[nrk:skole] Add extractor (Closes #8728)

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 5817140c0c407c8f0c9468dd7df3efd3e5f29500..b3bf739637344006c3ef1a096bf5ae9d7528c34b 100644 (file)
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -506,6 +506,7 @@ from .npr import NprIE
 from .nrk import (
     NRKIE,
     NRKPlaylistIE,
+    NRKSkoleIE,
     NRKTVIE,
 )
 from .ntvde import NTVDeIE

diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py
index a126f5054fbee3c178cf19915caec9fdb03df297..4ede1a3625dd323c5a8088f258e3e1d64154031d 100644 (file)
--- a/youtube_dl/extractor/nrk.py
+++ b/youtube_dl/extractor/nrk.py
@@ -87,7 +87,7 @@ class NRKIE(InfoExtractor):
 
 
 class NRKPlaylistIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video)(?:[^/]+/)+(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video|skole)(?:[^/]+/)+(?P<id>[^/]+)'
 
     _TESTS = [{
         'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',
@@ -126,6 +126,34 @@ class NRKPlaylistIE(InfoExtractor):
             entries, playlist_id, playlist_title, playlist_description)
 
 
+class NRKSkoleIE(InfoExtractor):
+    IE_DESC = 'NRK Skole'
+    _VALID_URL = r'https?://(?:www\.)?nrk\.no/skole/klippdetalj?.*\btopic=nrk(?::|%3[Aa])klipp(?:/|%2[Ff])(?P<id>\d+)'
+
+    _TESTS = [{
+        'url': 'http://nrk.no/skole/klippdetalj?topic=nrk:klipp/616532',
+        'md5': '04cd85877cc1913bce73c5d28a47e00f',
+        'info_dict': {
+            'id': '6021',
+            'ext': 'flv',
+            '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,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        nrk_id = self._search_regex(r'data-nrk-id=["\'](\d+)', webpage, 'nrk id')
+        return self.url_result('nrk:%s' % nrk_id)
+
+
 class NRKTVIE(InfoExtractor):
     IE_DESC = 'NRK TV and NRK Radio'
     _VALID_URL = r'(?P<baseurl>https?://(?:tv|radio)\.nrk(?:super)?\.no/)(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P<part_id>\d+))?'