2 from __future__
import unicode_literals
8 from .common
import InfoExtractor
9 from ..compat
import compat_str
22 class NRKBaseIE(InfoExtractor
):
23 _GEO_COUNTRIES
= ['NO']
24 _CDN_REPL_REGEX
= r
'''(?x)://
26 nrkod\d{1,2}-httpcache0-47115-cacheod0\.dna\.ip-only\.net/47115-cacheod0|
27 nrk-od-no\.telenorcdn\.net|
28 minicdn-od\.nrk\.no/od/nrkhd-osl-rr\.netwerk\.no/no
31 def _extract_nrk_formats(self
, asset_url
, video_id
):
32 if re
.match(r
'https?://[^/]+\.akamaihd\.net/i/', asset_url
):
33 return self
._extract
_akamai
_formats
(asset_url
, video_id
)
34 asset_url
= re
.sub(r
'(?:bw_(?:low|high)=\d+|no_audio_only)&?', '', asset_url
)
35 formats
= self
._extract
_m
3u8_formats
(
36 asset_url
, video_id
, 'mp4', 'm3u8_native', fatal
=False)
37 if not formats
and re
.search(self
._CDN
_REPL
_REGEX
, asset_url
):
38 formats
= self
._extract
_m
3u8_formats
(
39 re
.sub(self
._CDN
_REPL
_REGEX
, '://nrk-od-%02d.akamaized.net/no/' % random
.randint(0, 99), asset_url
),
40 video_id
, 'mp4', 'm3u8_native', fatal
=False)
43 def _raise_error(self
, data
):
45 'ProgramRightsAreNotReady': 'Du kan dessverre ikke se eller høre programmet',
46 'ProgramRightsHasExpired': 'Programmet har gått ut',
47 'NoProgramRights': 'Ikke tilgjengelig',
48 'ProgramIsGeoBlocked': 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',
50 message_type
= data
.get('messageType', '')
51 # Can be ProgramIsGeoBlocked or ChannelIsGeoBlocked*
52 if 'IsGeoBlocked' in message_type
or try_get(data
, lambda x
: x
['usageRights']['isGeoBlocked']) is True:
53 self
.raise_geo_restricted(
54 msg
=MESSAGES
.get('ProgramIsGeoBlocked'),
55 countries
=self
._GEO
_COUNTRIES
)
56 message
= data
.get('endUserMessage') or MESSAGES
.get(message_type
, message_type
)
57 raise ExtractorError('%s said: %s' % (self
.IE_NAME
, message
), expected
=True)
59 def _call_api(self
, path
, video_id
, item
=None, note
=None, fatal
=True, query
=None):
60 return self
._download
_json
(
61 urljoin('http://psapi.nrk.no/', path
),
62 video_id
, note
or 'Downloading %s JSON' % item
,
63 fatal
=fatal
, query
=query
,
64 headers
={'Accept-Encoding': 'gzip, deflate, br'}
)
67 class NRKIE(NRKBaseIE
):
73 (?:www\.)?nrk\.no/video/(?:PS\*|[^_]+_)|
74 v8[-.]psapi\.nrk\.no/mediaelement/
82 'url': 'http://www.nrk.no/video/PS*150533',
83 'md5': 'f46be075326e23ad0e524edfcb06aeb6',
87 'title': 'Dompap og andre fugler i Piip-Show',
88 'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f',
93 'url': 'http://www.nrk.no/video/PS*154915',
98 'title': 'Slik høres internett ut når du er blind',
99 'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
103 'url': 'nrk:ecc1b952-96dc-4a98-81b9-5296dc7a98d9',
104 'only_matching': True,
106 'url': 'nrk:clip/7707d5a3-ebe7-434a-87d5-a3ebe7a34a70',
107 'only_matching': True,
109 'url': 'https://v8-psapi.nrk.no/mediaelement/ecc1b952-96dc-4a98-81b9-5296dc7a98d9',
110 'only_matching': True,
112 'url': 'https://www.nrk.no/video/dompap-og-andre-fugler-i-piip-show_150533',
113 'only_matching': True,
115 'url': 'https://www.nrk.no/video/humor/kommentatorboksen-reiser-til-sjos_d1fda11f-a4ad-437a-a374-0398bc84e999',
