Added an IE for hark.com

pull/8/head
Yasoob 11 years ago
parent 356e067390
commit e3a88568b0

@ -29,6 +29,7 @@ from .gametrailers import GametrailersIE
from .generic import GenericIE from .generic import GenericIE
from .googleplus import GooglePlusIE from .googleplus import GooglePlusIE
from .googlesearch import GoogleSearchIE from .googlesearch import GoogleSearchIE
from .hark import HarkIE
from .hotnewhiphop import HotNewHipHopIE from .hotnewhiphop import HotNewHipHopIE
from .howcast import HowcastIE from .howcast import HowcastIE
from .hypem import HypemIE from .hypem import HypemIE

@ -0,0 +1,35 @@
# -*- coding: utf-8 -*-
import re
from .common import InfoExtractor
from ..utils import determine_ext
class HarkIE(InfoExtractor):
_VALID_URL = r'https?://www\.hark\.com/clips/(.+?)-.+'
_TEST = {
u'url': u'http://www.hark.com/clips/mmbzyhkgny-obama-beyond-the-afghan-theater-we-only-target-al-qaeda-on-may-23-2013',
u'file': u'mmbzyhkgny.mp3',
u'md5': u'6783a58491b47b92c7c1af5a77d4cbee',
u'info_dict': {
u"title": u"Obama: 'Beyond The Afghan Theater, We Only Target Al Qaeda' On May 23, 2013 ",
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group(1)
embed_url = "http://www.hark.com/clips/%s/homepage_embed" %(video_id)
webpage = self._download_webpage(embed_url, video_id)
final_url = self._search_regex(r'src="(.+?).mp3"',
webpage, 'video url')+'.mp3'
title = self._html_search_regex(r'<title>(.+?)</title>',
webpage, 'video title').replace(' Sound Clip and Quote - Hark','').replace(
'Sound Clip , Quote, MP3, and Ringtone - Hark','')
return {'id': video_id,
'url' : final_url,
'title': title,
'ext': determine_ext(final_url),
}
Loading…
Cancel
Save