测试李姐姐子域名枚举，返回的是域名+ip格式
但是有好多访问不了
原来写个单线程返回标题的 昨天闲着改了改多进程+端口
速度还凑合
import re
import requests
from bs4 import BeautifulSoup
from multiprocessing import Pool
scanlist = []
urllist = []
with open('alibaba.com_full.txt','r') as f:
for i in f.readlines():
if '114.80.132.160' not in i:
ip = i[31:]
i = i[:31]
i = re.sub(' ','',i)
i = re.sub('\t','',i)
ip = re.sub(' ','',ip)
ip = re.sub('\t','',ip)
i = i+' '+ip
urllist.append(i)
def get_title(url):
portlist = [80, 81, 82, 8080, 8081, 8000, 8001, 9200, 6379]
url = 'http://'+url
ret = []
for port in portlist:
u = url+':'+str(port)
print('[*]star '+url)
try:
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 UBrowser/6.0.1471.914 Safari/537.36'}
response = requests.get(url=u, headers=headers, timeout=5, verify=False)
# print(url)
response.encoding = response.apparent_encoding
response = BeautifulSoup(response.text,'lxml')
title = response.html.title.get_text()
except Exception as e:
# print(e)
title = '空'
res = u+' '+title
print(res)
ret.append(res)
with open('aliresult.txt','a+') as e:
for i in ret:
i = i + '\n'
e.write(i)
if __name__ =='__main__':
while urllist != []:
p = Pool(5)
for i in urllist[:5]:
# print('[*]start scan '+i)
urllist.remove(i)
i = re.split(' ',i)
p.apply_async(get_title, args=(i[0],))
p.close()
p.join()
