aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
authorSergey M․ <dstftw@gmail.com>2016-06-12 07:20:37 +0700
committerSergey M․ <dstftw@gmail.com>2016-06-12 07:20:37 +0700
commit971e3b7520563936f6e6946f5c08d64f65ab6f42 (patch)
treefc66909fe154b79c8a0c8dd0d160ddcb1ebe1046 /youtube_dl/extractor
parent4e790117292d060a3e449c9edfffe14d231aee96 (diff)
[nrk:skole] Fix extraction
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/nrk.py26
1 files changed, 15 insertions, 11 deletions
diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py
index 4a790da7b..6ded5bd45 100644
--- a/youtube_dl/extractor/nrk.py
+++ b/youtube_dl/extractor/nrk.py
@@ -260,30 +260,34 @@ class NRKPlaylistIE(InfoExtractor):
class NRKSkoleIE(InfoExtractor):
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 = [{
- 'url': 'http://nrk.no/skole/klippdetalj?topic=nrk:klipp/616532',
- 'md5': '04cd85877cc1913bce73c5d28a47e00f',
+ 'url': 'https://www.nrk.no/skole/?page=search&q=&mediaId=14099',
+ 'md5': '6bc936b01f9dd8ed45bc58b252b2d9b6',
'info_dict': {
'id': '6021',
- 'ext': 'flv',
+ 'ext': 'mp4',
'title': 'Genetikk og eneggede tvillinger',
'description': 'md5:3aca25dcf38ec30f0363428d2b265f8d',
'duration': 399,
},
}, {
- 'url': 'http://www.nrk.no/skole/klippdetalj?topic=nrk%3Aklipp%2F616532#embed',
- 'only_matching': True,
- }, {
- 'url': 'http://www.nrk.no/skole/klippdetalj?topic=urn:x-mediadb:21379',
+ 'url': 'https://www.nrk.no/skole/?page=objectives&subject=naturfag&objective=K15114&mediaId=19355',
'only_matching': True,
}]
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(
+ 'https://mimir.nrk.no/plugin/1.0/static?mediaId=%s' % video_id,
+ video_id)
- webpage = self._download_webpage(url, 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)