42 43 def _raise_error(self, data): 44 MESSAGES = { 45 'ProgramRightsAreNotReady': 'Du kan dessverre ikke se eller høre programmet', 46 'ProgramRightsHasExpired': 'Programmet har gått ut', 47 'NoProgramRights': 'Ikke tilgjengelig', 48 'ProgramIsGeoBlocked': 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge', 49 } 50 message_type = data.get('messageType', '') 51 # Can be ProgramIsGeoBlocked or ChannelIsGeoBlocked* 52 if 'IsGeoBlocked' in message_type or try_get(data, lambda x: x['usageRights']['isGeoBlocked']) is True: 53 self.raise_geo_restricted( 54 msg=MESSAGES.get('ProgramIsGeoBlocked'), 55 countries=self._GEO_COUNTRIES) 56 message = data.get('endUserMessage') or MESSAGES.get(message_type, message_type) 57 raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True) 58 59 def _call_api(self, path, video_id, item=None, note=None, fatal=True, query=None): 60 return self._download_json( 61 urljoin('https://psapi.nrk.no/', path), 62 video_id, note or 'Downloading %s JSON' % item, 63 fatal=fatal, query=query, 64 headers={'Accept-Encoding': 'gzip, deflate, br'}) 65 66 67 class NRKIE(NRKBaseIE): 68 _VALID_URL = r'''(?x) 69 (?: 70 nrk:| 71 https?:// 72 (?: 73 (?:www\.)?nrk\.no/video/(?:PS\*|[^_]+_)| 74 v8[-.]psapi\.nrk\.no/mediaelement/ 75 ) 76 ) 77 (?P<id>[^?\#&]+) 78 ''' 79 80 _TESTS = [{ 81 # video 82 'url': 'http://www.nrk.no/video/PS*150533', 83 'md5': 'f46be075326e23ad0e524edfcb06aeb6', 84 'info_dict': { 85 'id': '150533', 86 'ext': 'mp4', 87 'title': 'Dompap og andre fugler i Piip-Show', 88 'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f', 89 'duration': 262, 90 } 91 }, { 92 # audio 93 'url': 'http://www.nrk.no/video/PS*154915', 94 # MD5 is unstable 95 'info_dict': { 96 'id': '154915', 97 'ext': 'mp4', 98 'title': 'Slik høres internett ut når du er blind', 99 'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568', 100 'duration': 20, 101 } 102 }, { 103 'url': 'nrk:ecc1b952-96dc-4a98-81b9-5296dc7a98d9', 104 'only_matching': True, 105 }, { 106 'url': 'nrk:clip/7707d5a3-ebe7-434a-87d5-a3ebe7a34a70', 107 'only_matching': True, 108 }, { 109 'url': 'https://v8-psapi.nrk.no/mediaelement/ecc1b952-96dc-4a98-81b9-5296dc7a98d9', 110 'only_matching': True, 111 }, { 112 'url': 'https://www.nrk.no/video/dompap-og-andre-fugler-i-piip-show_150533', 113 'only_matching': True, 114 }, { 115 'url': 'https://www.nrk.no/video/humor/kommentatorboksen-reiser-til-sjos_d1fda11f-a4ad-437a-a374-0398bc84e999', 116 'only_matching': True, 117 }, { 118 # podcast 119 'url': 'nrk:l_96f4f1b0-de54-4e6a-b4f1-b0de54fe6af8', 120 'only_matching': True, 121 }, { 122 'url': 'nrk:podcast/l_96f4f1b0-de54-4e6a-b4f1-b0de54fe6af8', 123 'only_matching': True, 124 }, { 125 # clip 126 'url': 'nrk:150533', 127 'only_matching': True, 128 }, { 129 'url': 'nrk:clip/150533', 130 'only_matching': True, 131 }, { 132 # program 133 'url': 'nrk:MDDP12000117', 134 'only_matching': True, 135 }, { 136 'url': 'nrk:program/ENRK10100318', 137 'only_matching': True, 138 }, { 139 # direkte 140 'url': 'nrk:nrk1', 141 'only_matching': True, 142 }, { 143 'url': 'nrk:channel/nrk1', 144 'only_matching': True, 145 }] 146 147 def _real_extract(self, url): 148 video_id = self._match_id(url).split('/')[-1] 