116 'only_matching': True,
119 'url': 'nrk:l_96f4f1b0-de54-4e6a-b4f1-b0de54fe6af8',
120 'only_matching': True,
122 'url': 'nrk:podcast/l_96f4f1b0-de54-4e6a-b4f1-b0de54fe6af8',
123 'only_matching': True,
127 'only_matching': True,
129 'url': 'nrk:clip/150533',
130 'only_matching': True,
133 'url': 'nrk:MDDP12000117',
134 'only_matching': True,
136 'url': 'nrk:program/ENRK10100318',
137 'only_matching': True,
141 'only_matching': True,
143 'url': 'nrk:channel/nrk1',
144 'only_matching': True,
147 def _real_extract(self
, url
):
148 video_id
= self
._match
_id
(url
).split('/')[-1]
150 path_templ
= 'playback/%s/' + video_id
152 def call_playback_api(item
, query
=None):
153 return self
._call
_api
(path_templ
% item
, video_id
, item
, query
=query
)
154 # known values for preferredCdn: akamai, iponly, minicdn and telenor
155 manifest
= call_playback_api('manifest', {'preferredCdn': 'akamai'}
)
157 video_id
= try_get(manifest
, lambda x
: x
['id'], compat_str
) or video_id
159 if manifest
.get('playability') == 'nonPlayable':
160 self
._raise
_error
(manifest
['nonPlayable'])
162 playable
= manifest
['playable']
165 for asset
in playable
['assets']:
166 if not isinstance(asset
, dict):
168 if asset
.get('encrypted'):
170 format_url
= url_or_none(asset
.get('url'))
173 asset_format
= (asset
.get('format') or '').lower()
174 if asset_format
== 'hls' or determine_ext(format_url
) == 'm3u8':
175 formats
.extend(self
._extract
_nrk
_formats
(format_url
, video_id
))
176 elif asset_format
== 'mp3':
179 'format_id': asset_format
,
182 self
._sort
_formats
(formats
)
184 data
= call_playback_api('metadata')
186 preplay
= data
['preplay']
187 titles
= preplay
['titles']
188 title
= titles
['title']
189 alt_title
= titles
.get('subtitle')
191 description
= preplay
.get('description')
192 duration
= parse_duration(playable
.get('duration')) or parse_duration(data
.get('duration'))
195 for image
in try_get(
196 preplay
, lambda x
: x
['poster']['images'], list) or []:
197 if not isinstance(image
, dict):
199 image_url
= url_or_none(image
.get('url'))
204 'width': int_or_none(image
.get('pixelWidth')),
205 'height': int_or_none(image
.get('pixelHeight')),
209 for sub
in try_get(playable
, lambda x
: x
['subtitles'], list) or []:
210 if not isinstance(sub
, dict):
212 sub_url
= url_or_none(sub
.get('webVtt'))
215 sub_key
= str_or_none(sub
.get('language')) or 'nb'
216 sub_type
= str_or_none(sub
.get('type'))
218 sub_key
+= '-%s' % sub_type
219 subtitles
.setdefault(sub_key
, []).append({
224 data
, lambda x
: x
['legalAge']['body']['rating']['code'], compat_str
)
225 # https://en.wikipedia.org/wiki/Norwegian_Media_Authority
228 elif legal_age
.isdigit():
229 age_limit
= int_or_none(legal_age
)
233 is_series
= try_get(data
, lambda x
: x
['_links']['series']['name']) == 'series'
238 'alt_title': alt_title
,
239 'description': description
,
240 'duration': duration
,
241 'thumbnails': thumbnails
,
242 'age_limit': age_limit
,
244 'subtitles': subtitles
,
248 series
= season_id
= season_number
= episode
= episode_number
= None
249 programs
= self
._call
_api
(
250 'programs/%s' % video_id
, video_id
