2 from __future__ import unicode_literals
6 from .common import InfoExtractor
9 compat_urllib_parse_unquote,
22 class NRKBaseIE(InfoExtractor):
23 _GEO_COUNTRIES = ['NO']
27 def _real_extract(self, url):
28 video_id = self._match_id(url)
30 api_hosts = (self._api_host, ) if self._api_host else self._API_HOSTS
32 for api_host in api_hosts:
33 data = self._download_json(
34 'http://%s/mediaelement/%s' % (api_host, video_id),
35 video_id, 'Downloading mediaelement JSON',
36 fatal=api_host == api_hosts[-1])
39 self._api_host = api_host
42 title = data.get('fullTitle') or data.get('mainTitle') or data['title']
43 video_id = data.get('id') or video_id
47 conviva = data.get('convivaStatistics') or {}
48 live = (data.get('mediaElementType') == 'Live'
49 or data.get('isLive') is True or conviva.get('isLive'))
52 return self._live_title(t) if live else t
54 media_assets = data.get('mediaAssets')
55 if media_assets and isinstance(media_assets, list):
56 def video_id_and_title(idx):
57 return ((video_id, title) if len(media_assets) == 1
58 else ('%s-%d' % (video_id, idx), '%s (Part %d)' % (title, idx)))
59 for num, asset in enumerate(media_assets, 1):
60 asset_url = asset.get('url')
63 formats = self._extract_akamai_formats(asset_url, video_id)
66 self._sort_formats(formats)
68 # Some f4m streams may not work with hdcore in fragments' URLs
70 extra_param = f.get('extra_param_to_segment_url')
71 if extra_param and 'hdcore' in extra_param:
72 del f['extra_param_to_segment_url']
74 entry_id, entry_title = video_id_and_title(num)
75 duration = parse_duration(asset.get('duration'))
77 for subtitle in ('webVtt', 'timedText'):
78 subtitle_url = asset.get('%sSubtitlesUrl' % subtitle)
80 subtitles.setdefault('no', []).append({
81 'url': compat_urllib_parse_unquote(subtitle_url)
84 'id': asset.get('carrierId') or entry_id,
85 'title': make_title(entry_title),
87 'subtitles': subtitles,
92 media_url = data.get('mediaUrl')
94 formats = self._extract_akamai_formats(media_url, video_id)
95 self._sort_formats(formats)
96 duration = parse_duration(data.get('duration'))
99 'title': make_title(title),
100 'duration': duration,
106 'ProgramRightsAreNotReady': 'Du kan dessverre ikke se eller høre programmet',
107 'ProgramRightsHasExpired': 'Programmet har gått ut',
108 'NoProgramRights': 'Ikke tilgjengelig',
109 'ProgramIsGeoBlocked': 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',
111 message_type = data.get('messageType', '')
112 # Can be ProgramIsGeoBlocked or ChannelIsGeoBlocked*
113 if 'IsGeoBlocked' in message_type:
114 self.raise_geo_restricted(
115 msg=MESSAGES.get('ProgramIsGeoBlocked'),
116 countries=self._GEO_COUNTRIES)
117 raise ExtractorError(
118 '%s said: %s' % (self.IE_NAME, MESSAGES.get(
119 message_type, message_type)),
122 series = conviva.get('seriesName') or data.get('seriesTitle')
123 episode = conviva.get('episodeName') or data.get('episodeNumberOrDate')
126 episode_number = None
127 if data.get('mediaElementType') == 'Episode':