149 150 path_templ = 'playback/%s/' + video_id 151 152 def call_playback_api(item, query=None): 153 return self._call_api(path_templ % item, video_id, item, query=query) 154 # known values for preferredCdn: akamai, iponly, minicdn and telenor 155 manifest = call_playback_api('manifest', {'preferredCdn': 'akamai'}) 156 157 video_id = try_get(manifest, lambda x: x['id'], compat_str) or video_id 158 159 if manifest.get('playability') == 'nonPlayable': 160 self._raise_error(manifest['nonPlayable']) 161 162 playable = manifest['playable'] 163 164 formats = [] 165 for asset in playable['assets']: 166 if not isinstance(asset, dict): 167 continue 168 if asset.get('encrypted'): 169 continue 170 format_url = url_or_none(asset.get('url')) 171 if not format_url: 172 continue 173 asset_format = (asset.get('format') or '').lower() 174 if asset_format == 'hls' or determine_ext(format_url) == 'm3u8': 175 formats.extend(self._extract_nrk_formats(format_url, video_id)) 176 elif asset_format == 'mp3': 177 formats.append({ 178 'url': format_url, 179 'format_id': asset_format, 180 'vcodec': 'none', 181 }) 182 self._sort_formats(formats) 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 = preplay.get('description') 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 += '-%s' % 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'], compat_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 } 246 247 if is_series: 248 series = season_id = season_number = episode = episode_number = None 249 programs = self._call_api( 250 'programs/%s' % video_id, video_id, 'programs', fatal=False) 251 if programs and isinstance(programs, dict): 252 series = str_or_none(programs.get('seriesTitle')) 253 season_id = str_or_none(programs.get('seasonId')) 254 season_number = int_or_none(programs.get('seasonNumber')) 255 episode = str_or_none(programs.get('episodeTitle')) 256 episode_number = int_or_none(programs.get('episodeNumber')) 257 if not series: 258 series = title 259 if alt_title: 260 title += ' - %s' % alt_title 261 if not season_number: 262 season_number = int_or_none(self._search_regex( 263 r'Sesong\s+(\d+)', description or '', 'season number', 264 default=None)) 265 if not episode: 266 episode = alt_title if is_series else None 267 if not episode_number: 268 episode_number = int_or_none(self._search_regex( 269 r'^(\d+)\.', episode or '', 'episode number', 270 default=None)) 271 if not episode_number: 272 episode_number = int_or_none(self._search_regex( 273 r'\((\d+)\s*:\s*\d+\)', description or '', 274 'episode number', default=None)) 275 info.update({ 276 'title': title, 277 'series': series, 278 'season_id': season_id, 279 'season_number': season_number, 280 'episode': episode, 281 'episode_number': episode_number, 282 }) 283 284 return info 285 286 287 class NRKTVIE(InfoExtractor): 288 IE_DESC = 'NRK TV and NRK Radio' 289 _EPISODE_RE = r'(?P<id>[a-zA-Z]{4}\d{8})' 290 _VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/(?:[^/]+/)*%s' % _EPISODE_RE 291 _TESTS = [{ 292 'url': 'https://tv.nrk.no/program/MDDP12000117', 293 'md5': 'c4a5960f1b00b40d47db65c1064e0ab1', 294 'info_dict': { 295 'id': 'MDDP12000117', 296 'ext': 'mp4', 297 'title': 'Alarm