X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/540fd68c40df72763aee5d75598675c45cfa9aba..0fef6c070f2a2ec2c197d440b3e9bb8646c4f9ce:/youtube_dl/extractor/nrk.py diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py index cc70c29..072f920 100644 --- a/youtube_dl/extractor/nrk.py +++ b/youtube_dl/extractor/nrk.py @@ -1,290 +1,677 @@ -# encoding: utf-8 +# coding: utf-8 from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import ( + compat_str, + compat_urllib_parse_unquote, +) from ..utils import ( ExtractorError, - float_or_none, + int_or_none, + JSON_LD_RE, + NO_DEFAULT, + parse_age_limit, parse_duration, - unified_strdate, + try_get, ) -class NRKIE(InfoExtractor): - _VALID_URL = r'(?:nrk:|http://(?:www\.)?nrk\.no/video/PS\*)(?P\d+)' +class NRKBaseIE(InfoExtractor): + _GEO_COUNTRIES = ['NO'] - _TESTS = [ - { - 'url': 'http://www.nrk.no/video/PS*150533', - 'md5': 'bccd850baebefe23b56d708a113229c2', - 'info_dict': { - 'id': '150533', - 'ext': 'flv', - 'title': 'Dompap og andre fugler i Piip-Show', - 'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f', - 'duration': 263, - } - }, - { - 'url': 'http://www.nrk.no/video/PS*154915', - 'md5': '0b1493ba1aae7d9579a5ad5531bc395a', - 'info_dict': { - 'id': '154915', - 'ext': 'flv', - 'title': 'Slik høres internett ut når du er blind', - 'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568', - 'duration': 20, - } - }, - ] + _api_host = None def _real_extract(self, url): video_id = self._match_id(url) - data = self._download_json( - 'http://v8.psapi.nrk.no/mediaelement/%s' % video_id, - video_id, 'Downloading media JSON') + api_hosts = (self._api_host, ) if self._api_host else self._API_HOSTS + + for api_host in api_hosts: + data = self._download_json( + 'http://%s/mediaelement/%s' % (api_host, video_id), + video_id, 'Downloading mediaelement JSON', + fatal=api_host == api_hosts[-1]) + if not data: + continue + self._api_host = api_host + break + + title = data.get('fullTitle') or data.get('mainTitle') or data['title'] + video_id = data.get('id') or video_id + + entries = [] + + conviva = data.get('convivaStatistics') or {} + live = (data.get('mediaElementType') == 'Live' or + data.get('isLive') is True or conviva.get('isLive')) + + def make_title(t): + return self._live_title(t) if live else t + + media_assets = data.get('mediaAssets') + if media_assets and isinstance(media_assets, list): + def video_id_and_title(idx): + return ((video_id, title) if len(media_assets) == 1 + else ('%s-%d' % (video_id, idx), '%s (Part %d)' % (title, idx))) + for num, asset in enumerate(media_assets, 1): + asset_url = asset.get('url') + if not asset_url: + continue + formats = self._extract_akamai_formats(asset_url, video_id) + if not formats: + continue + self._sort_formats(formats) + + # Some f4m streams may not work with hdcore in fragments' URLs + for f in formats: + extra_param = f.get('extra_param_to_segment_url') + if extra_param and 'hdcore' in extra_param: + del f['extra_param_to_segment_url'] + + entry_id, entry_title = video_id_and_title(num) + duration = parse_duration(asset.get('duration')) + subtitles = {} + for subtitle in ('webVtt', 'timedText'): + subtitle_url = asset.get('%sSubtitlesUrl' % subtitle) + if subtitle_url: + subtitles.setdefault('no', []).append({ + 'url': compat_urllib_parse_unquote(subtitle_url) + }) + entries.append({ + 'id': asset.get('carrierId') or entry_id, + 'title': make_title(entry_title), + 'duration': duration, + 'subtitles': subtitles, + 'formats': formats, + }) + + if not entries: + media_url = data.get('mediaUrl') + if media_url: + formats = self._extract_akamai_formats(media_url, video_id) + self._sort_formats(formats) + duration = parse_duration(data.get('duration')) + entries = [{ + 'id': video_id, + 'title': make_title(title), + 'duration': duration, + 'formats': formats, + }] - if data['usageRights']['isGeoBlocked']: + if not entries: + MESSAGES = { + 'ProgramRightsAreNotReady': 'Du kan dessverre ikke se eller høre programmet', + 'ProgramRightsHasExpired': 'Programmet har gått ut', + '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: + self.raise_geo_restricted( + msg=MESSAGES.get('ProgramIsGeoBlocked'), + countries=self._GEO_COUNTRIES) raise ExtractorError( - 'NRK har ikke rettig-heter til å vise dette programmet utenfor Norge', + '%s said: %s' % (self.IE_NAME, MESSAGES.get( + message_type, message_type)), expected=True) - video_url = data['mediaUrl'] + '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81' + series = conviva.get('seriesName') or data.get('seriesTitle') + episode = conviva.get('episodeName') or data.get('episodeNumberOrDate') + + season_number = None + episode_number = None + if data.get('mediaElementType') == 'Episode': + _season_episode = data.get('scoresStatistics', {}).get('springStreamStream') or \ + data.get('relativeOriginUrl', '') + EPISODENUM_RE = [ + r'/s(?P\d{,2})e(?P\d{,2})\.', + r'/sesong-(?P\d{,2})/episode-(?P\d{,2})', + ] + season_number = int_or_none(self._search_regex( + EPISODENUM_RE, _season_episode, 'season number', + default=None, group='season')) + episode_number = int_or_none(self._search_regex( + EPISODENUM_RE, _season_episode, 'episode number', + default=None, group='episode')) + + thumbnails = None + images = data.get('images') + if images and isinstance(images, dict): + web_images = images.get('webImages') + if isinstance(web_images, list): + thumbnails = [{ + 'url': image['imageUrl'], + 'width': int_or_none(image.get('width')), + 'height': int_or_none(image.get('height')), + } for image in web_images if image.get('imageUrl')] + + description = data.get('description') + category = data.get('mediaAnalytics', {}).get('category') + + common_info = { + 'description': description, + 'series': series, + 'episode': episode, + 'season_number': season_number, + 'episode_number': episode_number, + 'categories': [category] if category else None, + 'age_limit': parse_age_limit(data.get('legalAge')), + 'thumbnails': thumbnails, + } - duration = parse_duration(data.get('duration')) + vcodec = 'none' if data.get('mediaType') == 'Audio' else None - images = data.get('images') - if images: - thumbnails = images['webImages'] - thumbnails.sort(key=lambda image: image['pixelWidth']) - thumbnail = thumbnails[-1]['imageUrl'] - else: - thumbnail = None - - return { - 'id': video_id, - 'url': video_url, + for entry in entries: + entry.update(common_info) + for f in entry['formats']: + f['vcodec'] = vcodec + + points = data.get('shortIndexPoints') + if isinstance(points, list): + chapters = [] + for next_num, point in enumerate(points, start=1): + if not isinstance(point, dict): + continue + start_time = parse_duration(point.get('startPoint')) + if start_time is None: + continue + end_time = parse_duration( + data.get('duration') + if next_num == len(points) + else points[next_num].get('startPoint')) + if end_time is None: + continue + chapters.append({ + 'start_time': start_time, + 'end_time': end_time, + 'title': point.get('title'), + }) + if chapters and len(entries) == 1: + entries[0]['chapters'] = chapters + + return self.playlist_result(entries, video_id, title, description) + + +class NRKIE(NRKBaseIE): + _VALID_URL = r'''(?x) + (?: + nrk:| + https?:// + (?: + (?:www\.)?nrk\.no/video/PS\*| + v8[-.]psapi\.nrk\.no/mediaelement/ + ) + ) + (?P[^?