128 _season_episode = data.get('scoresStatistics', {}).get('springStreamStream') or \
129 data.get('relativeOriginUrl', '')
131 r'/s(?P<season>\d{,2})e(?P<episode>\d{,2})\.',
132 r'/sesong-(?P<season>\d{,2})/episode-(?P<episode>\d{,2})',
134 season_number = int_or_none(self._search_regex(
135 EPISODENUM_RE, _season_episode, 'season number',
136 default=None, group='season'))
137 episode_number = int_or_none(self._search_regex(
138 EPISODENUM_RE, _season_episode, 'episode number',
139 default=None, group='episode'))
142 images = data.get('images')
143 if images and isinstance(images, dict):
144 web_images = images.get('webImages')
145 if isinstance(web_images, list):
147 'url': image['imageUrl'],
148 'width': int_or_none(image.get('width')),
149 'height': int_or_none(image.get('height')),
150 } for image in web_images if image.get('imageUrl')]
152 description = data.get('description')
153 category = data.get('mediaAnalytics', {}).get('category')
156 'description': description,
159 'season_number': season_number,
160 'episode_number': episode_number,
161 'categories': [category] if category else None,
162 'age_limit': parse_age_limit(data.get('legalAge')),
163 'thumbnails': thumbnails,
166 vcodec = 'none' if data.get('mediaType') == 'Audio' else None
168 for entry in entries:
169 entry.update(common_info)
170 for f in entry['formats']:
173 points = data.get('shortIndexPoints')
174 if isinstance(points, list):
176 for next_num, point in enumerate(points, start=1):
177 if not isinstance(point, dict):
179 start_time = parse_duration(point.get('startPoint'))
180 if start_time is None:
182 end_time = parse_duration(
184 if next_num == len(points)
185 else points[next_num].get('startPoint'))
189 'start_time': start_time,
190 'end_time': end_time,
191 'title': point.get('title'),
193 if chapters and len(entries) == 1:
194 entries[0]['chapters'] = chapters
196 return self.playlist_result(entries, video_id, title, description)
199 class NRKIE(NRKBaseIE):
200 _VALID_URL = r'''(?x)
205 (?:www\.)?nrk\.no/video/PS\*|
206 v8[-.]psapi\.nrk\.no/mediaelement/
211 _API_HOSTS = ('psapi.nrk.no', 'v8-psapi.nrk.no')
214 'url': 'http://www.nrk.no/video/PS*150533',
215 'md5': '706f34cdf1322577589e369e522b50ef',
219 'title': 'Dompap og andre fugler i Piip-Show',
220 'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f',
225 'url': 'http://www.nrk.no/video/PS*154915',
230 'title': 'Slik høres internett ut når du er blind',
231 'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
235 'url': 'nrk:ecc1b952-96dc-4a98-81b9-5296dc7a98d9',
236 'only_matching': True,
238 'url': 'nrk:clip/7707d5a3-ebe7-434a-87d5-a3ebe7a34a70',
239 'only_matching': True,
241 'url': 'https://v8-psapi.nrk.no/mediaelement/ecc1b952-96dc-4a98-81b9-5296dc7a98d9',
242 'only_matching': True,
246 class NRKTVIE(NRKBaseIE):
247 IE_DESC = 'NRK TV and NRK Radio'
248 _EPISODE_RE = r'(?P<id>[a-zA-Z]{4}\d{8})'
249 _VALID_URL = r'''(?x)
251 (?:tv|radio)\.nrk(?:super)?\.no/
252 (?:serie(?:/[^/]+){1,2}|program)/
254 (?:/\d{2}-\d{2}-\d{4})?
255 (?:\#del=(?P<part_id>\d+))?
