Question

我在Python 2.6中使用socksipy和urllib2。除了我点击挂起的URL时超时，一切正常。 urllib2函数超时参数或全局套接字默认超时都不起作用。我甚至尝试在下面的sublcassed处理程序中以多种不同的方式设置超时，但没有成功。有什么想法吗？

这是一个测试脚本（假设您安装了socksipy项目并将其添加到系统路径中）：

import os, sys
import httplib
sys.path.append( "/parent/path/to/socksipy/project" )
import socks # import socksipy
import socket
socket.setdefaulttimeout(30.0)
import urllib2

class SocksiPyConnection(httplib.HTTPConnection):
    def __init__(self, proxytype, proxyaddr, proxyport = None, rdns = False, username = None, password = None, *args, **kwargs):
        self.proxyargs = (proxytype, proxyaddr, proxyport, rdns, username, password)
        httplib.HTTPConnection.__init__(self, *args, **kwargs)

    def connect(self):
        self.sock = socks.socksocket()
        self.sock.setproxy(*self.proxyargs) 
        if isinstance(self.timeout, float):
            self.sock.settimeout(self.timeout)
        self.sock.connect((self.host, self.port))

class SocksiPyHandler(urllib2.HTTPHandler):
    def __init__(self, *args, **kwargs):
        self.args = args
        self.kw = kwargs
        urllib2.HTTPHandler.__init__(self)

    def http_open(self, req):
        def build(host, port=None, strict=None, timeout=0):
            conn = SocksiPyConnection(*self.args, host=host, port=port, strict=strict, timeout=timeout, **self.kw)
            return conn
        return self.do_open(build, req)

if __name__ == '__main__':

    #
    # this one works for non-hanging URL
    #
    proxyhost = "responder.w2"
    proxyport = 1050
    socks.setdefaultproxy(socks.PROXY_TYPE_SOCKS5, proxyhost, int(proxyport))
    socket.socket = socks.socksocket
    resp = urllib2.urlopen("http://www.google.com", timeout=30.0)
    # hang here
    print "returned 1"


    #
    # one way to go about it for a hanging URL
    #
    proxyhost = "responder.w2"
    proxyport = 1050
    socks.setdefaultproxy(socks.PROXY_TYPE_SOCKS5, proxyhost, int(proxyport))
    socket.socket = socks.socksocket
    resp = urllib2.urlopen("http://erma.orr.noaa.gov/cgi-bin/mapserver/charts?version=1.1.1&service=wms&request=GetCapabilities", timeout=30.0)
    # it hangs here
    print "returned 2"


    #  
    # another way to go about it for hanging URL
    #
    proxyhost = "responder.w2"
    proxyport = 1050
    opener = urllib2.build_opener(SocksiPyHandler(socks.PROXY_TYPE_SOCKS5, proxyhost, int(proxyport)) )
    resp = opener.open("http://erma.orr.noaa.gov/cgi-bin/mapserver/charts?version=1.1.1&service=wms&request=GetCapabilities", timeout=30.0)
    # it hangs here
    print "returned 3"

Answer 1

这对我有用：

socks.socket.setdefaulttimeout(7)

你应该避免直接编辑python socks库。

Answer 2

事实证明我上面提到的“挂起/超时”问题实际上是sockssipy socks.py代码中的“阻塞”问题。如果您正在命中仍然以200响应但没有发送数据（0字节）的端点，那么socks.py将阻止导致它的编写方式。这是创建自己的超时之前和之后：

socks.py之前：

def __recvall(self, bytes):
    """__recvall(bytes) -> data
    Receive EXACTLY the number of bytes requested from the socket.
    Blocks until the required number of bytes have been received.
    """
    data = ""
    while len(data) < bytes:
       data = data + self.recv(bytes-len(data))
    return data

socks.py AFTER with timeout ：

def __recvall(self, bytes):
    """__recvall(bytes) -> data
    Receive EXACTLY the number of bytes requested from the socket.
    Blocks until the required number of bytes have been received.
    """
    data = self.recv(bytes, socket.MSG_WAITALL)
    if type(data) not in (str, unicode) or len(data) != bytes:
        raise socket.timeout('timeout')
    return data

使用urllib2，socks5代理和socksipy超时无效

2 个答案: