由于HTTP 302,无法使用Python检索NTLM认证的网页

问题描述

|| 谁能帮我下面提供的python代码?我已对其进行了一些稍微的修改,以供自己使用。我试图从运行NTLM身份验证的Windows服务器访问网页。起初,我的问题是保持持久连接,这样我就不会出现http 401错误。现在,我已经克服了这一点,但是发生的是我收到了HTTP 302重定向错误以及在响应的set-cookie中发送回的cookie。因此,我添加一个cookie处理程序,但是没有做任何事情。另外,从服务器返回的“位置”字段包含我最初提交的原始URL。我不明白这一点。为什么从服务器发送回进行重定向的位置字段具有与我提交的完全相同的URL?
import urllib2
import httplib,socket 
import cookielib
import ntlm 
from ntlm import ntlm 

class AbstractNtlmAuthHandler: 

   httplib.httpconnection.debuglevel = 1 
   url1 = \"\"

   def __init__(self,password_mgr=None): 
      if password_mgr is None: 
         password_mgr = HTTPPasswordMgr() 
      self.passwd = password_mgr 
      self.add_password = self.passwd.add_password 

    def http_error_authentication_required(self,auth_header_field,req,fp,headers): 
      auth_header_value = headers.get(auth_header_field,None) 
      if auth_header_field: 
         if \'ntlm\' in auth_header_value.lower(): 
         if auth_header_value is not None and \'ntlm\' in auth_header_value.lower(): 
            fp.close() 
            return self.retry_using_http_NTLM_auth(req,None,headers) 

   def retry_using_http_NTLM_auth(self,realm,headers): 

      print req.get_full_url()
      print \"\\n\\n\"

      #user,pw = self.passwd.find_user_password(realm,req.get_full_url()) 
      user,url1) 
      if pw is not None: 
     # ntlm secures a socket,so we must use the same socket for the complete handshake 
     headers = dict(req.headers) 
     headers.update(req.unredirected_hdrs) 
     auth = \'NTLM %s\' % ntlm.create_NTLM_NEGOTIATE_MESSAGE(user) 

     if req.headers.get(self.auth_header,None) == auth: 
        return None 
     headers[self.auth_header] = auth 

     host = req.get_host() 
     if not host: 
        raise URLError(\'no host given\') 
     h = None 
     if req.get_full_url().startswith(\'https://\'): 
        h = httplib.HTTPSConnection(host) # will parse host:port 
     else: 
        h = httplib.httpconnection(host) # will parse host:port 
         # we must keep the connection because NTLM authenticates the connection,not single requests 
         headers[\"Connection\"] = \"Keep-Alive\" 
         headers = dict((name.title(),val) for name,val in headers.items()) 
         h.request(req.get_method(),req.get_selector(),req.data,headers) 
         r = h.getresponse() 
         r.begin() 
         r._safe_read(int(r.getheader(\'content-length\'))) 
         if r.getheader(\'set-cookie\'): 
            # this is important for some web applications that store authentication-related info in cookies (it took a long time to figure out) 
            headers[\'Cookie\'] = r.getheader(\'set-cookie\') 
         r.fp = None # remove the reference to the socket,so that it can not be closed by the response object (we want to keep the socket open) 
         auth_header_value = r.getheader(auth_header_field,None) 
         (ServerChallenge,NegotiateFlags) = ntlm.parse_NTLM_CHALLENGE_MESSAGE   (auth_header_value[5:]) 
         user_parts = user.split(\'\\\\\',1) 
         DomainName = user_parts[0].upper() 
         UserName = user_parts[1] 
         auth = \'NTLM %s\' % ntlm.create_NTLM_AUTHENTICATE_MESSAGE(ServerChallenge,UserName,DomainName,pw,NegotiateFlags) 
         headers[self.auth_header] = auth 
         headers[\"Connection\"] = \"Close\" 
         headers = dict((name.title(),val in headers.items()) 
         try: 
            h.request(req.get_method(),headers) 
            # none of the configured handlers are triggered,for example redirect-responses are not handled! 
            return h.getresponse() 
         except socket.error,err: 
            raise URLError(err) 
      else: 
         return None 


class HTTPNtlmAuthHandler(AbstractNtlmAuthHandler,urllib2.BaseHandler): 

   auth_header = \'Authorization\' 

   def http_error_401(self,code,msg,headers): 
      return self.http_error_authentication_required(\'www-authenticate\',headers) 


class ProxyNtlmAuthHandler(AbstractNtlmAuthHandler,urllib2.BaseHandler): 
   auth_header = \'Proxy-authorization\' 
   def http_error_407(self,headers): 
      return self.http_error_authentication_required(\'proxy-authenticate\',headers) 


if __name__ == \"__main__\": 
   url = \'HTTP WEB ADDRESS HERE\'
   url1 = url

   user = \'USERNAME\'
   password = \'PASSWORD\' 
   user_agent = \'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)\'
   data = \"\"
   headers = { \'User-Agent\' : user_agent }


   passman = urllib2.HTTPPasswordMgrWithDefaultRealm() 
   passman.add_password(None,url,user,password) 


   cookie_jar = cookielib.CookieJar()
   cookie_handler = urllib2.HTTPCookieProcessor(cookie_jar)

   redirect = urllib2.HTTPRedirectHandler()
   auth_basic = urllib2.HTTPBasicAuthHandler(passman) 
   auth_digest = urllib2.HTTPDigestAuthHandler(passman) 
   auth_NTLM = HTTPNtlmAuthHandler(passman) 

   opener = urllib2.build_opener(cookie_handler,auth_NTLM,auth_basic,auth_digest,redirect)
   urllib2.install_opener(opener) 

   req = urllib2.Request(url,data,headers)
   response = urllib2.urlopen(req)
    

解决方法

        从服务器获得响应后,请检查其是否为302状态。如果状态为302,请获取cookie并使用cookie信息进行另一个请求
if(response.code==302):
        header={\'Cookie\':response.headers[\'Set-Cookie\']}
        req=urllib2.Request(thesameurl,None,header)
        response=urllib2.urlopen(req)
response.read()