mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-10 09:07:58 +01:00
[nrk:skole] Fix extraction
This commit is contained in:
parent
4e79011729
commit
971e3b7520
1 changed files with 15 additions and 11 deletions
|
@ -260,30 +260,34 @@ def _real_extract(self, url):
|
||||||
|
|
||||||
class NRKSkoleIE(InfoExtractor):
|
class NRKSkoleIE(InfoExtractor):
|
||||||
IE_DESC = 'NRK Skole'
|
IE_DESC = 'NRK Skole'
|
||||||
_VALID_URL = r'https?://(?:www\.)?nrk\.no/skole/klippdetalj?.*\btopic=(?P<id>[^/?#&]+)'
|
_VALID_URL = r'https?://(?:www\.)?nrk\.no/skole/?\?.*\bmediaId=(?P<id>\d+)'
|
||||||
|
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'http://nrk.no/skole/klippdetalj?topic=nrk:klipp/616532',
|
'url': 'https://www.nrk.no/skole/?page=search&q=&mediaId=14099',
|
||||||
'md5': '04cd85877cc1913bce73c5d28a47e00f',
|
'md5': '6bc936b01f9dd8ed45bc58b252b2d9b6',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '6021',
|
'id': '6021',
|
||||||
'ext': 'flv',
|
'ext': 'mp4',
|
||||||
'title': 'Genetikk og eneggede tvillinger',
|
'title': 'Genetikk og eneggede tvillinger',
|
||||||
'description': 'md5:3aca25dcf38ec30f0363428d2b265f8d',
|
'description': 'md5:3aca25dcf38ec30f0363428d2b265f8d',
|
||||||
'duration': 399,
|
'duration': 399,
|
||||||
},
|
},
|
||||||
}, {
|
}, {
|
||||||
'url': 'http://www.nrk.no/skole/klippdetalj?topic=nrk%3Aklipp%2F616532#embed',
|
'url': 'https://www.nrk.no/skole/?page=objectives&subject=naturfag&objective=K15114&mediaId=19355',
|
||||||
'only_matching': True,
|
|
||||||
}, {
|
|
||||||
'url': 'http://www.nrk.no/skole/klippdetalj?topic=urn:x-mediadb:21379',
|
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
}]
|
}]
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
video_id = compat_urllib_parse_unquote(self._match_id(url))
|
video_id = self._match_id(url)
|
||||||
|
|
||||||
webpage = self._download_webpage(url, video_id)
|
webpage = self._download_webpage(
|
||||||
|
'https://mimir.nrk.no/plugin/1.0/static?mediaId=%s' % video_id,
|
||||||
|
video_id)
|
||||||
|
|
||||||
|
nrk_id = self._parse_json(
|
||||||
|
self._search_regex(
|
||||||
|
r'<script[^>]+type=["\']application/json["\'][^>]*>({.+?})</script>',
|
||||||
|
webpage, 'application json'),
|
||||||
|
video_id)['activeMedia']['psId']
|
||||||
|
|
||||||
nrk_id = self._search_regex(r'data-nrk-id=["\'](\d+)', webpage, 'nrk id')
|
|
||||||
return self.url_result('nrk:%s' % nrk_id)
|
return self.url_result('nrk:%s' % nrk_id)
|
||||||
|
|
Loading…
Reference in a new issue