python脚本 从wooyun.org获取厂商域名

#!/usr/bin/env python
#encoding: utf-8
#qq:831937

#从wooyun.org获取厂商域名

import urllib
import re

def getHtml(url):
page = urllib.urlopen(url)
html = page.read()
return html
#print html

def getDomain(html):
Reg='target="_blank">http://(.+)</a>'
DomainReg=re.compile(Reg)
DomainList=re.findall(DomainReg,html)
return DomainList

pagecount = 1
domains = []
while (pagecount<40):
html = getHtml("http://www.wooyun.org/corps/page/"+str(pagecount))
domains += getDomain(html)
pagecount +=1

print domains