#&]+) + ''' + _API_HOSTS = ('psapi.nrk.no', 'v8-psapi.nrk.no') + _TESTS = [{ + # video + 'url': 'http://www.nrk.no/video/PS*150533', + 'md5': '706f34cdf1322577589e369e522b50ef', + 'info_dict': { + 'id': '150533', + 'ext': 'mp4', + 'title': 'Dompap og andre fugler i Piip-Show', + 'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f', + 'duration': 262, + } + }, { + # audio + 'url': 'http://www.nrk.no/video/PS*154915', + # MD5 is unstable + 'info_dict': { + 'id': '154915', 'ext': 'flv', - 'title': data['title'], - 'description': data['description'], - 'duration': duration, - 'thumbnail': thumbnail, + 'title': 'Slik høres internett ut når du er blind', + 'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568', + 'duration': 20, } + }, { + '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, + }] + + +class NRKTVIE(NRKBaseIE): + IE_DESC = 'NRK TV and NRK Radio' + _EPISODE_RE = r'(?P[a-zA-Z]{4}\d{8})' + _VALID_URL = r'''(?x) + https?:// + (?:tv|radio)\.nrk(?:super)?\.no/ + (?:serie(?:/[^/]+){1,2}|program)/ + (?![Ee]pisodes)%s + (?:/\d{2}-\d{2}-\d{4})? + (?:\#del=(?P\d+))? + ''' % _EPISODE_RE + _API_HOSTS = ('psapi-ne.nrk.no', 'psapi-we.nrk.no') + _TESTS = [{ + 'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014', + 'md5': '9a167e54d04671eb6317a37b7bc8a280', + 'info_dict': { + 'id': 'MUHH48000314AA', + 'ext': 'mp4', + 'title': '20 spørsmål 23.05.2014', + 'description': 'md5:bdea103bc35494c143c6a9acdd84887a', + 'duration': 1741, + 'series': '20 spørsmål', + 'episode': '23.05.2014', + }, + }, { + 'url': 'https://tv.nrk.no/program/mdfp15000514', + 'info_dict': { + 'id': 'MDFP15000514CA', + 'ext': 'mp4', + 'title': 'Grunnlovsjubiléet - Stor ståhei for ingenting 24.05.2014', + 'description': 'md5:89290c5ccde1b3a24bb8050ab67fe1db', + 'duration': 4605, + 'series': 'Kunnskapskanalen', + 'episode': '24.05.2014', + }, + '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-part2', + 'ext': 'flv', + 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)', + 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26', + }, + 'params': { + 'skip_download': True, + }, + 'expected_warnings': ['Video is geo restricted'], + 'skip': 'particular part is not supported currently', + }, { + 'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015', + 'playlist': [{ + 'info_dict': { + 'id': 'MSPO40010515AH', + 'ext': 'mp4', + 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 1)', + 'description': 'md5:1f97a41f05a9486ee00c56f35f82993d', + 'duration': 772, + 'series': 'Tour de Ski', + 'episode': '06.01.2015', + }, + 'params': { + 'skip_download': True, + }, + }, { + 'info_dict': { + 'id': 'MSPO40010515BH', + 'ext': 'mp4', + 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 2)', + 'description': 'md5:1f97a41f05a9486ee00c56f35f82993d', + 'duration': 6175, + 'series': 'Tour de Ski', + 'episode': '06.01.2015', + }, + 'params': { + 'skip_download': True, + }, + }], + 'info_dict': { + 'id': 'MSPO40010515', + 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015', + 'description': 'md5:1f97a41f05a9486ee00c56f35f82993d', + }, + 'expected_warnings': ['Video is geo restricted'], + }, { + 'url': 'https://tv.nrk.no/serie/anno/KMTE50001317/sesong-3/episode-13', + 'info_dict': { + 'id': 'KMTE50001317AA', + 'ext': 'mp4', + 'title': 'Anno 13:30', + 'description': 'md5:11d9613661a8dbe6f9bef54e3a4cbbfa', + 'duration': 2340, + 'series': 'Anno', + 'episode': '13:30', + 'season_number': 3, + 'episode_number': 13, + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'https://tv.nrk.no/serie/nytt-paa-nytt/MUHH46000317/27-01-2017', + 'info_dict': { + 'id': 'MUHH46000317AA', + 'ext': 'mp4', + 'title': 'Nytt på Nytt 27.01.2017', + 'description': 'md5:5358d6388fba0ea6f0b6d11c48b9eb4b', + 'duration': 1796, + 'series': 'Nytt på nytt', + 'episode': '27.01.2017', + }, + 