Added HotNewHipHop IE

This commit is contained in:
Johny Mo Swag 2013-06-26 18:38:48 -07:00
parent e38af9e00c
commit 5b66de8859
2 changed files with 41 additions and 0 deletions

View file

@ -18,6 +18,7 @@
from .generic import GenericIE
from .googleplus import GooglePlusIE
from .googlesearch import GoogleSearchIE
from .hotnewhiphop import HotNewHipHopIE
from .howcast import HowcastIE
from .hypem import HypemIE
from .ina import InaIE
@ -136,6 +137,7 @@ def gen_extractors():
TudouIE(),
CSpanIE(),
WimpIE(),
HotNewHipHopIE(),
GenericIE()
]

View file

@ -0,0 +1,39 @@
import re
import base64
from .common import InfoExtractor
class HotNewHipHopIE(InfoExtractor):
_VALID_URL = r'(http://www\.hotnewhiphop.com/.*\.(?P<id>.*)\.html)'
IE_NAME = u'HotNewHipHop'
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
video_id = m.group('id')
webpage_src = self._download_webpage(url, video_id)
print video_id
video_url_base64 = self._search_regex(r'data-path="(.*?)"',
webpage_src, u'video URL')
video_url = base64.b64decode(video_url_base64)
video_title = self._html_search_regex(r"<title>(.*)</title>",
webpage_src, u'title')
#"og:image" content=
# Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
thumbnail = self._html_search_regex(r'"og:image" content="(.*)"',
webpage_src, u'thumbnail', fatal=False)
results = [{
'id': video_id,
'url' : video_url,
'title' : video_title,
'thumbnail' : thumbnail,
'ext' : 'mp3',
}]
return results