通过代理使用套接字发出 HTTP 请求

Question

我想使用套接字发出 HTTP 请求。到目前为止，这是我的代码：

   #include "stdafx.h"
#ifndef UNICODE
#define UNICODE
#endif

#define _WINSOCK_DEPRECATED_NO_WARNINGS
#define WIN32_LEAN_AND_MEAN

#include <winsock2.h>
#include <ws2tcpip.h>
#include <stdio.h>
#include <iostream>

#pragma comment(lib, "ws2_32.lib")
using namespace std;

int main()
{
    try {
        WSADATA wsaData;
        int iResult = WSAStartup(MAKEWORD(2, 2), &wsaData);
        sockaddr_in clientService;


        SOCKET Socket = socket(AF_INET, SOCK_STREAM, 0);

        memset(&clientService, 0, sizeof(clientService));
        clientService.sin_addr.s_addr = inet_addr("83.233.53.59"); // Proxy IP
        clientService.sin_family = AF_INET;
        clientService.sin_port = htons(10200);

        if (bind(Socket, (struct sockaddr *) &clientService, sizeof(clientService)) < 0) {
            perror("bind");
            exit(1);
        }
        system("pause");
        return 0;
        struct hostent *host;
        host = gethostbyname("www.google.com");
        SOCKADDR_IN SockAddr;
        SockAddr.sin_port = htons(80);
        SockAddr.sin_family = AF_INET;
        // SockAddr.sin_addr.s_addr = *((unsigned long*)host->h_addr);
        memcpy(host->h_addr, &(SockAddr.sin_addr.s_addr), host->h_length);
        std::cout << "Connecting...\n";

        iResult = connect(Socket, (SOCKADDR *)& clientService, sizeof(clientService));
        if (iResult != 0) {
            std::cout << "Could not connect";
            getchar();
            return 1;
        }
        std::cout << "Connected.\n";
        send(Socket, "GET / HTTP / 1.1\r\nHost: www.google.com\r\nConnection: close\r\n\r\n", strlen("GET / HTTP / 1.1\r\nHost: www.google.com\r\nConnection: close\r\n\r\n"), 0);
        char buffer[10000];
        int nDataLength;
        while ((nDataLength = recv(Socket, buffer, 10000, 0)) > 0) {
            int i = 0;
            while (buffer[i] >= 32 || buffer[i] == '\n' || buffer[i] == '\r') {
                std::cout << buffer[i];
                i += 1;
            }
        }
        iResult = closesocket(Socket);
        WSACleanup();

        system("pause");
    }
    catch (...) {
        system("pause");

    }
    return 0;
}

但它不起作用，没有程序自行关闭而不给我留下网页的 HTML 源代码。怎么了？

我该如何解决？

Answer 1

这适用于我的机器，但我不在 Windows 机器上。我在freeBSD（OS X）机器上。在解决 gethostbyname 时遇到问题，不确定这是怎么回事，但这有效并连接并从 google 下载了代码。

#include <stdio.h>
#include <sys/types.h>
#include <sys/socket.h>
#include <netinet/in.h>
#include <arpa/inet.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>

#define _WINSOCK_DEPRECATED_NO_WARNINGS
#define WIN32_LEAN_AND_MEAN

//#include <winsock2.h>
//#include <ws2tcpip.h>
#include <stdio.h>
#include <iostream>

#pragma comment(lib, "ws2_32.lib")
using namespace std;

int main()
{
    try {
        //        WSADATA wsaData;
        //        int iResult = WSAStartup(MAKEWORD(2, 2), &wsaData);
        // sockaddr_in clientService;


        int Socket = socket(AF_INET, SOCK_STREAM, 0);
        /*
         memset(&clientService, 0, sizeof(clientService));
         clientService.sin_addr.s_addr = inet_addr("83.233.53.59"); // Proxy IP
         clientService.sin_family = AF_INET;
         clientService.sin_port = htons(10200);

         if (bind(Socket, (struct sockaddr *) &clientService, sizeof clientService) == -1) {
         perror("bind");
         exit(1);
         }
         system("pause");
         return 0;
         */
         const char hostname[] ="www.google.com";
         struct hostent * host;
//         host = gethostbyname(hostname);

        sockaddr_in SockAddr;
        memset(&SockAddr, 0, sizeof(SockAddr));
        SockAddr.sin_port = htons(80);
        SockAddr.sin_family = AF_INET;
        SockAddr.sin_addr.s_addr = inet_addr("83.233.53.59");
        //        memcpy(host->h_addr, &(SockAddr.sin_addr.s_addr), host->h_length);
        std::cout << "Connecting...\n";

        int iResult = connect(Socket, (struct sockaddr *)& SockAddr, sizeof(SockAddr));
        if (iResult != 0) {
            std::cout << "Could not connect";
            getchar();
            return 1;
        }
        std::cout << "Connected.\n";
        send(Socket, "GET / HTTP / 1.1\r\nHost: www.google.com\r\nConnection: close\r\n\r\n", strlen("GET / HTTP / 1.1\r\nHost: www.google.com\r\nConnection: close\r\n\r\n"), 0);
        char buffer[10000];
        int nDataLength;
        while ((nDataLength = recv(Socket, buffer, 10000, 0)) > 0) {
            int i = 0;
            while (buffer[i] >= 32 || buffer[i] == '\n' || buffer[i] == '\r') {
                std::cout << buffer[i];
                i += 1;
            }
        }
        iResult = close(Socket);
        //        WSACleanup();

        system("pause");
    }
    catch (...) {
        system("pause");

    }
    return 0;
}

http: 级别的身份验证失败，但输出如下：

Connecting...
Connected.
HTTP/1.0 401 Unauthorized
Server: uhttpd/1.0.0
Date: Thu, 17 Dec 2015 18:29:04 GMT
WWW-Authenticate: Basic realm="                 "
Content-Type: text/html; charset="UTF-8"
Connection: close

<HTML><HEAD><META http-equiv='Pragma' content='no-cache'><META http-equiv='Cache-Control' content='no-cache'><TITLE> 401 Authorization</TITLE>
<script language=javascript type=text/javascript>
function cancelevent()
{
sh: pause: command not found
Program ended with exit code: 0

Answer 2

可能会出错的一件事是，您的应用程序在以下循环期间访问越界数组索引时可能会崩溃：

while (buffer[i] >= 32 || buffer[i] == '\n' || buffer[i] == '\r') {
    ...
    i += 1;
}

您当前的代码不能保证buffer 包含一个会使您的循环终止的字节，因此它可能会无限期地继续。您必须通过在访问数组索引之前进行额外检查来防止这种情况。考虑到nDataLength 总是小于或等于sizeof(buffer)，试试这个：

while (i < nDataLength &&
    (buffer[i] >= 32 || buffer[i] == '\n' || buffer[i] == '\r'))
{
    // Do your printing.
    i++;
}

或者更简单：

while (buffer[i] >= 32 || buffer[i] == '\n' || buffer[i] == '\r')
{
    // Do your printing.
    i++;

    if (i >= nDataLength)
        break; // Exit the loop.
}

Answer 3

system("pause");
return 0;

此代码阻止执行任何后续操作。删除。

您的代码还有许多其他问题。例如，您将套接字绑定到代理地址。那没有意义。消除。即将连接socket，完全不需要绑定。

然后您向代理发送了一个无效的 GET 请求。在这种情况下，GET 请求应该包含完整的 URL，而不仅仅是相对 URL。

当您搜索空间等时，您超出了接收缓冲区。您需要通过 recv() 返回的计数来绑定该搜索。

等等。