Trolltunga', 298 'description': 'md5:46923a6e6510eefcce23d5ef2a58f2ce', 299 'duration': 2223.44, 300 'age_limit': 6, 301 'subtitles': { 302 'nb-nor': [{ 303 'ext': 'vtt', 304 }], 305 'nb-ttv': [{ 306 'ext': 'vtt', 307 }] 308 }, 309 }, 310 }, { 311 'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014', 312 'md5': '8d40dab61cea8ab0114e090b029a0565', 313 'info_dict': { 314 'id': 'MUHH48000314', 315 'ext': 'mp4', 316 'title': '20 spørsmål - 23. mai 2014', 317 'alt_title': '23. mai 2014', 318 'description': 'md5:bdea103bc35494c143c6a9acdd84887a', 319 'duration': 1741, 320 'series': '20 spørsmål', 321 'episode': '23. mai 2014', 322 'age_limit': 0, 323 }, 324 }, { 325 'url': 'https://tv.nrk.no/program/mdfp15000514', 326 'info_dict': { 327 'id': 'MDFP15000514', 328 'ext': 'mp4', 329 'title': 'Kunnskapskanalen - Grunnlovsjubiléet - Stor ståhei for ingenting', 330 'description': 'md5:89290c5ccde1b3a24bb8050ab67fe1db', 331 'duration': 4605.08, 332 'series': 'Kunnskapskanalen', 333 'episode': 'Grunnlovsjubiléet - Stor ståhei for ingenting', 334 'age_limit': 0, 335 }, 336 'params': { 337 'skip_download': True, 338 }, 339 }, { 340 # single playlist video 341 'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2', 342 'info_dict': { 343 'id': 'MSPO40010515', 344 'ext': 'mp4', 345 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015', 346 'description': 'md5:c03aba1e917561eface5214020551b7a', 347 'age_limit': 0, 348 }, 349 'params': { 350 'skip_download': True, 351 }, 352 'expected_warnings': ['Failed to download m3u8 information'], 353 'skip': 'particular part is not supported currently', 354 }, { 355 'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015', 356 'info_dict': { 357 'id': 'MSPO40010515', 358 'ext': 'mp4', 359 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015', 360 'description': 'md5:c03aba1e917561eface5214020551b7a', 361 'age_limit': 0, 362 }, 363 'expected_warnings': ['Failed to download m3u8 information'], 364 'skip': 'Ikke tilgjengelig utenfor Norge', 365 }, { 366 'url': 'https://tv.nrk.no/serie/anno/KMTE50001317/sesong-3/episode-13', 367 'info_dict': { 368 'id': 'KMTE50001317', 369 'ext': 'mp4', 370 'title': 'Anno - 13. episode', 371 'description': 'md5:11d9613661a8dbe6f9bef54e3a4cbbfa', 372 'duration': 2340, 373 'series': 'Anno', 374 'episode': '13. episode', 375 'season_number': 3, 376 'episode_number': 13, 377 'age_limit': 0, 378 }, 379 'params': { 380 'skip_download': True, 381 }, 382 }, { 383 'url': 'https://tv.nrk.no/serie/nytt-paa-nytt/MUHH46000317/27-01-2017', 384 'info_dict': { 385 'id': 'MUHH46000317', 386 'ext': 'mp4', 387 'title': 'Nytt på Nytt 27.01.2017', 388 'description': 'md5:5358d6388fba0ea6f0b6d11c48b9eb4b', 389 'duration': 1796, 390 'series': 'Nytt på nytt', 391 'episode': '27.01.2017', 392 'age_limit': 0, 393 }, 394 'params': { 395 'skip_download': True, 396 }, 397 'skip': 'ProgramRightsHasExpired', 398 }, { 399 'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#', 400 'only_matching': True, 401 }, { 402 'url': 'https://tv.nrk.no/serie/lindmo/2018/MUHU11006318/avspiller', 403 'only_matching': True, 404 }, { 405 'url': 'https://radio.nrk.no/serie/dagsnytt/sesong/201507/NPUB21019315', 406 