, 'programs', fatal
=False)
251 if programs
and isinstance(programs
, dict):
252 series
= str_or_none(programs
.get('seriesTitle'))
253 season_id
= str_or_none(programs
.get('seasonId'))
254 season_number
= int_or_none(programs
.get('seasonNumber'))
255 episode
= str_or_none(programs
.get('episodeTitle'))
256 episode_number
= int_or_none(programs
.get('episodeNumber'))
260 title
+= ' - %s' % alt_title
261 if not season_number
:
262 season_number
= int_or_none(self
._search
_regex
(
263 r
'Sesong\s+(\d+)', description
or '', 'season number',
266 episode
= alt_title
if is_series
else None
267 if not episode_number
:
268 episode_number
= int_or_none(self
._search
_regex
(
269 r
'^(\d+)\.', episode
or '', 'episode number',
271 if not episode_number
:
272 episode_number
= int_or_none(self
._search
_regex
(
273 r
'\((\d+)\s*:\s*\d+\)', description
or '',
274 'episode number', default
=None))
278 'season_id': season_id
,
279 'season_number': season_number
,
281 'episode_number': episode_number
,
287 class NRKTVIE(InfoExtractor
):
288 IE_DESC
= 'NRK TV and NRK Radio'
289 _EPISODE_RE
= r
'(?P<id>[a-zA-Z]{4}\d{8})'
290 _VALID_URL
= r
'https?://(?:tv|radio)\.nrk(?:super)?\.no/(?:[^/]+/)*%s' % _EPISODE_RE
292 'url': 'https://tv.nrk.no/program/MDDP12000117',
293 'md5': 'c4a5960f1b00b40d47db65c1064e0ab1',
295 'id': 'MDDP12000117',
297 'title': 'Alarm Trolltunga',
298 'description': 'md5:46923a6e6510eefcce23d5ef2a58f2ce',
303 'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
304 'md5': '8d40dab61cea8ab0114e090b029a0565',
306 'id': 'MUHH48000314',
308 'title': '20 spørsmål - 23. mai 2014',
309 'alt_title': '23. mai 2014',
310 'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
312 'series': '20 spørsmål',
313 'episode': '23. mai 2014',
317 'url': 'https://tv.nrk.no/program/mdfp15000514',
319 'id': 'MDFP15000514',
321 'title': 'Kunnskapskanalen - Grunnlovsjubiléet - Stor ståhei for ingenting',
322 'description': 'md5:89290c5ccde1b3a24bb8050ab67fe1db',
324 'series': 'Kunnskapskanalen',
325 'episode': 'Grunnlovsjubiléet - Stor ståhei for ingenting',
329 'skip_download': True,
332 # single playlist video
333 'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
335 'id': 'MSPO40010515',
337 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015',
338 'description': 'md5:c03aba1e917561eface5214020551b7a',
342 'skip_download': True,
344 'expected_warnings': ['Failed to download m3u8 information'],
345 'skip': 'particular part is not supported currently',
347 'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
349 'id': 'MSPO40010515',
351 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015',
352 'description': 'md5:c03aba1e917561eface5214020551b7a',
355 'expected_warnings': ['Failed to download m3u8 information'],
356 'skip': 'Ikke tilgjengelig utenfor Norge',
358 'url': 'https://tv.nrk.no/serie/anno/KMTE50001317/sesong-3/episode-13',
360 'id': 'KMTE50001317',
362 'title': 'Anno - 13. episode',
363 'description': 'md5:11d9613661a8dbe6f9bef54e3a4cbbfa',
366 'episode': '13. episode',
368 'episode_number': 13,
372 'skip_download': True,
375 'url': 'https://tv.nrk.no/serie/nytt-paa-nytt/MUHH46000317/27-01-2017',
