Question

我有一项家庭作业，其中包括在Python中为网页实现代理缓存服务器。这是我的实现

from socket import *
import sys

def main():
    #Create a server socket, bind it to a port and start listening
    tcpSerSock = socket(AF_INET, SOCK_STREAM) #Initializing socket
    tcpSerSock.bind(("", 8030)) #Binding socket to port
    tcpSerSock.listen(5) #Listening for page requests
    while True:
        #Start receiving data from the client
        print 'Ready to serve...'
        tcpCliSock, addr = tcpSerSock.accept()
        print 'Received a connection from:', addr
        message = tcpCliSock.recv(1024)
        print message

        #Extract the filename from the given message
        filename = ""
        try:
            filename = message.split()[1].partition("/")[2].replace("/", "")
        except:
            continue
        fileExist = False

        try: #Check whether the file exists in the cache
            f = open(filename, "r")
            outputdata = f.readlines()
            fileExist = True
            #ProxyServer finds a cache hit and generates a response message
            tcpCliSock.send("HTTP/1.0 200 OK\r\n")
            tcpCliSock.send("Content-Type:text/html\r\n")
            for data in outputdata:
                tcpCliSock.send(data)
            print 'Read from cache'
        except IOError: #Error handling for file not found in cache
            if fileExist == False:

                c = socket(AF_INET, SOCK_STREAM) #Create a socket on the proxyserver

                try:
                    srv = getaddrinfo(filename, 80)
                    c.connect((filename, 80)) #https://docs.python.org/2/library/socket.html
                    # Create a temporary file on this socket and ask port 80 for
                    # the file requested by the client
                    fileobj = c.makefile('r', 0)
                    fileobj.write("GET " + "http://" + filename + " HTTP/1.0\r\n")
                    # Read the response into buffer
                    buffr = fileobj.readlines()
                    # Create a new file in the cache for the requested file.
                    # Also send the response in the buffer to client socket and the
                    # corresponding file in the cache
                    tmpFile = open(filename,"wb")
                    for data in buffr:
                        tmpFile.write(data)
                        tcpCliSock.send(data)
                except:
                    print "Illegal request"
            else: #File not found
                print "404: File Not Found"
        tcpCliSock.close() #Close the client and the server sockets

main()

我将浏览器配置为使用我的代理服务器

但我运行它的问题是，无论我尝试访问哪个网页，它都会返回初始连接的404错误，然后连接重置错误以及后续连接。我不知道为什么这样任何帮助都会非常感谢，谢谢！

Answer 1

您的代码存在很多问题。

您的网址解析器非常繁琐。而不是行

filename = message.split()[1].partition("/")[2].replace("/", "")

我会用

import re
parsed_url = re.match(r'GET\s+http://(([^/]+)(.*))\sHTTP/1.*$', message)
local_path = parsed_url.group(3)
host_name = parsed_url.group(2)
filename = parsed_url.group(1)

如果你在那里遇到异常，你应该抛出一个错误，因为这是你的代理人不理解的请求（例如POST）。

将请求汇编到目标服务器时，请使用

fileobj.write("GET {object} HTTP/1.0\n".format(object=local_path))
fileobj.write("Host: {host}\n\n".format(host=host_name))

您还应该包含原始请求中的一些标题行，因为它们可以对返回的内容产生重大影响。

此外，您当前使用所有标题行缓存整个响应，因此在从缓存提供服务时不应添加自己的响应。

无论如何，您所拥有的内容并不起作用，因为无法保证您将获得200和text/html内容。您应该检查响应代码，如果确实获得了200，则只缓存。

缓存代理服务器使用www.google.com返回404

1 个答案: