httpscan 爬虫扫描小工具

发表于 2016年08月08日
安全工具

httpscan是一个扫描指定网段的Web主机的小工具。和端口扫描器不一样，httpscan是以爬虫的方式进行Web主机发现，因此相对来说不容易被防火墙拦截。httpscan会返回IP http状态码 Web容器版本以及网站标题。

Usage：./httpscan IP/CIDR –t threads
Example:./httpscan.py 10.20.30.0/24 –t 10

1 2	Usage：./httpscan IP/CIDR –t threads Example:./httpscan.py 10.20.30.0/24 –t 10

主要代码：

#!/usr/bin/env python
#coding:utf-8
# Author: Zeroh

import re
import sys
import Queue
import threading
import optparse
import requests
from IPy import IP

printLock = threading.Semaphore(1)  #lock Screen print
TimeOut = 5  #request timeout

#User-Agent
header = {'User-Agent' : 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.125 Safari/537.36','Connection':'close'}

class scan():

  def __init__(self,cidr,threads_num):
    self.threads_num = threads_num
    self.cidr = IP(cidr)
    #build ip queue
    self.IPs = Queue.Queue()
    for ip in self.cidr:
      ip = str(ip)
      self.IPs.put(ip)

  def request(self):
    with threading.Lock():
      while self.IPs.qsize() > 0:
        ip = self.IPs.get()
        try:
          r = requests.Session().get('http://'+str(ip),headers=header,timeout=TimeOut)
          status = r.status_code
          title = re.search(r'<title>(.*)</title>', r.text) #get the title
          if title:
            title = title.group(1).strip().strip("\r").strip("\n")[:30]
          else:
            title = "None"
          banner = ''
          try:
            banner += r.headers['Server'][:20] #get the server banner
          except:pass
          printLock.acquire()
          print "|%-16s|%-6s|%-20s|%-30s|" % (ip,status,banner,title)
          print "+----------------+------+--------------------+------------------------------+"

          #Save log
          with open("./log/"+self.cidr.strNormal(3)+".log",'a') as f:
            f.write(ip+"\n")

        except Exception,e:
          printLock.acquire()
        finally:
          printLock.release()

  #Multi thread
  def run(self):
    for i in range(self.threads_num):
      t = threading.Thread(target=self.request)
      t.start()

if __name__ == "__main__":
  parser = optparse.OptionParser("Usage: %prog [options] target")
  parser.add_option("-t", "--thread", dest = "threads_num",
    default = 1, type = "int",
    help = "[optional]number of  theads,default=10")
  (options, args) = parser.parse_args()
  if len(args) < 1:
    parser.print_help()
    sys.exit(0)

  print "+----------------+------+--------------------+------------------------------+"
  print "|     IP         |Status|       Server       |            Title             |"
  print "+----------------+------+--------------------+------------------------------+"

  s = scan(cidr=args[0],threads_num=options.threads_num)
  s.run()

#!/usr/bin/env python

#coding:utf-8

# Author: Zeroh

import re

import sys

import Queue

import threading

import optparse

import requests

from IPy import IP

printLock = threading.Semaphore(1) #lock Screen print

TimeOut = 5 #request timeout

#User-Agent

header = {'User-Agent' : 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.125 Safari/537.36','Connection':'close'}

class scan():

def __init__(self,cidr,threads_num):

self.threads_num = threads_num

self.cidr = IP(cidr)

#build ip queue

self.IPs = Queue.Queue()

for ip in self.cidr:

ip = str(ip)

self.IPs.put(ip)

def request(self):

with threading.Lock():

while self.IPs.qsize() > 0: