2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
7 from ..compat
import compat_urllib_parse_unquote
16 class NRKBaseIE(InfoExtractor
):
17 _GEO_COUNTRIES
= ['NO']
19 def _real_extract(self
, url
):
20 video_id
= self
._match
_id
(url
)
22 data
= self
._download
_json
(
23 'http://%s/mediaelement/%s' % (self
._API
_HOST
, video_id
),
24 video_id
, 'Downloading mediaelement JSON')
26 title
= data
.get('fullTitle') or data
.get('mainTitle') or data
['title']
27 video_id
= data
.get('id') or video_id
31 conviva
= data
.get('convivaStatistics') or {}
32 live
= (data
.get('mediaElementType') == 'Live' or
33 data
.get('isLive') is True or conviva
.get('isLive'))
36 return self
._live
_title
(t
) if live
else t
38 media_assets
= data
.get('mediaAssets')
39 if media_assets
and isinstance(media_assets
, list):
40 def video_id_and_title(idx
):
41 return ((video_id
, title
) if len(media_assets
) == 1
42 else ('%s-%d' % (video_id
, idx
), '%s (Part %d)' % (title
, idx
)))
43 for num
, asset
in enumerate(media_assets
, 1):
44 asset_url
= asset
.get('url')
47 formats
= self
._extract
_akamai
_formats
(asset_url
, video_id
)
50 self
._sort
_formats
(formats
)
52 # Some f4m streams may not work with hdcore in fragments' URLs
54 extra_param
= f
.get('extra_param_to_segment_url')
55 if extra_param
and 'hdcore' in extra_param
:
56 del f
['extra_param_to_segment_url']
58 entry_id
, entry_title
= video_id_and_title(num
)
59 duration
= parse_duration(asset
.get('duration'))
61 for subtitle
in ('webVtt', 'timedText'):
62 subtitle_url
= asset
.get('%sSubtitlesUrl' % subtitle
)
64 subtitles
.setdefault('no', []).append({
65 'url': compat_urllib_parse_unquote(subtitle_url
)
68 'id': asset
.get('carrierId') or entry_id
,
69 'title': make_title(entry_title
),
71 'subtitles': subtitles
,
76 media_url
= data
.get('mediaUrl')
78 formats
= self
._extract
_akamai
_formats
(media_url
, video_id
)
79 self
._sort
_formats
(formats
)
80 duration
= parse_duration(data
.get('duration'))
83 'title': make_title(title
),
90 'ProgramRightsAreNotReady': 'Du kan dessverre ikke se eller høre programmet',
91 'ProgramRightsHasExpired': 'Programmet har gått ut',
92 'ProgramIsGeoBlocked': 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',
94 message_type
= data
.get('messageType', '')
95 # Can be ProgramIsGeoBlocked or ChannelIsGeoBlocked*
96 if 'IsGeoBlocked' in message_type
:
97 self
.raise_geo_restricted(
98 msg
=MESSAGES
.get('ProgramIsGeoBlocked'),
99 countries
=self
._GEO
_COUNTRIES
)
100 raise ExtractorError(
101 '%s said: %s' % (self
.IE_NAME
, MESSAGES
.get(
102 message_type
, message_type
)),
105 series
= conviva
.get('seriesName') or data
.get('seriesTitle')
106 episode
= conviva
.get('episodeName') or data
.get('episodeNumberOrDate')
109 episode_number
= None
110 if data
.get('mediaElementType') == 'Episode':
111 _season_episode
= data
.get('scoresStatistics', {}).get('springStreamStream') or \
112 data
.get('relativeOriginUrl', '')
114 r
