爬取joomla漏洞库中存在利用代码的链接

#! /usr/bin/env  python
# -*- coding:utf-8 -*-
# __ author__ == "tyomcat"
import re
import urllib2

def getContent(url):
headers={"User-Agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/46.0.2490.86 Safari/537.36"}
try:
request=urllib2.Request(url,headers=headers)
html=urllib2.urlopen(request)
content=html.read().decode("utf-8")

return content
except urllib2.URLError,e:
if hasattr(e,"code"):
print e.code
if hasattr(e,"reason"):
print e.reason
def joomla_exploit(content):
pattern=re.compile(r'<tr><td>(\d{4}-\d{2}-\d{2})</td><td><a.*?href="(.*?)">(.*?)</a></td>',re.S)
items = re.findall(pattern,content)
for item in items:
return item[1]
if __name__ == '__main__':

url='http://www.joomlaexploit.com/'
data=getContent(url)
pocUrl=joomla_exploit(data)
poc_content = getContent(pocUrl)
pattern=re.compile(r'<tr><td>(\d{4}-\d{2}-\d{2})</td><td><a.*?href="(.*?)">(.*?)</a></td>',re.S)
files= re.findall(pattern,poc_content)
if files == []:
print '利用该漏洞的poc不存在！'
else:
for file in files:
print file[0],file[1],file[2]
print "\n"