'only_matching': True, 407 }] 408 409 def _real_extract(self, url): 410 video_id = self._match_id(url) 411 return self.url_result( 412 'nrk:%s' % video_id, ie=NRKIE.ie_key(), video_id=video_id) 413 414 415 class NRKTVEpisodeIE(InfoExtractor): 416 _VALID_URL = r'https?://tv\.nrk\.no/serie/(?P<id>[^/]+/sesong/(?P<season_number>\d+)/episode/(?P<episode_number>\d+))' 417 _TESTS = [{ 418 'url': 'https://tv.nrk.no/serie/hellums-kro/sesong/1/episode/2', 419 'info_dict': { 420 'id': 'MUHH36005220', 421 'ext': 'mp4', 422 'title': 'Hellums kro - 2. Kro, krig og kjærlighet', 423 'description': 'md5:ad92ddffc04cea8ce14b415deef81787', 424 'duration': 1563.92, 425 'series': 'Hellums kro', 426 'season_number': 1, 427 'episode_number': 2, 428 'episode': '2. Kro, krig og kjærlighet', 429 'age_limit': 6, 430 }, 431 'params': { 432 'skip_download': True, 433 }, 434 }, { 435 'url': 'https://tv.nrk.no/serie/backstage/sesong/1/episode/8', 436 'info_dict': { 437 'id': 'MSUI14000816', 438 'ext': 'mp4', 439 'title': 'Backstage - 8. episode', 440 'description': 'md5:de6ca5d5a2d56849e4021f2bf2850df4', 441 'duration': 1320, 442 'series': 'Backstage', 443 'season_number': 1, 444 'episode_number': 8, 445 'episode': '8. episode', 446 'age_limit': 0, 447 }, 448 'params': { 449 'skip_download': True, 450 }, 451 'skip': 'ProgramRightsHasExpired', 452 }] 453 454 def _real_extract(self, url): 455 display_id, season_number, episode_number = re.match(self._VALID_URL, url).groups() 456 457 webpage = self._download_webpage(url, display_id) 458 459 info = self._search_json_ld(webpage, display_id, default={}) 460 nrk_id = info.get('@id') or self._html_search_meta( 461 'nrk:program-id', webpage, default=None) or self._search_regex( 462 r'data-program-id=["\'](%s)' % NRKTVIE._EPISODE_RE, webpage, 463 'nrk id') 464 assert re.match(NRKTVIE._EPISODE_RE, nrk_id) 465 466 info.update({ 467 '_type': 'url', 468 'id': nrk_id, 469 'url': 'nrk:%s' % nrk_id, 470 'ie_key': NRKIE.ie_key(), 471 'season_number': int(season_number), 472 'episode_number': int(episode_number), 473 }) 474 return info 475 476 477 class NRKTVSerieBaseIE(NRKBaseIE): 478 def _extract_entries(self, entry_list): 479 if not isinstance(entry_list, list): 480 return [] 481 entries = [] 482 for episode in entry_list: 483 nrk_id = episode.get('prfId') or episode.get('episodeId') 484 if not nrk_id or not isinstance(nrk_id, compat_str): 485 continue 486 entries.append(self.url_result( 487 'nrk:%s' % nrk_id, ie=NRKIE.ie_key(), video_id=nrk_id)) 488 return entries 489 490 _ASSETS_KEYS = ('episodes', 'instalments',) 491 492 def _extract_assets_key(self, embedded): 493 for asset_key in self._ASSETS_KEYS: 494 if embedded.get(asset_key): 495 return asset_key 496 497 @staticmethod 498 def _catalog_name(serie_kind): 499 return 'podcast' if serie_kind in ('podcast', 'podkast') else 'series' 500 501 def _entries(self, data, display_id): 502 for page_num in itertools.count(1): 503 embedded = data.get('_embedded') or data 504 if not isinstance(embedded, dict): 505 break 506 assets_key = self._extract_assets_key(embedded) 507 if not assets_key: 508 break 509 # Extract entries 510 entries = try_get( 511 embedded, 512 (lambda x: x[assets_key]['_embedded'][assets_key], 