'/s(?P<season>\d{,2})e(?P<episode>\d{,2})\.',
115 r
'/sesong-(?P<season>\d{,2})/episode-(?P<episode>\d{,2})',
117 season_number
= int_or_none(self
._search
_regex
(
118 EPISODENUM_RE
, _season_episode
, 'season number',
119 default
=None, group
='season'))
120 episode_number
= int_or_none(self
._search
_regex
(
121 EPISODENUM_RE
, _season_episode
, 'episode number',
122 default
=None, group
='episode'))
125 images
= data
.get('images')
126 if images
and isinstance(images
, dict):
127 web_images
= images
.get('webImages')
128 if isinstance(web_images
, list):
130 'url': image
['imageUrl'],
131 'width': int_or_none(image
.get('width')),
132 'height': int_or_none(image
.get('height')),
133 } for image
in web_images
if image
.get('imageUrl')]
135 description
= data
.get('description')
136 category
= data
.get('mediaAnalytics', {}).get('category')
139 'description': description
,
142 'season_number': season_number
,
143 'episode_number': episode_number
,
144 'categories': [category
] if category
else None,
145 'age_limit': parse_age_limit(data
.get('legalAge')),
146 'thumbnails': thumbnails
,
149 vcodec
= 'none' if data
.get('mediaType') == 'Audio' else None
151 for entry
in entries
:
152 entry
.update(common_info
)
153 for f
in entry
['formats']:
156 points
= data
.get('shortIndexPoints')
157 if isinstance(points
, list):
159 for next_num
, point
in enumerate(points
, start
=1):
160 if not isinstance(point
, dict):
162 start_time
= parse_duration(point
.get('startPoint'))
163 if start_time
is None:
165 end_time
= parse_duration(
167 if next_num
== len(points
)
168 else points
[next_num
].get('startPoint'))
172 'start_time': start_time
,
173 'end_time': end_time
,
174 'title': point
.get('title'),
176 if chapters
and len(entries
) == 1:
177 entries
[0]['chapters'] = chapters
179 return self
.playlist_result(entries
, video_id
, title
, description
)
182 class NRKIE(NRKBaseIE
):
183 _VALID_URL
= r
'''(?x)
188 (?:www\.)?nrk\.no/video/PS\*|
189 v8[-.]psapi\.nrk\.no/mediaelement/
194 _API_HOST
= 'v8-psapi.nrk.no'
197 'url': 'http://www.nrk.no/video/PS*150533',
198 'md5': '2f7f6eeb2aacdd99885f355428715cfa',
202 'title': 'Dompap og andre fugler i Piip-Show',
203 'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f',
208 'url': 'http://www.nrk.no/video/PS*154915',
213 'title': 'Slik høres internett ut når du er blind',
214 'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
218 'url': 'nrk:ecc1b952-96dc-4a98-81b9-5296dc7a98d9',
219 'only_matching': True,
221 'url': 'nrk:clip/7707d5a3-ebe7-434a-87d5-a3ebe7a34a70',
222 'only_matching': True,
224 'url': 'https://v8-psapi.nrk.no/mediaelement/ecc1b952-96dc-4a98-81b9-5296dc7a98d9',
225 'only_matching': True,
229 class NRKTVIE(NRKBaseIE
):
230 IE_DESC
= 'NRK TV and NRK Radio'
231 _EPISODE_RE
= r
'(?P<id>[a-zA-Z]{4}\d{8})'
232 _VALID_URL
= r
'''(?x)
234 (?:tv|radio)\.nrk(?:super)?\.no/
235 (?:serie/[^/]+|program)/
237 (?:/\d{2}-\d{2}-\d{4})?
238 (?:\#del=(?P<part_id>\d+))?
