1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-12-22 00:15:35 +08:00

[liveleak] Simplify

This commit is contained in:
Philipp Hagemeister 2014-01-28 21:57:38 +01:00
parent 9d2032932c
commit 7eeb5bef24

View File

@ -1,3 +1,5 @@
from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
@ -7,46 +9,36 @@ from ..utils import (
class LiveLeakIE(InfoExtractor): class LiveLeakIE(InfoExtractor):
_VALID_URL = r'^(?:http://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)' _VALID_URL = r'^(?:http://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
IE_NAME = u'liveleak'
_TEST = { _TEST = {
u'url': u'http://www.liveleak.com/view?i=757_1364311680', 'url': 'http://www.liveleak.com/view?i=757_1364311680',
u'file': u'757_1364311680.mp4', 'file': '757_1364311680.mp4',
u'md5': u'0813c2430bea7a46bf13acf3406992f4', 'md5': '0813c2430bea7a46bf13acf3406992f4',
u'info_dict': { 'info_dict': {
u"description": u"extremely bad day for this guy..!", 'description': 'extremely bad day for this guy..!',
u"uploader": u"ljfriel2", 'uploader': 'ljfriel2',
u"title": u"Most unlucky car accident" 'title': 'Most unlucky car accident'
} }
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('video_id') video_id = mobj.group('video_id')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
video_url = self._search_regex(
video_url = self._search_regex(r'file: "(.*?)",', r'file: "(.*?)",', webpage, 'video URL')
webpage, u'video URL')
video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip() video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip()
video_description = self._og_search_description(webpage) video_description = self._og_search_description(webpage)
video_uploader = self._html_search_regex(
r'By:.*?(\w+)</a>', webpage, 'uploader', fatal=False)
video_uploader = self._html_search_regex(r'By:.*?(\w+)</a>', return {
webpage, u'uploader', fatal=False) 'id': video_id,
info = {
'id': video_id,
'url': video_url, 'url': video_url,
'ext': 'mp4', 'ext': 'mp4',
'title': video_title, 'title': video_title,
'description': video_description, 'description': video_description,
'uploader': video_uploader 'uploader': video_uploader
} }
return [info]