From 3099b3127684d1386101e86005feb18c29136a81 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 2 Mar 2016 20:52:06 +0600 Subject: [PATCH] [nrk:skole] Add extractor (Closes #8728) --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/nrk.py | 30 +++++++++++++++++++++++++++++- 2 files changed, 30 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 5817140c0..b3bf73963 100644 --- 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 a126f5054..4ede1a362 100644 --- 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[^/]+)' + _VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video|skole)(?:[^/]+/)+(?P[^/]+)' _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\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'(?Phttps?://(?:tv|radio)\.nrk(?:super)?\.no/)(?:serie/[^/]+|program)/(?P[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P\d+))?'