python扫描网站目录

#!/usr/bin/python
#coding: utf-8

import httplib2
import sys

def subscan(subpath):
    for fileLine in fileList:
        newline=fileLine.strip()  #去掉每行头尾空白
        path=subpath+newline
        response,content=http.request(path,"GET")
        if response.status!=nonpathstatus and response.status!=nonpathextstatus:
            st=str(response.status)
            print(st+" : "+path)
if __name__=="__main__":
    if(len(sys.argv)<3):
        print "written by lanz...."
        print "usage: "+sys.argv[0]+" host "+" wordlist"+" ext"
        sys.exit(0)
    host=sys.argv[1]
    filename=sys.argv[2]
    ext=sys.argv[3]
    print host

    http=httplib2.Http(".cache")
    response,content=http.request(host)
    #测试两个肯定不存在的网址，记录下返回的状态值，便于后面比较用
    response,content=http.request(host+"/mustnotexistpath/")
    nonpathstatus=response.status

    response,content=http.request(host+"/mustnotexitspath/"+ext)
    nonpathextstatus=response.status
    print "NoneExistPathStatus",nonpathstatus
    print "NoneExistFilestatus",nonpathextstatus

    f=open(filename,'r')
    fileList=f.readlines()
    subscan(host)
    f.close()