使用Winsock2通过SOCKS5下载HTTP网站

您对initPacket1Length和的计算initPacket2Length是错误的，因此它们都分别设置为4，而不是3和10。这是因为您正在传递char*指针，sizeof而不是char[]像期望的那样传递缓冲区（sizeof()在32位系统上，任何指针类型为4，在64位系统上为8）。

这意味着第一个数据包将发送4个字节而不是3个字节，但是您没有分配4个字节，因此您将在第4个字节中发送垃圾（很幸运，您的代码并没有完全崩溃）。由于SOCKS服务器最初只期望3个字节，因此第4个字节和随后的4个字节被解释为格式错误的5字节命令，该命令失败。

由于在分配缓冲区时使用的是硬编码的大小，因此应该仅硬编码要匹配的长度。

//int initPacket1Length = sizeof(initPacket1) / sizeof(initPacket1[0]);
int initPacket1Length = 3;

//int initPacket2Length = sizeof(initPacket2) / sizeof(initPacket2[0]);
int initPacket2Length = 10;

同样，当memset()使用固定缓冲区时，使用strlen()来计算大小是完全错误的。您应该sizeof改为使用。

//memset( &reply1, '\0' , strlen((const char *)reply1) );
memset( &reply1, '\0' , sizeof(reply1));

您还忽略了send()和的返回值recv()。它们返回实际发送/接收的字节数。但是，您只检查失败的返回值，而不是成功。TCP是一个流媒体传输，send()并且recv()可以发送/接收的字节数更少比的要求，所以你必须考虑这一点。

话虽这么说，请尝试以下更类似的方法：

#include <winsock2.h>
#include <string>
#include <iostream>

#include "util.hpp"

using namespace std;

int sendData(SOCKET s, const void *buffer, int buflen)
{
    const char *pbuf = (const char*) buffer;
    while (buflen > 0)
    {
        int numSent = send(s, pbuf, buflen, 0);
        if (numSent == SOCKET_ERROR)
            return SOCKET_ERROR;
        pbuf += numSent;
        buflen -= numSent;
    }
    return 1;
}

int recvData(SOCKET s, void *buffer, int buflen)
{
    char *pbuf = (char*) buffer;
    while (buflen > 0)
    {
        int numRecv = recv(s, pbuf, buflen, 0);
        if (numRecv == SOCKET_ERROR)
            return SOCKET_ERROR;
        if (numRecv == 0)
            return 0;
        pbuf += numRecv;
        buflen -= numRecv;
    }
    return 1;
}

int main(void)
{
    //SOCKS5 info
    u_short sockPort = 45554;
    std::string sockIp = "xx.xx.xx.xx";

    //Destination info
    u_short destPort = 80;
    std::string destIPorHost = "checkip.dyndns.com";

    //Check to see if winsock2 is available
    WSADATA wsaData;
    if (WSAStartup(MAKEWORD(2,0), &wsaData) != 0)
    {
        cout << "WSA Startup Failed";
        return -1;
    }

    if (LOBYTE(wsaData.wVersion) < 2)
    {
        cout << "WSA Version error!";
        return -1;
    }

    ///////////////////////////////////////////////////////////////////////////////////////////
    //Init sockaddr for SOCKS5
    cout << "Initialize sock_addr for socks5 connection...";
    sockaddr_in sock;
    sock.sin_family = AF_INET;                      // host byte order
    sock.sin_port = htons(sockPort);                // short, network byte order
    if (!utils::getHostIP(sock.sin_addr.S_un.S_addr, sockIp)) // Write ip address in the right format
    {
        cout << "fail";
        return -1;
    }
    cout << "done" << endl;

    /////////////////////////////////////////////////////////////////////////////////////////////
    //Init sockaddr for destination server
    cout << "Initialize sockaddr for destination server...";
    sockaddr_in dest = {0};
    dest.sin_family = AF_INET;
    dest.sin_port = htons(destPort);
    if (!utils::getHostIP(dest.sin_addr.S_un.S_addr, destIPorHost)) // Write ip address in the right format
    {
        cout << "fail";
        return -1;
    }
    cout << "done" << endl;

    ////////////////////////////////////////////////////////////////////////////////////////////////
    //Time to connect to SOCKS5 server

    //Creating socket handler
    cout << "Creating socket handler...";
    SOCKET hSocketSock = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
    if (hSocketSock == INVALID_SOCKET)
    {
        cout << "fail";
        return -1;
    }
    cout << "done" << endl;

    cout << "Connecting to socks server...";
    if (connect(hSocketSock, reinterpret_cast<sockaddr *>(&sock), sizeof(sock)) != 0)
    {
        cout << "failed";
        return -1;
    }
    cout << "done" << endl;

    //Documentation: https://tools.ietf.org/html/rfc1928

    //We have to send first packet which tell to SOCKS5 to enter on
    //sub-negociation mode so we can connect to actual destination server

    //    The client connects to the server, and sends a version
    //    identifier/method selection message:
    //    +----+----------+----------+
    //    |VER | NMETHODS | METHODS  |
    //    +----+----------+----------+
    //    | 1  |    1     | 1 to 255 |
    //    +----+----------+----------+

    //Allocate space for the first initialize packet and his replay
    char initPacket1[3];        
    initPacket1[0] = 5;  //SOCKS Version. [VER]
    initPacket1[1] = 1;  //No. of methods [NMETHODS]
    initPacket1[2] = 0;  //No auth required [X’00’]

