Added an IE for Dump.com

This commit is contained in:
M.Yasoob Ullah Khalid ☺ 2014-08-22 01:30:49 +05:00
parent 61882bf7c6
commit 76beff70a8
2 changed files with 40 additions and 0 deletions

View File

@ -69,6 +69,7 @@
from .dotsub import DotsubIE from .dotsub import DotsubIE
from .dreisat import DreiSatIE from .dreisat import DreiSatIE
from .drtv import DRTVIE from .drtv import DRTVIE
from .dump import DumpIE
from .defense import DefenseGouvFrIE from .defense import DefenseGouvFrIE
from .discovery import DiscoveryIE from .discovery import DiscoveryIE
from .divxstage import DivxStageIE from .divxstage import DivxStageIE

View File

@ -0,0 +1,39 @@
# encoding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
)
class DumpIE(InfoExtractor):
_VALID_URL = r'^https?://(?:www\.)?dump\.com/(?P<id>[a-zA-Z0-9]+)/'
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
video_id = m.group('id')
# Note: There is an easier-to-parse configuration at
# http://www.aparat.com/video/video/config/videohash/%video_id
# but the URL in there does not work
webpage = self._download_webpage(url, video_id)
try:
video_url = re.findall(r'file","(.+?.flv)"', webpage)[-1]
except IndexError:
raise ExtractorError(u'No video URL found')
thumb = re.findall('<meta property="og:image" content="(.+?)"',webpage)[0]
title = self._search_regex(r'<b>([^"]+)</b>', webpage, u'title')
return {
'id': video_id,
'title': title,
'url': video_url,
'ext': 'flv',
'thumbnail': thumb,
}