import itertools import random import re import json from .common import InfoExtractor from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, determine_ext, int_or_none, parse_duration, parse_iso8601, float_or_none, str_or_none, traverse_obj, try_get, url_or_none, urljoin, ) class NRKBaseIE(InfoExtractor): _GEO_COUNTRIES = ['NO'] _CDN_REPL_REGEX = r'''(?x):// (?: nrkod\d{1,2}-httpcache0-47115-cacheod0\.dna\.ip-only\.net/47115-cacheod0| nrk-od-no\.telenorcdn\.net| minicdn-od\.nrk\.no/od/nrkhd-osl-rr\.netwerk\.no/no )/''' _NETRC_MACHINE = 'nrk' _LOGIN_URL = 'https://innlogging.nrk.no/logginn' _AUTH_TOKEN = '' _API_CALL_HEADERS = {'Accept': 'application/json;device=player-core'} def _extract_nrk_formats_and_subtitles(self, asset_url, video_id): if re.match(r'https?://[^/]+\.akamaihd\.net/i/', asset_url): return self._extract_akamai_formats(asset_url, video_id) asset_url = re.sub(r'(?:bw_(?:low|high)=\d+|no_audio_only|adap=.+?\b)&?', '', asset_url) formats, subtitles = self._extract_m3u8_formats_and_subtitles( asset_url, video_id, 'mp4', 'm3u8_native', fatal=False) if not formats and re.search(self._CDN_REPL_REGEX, asset_url): formats, subtitles = self._extract_m3u8_formats_and_subtitles( re.sub(self._CDN_REPL_REGEX, '://nrk-od-%02d.akamaized.net/no/' % random.randint(0, 99), asset_url), video_id, 'mp4', 'm3u8_native', fatal=False) return formats, subtitles def _raise_error(self, data): MESSAGES = { 'ProgramRightsAreNotReady': 'Du kan dessverre ikke se eller høre programmet', 'ProgramRightsHasExpired': 'Programmet har gått ut', 'NoProgramRights': 'Ikke tilgjengelig', 'ProgramIsGeoBlocked': 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge', } message_type = data.get('messageType', '') # Can be ProgramIsGeoBlocked or ChannelIsGeoBlocked* if 'IsGeoBlocked' in message_type or try_get(data, lambda x: x['usageRights']['isGeoBlocked']) is True: self.raise_geo_restricted( msg=MESSAGES.get('ProgramIsGeoBlocked'), countries=self._GEO_COUNTRIES) message = data.get('endUserMessage') or MESSAGES.get(message_type, message_type) raise ExtractorError(f'{self.IE_NAME} said: {message}', expected=True) def _call_api(self, path, video_id, item=None, note=None, fatal=True, query=None): return self._download_json( urljoin('https://psapi.nrk.no/', path), video_id, note or f'Downloading {item} JSON', fatal=fatal, query=query, headers=self._API_CALL_HEADERS) class NRKIE(NRKBaseIE): _VALID_URL = r'''(?x) (?: nrk:| https?:// (?: (?:www\.)?nrk\.no/video/(?:PS\*|[^_]+_)| v8[-.]psapi\.nrk\.no/mediaelement/ ) ) (?P[^?\#&]+) ''' _TESTS = [{ # video 'url': 'http://www.nrk.no/video/PS*150533', 'md5': '2b88a652ad2e275591e61cf550887eec', 'info_dict': { 'id': '150533', 'ext': 'mp4', 'title': 'Dompap og andre fugler i Piip-Show', 'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f', 'duration': 262, 'timestamp': 1395751833, 'upload_date': '20140325', 'thumbnail': 'https://gfx.nrk.no/0mZgeckEzRU6qTWrbQHD2QcyralHrYB08wBvh-K-AtAQ', 'alt_title': 'md5:d9261ba34c43b61c812cb6b0269a5c8f', }, }, { # audio 'url': 'http://www.nrk.no/video/PS*154915', # MD5 is unstable 'info_dict': { 'id': '154915', 'ext': 'mp4', 'title': 'Slik høres internett ut når du er blind', 'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568', 'duration': 20, 'alt_title': 'Cathrine Lie Wathne er blind, og bruker hurtigtaster for å navigere seg rundt på ulike nettsider.', 'upload_date': '20140425', 'timestamp': 1398429565, 'thumbnail': 'https://gfx.nrk.no/urxQMSXF-WnbfjBH5ke2igLGyN27EdJVWZ6FOsEAclhA', }, }, { 'url': 'nrk:ecc1b952-96dc-4a98-81b9-5296dc7a98d9', 'only_matching': True, }, { 'url': 'nrk:clip/7707d5a3-ebe7-434a-87d5-a3ebe7a34a70', 'only_matching': True, }, { 'url': 'https://v8-psapi.nrk.no/mediaelement/ecc1b952-96dc-4a98-81b9-5296dc7a98d9', 'only_matching': True, }, { 'url': 'https://www.nrk.no/video/dompap-og-andre-fugler-i-piip-show_150533', 'only_matching': True, }, { 'url': 'https://www.nrk.no/video/humor/kommentatorboksen-reiser-til-sjos_d1fda11f-a4ad-437a-a374-0398bc84e999', 'only_matching': True, }, { # podcast 'url': 'nrk:l_96f4f1b0-de54-4e6a-b4f1-b0de54fe6af8', 'only_matching': True, }, { 'url': 'nrk:podcast/l_96f4f1b0-de54-4e6a-b4f1-b0de54fe6af8', 'only_matching': True, }, { # clip 'url': 'nrk:150533', 'only_matching': True, }, { 'url': 'nrk:clip/150533', 'only_matching': True, }, { # program 'url': 'nrk:MDDP12000117', 'only_matching': True, }, { 'url': 'nrk:program/ENRK10100318', 'only_matching': True, }, { # direkte 'url': 'nrk:nrk1', 'only_matching': True, }, { 'url': 'nrk:channel/nrk1', 'only_matching': True, }] def _real_extract(self, url): video_id = self._match_id(url).split('/')[-1] # known values for preferredCdn: akamai, iponly, minicdn and telenor manifest = self._call_api(f'playback/manifest/{video_id}', video_id, 'manifest', query={'preferredCdn': 'akamai'}) manifest_type = try_get(manifest, lambda x: x['_links']['self']['href'], str).split('/')[3] video_id = try_get(manifest, lambda x: x['id'], str) or video_id if manifest.get('playability') == 'nonPlayable': self._raise_error(manifest['nonPlayable']) playable = manifest['playable'] formats = [] subtitles = {} for asset in playable['assets']: if not isinstance(asset, dict): continue if asset.get('encrypted'): pass # Unencrypted stream no longer available format_url = url_or_none(asset.get('url')) if not format_url: continue asset_format = (asset.get('format') or '').lower() if asset_format == 'hls' or determine_ext(format_url) == 'm3u8': fmts, subs = self._extract_nrk_formats_and_subtitles(format_url, video_id) formats.extend(fmts) self._merge_subtitles(subs, target=subtitles) elif asset_format == 'mp3': formats.append({ 'url': format_url, 'format_id': asset_format, 'vcodec': 'none', }) data = self._call_api(try_get(manifest, lambda x: x['_links']['metadata']['href']), video_id, 'metadata') preplay = try_get(data, lambda x: x['preplay']) titles = try_get(preplay, lambda x: x['titles']) title = try_get(titles, lambda x: x['title']) alt_title = try_get(titles, lambda x: x['subtitle']) description = try_get(preplay, lambda x: x['description'].replace('\r', '\n')) duration = parse_duration(playable.get('duration')) or parse_duration(data.get('duration')) or self._extract_m3u8_vod_duration(formats[0]['url'], video_id) thumbnails = [] for image in try_get( preplay, lambda x: x['poster']['images'], list) or []: if not isinstance(image, dict): continue image_url = url_or_none(image.get('url')) if not image_url: continue thumbnails.append({ 'url': image_url, 'width': int_or_none(image.get('pixelWidth')), 'height': int_or_none(image.get('pixelHeight')), }) for sub in try_get(playable, lambda x: x['subtitles'], list) or []: if not isinstance(sub, dict): continue sub_url = url_or_none(sub.get('webVtt')) if not sub_url: continue sub_key = str_or_none(sub.get('language')) or 'nb' sub_type = str_or_none(sub.get('type')) if sub_type: sub_key += f'-{sub_type}' subtitles.setdefault(sub_key, []).append({ 'url': sub_url, }) chapters = [] if data.get('skipDialogInfo'): chapters = [item for item in [{ 