1 #!/usr/bin/env python 2 # -*- coding: gbk -*- 3 # -*- coding: utf_8 -*- 4 # Date: 2015年9月11日 5 # Author:蔚藍行 6 # 博客 http://www.survivalescaperooms.com/duanv/ 7  8 import requests 9 import threading10 import Levenshtein11 import re12 13 def scan(original_r,cip,ip_begin,original_match,header):14     ip=cip+str(ip_begin)15     try:16         r=requests.get('http://'+ip,headers=header,timeout=1)17     except Exception:18         pass19     else:20         if(r.status_code==original_r.status_code):21             if r.content==original_r.content:22                 PRint '---everything is match!---/n'+ip+'/n--------------------------/n/n/n',23             else:24                 if Levenshtein.ratio(r.text,original_r.text)>0.8: 25                     match=re.search(r"<title>(.*?)</title>",r.content)26                     try:27                         if match==original_match or match.group()==original_match.group():28                             print '--matches>0.8-same title--/n'+ip+'/n--------------------------/n/n/n',29                         else:30                             print '--matches>0.8-diff title--/n'+ip+'/n--------------------------/n/n/n',31                     except Exception:32                         if match==None:33                             #掃描網頁無標題34                             print '-matches>0.8-none title-s-/n'+ip+'/n--------------------------/n/n/n',35                         else:36                             #原始網頁無標題37                             print '-matches>0.8-none title-o-/n'+ip+'/n--------------------------/n/n/n',38 39 def loop(original_r,cip,original_match,header):40     global ip_begin,ip_end,mutex41     while 1:42         mutex.acquire()43         if ip_begin > ip_end:44             mutex.release()45             break46         ip=ip_begin47         ip_begin += 148         mutex.release()49         scan(original_r,cip,ip,original_match,header)50 51 def start():52     global ip_begin,ip_end,mutex53 54     ip_begin=155     ip_end=25456     mutex=threading.Lock()57 58     cip='180.97.33.'59     address='www.baidu.com'60     61     #cip='220.181.136.'62     #address='www.219.me'63     64     header={"host":address,"Accept-Encoding":"identity","User-Agent":""}65     r=requests.get('http://'+address,headers=header)66     67     original_match=re.search(r"<title>(.*?)</title>",r.content)68     69     threads=[]70     for i in range(254):71         threads.append(threading.Thread(target=loop,args=(r,cip,original_match,header)))72     for t in threads:73         t.start()74 75 if __name__ == '__main__':76     start()