+class NRKTVEpisodeIE(InfoExtractor):
+ _VALID_URL = r'https?://tv\.nrk\.no/serie/(?P<id>[^/]+/sesong/\d+/episode/\d+)'
+ _TESTS = [{
+ 'url': 'https://tv.nrk.no/serie/hellums-kro/sesong/1/episode/2',
+ 'info_dict': {
+ 'id': 'MUHH36005220BA',
+ 'ext': 'mp4',
+ 'title': 'Kro, krig og kjærlighet 2:6',
+ 'description': 'md5:b32a7dc0b1ed27c8064f58b97bda4350',
+ 'duration': 1563,
+ 'series': 'Hellums kro',
+ 'season_number': 1,
+ 'episode_number': 2,
+ 'episode': '2:6',
+ 'age_limit': 6,
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ }, {
+ '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,
+ },
+ 'skip': 'ProgramRightsHasExpired',
+ }]
+
+ 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(?:_V\d)?_*\s*=\s*({.+?})\s*;',
+ r'({.+?})\s*,\s*"[^"]+"\s*\)\s*</script>'),
+ webpage, 'config', default='{}' if not fatal else NO_DEFAULT),
+ display_id, fatal=False, transform_source=js_to_json)
+ 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<id>\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<id>[^/]+)'
+ _ITEM_RE = r'(?:data-season=["\']|id=["\']season-)(?P<id>\d+)'
+ _TESTS = [{
+ 'url': 'https://tv.nrk.no/serie/blank',
+ 'info_dict': {
+ 'id': 'blank',
+ 'title': 'Blank',
+ 'description': 'md5:7664b4e7e77dc6810cd3bca367c25b6e',
+ },
+ 'playlist_mincount': 30,
+ }, {
+ # new layout, seasons
+ 'url': 'https://tv.nrk.no/serie/backstage',
+ 'info_dict': {
+ 'id': 'backstage',
+ 'title': 'Backstage',
+ 'description': 'md5:c3ec3a35736fca0f9e1207b5511143d3',
+ },
+ 'playlist_mincount': 60,
+ }, {
+ # new layout, instalments
+ 'url': 'https://tv.nrk.no/serie/groenn-glede',
+ 'info_dict': {
+ '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_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)
+
+
Rapsys Git / youtubedl / blobdiff