超時無法使用urllib2，socks5代理和socksipy

Question

我在Python 2.6中將ocklib和urllib2一起使用。 一切正常，除了我碰到一個懸掛URL的超時之外。 urllib2函數超時參數或全局套接字默認超時均無效。 我什至嘗試在下面的子處理程序中以多種不同方式設置超時，但沒有成功。 有任何想法嗎？

這是一個測試腳本（假設您已經安裝了socksipy項目並將其添加到系統路徑中）：

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

這對我有用：

socks.socket.setdefaulttimeout(7)

您應該避免直接編輯python襪子庫。

Answer 2

事實證明，我上面提到的“掛起/超時”問題實際上是sockssipy socks.py代碼中的“阻塞”問題。 如果命中的端點仍然響應200，但不發送任何數據（0字節），則socks.py將阻止，原因是這樣寫的。 這是創建自己的超時之前和之后的：

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之后超時 ：

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