240 _API_HOST
= 'psapi-ne.nrk.no'
243 'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
244 'md5': '4e9ca6629f09e588ed240fb11619922a',
246 'id': 'MUHH48000314AA',
248 'title': '20 spørsmål 23.05.2014',
249 'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
251 'series': '20 spørsmål - TV',
252 'episode': '23.05.2014',
255 'url': 'https://tv.nrk.no/program/mdfp15000514',
257 'id': 'MDFP15000514CA',
259 'title': 'Grunnlovsjubiléet - Stor ståhei for ingenting 24.05.2014',
260 'description': 'md5:89290c5ccde1b3a24bb8050ab67fe1db',
262 'series': 'Kunnskapskanalen',
263 'episode': '24.05.2014',
266 'skip_download': True,
269 # single playlist video
270 'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
272 'id': 'MSPO40010515-part2',
274 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
275 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
278 'skip_download': True,
280 'expected_warnings': ['Video is geo restricted'],
281 'skip': 'particular part is not supported currently',
283 'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
286 'id': 'MSPO40010515AH',
288 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 1)',
289 'description': 'md5:c03aba1e917561eface5214020551b7a',
291 'series': 'Tour de Ski',
292 'episode': '06.01.2015',
295 'skip_download': True,
299 'id': 'MSPO40010515BH',
301 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 2)',
302 'description': 'md5:c03aba1e917561eface5214020551b7a',
304 'series': 'Tour de Ski',
305 'episode': '06.01.2015',
308 'skip_download': True,
312 'id': 'MSPO40010515',
313 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015',
314 'description': 'md5:c03aba1e917561eface5214020551b7a',
316 'expected_warnings': ['Video is geo restricted'],
318 'url': 'https://tv.nrk.no/serie/anno/KMTE50001317/sesong-3/episode-13',
320 'id': 'KMTE50001317AA',
322 'title': 'Anno 13:30',
323 'description': 'md5:11d9613661a8dbe6f9bef54e3a4cbbfa',
328 'episode_number': 13,
331 'skip_download': True,
334 'url': 'https://tv.nrk.no/serie/nytt-paa-nytt/MUHH46000317/27-01-2017',
336 'id': 'MUHH46000317AA',
338 'title': 'Nytt på Nytt 27.01.2017',
339 'description': 'md5:5358d6388fba0ea6f0b6d11c48b9eb4b',
341 'series': 'Nytt på nytt',
342 'episode': '27.01.2017',
345 'skip_download': True,
348 'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#',
349 'only_matching': True,
353 class NRKTVDirekteIE(NRKTVIE
):
354 IE_DESC
= 'NRK TV Direkte and NRK Radio Direkte'
355 _VALID_URL
= r
'https?://(?:tv|radio)\.nrk\.no/direkte/(?P<id>[^/?#&]+)'
358 'url': 'https://tv.nrk.no/direkte/nrk1',
359 'only_matching': True,
361 'url': 'https://radio.nrk.no/direkte/p1_oslo_akershus',
362 'only_matching': True,
366 class NRKPlaylistBaseIE(InfoExtractor
):
367 def _extract_description(self
, webpage
):
370 def _real_extract(self
, url
):
371 playlist_id
= self
._match
_id
(url
)
373 webpage
= self
._download
_webpage
(url
, playlist_id
)
376 self
.url_result('nrk:%s' % video_id
, NRKIE
.ie_key())
377 for video_id
in re
.findall(self
._ITEM
_RE
, webpage
)
380 playlist_title
= self
. _extract_title(webpage
)
381 playlist_description
= self
._extract
_description
(webpage
)
383 return self
.playlist_result(
384 entries
, playlist_id
, playlist_title
, playlist_description
)
387 class NRKPlaylistIE(NRKPlaylistBaseIE
):
388 _VALID_URL
= r
'https?://(?:www\.)?nrk\.no/(?!video|skole)(?:[^/]+/)+(?P<id>[^/]+)'
389 _ITEM_RE
= r
'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"'
391 'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',
393 'id': 'gjenopplev-den-historiske-solformorkelsen-1.12270763',
394 'title': 'Gjenopplev den historiske solformørkelsen',
395 'description': 'md5:c2df8ea3bac5654a26fc2834a542feed',
399 'url': 'http://www.nrk.no/kultur/bok/rivertonprisen-til-karin-fossum-1.12266449',
401 'id': 'rivertonprisen-til-karin-fossum-1.12266449',
402 'title': 'Rivertonprisen til Karin Fossum',
403 'description': 'Første kvinne på 15 år til å vinne krimlitteraturprisen.',
408 def _extract_title(self
, webpage
):
409 return self
._og
_search
_title
(webpage
, fatal
=False)
411 def _extract_description(self
, webpage
):
412 return self
._og
_search
_description
(webpage
)
415 class NRKTVEpisodesIE(NRKPlaylistBaseIE
):
416 _VALID_URL
= r
'https?://tv\.nrk\.no/program/[Ee]pisodes/[^/]+/(?P<id>\d+)'
417 _ITEM_RE
= r
'data-episode=["\']%s' % NRKTVIE._EPISODE_RE
419 'url
': 'https
://tv
.nrk
.no
/program
/episodes
/nytt
-paa
-nytt
/69031',
422 'title
': 'Nytt på nytt
, sesong
: 201210',
427 def _extract_title(self, webpage):
428 return self._html_search_regex(
429 r'<h1
>([^
<]+)</h1
>', webpage, 'title
', fatal=False)
432 class NRKTVSeriesIE(InfoExtractor):
433 _VALID_URL = r'https?