377 'id': 'MUHH46000317',
379 'title': 'Nytt på Nytt 27.01.2017',
380 'description': 'md5:5358d6388fba0ea6f0b6d11c48b9eb4b',
382 'series': 'Nytt på nytt',
383 'episode': '27.01.2017',
387 'skip_download': True,
389 'skip': 'ProgramRightsHasExpired',
391 'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#',
392 'only_matching': True,
394 'url': 'https://tv.nrk.no/serie/lindmo/2018/MUHU11006318/avspiller',
395 'only_matching': True,
397 'url': 'https://radio.nrk.no/serie/dagsnytt/sesong/201507/NPUB21019315',
398 'only_matching': True,
401 def _real_extract(self
, url
):
402 video_id
= self
._match
_id
(url
)
403 return self
.url_result(
404 'nrk:%s' % video_id
, ie
=NRKIE
.ie_key(), video_id
=video_id
)
407 class NRKTVEpisodeIE(InfoExtractor
):
408 _VALID_URL
= r
'https?://tv\.nrk\.no/serie/(?P<id>[^/]+/sesong/(?P<season_number>\d+)/episode/(?P<episode_number>\d+))'
410 'url': 'https://tv.nrk.no/serie/hellums-kro/sesong/1/episode/2',
412 'id': 'MUHH36005220',
414 'title': 'Hellums kro - 2. Kro, krig og kjærlighet',
415 'description': 'md5:ad92ddffc04cea8ce14b415deef81787',
417 'series': 'Hellums kro',
420 'episode': '2. Kro, krig og kjærlighet',
424 'skip_download': True,
427 'url': 'https://tv.nrk.no/serie/backstage/sesong/1/episode/8',
429 'id': 'MSUI14000816',
431 'title': 'Backstage - 8. episode',
432 'description': 'md5:de6ca5d5a2d56849e4021f2bf2850df4',
434 'series': 'Backstage',
437 'episode': '8. episode',
441 'skip_download': True,
443 'skip': 'ProgramRightsHasExpired',
446 def _real_extract(self
, url
):
447 display_id
, season_number
, episode_number
= re
.match(self
._VALID
_URL
, url
).groups()
449 webpage
= self
._download
_webpage
(url
, display_id
)
451 info
= self
._search
_json
_ld
(webpage
, display_id
, default
={})
452 nrk_id
= info
.get('@id') or self
._html
_search
_meta
(
453 'nrk:program-id', webpage
, default
=None) or self
._search
_regex
(
454 r
'data-program-id=["\'](%s)' % NRKTVIE._EPISODE_RE, webpage,
456 assert re.match(NRKTVIE._EPISODE_RE, nrk_id)
461 'url
': 'nrk
:%s' % nrk_id,
462 'ie_key
': NRKIE.ie_key(),
463 'season_number
': int(season_number),
464 'episode_number
': int(episode_number),
469 class NRKTVSerieBaseIE(NRKBaseIE):
470 def _extract_entries(self, entry_list):
471 if not isinstance(entry_list, list):
474 for episode in entry_list:
475 nrk_id = episode.get('prfId
') or episode.get('episodeId
')
476 if not nrk_id or not isinstance(nrk_id, compat_str):
478 entries.append(self.url_result(
479 'nrk
:%s' % nrk_id, ie=NRKIE.ie_key(), video_id=nrk_id))
482 _ASSETS_KEYS = ('episodes
', 'instalments
',)
484 def _extract_assets_key(self, embedded):
485 for asset_key in self._ASSETS_KEYS:
486 if embedded.get(asset_key):
490 def _catalog_name(serie_kind):
491 return 'podcast
' if serie_kind in ('podcast
', 'podkast
') else 'series
'
493 def _entries(self, data, display_id):
494 for page_num in itertools.count(1):
495 embedded = data.get('_embedded
') or data
496 if not isinstance(embedded, dict):
498 assets_key = self._extract_assets_key(embedded)
504 (lambda x: x[assets_key]['_embedded
'][assets_key],
505 lambda x: x[assets_key]),
