]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/nrk.py
2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
14 class NRKIE(InfoExtractor
):
15 _VALID_URL
= r
'http://(?:www\.)?nrk\.no/(?:video|lyd)/[^/]+/(?P<id>[\dA-F]{16})'
19 'url': 'http://www.nrk.no/video/dompap_og_andre_fugler_i_piip_show/D0FA54B5C8B6CE59/emne/piipshow/',
20 'md5': 'a6eac35052f3b242bb6bb7f43aed5886',
24 'title': 'Dompap og andre fugler i Piip-Show',
25 'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f'
29 'url': 'http://www.nrk.no/lyd/lyd_av_oppleser_for_blinde/AEFDDD5473BA0198/',
30 'md5': '3471f2a51718195164e88f46bf427668',
34 'title': 'Slik høres internett ut når du er blind',
35 'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
40 def _real_extract(self
, url
):
41 mobj
= re
.match(self
._VALID
_URL
, url
)
42 video_id
= mobj
.group('id')
44 page
= self
._download
_webpage
(url
, video_id
)
46 video_id
= self
._html
_search
_regex
(r
'<div class="nrk-video" data-nrk-id="(\d+)">', page
, 'video id')
48 data
= self
._download
_json
(
49 'http://v7.psapi.nrk.no/mediaelement/%s' % video_id
, video_id
, 'Downloading media JSON')
51 if data
['usageRights']['isGeoBlocked']:
52 raise ExtractorError('NRK har ikke rettig-heter til å vise dette programmet utenfor Norge', expected
=True)
54 video_url
= data
['mediaUrl'] + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124'
56 images
= data
.get('images')
58 thumbnails
= images
['webImages']
59 thumbnails
.sort(key
=lambda image
: image
['pixelWidth'])
60 thumbnail
= thumbnails
[-1]['imageUrl']
68 'title': data
['title'],
69 'description': data
['description'],
70 'thumbnail': thumbnail
,
74 class NRKTVIE(InfoExtractor
):
75 _VALID_URL
= r
'http://tv\.nrk(?:super)?\.no/(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P<part_id>\d+))?'
79 'url': 'http://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
80 'md5': 'adf2c5454fa2bf032f47a9f8fb351342',
84 'title': '20 spørsmål',
85 'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
86 'upload_date': '20140523',
91 'url': 'http://tv.nrk.no/program/mdfp15000514',
92 'md5': '383650ece2b25ecec996ad7b5bb2a384',
96 'title': 'Kunnskapskanalen: Grunnlovsjubiléet - Stor ståhei for ingenting',
97 'description': 'md5:654c12511f035aed1e42bdf5db3b206a',
98 'upload_date': '20140524',
103 # single playlist video
104 'url': 'http://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
105 'md5': 'adbd1dbd813edaf532b0a253780719c2',
107 'id': 'MSPO40010515-part2',
109 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
110 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
111 'upload_date': '20150106',
113 'skip': 'Only works from Norway',
116 'url': 'http://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
119 'md5': '9480285eff92d64f06e02a5367970a7a',
121 'id': 'MSPO40010515-part1',
123 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 1:2)',
124 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
125 'upload_date': '20150106',
129 'md5': 'adbd1dbd813edaf532b0a253780719c2',
131 'id': 'MSPO40010515-part2',
133 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
134 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
135 'upload_date': '20150106',
140 'id': 'MSPO40010515',
141 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn',
142 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
143 'upload_date': '20150106',
144 'duration': 6947.5199999999995,
146 'skip': 'Only works from Norway',
150 def _extract_f4m(self
, manifest_url
, video_id
):
151 return self
._extract
_f
4m
_formats
(manifest_url
+ '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124', video_id
)
153 def _real_extract(self
, url
):
154 mobj
= re
.match(self
._VALID
_URL
, url
)
155 video_id
= mobj
.group('id')
156 part_id
= mobj
.group('part_id')
158 webpage
= self
._download
_webpage
(url
, video_id
)
160 title
= self
._html
_search
_meta
(
161 'title', webpage
, 'title')
162 description
= self
._html
_search
_meta
(
163 'description', webpage
, 'description')
165 thumbnail
= self
._html
_search
_regex
(
166 r
'data-posterimage="([^"]+)"',
167 webpage
, 'thumbnail', fatal
=False)
168 upload_date
= unified_strdate(self
._html
_search
_meta
(
169 'rightsfrom', webpage
, 'upload date', fatal
=False))
170 duration
= float_or_none(self
._html
_search
_regex
(
171 r
'data-duration="([^"]+)"',
172 webpage
, 'duration', fatal
=False))
176 r
'<a href="#del=(\d+)"[^>]+data-argument="([^"]+)">([^<]+)</a>', webpage
)
179 for current_part_id
, stream_url
, part_title
in parts
:
180 if part_id
and current_part_id
!= part_id
:
182 video_part_id
= '%s-part%s' % (video_id
, current_part_id
)
183 formats
= self
._extract
_f
4m
(stream_url
, video_part_id
)
187 'description': description
,
188 'thumbnail': thumbnail
,
189 'upload_date': upload_date
,
196 playlist
= self
.playlist_result(entries
, video_id
, title
, description
)
198 'thumbnail': thumbnail
,
199 'upload_date': upload_date
,
200 'duration': duration
,
206 f4m_url
= re
.search(r
'data-media="([^"]+)"', webpage
)
208 formats
.extend(self
._extract
_f
4m
(f4m_url
.group(1), video_id
))
210 m3u8_url
= re
.search(r
'data-hls-media="([^"]+)"', webpage
)
212 formats
.extend(self
._extract
_m
3u8_formats
(m3u8_url
.group(1), video_id
, 'mp4'))
214 self
._sort
_formats
(formats
)
219 'description': description
,
220 'thumbnail': thumbnail
,
221 'upload_date': upload_date
,
222 'duration': duration
,