'params': { + 'skip_download': True, + }, + }, { + '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, + }] -class NRKPlaylistIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?nrk\.no/(?!video)(?:[^/]+/)+(?P[^/]+)' +class NRKTVEpisodeIE(InfoExtractor): + _VALID_URL = r'https?://tv\.nrk\.no/serie/(?P[^/]+/sesong/\d+/episode/\d+)' + _TEST = { + 'url': 'https://tv.nrk.no/serie/backstage/sesong/1/episode/8', + 'info_dict': { + 'id': 'MSUI14000816AA', + 'ext': 'mp4', + 'title': 'Backstage 8:30', + 'description': 'md5:de6ca5d5a2d56849e4021f2bf2850df4', + 'duration': 1320, + 'series': 'Backstage', + 'season_number': 1, + 'episode_number': 8, + 'episode': '8:30', + }, + 'params': { + 'skip_download': True, + }, + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + nrk_id = self._parse_json( + self._search_regex(JSON_LD_RE, webpage, 'JSON-LD', group='json_ld'), + display_id)['@id'] + + assert re.match(NRKTVIE._EPISODE_RE, nrk_id) + return self.url_result( + 'nrk:%s' % nrk_id, ie=NRKIE.ie_key(), video_id=nrk_id) + + +class NRKTVSerieBaseIE(InfoExtractor): + def _extract_series(self, webpage, display_id, fatal=True): + config = self._parse_json( + self._search_regex( + (r'INITIAL_DATA_*\s*=\s*({.+?})\s*;', + r'({.+?})\s*,\s*"[^"]+"\s*\)\s*'), + webpage, 'config', default='{}' if not fatal else NO_DEFAULT), + display_id, fatal=False) + if not config: + return + return try_get( + config, + (lambda x: x['initialState']['series'], lambda x: x['series']), + dict) + + def _extract_seasons(self, seasons): + if not isinstance(seasons, list): + return [] + entries = [] + for season in seasons: + entries.extend(self._extract_episodes(season)) + return entries + + def _extract_episodes(self, season): + if not isinstance(season, dict): + return [] + return self._extract_entries(season.get('episodes')) + + def _extract_entries(self, entry_list): + if not isinstance(entry_list, list): + return [] + entries = [] + for episode in entry_list: + nrk_id = episode.get('prfId') + if not nrk_id or not isinstance(nrk_id, compat_str): + continue + entries.append(self.url_result( + 'nrk:%s' % nrk_id, ie=NRKIE.ie_key(), video_id=nrk_id)) + return entries + + +class NRKTVSeasonIE(NRKTVSerieBaseIE): + _VALID_URL = r'https?://tv\.nrk\.no/serie/[^/]+/sesong/(?P\d+)' + _TEST = { + 'url': 'https://tv.nrk.no/serie/backstage/sesong/1', + 'info_dict': { + 'id': '1', + 'title': 'Sesong 1', + }, + 'playlist_mincount': 30, + } + @classmethod + def suitable(cls, url): + return (False if NRKTVIE.suitable(url) or NRKTVEpisodeIE.suitable(url) + else super(NRKTVSeasonIE, cls).suitable(url)) + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + series = self._extract_series(webpage, display_id) + + season = next( + s for s in series['seasons'] + if int(display_id) == s.get('seasonNumber')) + + title = try_get(season, lambda x: x['titles']['title'], compat_str) + return self.playlist_result( + self._extract_episodes(season), display_id, title) + + +class NRKTVSeriesIE(NRKTVSerieBaseIE): + _VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/serie/(?P[^/]+)' + _ITEM_RE = r'(?:data-season=["\']|id=["\']season-)(?P\d+)' _TESTS = [{ - 'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763', + # new layout, seasons + 'url': 'https://tv.nrk.no/serie/backstage', 'info_dict': { - 'id': 'gjenopplev-den-historiske-solformorkelsen-1.12270763', - 'title': 'Gjenopplev den historiske solformørkelsen', - 'description': 'md5:c2df8ea3bac5654a26fc2834a542feed', + 'id': 'backstage', + 'title': 'Backstage', + 'description': 'md5:c3ec3a35736fca0f9e1207b5511143d3', }, - 'playlist_count': 2, + 'playlist_mincount': 60, }, { - 'url': 'http://www.nrk.no/kultur/bok/rivertonprisen-til-karin-fossum-1.12266449', + # new