507 for e in self._extract_entries(entries):
510 next_url_path = try_get(
512 (lambda x: x['_links
']['next
']['href
'],
513 lambda x: x['_embedded
'][assets_key]['_links
']['next
']['href
']),
515 if not next_url_path:
517 data = self._call_api(
518 next_url_path, display_id,
519 note='Downloading
%s JSON page
%d' % (assets_key, page_num),
525 class NRKTVSeasonIE(NRKTVSerieBaseIE):
526 _VALID_URL = r'''(?x)
528 (?P<domain>tv|radio)\.nrk\.no/
529 (?P<serie_kind>serie|pod[ck]ast)/
532 (?:sesong/)?(?P<id>\d+)|
533 sesong/(?P<id_2>[^/?#&]+)
537 'url
': 'https
://tv
.nrk
.no
/serie
/backstage
/sesong
/1',
542 'playlist_mincount
': 30,
544 # no /sesong/ in path
545 'url
': 'https
://tv
.nrk
.no
/serie
/lindmo
/2016',
550 'playlist_mincount
': 29,
552 # weird nested _embedded in catalog JSON response
553 'url
': 'https
://radio
.nrk
.no
/serie
/dickie
-dick
-dickens
/sesong
/1',
555 'id': 'dickie
-dick
-dickens
/1',
558 'playlist_mincount
': 11,
560 # 841 entries, multi page
561 'url
': 'https
://radio
.nrk
.no
/serie
/dagsnytt
/sesong
/201509',
563 'id': 'dagsnytt
/201509',
564 'title
': 'September
2015',
566 'playlist_mincount
': 841,
568 # 180 entries, single page
569 'url
': 'https
://tv
.nrk
.no
/serie
/spangas
/sesong
/1',
570 'only_matching
': True,
572 'url
': 'https
://radio
.nrk
.no
/podkast
/hele_historien
/sesong
/diagnose
-kverulant
',
574 'id': 'hele_historien
/diagnose
-kverulant
',
575 'title
': 'Diagnose kverulant
',
577 'playlist_mincount
': 3,
579 'url
': 'https
://radio
.nrk
.no
/podkast
/loerdagsraadet
/sesong
/202101',
580 'only_matching
': True,
584 def suitable(cls, url):
585 return (False if NRKTVIE.suitable(url) or NRKTVEpisodeIE.suitable(url) or NRKRadioPodkastIE.suitable(url)
586 else super(NRKTVSeasonIE, cls).suitable(url))
588 def _real_extract(self, url):
589 mobj = re.match(self._VALID_URL, url)
590 domain = mobj.group('domain
')
591 serie_kind = mobj.group('serie_kind
')
592 serie = mobj.group('serie
')
593 season_id = mobj.group('id') or mobj.group('id_2
')
594 display_id = '%s/%s' % (serie, season_id)
596 data = self._call_api(
597 '%s/catalog
/%s/%s/seasons
/%s'
598 % (domain, self._catalog_name(serie_kind), serie, season_id),
599 display_id, 'season
', query={'pageSize': 50})
601 title = try_get(data, lambda x: x['titles
']['title
'], compat_str) or display_id
602 return self.playlist_result(
603 self._entries(data, display_id),
607 class NRKTVSeriesIE(NRKTVSerieBaseIE):
608 _VALID_URL = r'https?
://(?P
<domain
>(?
:tv|radio
)\
.nrk|
(?
:tv\
.)?nrksuper
)\
.no
/(?P
<serie_kind
>serie|pod
[ck
]ast
)/(?P
<id>[^
/]+)'
610 # new layout, instalments
611 'url
': 'https
://tv
.nrk
.no
/serie
/groenn
-glede
',
613 'id': 'groenn
-glede
',
614 'title
': 'Grønn glede
',
615 'description
': 'md5
:7576e92ae7f65da6993cf90ee29e4608
',
617 'playlist_mincount
': 90,
619 # new layout, instalments, more entries
620 'url
': 'https
://tv
.nrk
.no
/serie
/lindmo
',
621 'only_matching
': True,
623 'url
': 'https
://tv
.nrk
.no
/serie
/blank
',
627 'description
': 'md5
:7664b4e7e77dc6810cd3bca367c25b6e
',
629 'playlist_mincount
': 30,
631 # new layout, seasons
