github-com-ytdl-org/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-01-07 17:16:08 +00:00
Code Issues Releases Wiki Activity

[lifenews] Add support for video URLs (Closes #5660)

Browse source
This commit is contained in:
Sergey M․ 2015-05-10 00:26:42 +06:00
parent f2e0056579
commit 480065172d
1 changed files with 6 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
youtube_dl/extractor/lifenews.py
View file

@ -14,7 +14,7 @@ from ..utils import (
class LifeNewsIE(InfoExtractor): class LifeNewsIE(InfoExtractor):
IE_NAME = 'lifenews' IE_NAME = 'lifenews'
IE_DESC = 'LIFE | NEWS' IE_DESC = 'LIFE | NEWS'
_VALID_URL = r'http://lifenews\.ru/(?:mobile/)?news/(?P<id>\d+)' _VALID_URL = r'http://lifenews\.ru/(?:mobile/)?(?P<section>news|video)/(?P<id>\d+)'
_TESTS = [{ _TESTS = [{
'url': 'http://lifenews.ru/news/126342', 'url': 'http://lifenews.ru/news/126342',
@ -55,12 +55,15 @@ class LifeNewsIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id = mobj.group('id')
section = mobj.group('section')
webpage = self._download_webpage('http://lifenews.ru/news/%s' % video_id, video_id, 'Downloading page') webpage = self._download_webpage(
'http://lifenews.ru/%s/%s' % (section, video_id),
video_id, 'Downloading page')
videos = re.findall(r'<video.*?poster="(?P<poster>[^"]+)".*?src="(?P<video>[^"]+)".*?></video>', webpage) videos = re.findall(r'<video.*?poster="(?P<poster>[^"]+)".*?src="(?P<video>[^"]+)".*?></video>', webpage)
iframe_link = self._html_search_regex( iframe_link = self._html_search_regex(
'<iframe[^>]+src="([^"]+)', webpage, 'iframe link', default=None) '<iframe[^>]+src=["\']([^"\']+)["\']', webpage, 'iframe link', default=None)
if not videos and not iframe_link: if not videos and not iframe_link:
raise ExtractorError('No media links available for %s' % video_id) raise ExtractorError('No media links available for %s' % video_id)