#!/usr/bin/env python#encoding: utf-8import reimport sysimport jsonimport timeimport requestsimport urllibimport requests.packages.urllib3from multiprocessing import Poolfrom BeautifulSoup import BeautifulSouprequests.packages.urllib3.disable_warnings() headers = {'User-Agent' : 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20'} def links_ip(host):    '''  查詢同IP網站  '''  ip2hosts = []  ip2hosts.append("http://"+host)  try:    source = requests.get('http://i.links.cn/sameip/' + host + '.html', headers=headers,verify=False)    soup = BeautifulSoup(source.text)    divs = soup.findAll(style="word-break:break-all")         if divs == []: #抓取結果為空      print 'Sorry! Not found!'      return ip2hosts     for div in divs:      #print div.a.string      ip2hosts.append(div.a.string)  except Exception, e:    print str(e)    return ip2hosts  return ip2hosts def ip2host_get(host):  ip2hosts = []  ip2hosts.append("http://"+host)  try:    req=requests.get('http://www.ip2hosts.com/search.php?ip='+str(host), headers=headers,verify=False)    src=req.content    if src.find('result') != -1:      result = json.loads(src)['result']      ip = json.loads(src)['ip']      if len(result)>0:        for item in result:          if len(item)>0:            #log(scan_type,host,port,str(item))            ip2hosts.append(item)  except Exception, e:    print str(e)    return ip2hosts  return ip2hosts  def filter(host):  '''    打不開的網站...  '''  try:    response = requests.get(host, headers=headers ,verify=False)    server = response.headers['Server']    title = re.findall(r'<title>(.*?)</title>',response.content)[0]  except Exception,e:    #print "%s" % str(e)    #print host    pass  else:    print host,server def aizhan(host):  ip2hosts = []  ip2hosts.append("http://"+host)  regexp = r'''<a href="[^']+?([^']+?)/" rel="external nofollow"  target="_blank">/1</a>'''  regexp_next = r'''<a  rel="external nofollow" >%d</a>'''  url = 'http://dns.aizhan.com/%s/%d/'   page = 1  while True:    if page > 2:      time.sleep(1)  #防止拒絕訪問    req = requests.get(url % (host , page) ,headers=headers ,verify=False)    try:      html = req.content.decode('utf-8') #取得頁面      if req.status_code == 400:        break    except Exception as e:      print str(e)      pass    for site in re.findall(regexp , html):      ip2hosts.append("http://"+site)    if re.search(regexp_next % (page+1 , page+1) , html) is None:      return ip2hosts      break    page += 1   return ip2hosts def chinaz(host):  ip2hosts = []  ip2hosts.append("http://"+host)  regexp = r'''<a href='[^']+?([^']+?)' target=_blank>/1</a>'''  regexp_next = r'''<a href="javascript:" rel="external nofollow" val="%d" class="item[^"]*?">%d</a>'''  url = 'http://s.tool.chinaz.com/same?s=%s&page=%d'   page = 1  while True:    if page > 1:      time.sleep(1)  #防止拒絕訪問    req = requests.get(url % (host , page) , headers=headers ,verify=False)    html = req.content.decode('utf-8') #取得頁面    for site in re.findall(regexp , html):      ip2hosts.append("http://"+site)    if re.search(regexp_next % (page+1 , page+1) , html) is None:      return ip2hosts      break    page += 1  return ip2hosts def same_ip(host):  mydomains = []  mydomains.extend(ip2host_get(host))  mydomains.extend(links_ip(host))  mydomains.extend(aizhan(host))  mydomains.extend(chinaz(host))  mydomains = list(set(mydomains))  p = Pool()  for host in mydomains:    p.apply_async(filter, args=(host,))  p.close()  p.join()  if __name__=="__main__":  if len(sys.argv) == 2:    same_ip(sys.argv[1])  else:    print ("usage: %s host" % sys.argv[0])    sys.exit(-1)