632 'url
': 'https
://tv
.nrk
.no
/serie
/backstage
',
635 'title
': 'Backstage
',
636 'description
': 'md5
:63692ceb96813d9a207e9910483d948b
',
638 'playlist_mincount
': 60,
641 'url
': 'https
://tv
.nrksuper
.no
/serie
/labyrint
',
645 'description
': 'I Daidalos sin undersjøiske Labyrint venter spennende oppgaver
, skumle robotskapninger og slim
.',
647 'playlist_mincount
': 3,
649 'url
': 'https
://tv
.nrk
.no
/serie
/broedrene
-dal
-og
-spektralsteinene
',
650 'only_matching
': True,
652 'url
': 'https
://tv
.nrk
.no
/serie
/saving
-the
-human
-race
',
653 'only_matching
': True,
655 'url
': 'https
://tv
.nrk
.no
/serie
/postmann
-pat
',
656 'only_matching
': True,
658 'url
': 'https
://radio
.nrk
.no
/serie
/dickie
-dick
-dickens
',
660 'id': 'dickie
-dick
-dickens
',
661 'title
': 'Dickie Dick Dickens
',
662 'description
': 'md5
:19e67411ffe57f7dce08a943d7a0b91f
',
664 'playlist_mincount
': 8,
666 'url
': 'https
://nrksuper
.no
/serie
/labyrint
',
667 'only_matching
': True,
669 'url
': 'https
://radio
.nrk
.no
/podkast
/ulrikkes_univers
',
671 'id': 'ulrikkes_univers
',
673 'playlist_mincount
': 10,
675 'url
': 'https
://radio
.nrk
.no
/podkast
/ulrikkes_univers
/nrkno
-poddkast
-26588-134079-05042018030000',
676 'only_matching
': True,
680 def suitable(cls, url):
682 False if any(ie.suitable(url)
683 for ie in (NRKTVIE, NRKTVEpisodeIE, NRKRadioPodkastIE, NRKTVSeasonIE))
684 else super(NRKTVSeriesIE, cls).suitable(url))
686 def _real_extract(self, url):
687 site, serie_kind, series_id = re.match(self._VALID_URL, url).groups()
688 is_radio = site == 'radio
.nrk
'
689 domain = 'radio
' if is_radio else 'tv
'
691 size_prefix = 'p
' if is_radio else 'embeddedInstalmentsP
'
692 series = self._call_api(
694 % (domain, self._catalog_name(serie_kind), series_id),
695 series_id, 'serie
', query={size_prefix + 'ageSize': 50})
696 titles = try_get(series, [
697 lambda x: x['titles
'],
698 lambda x: x[x['type']]['titles
'],
699 lambda x: x[x['seriesType
']]['titles
'],
703 entries.extend(self._entries(series, series_id))
704 embedded = series.get('_embedded
') or {}
705 linked_seasons = try_get(series, lambda x: x['_links
']['seasons
']) or []
706 embedded_seasons = embedded.get('seasons
') or []
707 if len(linked_seasons) > len(embedded_seasons):
708 for season in linked_seasons:
709 season_url = urljoin(url, season.get('href
'))
711 season_name = season.get('name
')
712 if season_name and isinstance(season_name, compat_str):
713 season_url = 'https
://%s.nrk
.no
/serie
/%s/sesong
/%s' % (domain, series_id, season_name)
715 entries.append(self.url_result(
716 season_url, ie=NRKTVSeasonIE.ie_key(),
717 video_title=season.get('title
')))
719 for season in embedded_seasons:
720 entries.extend(self._entries(season, series_id))
721 entries.extend(self._entries(
722 embedded.get('extraMaterial
') or {}, series_id))
724 return self.playlist_result(
725 entries, series_id, titles.get('title
'), titles.get('subtitle
'))
728 class NRKTVDirekteIE(NRKTVIE):
729 IE_DESC = 'NRK TV Direkte
and NRK Radio Direkte
'
730 _VALID_URL = r'https?
://(?
:tv|radio
)\
.nrk\
.no
/direkte
/(?P
<id>[^
/?