513 lambda x: x[assets_key]), 514 list) 515 for e in self._extract_entries(entries): 516 yield e 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 compat_str) 523 if not next_url_path: 524 break 525 data = self._call_api( 526 next_url_path, display_id, 527 note='Downloading %s JSON page %d' % (assets_key, 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(NRKTVSeasonIE, cls).suitable(url)) 595 596 def _real_extract(self, url): 597 mobj = re.match(self._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 = '%s/%s' % (serie, season_id) 603 604 data = self._call_api( 605 '%s/catalog/%s/%s/seasons/%s' 606 % (domain, self._catalog_name(serie_kind), serie, season_id), 607 display_id, 'season', query={'pageSize': 50}) 608 609 title = try_get(data, lambda x: x['titles']['title'], compat_str) or display_id 610 return self.playlist_result( 611 self._entries(data, display_id), 612 display_id, title) 613 614 615 class NRKTVSeriesIE(NRKTVSerieBaseIE): 616 _VALID_URL = r'https?://(?P<domain>(?:tv|radio)\.nrk|(?:tv\.)?nrksuper)\.no/(?P<serie_kind>serie|pod[ck]ast)/(?P<id>[^/]+)' 617 _TESTS = [{ 618 # new layout, instalments 619 'url': 'https://tv.nrk.no/serie/groenn-glede', 620 'info_dict': { 621 'id': 'groenn-glede', 622 'title': 'Grønn glede', 623 'description': 'md5:7576e92ae7f65da6993cf90ee29e4608', 624 }, 625 'playlist_mincount': 90, 626 }, { 627 # new layout, instalments, more entries 628 'url': 'https://tv.nrk.no/serie/lindmo', 629 'only_matching': True, 630 }, { 631 'url': 'https://tv.nrk.no/serie/blank', 632 'info_dict': { 633 'id': 'blank', 634 'title': 'Blank', 635 'description': 'md5:7664b4e7e77dc6810cd3bca367c25b6e', 636 }, 637 'playlist_mincount': 30, 638 }, { 639 # new layout, seasons 640 'url': 'https://tv.nrk.no/serie/backstage', 641 'info_dict': { 642 'id': 'backstage', 643 'title': 'Backstage', 644 'description': 'md5:63692ceb96813d9a207e9910483d948b', 645 }, 646 'playlist_mincount': 60, 647 }, { 648 # old layout 649 'url': 'https://tv.nrksuper.no/serie/labyrint', 650 'info_dict': { 651 'id': 'labyrint', 652 'title': 'Labyrint', 653 'description': 'I Daidalos sin undersjøiske Labyrint venter spennende oppgaver, skumle robotskapninger og slim.', 654 }, 655 'playlist_mincount': 3, 656 }, { 657 'url': 'https://tv.nrk.no/serie/broedrene-dal-og-spektralsteinene', 658 'only_matching': True, 659 }, { 660 'url': 'https://tv.nrk.no/serie/saving-the-human-race', 661 'only_matching': True, 662 }, { 663 'url': 'https://tv.nrk.no/serie/postmann-pat', 664 'only_matching': True, 665 }, { 666 'url': 'https://radio.nrk.no/serie/dickie-dick-dickens', 667 'info_dict': { 668 'id': 'dickie-dick-dickens', 669 'title': 'Dickie Dick Dickens', 670 'description': 'md5:19e67411ffe57f7dce08a943d7a0b91f', 671 }, 672 'playlist_mincount': 8, 673 }, { 674 'url': 'https://nrksuper.no/serie/labyrint', 675 'only_matching': True, 676 }, { 677 'url': 'https://radio.nrk.no/podkast/ulrikkes_univers', 678 'info_dict': { 679 'id': 'ulrikkes_univers', 680 }, 681 'playlist_mincount': 10, 682 }, { 683 'url': 'https://radio.nrk.no/podkast/ulrikkes_univers/nrkno-poddkast-26588-134079-05042018030000', 684 'only_matching': True, 685 }] 686 687 @classmethod 688 