2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
15 class NRKIE(InfoExtractor
):
16 _VALID_URL
= r
'(?:nrk:|https?://(?:www\.)?nrk\.no/video/PS\*)(?P<id>\d+)'
20 'url': 'http://www.nrk.no/video/PS*150533',
21 'md5': 'bccd850baebefe23b56d708a113229c2',
25 'title': 'Dompap og andre fugler i Piip-Show',
26 'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f',
31 'url': 'http://www.nrk.no/video/PS*154915',
32 'md5': '0b1493ba1aae7d9579a5ad5531bc395a',
36 'title': 'Slik høres internett ut når du er blind',
37 'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
43 def _real_extract(self
, url
):
44 video_id
= self
._match
_id
(url
)
46 data
= self
._download
_json
(
47 'http://v8.psapi.nrk.no/mediaelement/%s' % video_id
,
48 video_id
, 'Downloading media JSON')
50 if data
['usageRights']['isGeoBlocked']:
52 'NRK har ikke rettig-heter til å vise dette programmet utenfor Norge',
55 video_url
= data
['mediaUrl'] + '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81'
57 duration
= parse_duration(data
.get('duration'))
59 images
= data
.get('images')
61 thumbnails
= images
['webImages']
62 thumbnails
.sort(key
=lambda image
: image
['pixelWidth'])
63 thumbnail
= thumbnails
[-1]['imageUrl']
71 'title': data
['title'],
72 'description': data
['description'],
74 'thumbnail': thumbnail
,
78 class NRKPlaylistIE(InfoExtractor
):
79 _VALID_URL
= r
'https?://(?:www\.)?nrk\.no/(?!video)(?:[^/]+/)+(?P<id>[^/]+)'
82 'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',
84 'id': 'gjenopplev-den-historiske-solformorkelsen-1.12270763',
85 'title': 'Gjenopplev den historiske solformørkelsen',
86 'description': 'md5:c2df8ea3bac5654a26fc2834a542feed',
90 'url': 'http://www.nrk.no/kultur/bok/rivertonprisen-til-karin-fossum-1.12266449',
92 'id': 'rivertonprisen-til-karin-fossum-1.12266449',
93 'title': 'Rivertonprisen til Karin Fossum',
94 'description': 'Første kvinne på 15 år til å vinne krimlitteraturprisen.',
99 def _real_extract(self
, url
):
100 playlist_id
= self
._match
_id
(url
)
102 webpage
= self
._download
_webpage
(url
, playlist_id
)
105 self
.url_result('nrk:%s' % video_id
, 'NRK')
106 for video_id
in re
.findall(
107 r
'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"',
111 playlist_title
= self
._og
_search
_title
(webpage
)
112 playlist_description
= self
._og
_search
_description
(webpage
)
114 return self
.playlist_result(
115 entries
, playlist_id
, playlist_title
, playlist_description
)
118 class NRKTVIE(InfoExtractor
):
119 IE_DESC
= 'NRK TV and NRK Radio'
120 _VALID_URL
= r
'(?P<baseurl>https?://(?:tv|radio)\.nrk(?:super)?\.no/)(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P<part_id>\d+))?'
