Python的httplib
創建隧道時實際上忽略了這些標頭。這是哈克,但你可以攔截下來併合並與實際HTTP響應的頭部的「頭」行:
import socket
import httplib
import requests
from requests.packages.urllib3.connection import HTTPSConnection
from requests.packages.urllib3.connectionpool import HTTPSConnectionPool
from requests.packages.urllib3.poolmanager import ProxyManager
from requests.adapters import HTTPAdapter
class ProxyHeaderHTTPSConnection(HTTPSConnection):
def __init__(self, *args, **kwargs):
super(ProxyHeaderHTTPSConnection, self).__init__(*args, **kwargs)
self._proxy_headers = []
def _tunnel(self):
self.send("CONNECT %s:%d HTTP/1.0\r\n" % (self._tunnel_host, self._tunnel_port))
for header, value in self._tunnel_headers.iteritems():
self.send("%s: %s\r\n" % (header, value))
self.send("\r\n")
response = self.response_class(self.sock, strict=self.strict, method=self._method)
version, code, message = response._read_status()
if version == "HTTP/0.9":
# HTTP/0.9 doesn't support the CONNECT verb, so if httplib has
# concluded HTTP/0.9 is being used something has gone wrong.
self.close()
raise socket.error("Invalid response from tunnel request")
if code != 200:
self.close()
raise socket.error("Tunnel connection failed: %d %s" % (code, message.strip()))
self._proxy_headers = []
while True:
line = response.fp.readline(httplib._MAXLINE + 1)
if len(line) > httplib._MAXLINE:
raise LineTooLong("header line")
if not line or line == '\r\n':
break
# The line is a header, save it
if ':' in line:
self._proxy_headers.append(line)
def getresponse(self, buffering=False):
response = super(ProxyHeaderHTTPSConnection, self).getresponse(buffering)
response.msg.headers.extend(self._proxy_headers)
return response
class ProxyHeaderHTTPSConnectionPool(HTTPSConnectionPool):
ConnectionCls = ProxyHeaderHTTPSConnection
class ProxyHeaderProxyManager(ProxyManager):
def _new_pool(self, scheme, host, port):
assert scheme == 'https'
return ProxyHeaderHTTPSConnectionPool(host, port, **self.connection_pool_kw)
class ProxyHeaderHTTPAdapter(HTTPAdapter):
def proxy_manager_for(self, proxy, **proxy_kwargs):
if proxy in self.proxy_manager:
manager = self.proxy_manager[proxy]
else:
proxy_headers = self.proxy_headers(proxy)
manager = self.proxy_manager[proxy] = ProxyHeaderProxyManager(
proxy_url=proxy,
proxy_headers=proxy_headers,
num_pools=self._pool_connections,
maxsize=self._pool_maxsize,
block=self._pool_block,
**proxy_kwargs)
return manager
然後,您可以將適配器安裝到會話:
session = requests.Session()
session.mount('https://', ProxyHeaderHTTPAdapter())
response = session.get('https://example.com', proxies={...})
代理的標題將被合併到響應頭中,所以它應該像代理直接修改響應頭那樣工作。
這張照片有兩件事是錯誤的。首先,對CONNECT的響應有標題是完全正確的。其次,你不應該有任何負載,因爲接下來是客戶端發起的TLS握手。 – Adrien
@Adrien:正如我所說的,'httplib'丟棄'CONNECT'後發送的頭文件。這不應該,但它確實。至於有效載荷部分,我同意,這是錯誤的。我已將其刪除。 – Blender