From 0ceab8474924c4e7a6e28497c8da40cc5002c8d3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 8 May 2015 22:18:43 +0600 Subject: [PATCH] [vgtv] Add support for bt.no articles (#5620) --- youtube_dl/extractor/__init__.py | 5 +++- youtube_dl/extractor/vgtv.py | 39 +++++++++++++++++++++++++++++++- 2 files changed, 42 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 5dfa781f88..587a459406 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -587,7 +587,10 @@ from .vessel import VesselIE from .vesti import VestiIE from .vevo import VevoIE -from .vgtv import VGTVIE +from .vgtv import ( + BTArticleIE, + VGTVIE, +) from .vh1 import VH1IE from .vice import ViceIE from .viddler import ViddlerIE diff --git a/youtube_dl/extractor/vgtv.py b/youtube_dl/extractor/vgtv.py index b0f0b3bc29..ad07e54c9d 100644 --- a/youtube_dl/extractor/vgtv.py +++ b/youtube_dl/extractor/vgtv.py @@ -9,7 +9,18 @@ class VGTVIE(InfoExtractor): IE_DESC = 'VGTV and BTTV' - _VALID_URL = r'http://(?:www\.)?(?Pvgtv|bt)\.no/(?:(?:tv/)?#!/(?:video|live)/(?P[0-9]+)|(?:[^/]+/)*(?P[^/]+))' + _VALID_URL = r'''(?x) + (?: + vgtv:| + http://(?:www\.)? + ) + (?Pvgtv|bt) + (?: + :| + \.no/(?:tv/)?#!/(?:video|live)/ + ) + (?P[0-9]+) + ''' _TESTS = [ { # streamType: vod @@ -129,3 +140,29 @@ def _real_extract(self, url): 'view_count': data['displays'], 'formats': formats, } + + +class BTArticleIE(InfoExtractor): + IE_DESC = 'Bergens Tidende' + _VALID_URL = 'http://(?:www\.)?bt\.no/(?:[^/]+/)+(?P[^/]+)-\d+\.html' + _TEST = { + 'url': 'http://www.bt.no/nyheter/lokalt/Kjemper-for-internatet-1788214.html', + 'md5': 'd055e8ee918ef2844745fcfd1a4175fb', + 'info_dict': { + 'id': '23199', + 'ext': 'mp4', + 'title': 'Alrekstad internat', + 'description': 'md5:dc81a9056c874fedb62fc48a300dac58', + 'thumbnail': 're:^https?://.*\.jpg', + 'duration': 191, + 'timestamp': 1289991323, + 'upload_date': '20101117', + 'view_count': int, + }, + } + + def _real_extract(self, url): + webpage = self._download_webpage(url, self._match_id(url)) + video_id = self._search_regex( + r'SVP\.Player\.load\(\s*(\d+)', webpage, 'video id') + return self.url_result('vgtv:bt:%s' % video_id, 'VGTV')