layout, instalments + 'url': 'https://tv.nrk.no/serie/groenn-glede', 'info_dict': { - 'id': 'rivertonprisen-til-karin-fossum-1.12266449', - 'title': 'Rivertonprisen til Karin Fossum', - 'description': 'Første kvinne på 15 år til å vinne krimlitteraturprisen.', + 'id': 'groenn-glede', + 'title': 'Grønn glede', + 'description': 'md5:7576e92ae7f65da6993cf90ee29e4608', + }, + 'playlist_mincount': 10, + }, { + # old layout + 'url': 'https://tv.nrksuper.no/serie/labyrint', + 'info_dict': { + 'id': 'labyrint', + 'title': 'Labyrint', + 'description': 'md5:318b597330fdac5959247c9b69fdb1ec', }, - 'playlist_count': 5, + 'playlist_mincount': 3, + }, { + 'url': 'https://tv.nrk.no/serie/broedrene-dal-og-spektralsteinene', + 'only_matching': True, + }, { + 'url': 'https://tv.nrk.no/serie/saving-the-human-race', + 'only_matching': True, + }, { + 'url': 'https://tv.nrk.no/serie/postmann-pat', + 'only_matching': True, }] + @classmethod + def suitable(cls, url): + return ( + False if any(ie.suitable(url) + for ie in (NRKTVIE, NRKTVEpisodeIE, NRKTVSeasonIE)) + else super(NRKTVSeriesIE, cls).suitable(url)) + + def _real_extract(self, url): + series_id = self._match_id(url) + + webpage = self._download_webpage(url, series_id) + + # New layout (e.g. https://tv.nrk.no/serie/backstage) + series = self._extract_series(webpage, series_id, fatal=False) + if series: + title = try_get(series, lambda x: x['titles']['title'], compat_str) + description = try_get( + series, lambda x: x['titles']['subtitle'], compat_str) + entries = [] + entries.extend(self._extract_seasons(series.get('seasons'))) + entries.extend(self._extract_entries(series.get('instalments'))) + entries.extend(self._extract_episodes(series.get('extraMaterial'))) + return self.playlist_result(entries, series_id, title, description) + + # Old layout (e.g. https://tv.nrksuper.no/serie/labyrint) + entries = [ + self.url_result( + 'https://tv.nrk.no/program/Episodes/{series}/{season}'.format( + series=series_id, season=season_id)) + for season_id in re.findall(self._ITEM_RE, webpage) + ] + + title = self._html_search_meta( + 'seriestitle', webpage, + 'title', default=None) or self._og_search_title( + webpage, fatal=False) + if title: + title = self._search_regex( + r'NRK (?:Super )?TV\s*[-–]\s*(.+)', title, 'title', default=title) + + description = self._html_search_meta( + 'series_description', webpage, + 'description', default=None) or self._og_search_description(webpage) + + return self.playlist_result(entries, series_id, title, description) + + +class NRKTVDirekteIE(NRKTVIE): + IE_DESC = 'NRK TV Direkte and NRK Radio Direkte' + _VALID_URL = r'https?://(?:tv|radio)\.nrk\.no/direkte/(?P[^/?#&]+)' + + _TESTS = [{ + 'url': 'https://tv.nrk.no/direkte/nrk1', + 'only_matching': True, + }, { + 'url': 'https://radio.nrk.no/direkte/p1_oslo_akershus', + 'only_matching': True, + }] + + +class NRKPlaylistBaseIE(InfoExtractor): + def _extract_description(self, webpage): + pass + def _real_extract(self, url): playlist_id = self._match_id(url) webpage = self._download_webpage(url, playlist_id) entries = [ - self.url_result('nrk:%s' % video_id, 'NRK') - for video_id in re.findall( - r'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"', - webpage) + self.url_result('nrk:%s' % video_id, NRKIE.ie_key()) + for video_id in re.findall(self._ITEM_RE, webpage) ] - playlist_title = self._og_search_title(webpage) - playlist_description = self._og_search_description(webpage) + playlist_title = self. _extract_title(webpage) + playlist_description = self._extract_description(webpage) return self.playlist_result( entries, playlist_id, playlist_title, playlist_description) -class NRKTVIE(InfoExtractor): - _VALID_URL = r'(?Phttp://tv\.nrk(?:super)?