'start_time': float_or_none(traverse_obj(data, ('skipDialogInfo', 'startIntroInSeconds'))), 'end_time': float_or_none(traverse_obj(data, ('skipDialogInfo', 'endIntroInSeconds'))), 'title': 'Intro', }, { 'start_time': float_or_none(traverse_obj(data, ('skipDialogInfo', 'startCreditsInSeconds'))), 'end_time': duration, 'title': 'Outro', }] if not item['start_time'] == item['end_time']] if try_get(data, lambda x: x['preplay']['indexPoints']): seconds_or_none = lambda x: float_or_none(parse_duration(x)) chapters += traverse_obj(data['preplay'], ('indexPoints', ..., { 'start_time': ('startPoint', {seconds_or_none}), 'end_time': ('endPoint', {seconds_or_none}), 'title': ('title', {lambda x: x}), })) chapters = sorted(chapters, key=lambda x: x['start_time']) if chapters else None legal_age = try_get( data, lambda x: x['legalAge']['body']['rating']['code'], str) # https://en.wikipedia.org/wiki/Norwegian_Media_Authority age_limit = None if legal_age: if legal_age == 'A': age_limit = 0 elif legal_age.isdigit(): age_limit = int_or_none(legal_age) is_series = try_get(data, lambda x: x['_links']['series']['name']) == 'series' info = { 'id': video_id, 'title': title, 'alt_title': alt_title, 'description': description, 'duration': duration, 'thumbnails': thumbnails, 'age_limit': age_limit, 'formats': formats, 'subtitles': subtitles, 'chapters': chapters, 'timestamp': parse_iso8601(try_get(data, lambda x: x['availability']['onDemand']['from'], str)), } if is_series: series = season_id = season_number = episode = episode_number = None programs = self._call_api( f'programs/{video_id}', video_id, 'programs', fatal=False) match = re.search(r'\d+', try_get(programs, lambda x: x['firstTimeTransmitted']['publicationDate'] or x['usageRights']['availableFrom'], str) or try_get(programs, lambda x: x['usageRights']['availableFrom'], str)) if match: info.update({'timestamp': min(info['timestamp'], int(match.group()) // 1000)}) if programs and isinstance(programs, dict): series = str_or_none(programs.get('seriesTitle')) season_id = str_or_none(programs.get('seasonId')) season_number = int_or_none(programs.get('seasonNumber')) episode = str_or_none(programs.get('episodeTitle')) episode_number = int_or_none(programs.get('episodeNumber')) if not series: series = title if alt_title: title += f' - {alt_title}' if not season_number: season_number = int_or_none(self._search_regex( r'Sesong\s+(\d+)', description or '', 'season number', default=None)) if not episode: episode = alt_title if is_series else None if not episode_number: episode_number = int_or_none(self._search_regex( r'^(\d+)\.', episode or '', 'episode number', default=None)) if not episode_number: episode_number = int_or_none(self._search_regex( r'\((\d+)\s*:\s*\d+\)', description or '', 'episode number', default=None)) info.update({ 'title': title, 'series': series, 'season_id': season_id, 'season_number': season_number, 'episode': episode, 'episode_number': episode_number, }) return info def _perform_login(self, username, password): try: self._download_json( self._LOGIN_URL, None, headers={'Content-Type': 'application/json; charset=UTF-8', 'accept': 'application/json; charset=utf-8'}, data=json.dumps({ 'clientId': '', 'hashedPassword': {'current': { 'hash': password, 'recipe': { 'algorithm': 'cleartext', 'salt': '' } } }, 'password': password, 'username': username, }).encode()) self._download_webpage('https://tv.nrk.no/auth/web/login/opsession', None) response = self._download_json('https://tv.nrk.no/auth/session/tokenforsub/_', None) self._AUTH_TOKEN = try_get(response, lambda x: x['session']['accessToken']) self._API_CALL_HEADERS['authorization'] = f'Bearer {self._AUTH_TOKEN}' except ExtractorError as e: message = None if isinstance(e.cause, HTTPError) and e.cause.status in (401, 400): resp = self._parse_json( e.cause.response.read().decode(), None, fatal=False) or {} message = next((error['message'] for error in resp['errors'] if error['field'] == 'Password'), None) self.report_warning(message or 'Unable to log in') class NRKTVIE(InfoExtractor): IE_DESC = 'NRK TV and NRK Radio' _EPISODE_RE = r'(?P[a-zA-Z]{4}\d{8})' _VALID_URL = rf'https?://(?:tv|radio)\.nrk(?:super)?\.no/(?:[^/]+/)*{_EPISODE_RE}' _NETRC_MACHINE = 'nrk' _TESTS = [{ 'url': 'https://tv.nrk.no/program/MDDP12000117', 'md5': 'c4a5960f1b00b40d47db65c1064e0ab1', 'info_dict': { 'id': 'MDDP12000117', 'ext': 'mp4', 'title': 'Alarm Trolltunga', 'description': 'md5:46923a6e6510eefcce23d5ef2a58f2ce', 'duration': 2223.44, 'age_limit': 6, 'subtitles': { 'nb-nor': [{ 'ext': 'vtt', }], 'nb-ttv': [{ 'ext': 'vtt', }], }, 'upload_date': '20170627', 'chapters': [{'start_time': 0, 'end_time': 2213.0, 'title': ''}, {'start_time': 2213.0, 'end_time': 2223.44, 'title': 'Outro'}], 'timestamp': 1498591822, 'thumbnail': 'https://gfx.nrk.no/myRSc4vuFlahB60P3n6swwRTQUZI1LqJZl9B7icZFgzA', 'alt_title': 'md5:46923a6e6510eefcce23d5ef2a58f2ce', }, 'params': { 'skip_download': True, }, }, { 'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014', 'md5': '8d40dab61cea8ab0114e090b029a0565', 'info_dict': { 'id': 'MUHH48000314', 'ext': 'mp4', 'title': '20 spørsmål - 23. mai 2014', 'alt_title': '23. mai 2014', 'description': 'md5:bdea103bc35494c143c6a9acdd84887a', 'duration': 1741, 'age_limit': 0, 'series': '20 spørsmål', 'episode': '23. mai 2014', 'upload_date': '20140523', 'thumbnail': 'https://gfx.nrk.no/u7uCe79SEfPVGRAGVp2_uAZnNc4mfz_kjXg6Bgek8lMQ', 'season_id': '126936', 'season_number': 2014, 'season': 'Season 2014', 'chapters': [{'start_time': 0.0, 'end_time': 39.0, 'title': 'Intro'}, {'start_time': 0.0, 'title': 'Velkommen', 'end_time': 152.32}, {'start_time': 152.32, 'title': 'Tannpirker', 'end_time': 304.76}, {'start_time': 304.76, 'title': 'Orgelbrus', 'end_time': 513.48}, {'start_time': 513.48, 'title': 'G-streng', 'end_time': 712.96}, {'start_time': 712.96, 'title': 'Medalje', 'end_time': 837.76}, {'start_time': 837.76, 'title': 'Globus', 'end_time': 1124.48}, {'start_time': 1124.48, 'title': 'Primstav', 'end_time': 1417.4}, {'start_time': 1417.4, 'title': 'Fyr', 'end_time': 1721.0}, {'start_time': 1721.0, 'end_time': 1741.0, 'title': 'Outro'}], 'episode_number': 3, 'timestamp': 1400871900, }, 'params': { 'skip_download': True, }, }, { 'url': 'https://tv.nrk.no/program/mdfp15000514', 'info_dict': { 'id': 'MDFP15000514', 'ext': 'mp4', 'title': 'Kunnskapskanalen - Grunnlovsjubiléet - Stor ståhei for ingenting', 'description': 'md5:09fd0f9cd47ba6b857836a385b88ed56', 'duration': 4605.08, 'series': 'Kunnskapskanalen', 'episode': 'Grunnlovsjubiléet - Stor ståhei for ingenting', 'age_limit': 0, 'upload_date': '20140524', 'episode_number': 17, 'chapters': [{'start_time': 0, 'end_time': 4595.0, 'title': ''}, {'start_time': 4595.0, 'end_time': 4605.08, 'title': 'Outro'}], 'season': 'Season 2014', 'timestamp': 1400937600, 'thumbnail': 'https://gfx.nrk.no/D2u6-EyVUZpVCq0PdSNHRgdBZCV40ekpk6s9fZWiMtyg', 'season_number': 2014, 'season_id': '39240', 'alt_title': 'Grunnlovsjubiléet - Stor ståhei for ingenting', }, 'params': { 'skip_download': True, }, }, { # single playlist video 