- 'skip': 'Only works from Norway',
- }
- ]
-
- def _seconds2str(self, s):
- return '%02d:%02d:%02d.%03d' % (s / 3600, (s % 3600) / 60, s % 60, (s % 1) * 1000)
-
- def _debug_print(self, txt):
- if self._downloader.params.get('verbose', False):
- self.to_screen('[debug] %s' % txt)
-
- 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',
- transform_source=lambda s: s.replace(r'<br />', '\r\n'))
- lang = captions.get('lang', 'no')
- ps = captions.findall('./{0}body/{0}div/{0}p'.format('{http://www.w3.org/ns/ttml}'))
- srt = ''
- for pos, p in enumerate(ps):
- begin = parse_duration(p.get('begin'))
- duration = parse_duration(p.get('dur'))
- starttime = self._seconds2str(begin)
- endtime = self._seconds2str(begin + duration)
- srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (compat_str(pos), starttime, endtime, p.text)
- return {lang: [
- {'ext': 'ttml', 'url': url},
- {'ext': 'srt', 'data': srt},
- ]}
-
- 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)
+ '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 NRKTVEpisodeIE(InfoExtractor):
+ _VALID_URL = r'https?://tv\.nrk\.no/serie/(?P<id>[^/]+/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*</script>'),
+ 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<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 = [{
+ # 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))
Rapsys Git / youtubedl / blobdiff