for subtitle in ('webVtt', 'timedText'):
subtitle_url = asset.get('%sSubtitlesUrl' % subtitle)
if subtitle_url:
- subtitles.setdefault('no', []).append({'url': subtitle_url})
+ subtitles.setdefault('no', []).append({
+ 'url': compat_urllib_parse_unquote(subtitle_url)
+ })
entries.append({
'id': asset.get('carrierId') or entry_id,
'title': entry_title,
'ext': 'mp4',
'title': '20 spørsmål 23.05.2014',
'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
- 'duration': 1741.52,
+ 'duration': 1741,
},
}, {
'url': 'https://tv.nrk.no/program/mdfp15000514',
'ext': 'mp4',
'title': 'Grunnlovsjubiléet - Stor ståhei for ingenting 24.05.2014',
'description': 'md5:89290c5ccde1b3a24bb8050ab67fe1db',
- 'duration': 4605.08,
+ 'duration': 4605,
},
}, {
# single playlist video
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)