X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Ftv2.py;h=86bb7915db170ecf4c75fdc2b960160a65daa1c0;hb=ffa2cecf7291a7b9aa40dba84a76c71fba20cc57;hp=2dcc0e971e4bd72aa1038480ce8b410a6a4e8e15;hpb=bc0f937b55aae6ce731d259a7658b0281c2e62ec;p=youtube-dl diff --git a/youtube_dl/extractor/tv2.py b/youtube_dl/extractor/tv2.py index 2dcc0e971..86bb7915d 100644 --- a/youtube_dl/extractor/tv2.py +++ b/youtube_dl/extractor/tv2.py @@ -1,31 +1,37 @@ # encoding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..utils import ( determine_ext, int_or_none, float_or_none, parse_iso8601, + remove_end, ) class TV2IE(InfoExtractor): - _VALID_URL = 'http://(?:www\.)?tv2\.no/v/(?P\d+)' + _VALID_URL = r'https?://(?:www\.)?tv2\.no/v/(?P\d+)' _TEST = { 'url': 'http://www.tv2.no/v/916509/', - 'md5': '9cb9e3410b18b515d71892f27856e9b1', 'info_dict': { 'id': '916509', - 'ext': 'flv', - 'title': 'Se Gryttens hyllest av Steven Gerrard', + 'ext': 'mp4', + 'title': 'Se Frode Gryttens hyllest av Steven Gerrard', 'description': 'TV 2 Sportens huspoet tar avskjed med Liverpools kaptein Steven Gerrard.', 'timestamp': 1431715610, 'upload_date': '20150515', 'duration': 156.967, 'view_count': int, 'categories': list, - } + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, } def _real_extract(self, url): @@ -91,3 +97,33 @@ class TV2IE(InfoExtractor): 'categories': categories, 'formats': formats, } + + +class TV2ArticleIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?tv2\.no/(?:a|\d{4}/\d{2}/\d{2}(/[^/]+)+)/(?P\d+)' + _TESTS = [{ + 'url': 'http://www.tv2.no/2015/05/16/nyheter/alesund/krim/pingvin/6930542', + 'info_dict': { + 'id': '6930542', + 'title': 'Russen hetses etter pingvintyveri – innrømmer å ha åpnet luken på buret', + 'description': 'md5:339573779d3eea3542ffe12006190954', + }, + 'playlist_count': 2, + }, { + 'url': 'http://www.tv2.no/a/6930542', + 'only_matching': True, + }] + + def _real_extract(self, url): + playlist_id = self._match_id(url) + + webpage = self._download_webpage(url, playlist_id) + + entries = [ + self.url_result('http://www.tv2.no/v/%s' % video_id, 'TV2') + for video_id in re.findall(r'data-assetid="(\d+)"', webpage)] + + title = remove_end(self._og_search_title(webpage), ' - TV2.no') + description = remove_end(self._og_search_description(webpage), ' - TV2.no') + + return self.playlist_result(entries, playlist_id, title, description)