#coding=utf-8
import urllib2
import re
import time
def timestamp():
return str(time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()))
print 'start time:' + timestamp()
for i in range(1,200):
print i
web1 = urllib2.urlopen('http://wooyun.org/bugs/new_submit/')
web2 = urllib2.urlopen('https://butian.360.cn/vul/list')
html1 = web1.read()
html2 = web2.read()
m = re.findall('<td><a href="(.*(凤凰|乐视|头条|中石化|石油|TCL|中科院).*<)', html1)
n = re.findall('</a> 发布 <a href="(.*(凤凰|乐视|头条|中石化|石油|TCL|中科院).*</a> </p>)', html2)
for url1 in m:
print "http://www.wooyun.org" + url1[0]
for url2 in n:
print "http://butian.360.cn" + url2[0]
time.sleep(300)
print 'end time:' + timestamp()