257 _API_HOSTS = ('psapi-ne.nrk.no', 'psapi-we.nrk.no')
259 'url': 'https://tv.nrk.no/program/MDDP12000117',
260 'md5': '8270824df46ec629b66aeaa5796b36fb',
262 'id': 'MDDP12000117AA',
264 'title': 'Alarm Trolltunga',
265 'description': 'md5:46923a6e6510eefcce23d5ef2a58f2ce',
270 'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
271 'md5': '9a167e54d04671eb6317a37b7bc8a280',
273 'id': 'MUHH48000314AA',
275 'title': '20 spørsmål 23.05.2014',
276 'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
278 'series': '20 spørsmål',
279 'episode': '23.05.2014',
281 'skip': 'NoProgramRights',
283 'url': 'https://tv.nrk.no/program/mdfp15000514',
285 'id': 'MDFP15000514CA',
287 'title': 'Grunnlovsjubiléet - Stor ståhei for ingenting 24.05.2014',
288 'description': 'md5:89290c5ccde1b3a24bb8050ab67fe1db',
290 'series': 'Kunnskapskanalen',
291 'episode': '24.05.2014',
294 'skip_download': True,
297 # single playlist video
298 'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
300 'id': 'MSPO40010515-part2',
302 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
303 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
306 'skip_download': True,
308 'expected_warnings': ['Video is geo restricted'],
309 'skip': 'particular part is not supported currently',
311 'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
314 'id': 'MSPO40010515AH',
316 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 1)',
317 'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',
319 'series': 'Tour de Ski',
320 'episode': '06.01.2015',
323 'skip_download': True,
327 'id': 'MSPO40010515BH',
329 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 2)',
330 'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',
332 'series': 'Tour de Ski',
333 'episode': '06.01.2015',
336 'skip_download': True,
340 'id': 'MSPO40010515',
341 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015',
342 'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',
344 'expected_warnings': ['Video is geo restricted'],
346 'url': 'https://tv.nrk.no/serie/anno/KMTE50001317/sesong-3/episode-13',
348 'id': 'KMTE50001317AA',
350 'title': 'Anno 13:30',
351 'description': 'md5:11d9613661a8dbe6f9bef54e3a4cbbfa',
356 'episode_number': 13,
359 'skip_download': True,
362 'url': 'https://tv.nrk.no/serie/nytt-paa-nytt/MUHH46000317/27-01-2017',
364 'id': 'MUHH46000317AA',
366 'title': 'Nytt på Nytt 27.01.2017',
367 'description': 'md5:5358d6388fba0ea6f0b6d11c48b9eb4b',
369 'series': 'Nytt på nytt',
370 'episode': '27.01.2017',
373 'skip_download': True,
376 'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#',
377 'only_matching': True,
379 'url': 'https://tv.nrk.no/serie/lindmo/2018/MUHU11006318/avspiller',
380 'only_matching': True,
384 class NRKTVEpisodeIE(InfoExtractor):
385 _VALID_URL = r'https?://tv\.nrk\.no/serie/(?P<id>[^/]+/sesong/\d+/episode/\d+)'
387 'url': 'https://tv.nrk.no/serie/hellums-kro/sesong/1/episode/2',
389 'id': 'MUHH36005220BA',
391 'title': 'Kro, krig og kjærlighet 2:6',
392 'description': 'md5:b32a7dc0b1ed27c8064f58b97bda4350',
394 'series': 'Hellums kro',
401 'skip_download': True,
404 'url': 'https://tv.nrk.no/serie/backstage/sesong/1/episode/8',
406 'id': 'MSUI14000816AA',
408 'title': 'Backstage 8:30',
409 'description': 'md5:de6ca5d5a2d56849e4021f2bf2850df4',
411 'series': 'Backstage',
417 'skip_download': True,
419 'skip': 'ProgramRightsHasExpired',
422 def _real_extract(self, url):
423 display_id = self._match_id(url)
425 webpage = self._download_webpage(url, display_id)
427 info = self._search_json_ld(webpage, display_id, default={})
428 nrk_id = info.get('@id') or self._html_search_meta(
429 'nrk:program-id', webpage, default=None) or self._search_regex(
430 r'data-program-id=["\'](%s)' % NRKTVIE._EPISODE_RE, webpage,
432 assert re.match(NRKTVIE._EPISODE_RE, nrk_id)