'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2', 'info_dict': { 'id': 'MSPO40010515', 'ext': 'mp4', 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015', 'description': 'md5:c03aba1e917561eface5214020551b7a', 'age_limit': 0, }, 'params': { 'skip_download': True, }, 'expected_warnings': ['Failed to download m3u8 information'], 'skip': 'particular part is not supported currently', }, { 'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015', 'info_dict': { 'id': 'MSPO40010515', 'ext': 'mp4', 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015', 'description': 'md5:c03aba1e917561eface5214020551b7a', 'age_limit': 0, }, 'expected_warnings': ['Failed to download m3u8 information'], 'skip': 'Ikke tilgjengelig utenfor Norge', }, { 'url': 'https://tv.nrk.no/serie/anno/KMTE50001317/sesong-3/episode-13', 'info_dict': { 'id': 'KMTE50001317', 'ext': 'mp4', 'title': 'Anno - 13. episode', 'description': 'md5:11d9613661a8dbe6f9bef54e3a4cbbfa', 'duration': 2340, 'series': 'Anno', 'episode': '13. episode', 'season_number': 3, 'episode_number': 13, 'age_limit': 0, }, 'params': { 'skip_download': True, }, 'skip': 'ProgramRightsHasExpired', }, { 'url': 'https://tv.nrk.no/serie/nytt-paa-nytt/MUHH46000317/27-01-2017', 'info_dict': { 'id': 'MUHH46000317', 'ext': 'mp4', 'title': 'Nytt på Nytt 27.01.2017', 'description': 'md5:5358d6388fba0ea6f0b6d11c48b9eb4b', 'duration': 1796, 'series': 'Nytt på nytt', 'episode': '27.01.2017', 'age_limit': 0, }, 'params': { 'skip_download': True, }, 'skip': 'ProgramRightsHasExpired', }, { 'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#', 'only_matching': True, }, { 'url': 'https://tv.nrk.no/serie/lindmo/2018/MUHU11006318/avspiller', 'only_matching': True, }, { 'url': 'https://radio.nrk.no/serie/dagsnytt/sesong/201507/NPUB21019315', 'only_matching': True, }] def _real_extract(self, url): video_id = self._match_id(url) return self.url_result( f'nrk:{video_id}', ie=NRKIE.ie_key(), video_id=video_id) class NRKTVEpisodeIE(InfoExtractor): _VALID_URL = r'https?://tv\.nrk\.no/serie/(?P[^/]+/sesong/(?P\d+)/episode/(?P\d+))' _TESTS = [{ 'url': 'https://tv.nrk.no/serie/hellums-kro/sesong/1/episode/2', 'info_dict': { 'id': 'MUHH36005220', 'ext': 'mp4', 'title': 'Hellums kro - 2. Kro, krig og kjærlighet', 'description': 'md5:b32a7dc0b1ed27c8064f58b97bda4350', 'duration': 1563.92, 'series': 'Hellums kro', 'season_number': 1, 'episode_number': 2, 'episode': '2. Kro, krig og kjærlighet', 'age_limit': 6, 'timestamp': 1572584520, 'upload_date': '20191101', 'thumbnail': 'https://gfx.nrk.no/2_4mhU2JhR-8IYRC_OMmAQDbbOHgwcHqgi2sBrNrsjkg', 'alt_title': '2. Kro, krig og kjærlighet', 'season': 'Season 1', 'season_id': '124163', 'chapters': [{'start_time': 0, 'end_time': 29.0, 'title': ''}, {'start_time': 29.0, 'end_time': 50.0, 'title': 'Intro'}, {'start_time': 1530.0, 'end_time': 1563.92, 'title': 'Outro'}], }, 'params': { 'skip_download': True, }, }, { 'url': 'https://tv.nrk.no/serie/backstage/sesong/1/episode/8', 'info_dict': { 'id': 'MSUI14000816', 'ext': 'mp4', 'title': 'Backstage - 8. episode', 'description': 'md5:de6ca5d5a2d56849e4021f2bf2850df4', 'duration': 1320, 'series': 'Backstage', 'season_number': 1, 'episode_number': 8, 'episode': '8. episode', 'age_limit': 0, }, 'params': { 'skip_download': True, }, 'skip': 'ProgramRightsHasExpired', }] def _real_extract(self, url): display_id, season_number, episode_number = self._match_valid_url(url).groups() webpage = self._download_webpage(url, display_id) info = self._parse_json(self._search_regex(r'