124 'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
125 'md5': 'adf2c5454fa2bf032f47a9f8fb351342',
127 'id': 'MUHH48000314',
129 'title': '20 spørsmål',
130 'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
131 'upload_date': '20140523',
136 'url': 'https://tv.nrk.no/program/mdfp15000514',
137 'md5': '383650ece2b25ecec996ad7b5bb2a384',
139 'id': 'mdfp15000514',
141 'title': 'Kunnskapskanalen: Grunnlovsjubiléet - Stor ståhei for ingenting',
142 'description': 'md5:654c12511f035aed1e42bdf5db3b206a',
143 'upload_date': '20140524',
148 # single playlist video
149 'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
150 'md5': 'adbd1dbd813edaf532b0a253780719c2',
152 'id': 'MSPO40010515-part2',
154 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
155 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
156 'upload_date': '20150106',
158 'skip': 'Only works from Norway',
161 'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
164 'md5': '9480285eff92d64f06e02a5367970a7a',
166 'id': 'MSPO40010515-part1',
168 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 1:2)',
169 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
170 'upload_date': '20150106',
174 'md5': 'adbd1dbd813edaf532b0a253780719c2',
176 'id': 'MSPO40010515-part2',
178 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
179 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
180 'upload_date': '20150106',
185 'id': 'MSPO40010515',
186 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn',
187 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
188 'upload_date': '20150106',
189 'duration': 6947.5199999999995,
191 'skip': 'Only works from Norway',
194 'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#',
195 'only_matching': True,
199 def _debug_print(self
, txt
):
200 if self
._downloader
.params
.get('verbose', False):
201 self
.to_screen('[debug] %s' % txt
)
203 def _get_subtitles(self
, subtitlesurl
, video_id
, baseurl
):
204 url
= "%s%s" % (baseurl
, subtitlesurl
)
205 self
._debug
_print
('%s: Subtitle url: %s' % (video_id
, url
))
206 captions
= self
._download
_xml
(
207 url
, video_id
, 'Downloading subtitles')
208 lang
= captions
.get('lang', 'no')
210 {'ext': 'ttml', 'url': url}
,
213 def _extract_f4m(self
, manifest_url
, video_id
):
214 return self
._extract
_f
4m
_formats
(
215 manifest_url
+ '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124', video_id
, f4m_id
='hds')
217 def _real_extract(self
, url
):
218 mobj
= re
.match(self
._VALID
_URL
, url
)
219 video_id
= mobj
.group('id')
220 part_id
= mobj
.group('part_id')
221 baseurl
= mobj
.group('baseurl')
223 webpage
= self
._download
_webpage
(url
, video_id
)
225 title
= self
._html
_search
_meta
(
226 'title', webpage
, 'title')
227 description
= self
._html
_search
_meta
(
228 'description', webpage
, 'description')
230 thumbnail
= self
._html
_search
_regex
(
231 r
'data-posterimage="([^"]+)"',
232 webpage
, 'thumbnail', fatal
=False)
233 upload_date
= unified_strdate(self
._html
_search
_meta
(
234 'rightsfrom', webpage
, 'upload date', fatal
=False))
235 duration
= float_or_none(self
._html
_search
_regex
(
236 r
'data-duration="([^"]+)"',
237 webpage
, 'duration', fatal
=False))
241 r
'<a href="#del=(\d+)"[^>]+data-argument="([^"]+)">([^<]+)</a>', webpage
)
244 for current_part_id
, stream_url
, part_title
in parts
:
245 if part_id
and current_part_id
!= part_id
:
247 video_part_id
= '%s-part%s' % (video_id
, current_part_id
)
248 formats
= self
._extract
_f
4m
(stream_url
, video_part_id
)
252 'description': description
,
253 'thumbnail': thumbnail
,
254 'upload_date': upload_date
,
261 playlist
= self
.playlist_result(entries
, video_id
, title
, description
)
263 'thumbnail': thumbnail
,
264 'upload_date': upload_date
,
265 'duration': duration
,
271 f4m_url
= re
.search(r
'data-media="([^"]+)"', webpage
)
273 formats
.extend(self
._extract
_f
4m
(f4m_url
.group(1), video_id
))
275 m3u8_url
= re
.search(r
'data-hls-media="([^"]+)"', webpage
)
277 formats
.extend(self
._extract
_m
3u8_formats
(m3u8_url
.group(1), video_id
, 'mp4', m3u8_id
='hls'))
278 self
._sort
_formats
(formats
)
280 subtitles_url
= self
._html
_search
_regex
(
281 r
'data-subtitlesurl[ ]*=[ ]*"([^"]+)"',
282 webpage
, 'subtitle URL', default
=None)
285 subtitles
= self
.extract_subtitles(subtitles_url
, video_id
, baseurl
)
290 'description': description
,
291 'thumbnail': thumbnail
,
292 'upload_date': upload_date
,
293 'duration': duration
,
295 'subtitles': subtitles
,