435 '_type': 'url_transparent',
437 'url': 'nrk:%s' % nrk_id,
438 'ie_key': NRKIE.ie_key(),
443 class NRKTVSerieBaseIE(InfoExtractor):
444 def _extract_series(self, webpage, display_id, fatal=True):
445 config = self._parse_json(
447 (r'INITIAL_DATA(?:_V\d)?_*\s*=\s*({.+?})\s*;',
448 r'({.+?})\s*,\s*"[^"]+"\s*\)\s*</script>'),
449 webpage, 'config', default='{}' if not fatal else NO_DEFAULT),
450 display_id, fatal=False, transform_source=js_to_json)
455 (lambda x: x['initialState']['series'], lambda x: x['series']),
458 def _extract_seasons(self, seasons):
459 if not isinstance(seasons, list):
462 for season in seasons:
463 entries.extend(self._extract_episodes(season))
466 def _extract_episodes(self, season):
467 if not isinstance(season, dict):
469 return self._extract_entries(season.get('episodes'))
471 def _extract_entries(self, entry_list):
472 if not isinstance(entry_list, list):
475 for episode in entry_list:
476 nrk_id = episode.get('prfId')
477 if not nrk_id or not isinstance(nrk_id, compat_str):
479 entries.append(self.url_result(
480 'nrk:%s' % nrk_id, ie=NRKIE.ie_key(), video_id=nrk_id))
484 class NRKTVSeasonIE(NRKTVSerieBaseIE):
485 _VALID_URL = r'https?://tv\.nrk\.no/serie/[^/]+/sesong/(?P<id>\d+)'
487 'url': 'https://tv.nrk.no/serie/backstage/sesong/1',
492 'playlist_mincount': 30,
496 def suitable(cls, url):
497 return (False if NRKTVIE.suitable(url) or NRKTVEpisodeIE.suitable(url)
498 else super(NRKTVSeasonIE, cls).suitable(url))
500 def _real_extract(self, url):
501 display_id = self._match_id(url)
503 webpage = self._download_webpage(url, display_id)
505 series = self._extract_series(webpage, display_id)
508 s for s in series['seasons']
509 if int(display_id) == s.get('seasonNumber'))
511 title = try_get(season, lambda x: x['titles']['title'], compat_str)
512 return self.playlist_result(
513 self._extract_episodes(season), display_id, title)
516 class NRKTVSeriesIE(NRKTVSerieBaseIE):
517 _VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/serie/(?P<id>[^/]+)'
518 _ITEM_RE = r'(?:data-season=["\']|id=["\']season-)(?P<id>\d+)'
520 'url': 'https://tv.nrk.no/serie/blank',
524 'description': 'md5:7664b4e7e77dc6810cd3bca367c25b6e',
526 'playlist_mincount': 30,
528 # new layout, seasons
529 'url': 'https://tv.nrk.no/serie/backstage',
532 'title': 'Backstage',
533 'description': 'md5:c3ec3a35736fca0f9e1207b5511143d3',
535 'playlist_mincount': 60,
537 # new layout, instalments
538 'url': 'https://tv.nrk.no/serie/groenn-glede',
540 'id': 'groenn-glede',
541 'title': 'Grønn glede',
542 'description': 'md5:7576e92ae7f65da6993cf90ee29e4608',
544 'playlist_mincount': 10,
547 'url': 'https://tv.nrksuper.no/serie/labyrint',
551 'description': 'md5:318b597330fdac5959247c9b69fdb1ec',
553 'playlist_mincount': 3,
555 'url': 'https://tv.nrk.no/serie/broedrene-dal-og-spektralsteinene',
556 'only_matching': True,
558 'url': 'https://tv.nrk.no/serie/saving-the-human-race',
559 'only_matching': True,
561 'url': 'https://tv.nrk.no/serie/postmann-pat',
562 'only_matching': True,
566 def suitable(cls, url):
568 False if any(ie.suitable(url)
569 for ie in (NRKTVIE, NRKTVEpisodeIE, NRKTVSeasonIE))
570 else super(NRKTVSeriesIE, cls).suitable(url))
572 def _real_extract(self, url):
573 series_id = self._match_id(url)
575 webpage = self._download_webpage(url, series_id)
577 # New layout (e.g. https://tv.nrk.no/serie/backstage)
578 series = self._extract_series(webpage, series_id, fatal=False)
580 title = try_get(series, lambda x: x['titles']['title'], compat_str)
581 description = try_get(
582 series, lambda x: x['titles']['subtitle'], compat_str)
584 entries.extend(self._extract_seasons(series.get('seasons')))
585 entries.extend(self._extract_entries(series.get('instalments')))
586 entries.extend(self._extract_episodes(series.get('extraMaterial')))
587 return self.playlist_result(entries, series_id, title, description)
