X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Flifenews.py;h=8d9491f233bf578bc9274a18fe022a1538effad6;hb=e423e0baaabe16e80af693d1f05ffc560747b3b8;hp=0512598578847b35611f81b539afeb860cdd0013;hpb=3c493256584fa5563df1e7963a40cb82ba1d1d01;p=youtube-dl diff --git a/youtube_dl/extractor/lifenews.py b/youtube_dl/extractor/lifenews.py index 051259857..8d9491f23 100644 --- a/youtube_dl/extractor/lifenews.py +++ b/youtube_dl/extractor/lifenews.py @@ -4,22 +4,27 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import unified_strdate +from ..utils import ( + int_or_none, + unified_strdate, + ExtractorError, +) class LifeNewsIE(InfoExtractor): IE_NAME = 'lifenews' IE_DESC = 'LIFE | NEWS' _VALID_URL = r'http://lifenews\.ru/(?:mobile/)?news/(?P\d+)' - + _TEST = { 'url': 'http://lifenews.ru/news/126342', - 'file': '126342.mp4', 'md5': 'e1b50a5c5fb98a6a544250f2e0db570a', 'info_dict': { + 'id': '126342', + 'ext': 'mp4', 'title': 'МВД разыскивает мужчин, оставивших в IKEA сумку с автоматом', 'description': 'Камеры наблюдения гипермаркета зафиксировали троих мужчин, спрятавших оружейный арсенал в камере хранения.', - 'thumbnail': 'http://lifenews.ru/static/posts/2014/1/126342/.video.jpg', + 'thumbnail': 're:http://.*\.jpg', 'upload_date': '20140130', } } @@ -28,13 +33,11 @@ class LifeNewsIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - webpage = self._download_webpage('http://lifenews.ru/mobile/news/%s' % video_id, video_id, 'Downloading page') + webpage = self._download_webpage('http://lifenews.ru/news/%s' % video_id, video_id, 'Downloading page') - video_url = self._html_search_regex( - r'', webpage, 'video URL') - - thumbnail = self._html_search_regex( - r'', webpage, 'video thumbnail') + videos = re.findall(r'[^"]+)".*?src="(?P', webpage) + if not videos: + raise ExtractorError('No media links available for %s' % video_id) title = self._og_search_title(webpage) TITLE_SUFFIX = ' - Первый по срочным новостям — LIFE | NEWS' @@ -44,20 +47,28 @@ class LifeNewsIE(InfoExtractor): description = self._og_search_description(webpage) view_count = self._html_search_regex( - r'
(\d+)
', webpage, 'view count') + r'
(\d+)
', webpage, 'view count', fatal=False) comment_count = self._html_search_regex( - r'
(\d+)
', webpage, 'comment count') + r'
\s*(\d+)', webpage, 'comment count', fatal=False) upload_date = self._html_search_regex( - r'