3
任何人都可以用我下面的Python代碼來幫助我嗎?這是一些開源,我稍微修改了自己的使用。我試圖從運行NTLM身份驗證的Windows服務器訪問網頁。起初我的問題是保持一個持久的連接,以便我不會得到HTTP 401錯誤。現在我已經過去了,但是會發生一個http 302重定向錯誤以及在響應的set-cookie中發回的cookie。因此我添加了一個cookie處理程序,但那沒有做任何事情。此外,從服務器返回的「位置」字段包含我首先提交的原始網址。我不明白這一點。爲什麼從服務器返回的重定向位置字段與我提交的URL完全相同?無法使用Python檢索NTLM認證網頁,因爲HTTP 302
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, auth_header_field, None, headers)
def retry_using_http_NTLM_auth(self, req, auth_header_field, realm, headers):
print req.get_full_url()
print "\n\n"
#user, pw = self.passwd.find_user_password(realm, req.get_full_url())
user, pw = self.passwd.find_user_password(realm, 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) for name, val in headers.items())
try:
h.request(req.get_method(), req.get_selector(), req.data, 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, req, fp, code, msg, headers):
return self.http_error_authentication_required('www-authenticate', req, fp, headers)
class ProxyNtlmAuthHandler(AbstractNtlmAuthHandler, urllib2.BaseHandler):
auth_header = 'Proxy-authorization'
def http_error_407(self, req, fp, code, msg, headers):
return self.http_error_authentication_required('proxy-authenticate', req, fp, 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)
要回答你的問題的最後一部分,另一個請求:它要求你重新提交該頁面你的要求,但這次*與* cookie數據(因此它知道你已經通過了身份驗證,並且可以爲你提供有權查看的內容)。 – ewall
請原諒我的無知,但不應該讓python的cookie處理程序爲我照顧這件事?我假設我必須手動重新提交呢? : -/ – Jay
我看到代碼在服務器的響應中收到它時保存了cookie,這很好。我認爲下一步是按照服務器建議(301代碼)重新加載頁面 - 但是這次您存儲的cookie包含在請求中。 – ewall