]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/nrk.py
2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
7 from ..compat
import compat_urlparse
17 class NRKIE(InfoExtractor
):
18 _VALID_URL
= r
'(?:nrk:|https?://(?:www\.)?nrk\.no/video/PS\*)(?P<id>\d+)'
22 'url': 'http://www.nrk.no/video/PS*150533',
23 'md5': 'bccd850baebefe23b56d708a113229c2',
27 'title': 'Dompap og andre fugler i Piip-Show',
28 'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f',
33 'url': 'http://www.nrk.no/video/PS*154915',
34 'md5': '0b1493ba1aae7d9579a5ad5531bc395a',
38 'title': 'Slik høres internett ut når du er blind',
39 'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
45 def _real_extract(self
, url
):
46 video_id
= self
._match
_id
(url
)
48 data
= self
._download
_json
(
49 'http://v8.psapi.nrk.no/mediaelement/%s' % video_id
,
50 video_id
, 'Downloading media JSON')
52 media_url
= data
.get('mediaUrl')
55 if data
['usageRights']['isGeoBlocked']:
57 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',
60 if determine_ext(media_url
) == 'f4m':
61 formats
= self
._extract
_f
4m
_formats
(
62 media_url
+ '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81', video_id
, f4m_id
='hds')
69 duration
= parse_duration(data
.get('duration'))
71 images
= data
.get('images')
73 thumbnails
= images
['webImages']
74 thumbnails
.sort(key
=lambda image
: image
['pixelWidth'])
75 thumbnail
= thumbnails
[-1]['imageUrl']
81 'title': data
['title'],
82 'description': data
['description'],
84 'thumbnail': thumbnail
,
89 class NRKPlaylistIE(InfoExtractor
):
90 _VALID_URL
= r
'https?://(?:www\.)?nrk\.no/(?!video)(?:[^/]+/)+(?P<id>[^/]+)'
93 'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',
95 'id': 'gjenopplev-den-historiske-solformorkelsen-1.12270763',
96 'title': 'Gjenopplev den historiske solformørkelsen',
97 'description': 'md5:c2df8ea3bac5654a26fc2834a542feed',
101 'url': 'http://www.nrk.no/kultur/bok/rivertonprisen-til-karin-fossum-1.12266449',
103 'id': 'rivertonprisen-til-karin-fossum-1.12266449',
104 'title': 'Rivertonprisen til Karin Fossum',
105 'description': 'Første kvinne på 15 år til å vinne krimlitteraturprisen.',
110 def _real_extract(self
, url
):
111 playlist_id
= self
._match
_id
(url
)
113 webpage
= self
._download
_webpage
(url
, playlist_id
)
116 self
.url_result('nrk:%s' % video_id
, 'NRK')
117 for video_id
in re
.findall(
118 r
'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"',
122 playlist_title
= self
._og
_search
_title
(webpage
)
123 playlist_description
= self
._og
_search
_description
(webpage
)
125 return self
.playlist_result(
126 entries
, playlist_id
, playlist_title
, playlist_description
)
129 class NRKTVIE(InfoExtractor
):
130 IE_DESC
= 'NRK TV and NRK Radio'
131 _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+))?'
135 'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
137 'id': 'MUHH48000314',
139 'title': '20 spørsmål',
140 'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
141 'upload_date': '20140523',
146 'skip_download': True,
150 'url': 'https://tv.nrk.no/program/mdfp15000514',
152 'id': 'mdfp15000514',
154 'title': 'Grunnlovsjubiléet - Stor ståhei for ingenting',
155 'description': 'md5:654c12511f035aed1e42bdf5db3b206a',
156 'upload_date': '20140524',
161 'skip_download': True,
165 # single playlist video
166 'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
167 'md5': 'adbd1dbd813edaf532b0a253780719c2',
169 'id': 'MSPO40010515-part2',
171 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
172 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
173 'upload_date': '20150106',
175 'skip': 'Only works from Norway',
178 'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
181 'md5': '9480285eff92d64f06e02a5367970a7a',
183 'id': 'MSPO40010515-part1',
185 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 1:2)',
186 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
187 'upload_date': '20150106',
191 'md5': 'adbd1dbd813edaf532b0a253780719c2',
193 'id': 'MSPO40010515-part2',
195 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
196 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
197 'upload_date': '20150106',
202 'id': 'MSPO40010515',
203 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn',
204 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
205 'upload_date': '20150106',
206 'duration': 6947.5199999999995,
208 'skip': 'Only works from Norway',
211 'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#',
212 'only_matching': True,
216 def _extract_f4m(self
, manifest_url
, video_id
):
217 return self
._extract
_f
4m
_formats
(
218 manifest_url
+ '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124', video_id
, f4m_id
='hds')
220 def _real_extract(self
, url
):
221 mobj
= re
.match(self
._VALID
_URL
, url
)
222 video_id
= mobj
.group('id')
223 part_id
= mobj
.group('part_id')
224 base_url
= mobj
.group('baseurl')
226 webpage
= self
._download
_webpage
(url
, video_id
)
228 title
= self
._html
_search
_meta
(
229 'title', webpage
, 'title')
230 description
= self
._html
_search
_meta
(
231 'description', webpage
, 'description')
233 thumbnail
= self
._html
_search
_regex
(
234 r
'data-posterimage="([^"]+)"',
235 webpage
, 'thumbnail', fatal
=False)
236 upload_date
= unified_strdate(self
._html
_search
_meta
(
237 'rightsfrom', webpage
, 'upload date', fatal
=False))
238 duration
= float_or_none(self
._html
_search
_regex
(
239 r
'data-duration="([^"]+)"',
240 webpage
, 'duration', fatal
=False))
244 r
'<a href="#del=(\d+)"[^>]+data-argument="([^"]+)">([^<]+)</a>', webpage
)
247 for current_part_id
, stream_url
, part_title
in parts
:
248 if part_id
and current_part_id
!= part_id
:
250 video_part_id
= '%s-part%s' % (video_id
, current_part_id
)
251 formats
= self
._extract
_f
4m
(stream_url
, video_part_id
)
255 'description': description
,
256 'thumbnail': thumbnail
,
257 'upload_date': upload_date
,
264 playlist
= self
.playlist_result(entries
, video_id
, title
, description
)
266 'thumbnail': thumbnail
,
267 'upload_date': upload_date
,
268 'duration': duration
,
274 f4m_url
= re
.search(r
'data-media="([^"]+)"', webpage
)
276 formats
.extend(self
._extract
_f
4m
(f4m_url
.group(1), video_id
))
278 m3u8_url
= re
.search(r
'data-hls-media="([^"]+)"', webpage
)
280 formats
.extend(self
._extract
_m
3u8_formats
(m3u8_url
.group(1), video_id
, 'mp4', m3u8_id
='hls'))
281 self
._sort
_formats
(formats
)
283 subtitles_url
= self
._html
_search
_regex
(
284 r
'data-subtitlesurl\s*=\s*(["\'])(?P
<url
>.+?
)\
1',
285 webpage, 'subtitle URL
', default=None, group='url
')
290 'url
': compat_urlparse.urljoin(base_url, subtitles_url),
296 'description
': description,
297 'thumbnail
': thumbnail,
298 'upload_date
': upload_date,
299 'duration
': duration,
301 'subtitles
': subtitles,