diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index e89b5cf9d..7b71b9c70 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -110,6 +110,7 @@ from .khanacademy import KhanAcademyIE from .kickstarter import KickStarterIE from .keek import KeekIE from .la7 import LA7IE +from .lifenews import LifeNewsIE from .liveleak import LiveLeakIE from .livestream import LivestreamIE, LivestreamOriginalIE from .lynda import ( diff --git a/youtube_dl/extractor/lifenews.py b/youtube_dl/extractor/lifenews.py new file mode 100644 index 000000000..4bce9a9b5 --- /dev/null +++ b/youtube_dl/extractor/lifenews.py @@ -0,0 +1,63 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import unified_strdate + + +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': { + 'title': 'МВД разыскивает троих 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', + 'upload_date': '20140130', + } + } + + def _real_extract(self, url): + 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') + + video_url = self._html_search_regex( + r'', webpage, 'video URL') + + thumbnail = self._html_search_regex( + r'', webpage, 'video thumbnail') + + title = self._og_search_title(webpage) + TITLE_SUFFIX = ' - Первый по срочным новостям — LIFE | NEWS' + if title.endswith(TITLE_SUFFIX): + title = title[:-len(TITLE_SUFFIX)] + + description = self._og_search_description(webpage) + + view_count = self._html_search_regex( + r'
(\d+)
', webpage, 'view count') + comment_count = self._html_search_regex( + r'
(\d+)
', webpage, 'comment count') + + upload_date = self._html_search_regex( + r'