://(?
:tv|radio
)\
.nrk(?
:super)?\
.no
/serie
/(?P
<id>[^
/]+)'
434 _ITEM_RE = r'(?
:data
-season
=["\']|id=["\']season
-)(?P
<id>\d
+)'
436 'url
': 'https
://tv
.nrk
.no
/serie
/groenn
-glede
',
438 'id': 'groenn
-glede
',
439 'title
': 'Grønn glede
',
440 'description
': 'md5
:7576e92ae7f65da6993cf90ee29e4608
',
442 'playlist_mincount
': 9,
444 'url
': 'http
://tv
.nrksuper
.no
/serie
/labyrint
',
448 'description
': 'md5
:58afd450974c89e27d5a19212eee7115
',
450 'playlist_mincount
': 3,
452 'url
': 'https
://tv
.nrk
.no
/serie
/broedrene
-dal
-og
-spektralsteinene
',
453 'only_matching
': True,
455 'url
': 'https
://tv
.nrk
.no
/serie
/saving
-the
-human
-race
',
456 'only_matching
': True,
458 'url
': 'https
://tv
.nrk
.no
/serie
/postmann
-pat
',
459 'only_matching
': True,
463 def suitable(cls, url):
464 return False if NRKTVIE.suitable(url) else super(NRKTVSeriesIE, cls).suitable(url)
466 def _real_extract(self, url):
467 series_id = self._match_id(url)
469 webpage = self._download_webpage(url, series_id)
473 'https
://tv
.nrk
.no
/program
/Episodes
/{series}
/{season}
'.format(
474 series=series_id, season=season_id))
475 for season_id in re.findall(self._ITEM_RE, webpage)
478 title = self._html_search_meta(
479 'seriestitle
', webpage,
480 'title
', default=None) or self._og_search_title(
481 webpage, fatal=False)
483 description = self._html_search_meta(
484 'series_description
', webpage,
485 'description
', default=None) or self._og_search_description(webpage)
487 return self.playlist_result(entries, series_id, title, description)
490 class NRKSkoleIE(InfoExtractor):
491 IE_DESC = 'NRK Skole
'
492 _VALID_URL = r'https?
://(?
:www\
.)?nrk\
.no
/skole
/?
\?.*\bmediaId
=(?P
<id>\d
+)'
495 'url
': 'https
://www
.nrk
.no
/skole
/?page
=search
&q
=&mediaId
=14099',
496 'md5
': '6bc936b01f9dd8ed45bc58b252b2d9b6
',
500 'title
': 'Genetikk og eneggede tvillinger
',
501 'description
': 'md5
:3aca25dcf38ec30f0363428d2b265f8d
',
505 'url
': 'https
://www
.nrk
.no
/skole
/?page
=objectives
&subject
=naturfag
&objective
=K15114
&mediaId
=19355',
506 'only_matching
': True,
509 def _real_extract(self, url):
510 video_id = self._match_id(url)
512 webpage = self._download_webpage(
513 'https
://mimir
.nrk
.no
/plugin
/1.0/static?mediaId
=%s' % video_id,
516 nrk_id = self._parse_json(
518 r'<script
[^
>]+type=["\']application/json["\'][^
>]*>({.+?
})</script
>',
519 webpage, 'application json
'),
520 video_id)['activeMedia
']['psId
']
522 return self.url_result('nrk
:%s' % nrk_id)