]>
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})'
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',
104 def _real_extract(self
, url
):
105 mobj
= re
.match(self
._VALID
_URL
, url
)
106 video_id
= mobj
.group('id')
108 page
= self
._download
_webpage
(url
, video_id
)
110 title
= self
._html
_search
_meta
('title', page
, 'title')
111 description
= self
._html
_search
_meta
('description', page
, 'description')
112 thumbnail
= self
._html
_search
_regex
(r
'data-posterimage="([^"]+)"', page
, 'thumbnail', fatal
=False)
113 upload_date
= unified_strdate(self
._html
_search
_meta
('rightsfrom', page
, 'upload date', fatal
=False))
114 duration
= float_or_none(
115 self
._html
_search
_regex
(r
'data-duration="([^"]+)"', page
, 'duration', fatal
=False))
119 f4m_url
= re
.search(r
'data-media="([^"]+)"', page
)
122 'url': f4m_url
.group(1) + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124',
127 m3u8_url
= re
.search(r
'data-hls-media="([^"]+)"', page
)
130 'url': m3u8_url
.group(1),
134 self
._sort
_formats
(formats
)
139 'description': description
,
140 'thumbnail': thumbnail
,
141 'upload_date': upload_date
,
142 'duration': duration
,