589 # Old layout (e.g. https://tv.nrksuper.no/serie/labyrint)
592 'https://tv.nrk.no/program/Episodes/{series}/{season}'.format(
593 series=series_id, season=season_id))
594 for season_id in re.findall(self._ITEM_RE, webpage)
597 title = self._html_search_meta(
598 'seriestitle', webpage,
599 'title', default=None) or self._og_search_title(
600 webpage, fatal=False)
602 title = self._search_regex(
603 r'NRK (?:Super )?TV\s*[-–]\s*(.+)', title, 'title', default=title)
605 description = self._html_search_meta(
606 'series_description', webpage,
607 'description', default=None) or self._og_search_description(webpage)
609 return self.playlist_result(entries, series_id, title, description)
612 class NRKTVDirekteIE(NRKTVIE):
613 IE_DESC = 'NRK TV Direkte and NRK Radio Direkte'
614 _VALID_URL = r'https?://(?:tv|radio)\.nrk\.no/direkte/(?P<id>[^/?#&]+)'
617 'url': 'https://tv.nrk.no/direkte/nrk1',
618 'only_matching': True,
620 'url': 'https://radio.nrk.no/direkte/p1_oslo_akershus',
621 'only_matching': True,
625 class NRKPlaylistBaseIE(InfoExtractor):
626 def _extract_description(self, webpage):
629 def _real_extract(self, url):
630 playlist_id = self._match_id(url)
632 webpage = self._download_webpage(url, playlist_id)
635 self.url_result('nrk:%s' % video_id, NRKIE.ie_key())
636 for video_id in re.findall(self._ITEM_RE, webpage)
639 playlist_title = self. _extract_title(webpage)
640 playlist_description = self._extract_description(webpage)
642 return self.playlist_result(
643 entries, playlist_id, playlist_title, playlist_description)
646 class NRKPlaylistIE(NRKPlaylistBaseIE):
647 _VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video|skole)(?:[^/]+/)+(?P<id>[^/]+)'
648 _ITEM_RE = r'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"'
650 'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',
652 'id': 'gjenopplev-den-historiske-solformorkelsen-1.12270763',
653 'title': 'Gjenopplev den historiske solformørkelsen',
654 'description': 'md5:c2df8ea3bac5654a26fc2834a542feed',
658 'url': 'http://www.nrk.no/kultur/bok/rivertonprisen-til-karin-fossum-1.12266449',
660 'id': 'rivertonprisen-til-karin-fossum-1.12266449',
661 'title': 'Rivertonprisen til Karin Fossum',
662 'description': 'Første kvinne på 15 år til å vinne krimlitteraturprisen.',
667 def _extract_title(self, webpage):
668 return self._og_search_title(webpage, fatal=False)
670 def _extract_description(self, webpage):
671 return self._og_search_description(webpage)
674 class NRKTVEpisodesIE(NRKPlaylistBaseIE):
675 _VALID_URL = r'https?://tv\.nrk\.no/program/[Ee]pisodes/[^/]+/(?P<id>\d+)'
676 _ITEM_RE = r'data-episode=["\']%s' % NRKTVIE._EPISODE_RE
678 'url': 'https://tv.nrk.no/program/episodes/nytt-paa-nytt/69031',
681 'title': 'Nytt på nytt, sesong: 201210',
686 def _extract_title(self, webpage):
687 return self._html_search_regex(
688 r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False)
691 class NRKSkoleIE(InfoExtractor):
692 IE_DESC = 'NRK Skole'
693 _VALID_URL = r'https?://(?:www\.)?nrk\.no/skole/?\?.*\bmediaId=(?P<id>\d+)'
696 'url': 'https://www.nrk.no/skole/?page=search&q=&mediaId=14099',
697 'md5': '18c12c3d071953c3bf8d54ef6b2587b7',
701 'title': 'Genetikk og eneggede tvillinger',
702 'description': 'md5:3aca25dcf38ec30f0363428d2b265f8d',
706 'url': 'https://www.nrk.no/skole/?page=objectives&subject=naturfag&objective=K15114&mediaId=19355',
707 'only_matching': True,
710 def _real_extract(self, url):
711 video_id = self._match_id(url)
713 webpage = self._download_webpage(
714 'https://mimir.nrk.no/plugin/1.0/static?mediaId=%s' % video_id,
717 nrk_id = self._parse_json(
719 r'<script[^>]+type=["\']application/json["\'][^>]*>({.+?})</script>',
720 webpage, 'application json'),
721 video_id)['activeMedia']['psId']
723 return self.url_result('nrk:%s' % nrk_id)