[liveleak] Support old and new URLs

This commit is contained in:
Philipp Hagemeister 2014-01-30 06:09:06 +01:00
parent 79752e18b1
commit 89acb96927
1 changed files with 17 additions and 3 deletions

View File

@ -11,7 +11,7 @@ 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_]+)(?:.*)'
_TEST = { _TESTS = [{
'url': 'http://www.liveleak.com/view?i=757_1364311680', 'url': 'http://www.liveleak.com/view?i=757_1364311680',
'file': '757_1364311680.mp4', 'file': '757_1364311680.mp4',
'md5': '0813c2430bea7a46bf13acf3406992f4', 'md5': '0813c2430bea7a46bf13acf3406992f4',
@ -20,7 +20,17 @@ class LiveLeakIE(InfoExtractor):
'uploader': 'ljfriel2', 'uploader': 'ljfriel2',
'title': 'Most unlucky car accident' 'title': 'Most unlucky car accident'
} }
} },
{
'url': 'http://www.liveleak.com/view?i=f93_1390833151',
'file': 'f93_1390833151.mp4',
'md5': 'd3f1367d14cc3c15bf24fbfbe04b9abf',
'info_dict': {
'description': 'German Television Channel NDR does an exclusive interview with Edward Snowden.\r\nUploaded on LiveLeak cause German Television thinks the rest of the world isn\'t intereseted in Edward Snowden.',
'uploader': 'ARD_Stinkt',
'title': 'German Television does first Edward Snowden Interview (ENGLISH)',
}
}]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
@ -28,7 +38,11 @@ class LiveLeakIE(InfoExtractor):
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)
sources_raw = self._search_regex( sources_raw = self._search_regex(
r'(?s)sources:\s*(\[.*?\]),', webpage, 'video URLs') r'(?s)sources:\s*(\[.*?\]),', webpage, 'video URLs', default=None)
if sources_raw is None:
sources_raw = '[{ %s}]' % (
self._search_regex(r'(file: ".*?"),', webpage, 'video URL'))
sources_json = re.sub(r'\s([a-z]+):\s', r'"\1": ', sources_raw) sources_json = re.sub(r'\s([a-z]+):\s', r'"\1": ', sources_raw)
sources = json.loads(sources_json) sources = json.loads(sources_json)