#&]+)'
733 'url': 'https://tv.nrk.no/direkte/nrk1',
734 'only_matching': True,
736 'url': 'https://radio.nrk.no/direkte/p1_oslo_akershus',
737 'only_matching': True,
741 class NRKRadioPodkastIE(InfoExtractor
):
742 _VALID_URL
= r
'https?://radio\.nrk\.no/pod[ck]ast/(?:[^/]+/)+(?P<id>l_[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
745 'url': 'https://radio.nrk.no/podkast/ulrikkes_univers/l_96f4f1b0-de54-4e6a-b4f1-b0de54fe6af8',
746 'md5': '8d40dab61cea8ab0114e090b029a0565',
748 'id': 'MUHH48000314AA',
750 'title': '20 spørsmål 23.05.2014',
751 'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
753 'series': '20 spørsmål',
754 'episode': '23.05.2014',
757 'url': 'https://radio.nrk.no/podcast/ulrikkes_univers/l_96f4f1b0-de54-4e6a-b4f1-b0de54fe6af8',
758 'only_matching': True,
760 'url': 'https://radio.nrk.no/podkast/ulrikkes_univers/sesong/1/l_96f4f1b0-de54-4e6a-b4f1-b0de54fe6af8',
761 'only_matching': True,
763 'url': 'https://radio.nrk.no/podkast/hele_historien/sesong/bortfoert-i-bergen/l_774d1a2c-7aa7-4965-8d1a-2c7aa7d9652c',
764 'only_matching': True,
767 def _real_extract(self
, url
):
768 video_id
= self
._match
_id
(url
)
769 return self
.url_result(
770 'nrk:%s' % video_id
, ie
=NRKIE
.ie_key(), video_id
=video_id
)
773 class NRKPlaylistBaseIE(InfoExtractor
):
774 def _extract_description(self
, webpage
):
777 def _real_extract(self
, url
):
778 playlist_id
= self
._match
_id
(url
)
780 webpage
= self
._download
_webpage
(url
, playlist_id
)
783 self
.url_result('nrk:%s' % video_id
, NRKIE
.ie_key())
784 for video_id
in re
.findall(self
._ITEM
_RE
, webpage
)
787 playlist_title
= self
. _extract_title(webpage
)
788 playlist_description
= self
._extract
_description
(webpage
)
790 return self
.playlist_result(
791 entries
, playlist_id
, playlist_title
, playlist_description
)
794 class NRKPlaylistIE(NRKPlaylistBaseIE
):
795 _VALID_URL
= r
'https?://(?:www\.)?nrk\.no/(?!video|skole)(?:[^/]+/)+(?P<id>[^/]+)'
796 _ITEM_RE
= r
'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"'
798 'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',
800 'id': 'gjenopplev-den-historiske-solformorkelsen-1.12270763',
801 'title': 'Gjenopplev den historiske solformørkelsen',
802 'description': 'md5:c2df8ea3bac5654a26fc2834a542feed',
806 'url': 'http://www.nrk.no/kultur/bok/rivertonprisen-til-karin-fossum-1.12266449',
808 'id': 'rivertonprisen-til-karin-fossum-1.12266449',
809 'title': 'Rivertonprisen til Karin Fossum',
810 'description': 'Første kvinne på 15 år til å vinne krimlitteraturprisen.',
815 def _extract_title(self
, webpage
):
816 return self
._og
_search
_title
(webpage
, fatal
=False)
818 def _extract_description(self
, webpage
):
819 return self
._og
_search
_description
(webpage
)
822 class NRKTVEpisodesIE(NRKPlaylistBaseIE
):
823 _VALID_URL
= r
'https?://tv\.nrk\.no/program/[Ee]pisodes/[^/]+/(?P<id>\d+)'
824 _ITEM_RE
= r
'data-episode=["\']%s' % NRKTVIE._EPISODE_RE
826 'url
': 'https
://tv
.nrk
.no
/program
/episodes
/nytt
-paa
-nytt
/69031',
829 'title
': 'Nytt på nytt
, sesong
: 201210',
834 def _extract_title(self, webpage):
835 return self._html_search_regex(
836 r'<h1
>([^
<]+)</h1
>', webpage, 'title
', fatal=False)
839 class NRKSkoleIE(InfoExtractor):
840 IE_DESC = 'NRK Skole
'
841 _VALID_URL = r'https?
://(?
:www\
.)?nrk\
.no
/skole
/?
\?.*\bmediaId
=(?P
<id>\d
+)'
844 'url
': 'https
://www
.nrk
.no
/skole
/?page
=search
&q
=&mediaId
=14099',
845 'md5
': '18c12c3d071953c3bf8d54ef6b2587b7
',
849 'title
': 'Genetikk og eneggede tvillinger
',
850 'description
': 'md5
:3aca25dcf38ec30f0363428d2b265f8d
',
854 'url
': 'https
://www
.nrk
.no
/skole
/?page
=objectives
&subject
=naturfag
&objective
=K15114
&mediaId
=19355',
855 'only_matching
': True,
858 def _real_extract(self, url):
859 video_id = self._match_id(url)
861 nrk_id = self._download_json(
862 'https
://nrkno
-skole
-prod
.kube
.nrk
.no
/skole
/api
/media
/%s' % video_id,
865 return self.url_result('nrk
:%s' % nrk_id)