\.no/)(?:serie/[^/]+|program)/(?P[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P\d+))?' - - _TESTS = [ - { - 'url': 'http://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014', - 'md5': 'adf2c5454fa2bf032f47a9f8fb351342', - 'info_dict': { - 'id': 'MUHH48000314', - 'ext': 'flv', - 'title': '20 spørsmål', - 'description': 'md5:bdea103bc35494c143c6a9acdd84887a', - 'upload_date': '20140523', - 'duration': 1741.52, - }, - }, - { - 'url': 'http://tv.nrk.no/program/mdfp15000514', - 'md5': '383650ece2b25ecec996ad7b5bb2a384', - 'info_dict': { - 'id': 'mdfp15000514', - 'ext': 'flv', - 'title': 'Kunnskapskanalen: Grunnlovsjubiléet - Stor ståhei for ingenting', - 'description': 'md5:654c12511f035aed1e42bdf5db3b206a', - 'upload_date': '20140524', - 'duration': 4605.0, - }, +class NRKPlaylistIE(NRKPlaylistBaseIE): + _VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video|skole)(?:[^/]+/)+(?P[^/]+)' + _ITEM_RE = r'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"' + _TESTS = [{ + 'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763', + 'info_dict': { + 'id': 'gjenopplev-den-historiske-solformorkelsen-1.12270763', + 'title': 'Gjenopplev den historiske solformørkelsen', + 'description': 'md5:c2df8ea3bac5654a26fc2834a542feed', }, - { - # single playlist video - 'url': 'http://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2', - 'md5': 'adbd1dbd813edaf532b0a253780719c2', - 'info_dict': { - 'id': 'MSPO40010515-part2', - 'ext': 'flv', - 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)', - 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26', - 'upload_date': '20150106', - }, - 'skip': 'Only works from Norway', + 'playlist_count': 2, + }, { + 'url': 'http://www.nrk.no/kultur/bok/rivertonprisen-til-karin-fossum-1.12266449', + 'info_dict': { + 'id': 'rivertonprisen-til-karin-fossum-1.12266449', + 'title': 'Rivertonprisen til Karin Fossum', + 'description': 'Første kvinne på 15 år til å vinne krimlitteraturprisen.', }, - { - 'url': 'http://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015', - 'playlist': [ - { - 'md5': '9480285eff92d64f06e02a5367970a7a', - 'info_dict': { - 'id': 'MSPO40010515-part1', - 'ext': 'flv', - 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 1:2)', - 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26', - 'upload_date': '20150106', - }, - }, - { - 'md5': 'adbd1dbd813edaf532b0a253780719c2', - 'info_dict': { - 'id': 'MSPO40010515-part2', - 'ext': 'flv', - 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)', - 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26', - 'upload_date': '20150106', - }, - }, - ], - 'info_dict': { - 'id': 'MSPO40010515', - 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn', - 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26', - 'upload_date': '20150106', - 'duration': 6947.5199999999995, - }, - 'skip': 'Only works from Norway', - } - ] + 'playlist_count': 2, + }] - def _debug_print(self, txt): - if self._downloader.params.get('verbose', False): - self.to_screen('[debug] %s' % txt) + def _extract_title(self, webpage): + return self._og_search_title(webpage, fatal=False) - def _get_subtitles(self, subtitlesurl, video_id, baseurl): - url = "%s%s" % (baseurl, subtitlesurl) - self._debug_print('%s: Subtitle url: %s' % (video_id, url)) - captions = self._download_xml( - url, video_id, 'Downloading subtitles') - lang = captions.get('lang', 'no') - return {lang: [ - {'ext': 'ttml', 'url': url}, - ]} + def _extract_description(self, webpage): + return self._og_search_description(webpage) - def _extract_f4m(self, manifest_url, video_id): - return self._extract_f4m_formats(manifest_url + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124', video_id) - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - part_id = mobj.group('part_id') - baseurl = mobj.group('baseurl') +class NRKTVEpisodesIE(NRKPlaylistBaseIE): + _VALID_URL = r'https?://tv\.nrk\.no/program/[Ee]pisodes/[^/]+/(?P\d+)' + _ITEM_RE = r'data-episode=["\']%s' % NRKTVIE._EPISODE_RE + _TESTS = [{ + 'url': 'https://tv.nrk.no/program/episodes/nytt-paa-nytt/69031', + 'info_dict': { + 'id': '69031', + 'title': 'Nytt på nytt, sesong: 201210', + }, + 'playlist_count': 4, + }] - webpage = self._download_webpage(url, video_id) + def _extract_title(self, webpage): + return self._html_search_regex( + r'

([^<]+)

', webpage, 'title', fatal=False) - title = self._html_search_meta( - 'title', webpage, 'title') - description = self._html_search_meta( - 'description', webpage, 'description') - - thumbnail = self._html_search_regex( - r'data-posterimage="([^"]+)"', - webpage, 'thumbnail', fatal=False) - upload_date = unified_strdate(self._html_search_meta( - 'rightsfrom', webpage, 'upload date', fatal=False)) - duration = float_or_none(self._html_search_regex( - r'data-duration="([^"]+)"', - webpage, 'duration', fatal=False)) - - # playlist - parts = re.findall( - r']+data-argument="([^"]+)">([^<]+)', webpage) - if parts: - entries = [] - for current_part_id, stream_url, part_title in parts: - if part_id and current_part_id != part_id: - continue - video_part_id = '%s-part%s' % (video_id, current_part_id) - formats = self._extract_f4m(stream_url, video_part_id) - entries.append({ - 'id': video_part_id, - 'title': part_title, - 'description': description, - 'thumbnail': thumbnail, - 'upload_date': upload_date, - 'formats': formats, - }) - if part_id: - if entries: - return entries[0] - else: - playlist = self.playlist_result(entries, video_id, title, description) - playlist.update({ - 'thumbnail': thumbnail, - 'upload_date': upload_date, - 'duration': duration, - }) - return playlist - formats = [] +class NRKSkoleIE(InfoExtractor): + IE_DESC = 'NRK Skole' + _VALID_URL = r'https?://(?:www\.)?nrk\.no/skole/?\?.*\bmediaId=(?P\d+)' - f4m_url = re.search(r'data-media="([^"]+)"', webpage) - if f4m_url: - formats.extend(self._extract_f4m(f4m_url.group(1), video_id)) + _TESTS = [{ + 'url': 'https://www.nrk.no/skole/?page=search&q=&mediaId=14099', + 'md5': '6bc936b01f9dd8ed45bc58b252b2d9b6', + 'info_dict': { + 'id': '6021', + 'ext': 'mp4', + 'title': 'Genetikk og eneggede tvillinger', + 'description': 'md5:3aca25dcf38ec30f0363428d2b265f8d', + 'duration': 399, + }, + }, { + 'url': 'https://www.nrk.no/skole/?page=objectives&subject=naturfag&objective=K15114&mediaId=19355', + 'only_matching': True, + }] - m3u8_url = re.search(r'data-hls-media="([^"]+)"', webpage) - if m3u8_url: - formats.extend(self._extract_m3u8_formats(m3u8_url.group(1), video_id, 'mp4')) - self._sort_formats(formats) + def _real_extract(self, url): + video_id = self._match_id(url) - subtitles_url = self._html_search_regex( - r'data-subtitlesurl[ ]*=[ ]*"([^"]+)"', - webpage, 'subtitle URL', default=None) - subtitles = None - if subtitles_url: - subtitles = self.extract_subtitles(subtitles_url, video_id, baseurl) + webpage = self._download_webpage( + 'https://mimir.nrk.no/plugin/1.0/static?mediaId=%s' % video_id, + video_id) - return { - 'id': video_id, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'upload_date': upload_date, - 'duration': duration, - 'formats': formats, - 'subtitles': subtitles, - } + nrk_id = self._parse_json( + self._search_regex( + r']+type=["\']application/json["\'][^>]*>({.+?})', + webpage, 'application json'), + video_id)['activeMedia']['psId'] + + return self.url_result('nrk:%s' % nrk_id)