def suitable(cls, url): 689 return ( 690 False if any(ie.suitable(url) 691 for ie in (NRKTVIE, NRKTVEpisodeIE, NRKRadioPodkastIE, NRKTVSeasonIE)) 692 else super(NRKTVSeriesIE, cls).suitable(url)) 693 694 def _real_extract(self, url): 695 site, serie_kind, series_id = re.match(self._VALID_URL, url).groups() 696 is_radio = site == 'radio.nrk' 697 domain = 'radio' if is_radio else 'tv' 698 699 size_prefix = 'p' if is_radio else 'embeddedInstalmentsP' 700 series = self._call_api( 701 '%s/catalog/%s/%s' 702 % (domain, self._catalog_name(serie_kind), series_id), 703 series_id, 'serie', query={size_prefix + 'ageSize': 50}) 704 titles = try_get(series, [ 705 lambda x: x['titles'], 706 lambda x: x[x['type']]['titles'], 707 lambda x: x[x['seriesType']]['titles'], 708 ]) or {} 709 710 entries = [] 711 entries.extend(self._entries(series, series_id)) 712 embedded = series.get('_embedded') or {} 713 linked_seasons = try_get(series, lambda x: x['_links']['seasons']) or [] 714 embedded_seasons = embedded.get('seasons') or [] 715 if len(linked_seasons) > len(embedded_seasons): 716 for season in linked_seasons: 717 season_url = urljoin(url, season.get('href')) 718 if not season_url: 719 season_name = season.get('name') 720 if season_name and isinstance(season_name, compat_str): 721 season_url = 'https://%s.nrk.no/serie/%s/sesong/%s' % (domain, series_id, season_name) 722 if season_url: 723 entries.append(self.url_result( 724 season_url, ie=NRKTVSeasonIE.ie_key(), 725 video_title=season.get('title'))) 726 else: 727 for season in embedded_seasons: 728 entries.extend(self._entries(season, series_id)) 729 entries.extend(self._entries( 730 embedded.get('extraMaterial') or {}, series_id)) 731 732 return self.playlist_result( 733 entries, series_id, titles.get('title'), titles.get('subtitle')) 734 735 736 class NRKTVDirekteIE(NRKTVIE): 737 IE_DESC = 'NRK TV Direkte and NRK Radio Direkte' 738 _VALID_URL = r'https?://(?:tv|radio)\.nrk\.no/direkte/(?P<id>[^/?#&]+)' 739 740 _TESTS = [{ 741 'url': 'https://tv.nrk.no/direkte/nrk1', 742 'only_matching': True, 743 }, { 744 'url': 'https://radio.nrk.no/direkte/p1_oslo_akershus', 745 'only_matching': True, 746 }] 747 748 749 class NRKRadioPodkastIE(InfoExtractor): 750 _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})' 751 752 _TESTS = [{ 753 'url': 'https://radio.nrk.no/podkast/ulrikkes_univers/l_96f4f1b0-de54-4e6a-b4f1-b0de54fe6af8', 754 'md5': '8d40dab61cea8ab0114e090b029a0565', 755 'info_dict': { 756 'id': 'MUHH48000314AA', 757 'ext': 'mp4', 758 'title': '20 spørsmål 23.05.2014', 759 'description': 'md5:bdea103bc35494c143c6a9acdd84887a', 760 'duration': 1741, 761 'series': '20 spørsmål', 762 'episode': '23.05.2014', 763 }, 764 }, { 765 'url': 'https://radio.nrk.no/podcast/ulrikkes_univers/l_96f4f1b0-de54-4e6a-b4f1-b0de54fe6af8', 766 'only_matching': True, 767 }, { 768 'url': 'https://radio.nrk.no/podkast/ulrikkes_univers/sesong/1/l_96f4f1b0-de54-4e6a-b4f1-b0de54fe6af8', 769 'only_matching': True, 770 }, { 771 'url': 'https://radio.nrk.no/podkast/hele_historien/sesong/bortfoert-i-bergen/l_774d1a2c-7aa7-4965-8d1a-2c7aa7d9652c', 772 'only_matching': True, 773 }] 774 775 def _real_extract(self, url): 776 video_id = self._match_id(url) 777 return self.url_result( 778 'nrk:%s' % video_id, ie=NRKIE.ie_key(), video_id=video_id) 779 780 781 class NRKPlaylistBaseIE(InfoExtractor): 782 def _extract_description(self, webpage): 783 pass 784 785 def _real_extract(self, url): 786 playlist_id = self._match_id(url) 787 788 webpage = self._download_webpage(url, playlist_id) 789 790 entries = [ 791 self.url_result('nrk:%s' % video_id, NRKIE.ie_key()) 792 for video_id in re.findall(self._ITEM_RE, webpage) 793 ] 794 795 playlist_title = self. _extract_title(webpage) 796 playlist_description = self._extract_description(webpage) 797 798 return self.playlist_result( 799 entries, playlist_id, playlist_title, playlist_description) 800 801 802 class NRKPlaylistIE(NRKPlaylistBaseIE): 803 _VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video|skole)(?:[^/]+/)+(?P<id>[^/]+)' 804 _ITEM_RE = r'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"' 805 _TESTS = [{ 806 'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763', 807 'info_dict': { 808 'id': 'gjenopplev-den-historiske-solformorkelsen-1.12270763', 809 'title': 'Gjenopplev den historiske solformørkelsen', 810 'description': 'md5:c2df8ea3bac5654a26fc2834a542feed', 811 }, 812 'playlist_count': 2, 813 }, { 814 'url': 'http://www.nrk.no/kultur/bok/rivertonprisen-til-karin-fossum-1.12266449', 815 'info_dict': { 816 'id': 'rivertonprisen-til-karin-fossum-1.12266449', 817 'title': 'Rivertonprisen til Karin Fossum', 818 'description': 'Første kvinne på 15 år til å vinne krimlitteraturprisen.', 819 }, 820 'playlist_count': 2, 821 }] 822 823 def _extract_title(self, webpage): 824 return self._og_search_title(webpage, fatal=False) 825 826 def _extract_description(self, webpage): 827 return self._og_search_description(webpage) 828 829 830 class NRKTVEpisodesIE(NRKPlaylistBaseIE): 831 _VALID_URL = r'https?://tv\.nrk\.no/program/[Ee]pisodes/[^/]+/(?P<id>\d+)' 832 _ITEM_RE = r'data-episode=["\']%s' % NRKTVIE._EPISODE_RE 833 _TESTS = [{ 834 'url': 'https://tv.nrk.no/program/episodes/nytt-paa-nytt/69031', 835 'info_dict': { 836 'id': '69031', 837 'title': 'Nytt på nytt, sesong: 201210', 838 }, 839 'playlist_count': 4, 840 }] 841 842 def _extract_title(self, webpage): 843 return self._html_search_regex( 844 r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False) 845 846 847 class NRKSkoleIE(InfoExtractor): 848 IE_DESC = 'NRK Skole' 849 _VALID_URL = r'https?://(?:www\.)?nrk\.no/skole/?\?.*\bmediaId=(?P<id>\d+)' 850 851 _TESTS = [{ 852 'url': 'https://www.nrk.no/skole/?page=search&q=&mediaId=14099', 853 'md5': '18c12c3d071953c3bf8d54ef6b2587b7', 854 'info_dict': { 855 'id': '6021', 856 'ext': 'mp4', 857 'title': 'Genetikk og eneggede tvillinger', 858 'description': 'md5:3aca25dcf38ec30f0363428d2b265f8d', 859 'duration': 399, 860 }, 861 }, { 862 'url': 'https://www.nrk.no/skole/?page=objectives&subject=naturfag&objective=K15114&mediaId=19355', 863 'only_matching': True, 864 }] 865 866 def _real_extract(self, url): 867 video_id = self._match_id(url) 868 869 nrk_id = self._download_json( 870 'https://nrkno-skole-prod.kube.nrk.no/skole/api/media/%s' % video_id, 871 video_id)['psId'] 872 873 return self.url_result('nrk:%s' % nrk_id)