    //Now we are sending the packet we just created
    cout << "Sending first init packet...";
    if (sendData(hSocketSock, initPacket1, 3) < 0)
    {
        cout << "failed";
        closesocket(hSocketSock);
        return -1;
    }
    cout << "done" << endl;

    //And our expected replay format:
    //
    //    The server selects from one of the methods given in METHODS, and
    //    sends a METHOD selection message:
    //    +----+--------+
    //    |VER | METHOD |
    //    +----+--------+
    //    | 1  |   1    |
    //    +----+--------+

    //Receiving response from server

    char reply1[2];
    cout << "Waiting for response...";
    if (recvData(hSocketSock, reply1, 2) <= 0)
    {
        cout << "failed";
        closesocket(hSocketSock);
        return -1;
    }
    cout << "done" << endl;

    //reply[0] = our version
    //reply[1] = out method. [X’00’ NO AUTHENTICATION REQUIRED]
    if( !(reply1[0] == 5 && reply1[1] == 0) )
    {
        cout << "Error: bad result on reply:" << (int)reply1[0] << " " << (int)reply1[1] << endl;
        closesocket(hSocketSock);
        return -1;
    }

    //We have to build initialize packet. This will transmit to SOCKS5 server
    //the web server we want to connect to.
    //
    //    The SOCKS request is formed as follows:
    //
    //    +----+-----+-------+------+----------+----------+
    //    |VER | CMD |  RSV  | ATYP | DST.ADDR | DST.PORT |
    //    +----+-----+-------+------+----------+----------+
    //    | 1  |  1  | X’00’ |   1  | Variable |    2     |
    //    +----+-----+-------+------+----------+----------+
    //
    //    Where:
    //    o VER protocol version: X’05’
    //    o CMD
    //    o CONNECT X’01’
    //    o BIND X’02’
    //    o UDP ASSOCIATE X’03’
    //    o RSV RESERVED
    //    o ATYP address type of following address
    //    o IP V4 address: X’01’
    //    o DOMAINNAME: X’03’
    //    o IP V6 address: X’04’
    //    o DST.ADDR desired destination address
    //    o DST.PORT desired destination port in network octet
    //    order

    //Building that packet
    char initPacket2[10];
    initPacket2[0] = 5; //SOCKS Version;
    initPacket2[1] = 1; //1 = CONNECT, 2 = BIND, 3 = UDP ASSOCIATE;
    initPacket2[2] = 0; //Reserved byte
    initPacket2[3] = 1; //1 = IPv4, 3 = DOMAINNAME, 4 = IPv6

    memcpy(&initPacket2[4], &dest.sin_addr.S_un.S_addr, 4);
    memcpy(&initPacket2[8], &dest.sin_port, 2);

    //Send the second init packet to server. This will inform the SOCKS5 server
    //what is our target.
    cout << "Sending second init packet...";
    if (sendData(hSocketSock, initPacket2, 10) < 0)
    {
        cout << "failed";
        closesocket(hSocketSock);
        return -1;
    }
    cout << "done" << endl;

    //Reading the response
    //Expected response format:

    //    The SOCKS request information is sent by the client as soon as it has
    //    established a connection to the SOCKS server, and completed the
    //    authentication negotiations. The server evaluates the request, and
    //    returns a reply formed as follows:

    //    +----+-----+-------+------+----------+----------+
    //    |VER | REP |  RSV  | ATYP | BND.ADDR | BND.PORT |
    //    +----+-----+-------+------+----------+----------+
    //    | 1  |  1  | X’00’ |  1   | Variable |   2      |
    //    +----+-----+-------+------+----------+----------+
    //                              Where:
    //    o VER protocol version: X’05’
    //    o REP Reply field:
    //        o X’00’ succeeded
    //        o X’01’ general SOCKS server failure
    //        o X’02’ connection not allowed by ruleset
    //        o X’03’ Network unreachable
    //        o X’04’ Host unreachable
    //        o X’05’ Connection refused
    //        o X’06’ TTL expired
    //        o X’07’ Command not supported
    //        o X’08’ Address type not supported
    //        o X’09’ to X’FF’ unassigned
    //    ......................................

    char reply2[10];
    cout << "Waiting for response...";
    if (recvData(hSocketSock, reply2, 10) <= 0)
    {
        cout << "failed";
        closesocket(hSocketSock);
        return -1;
    }
    cout << "done" << endl;

    cout << "Returned packets: " << endl;
    cout << "VER: " << (int)reply2[0] << endl;
    cout << "REP: " << (int)reply2[1] << endl;
    cout << "RSV: " << (int)reply2[2] << endl;
    cout << "ATY: " << (int)reply2[3] << endl;
    cout << endl;

    // use hSocketSock as needed for subsequent traffic...

    closesocket(hSocketSock);
    return 0;
}

另外，为什么www.要从主机名中删除？这是实际主机名的一部分，不应删除。它确实有所作为，因为www.domain.com可能解析为与IP地址不同的IP地址domain.com。

通过让SOCKS服务器为您解析主机名，可以稍微简化应用程序的开销。有时，最终客户端解析的IP与代理解析的IP不同，这取决于代理在网络中的位置。由于代理是与目标主机进行实际连接的代理，因此它应该是解析IP的代理：

#include <winsock2.h>
#include <string>
#include <iostream>

#include "util.hpp"

using namespace std;

int sendData(SOCKET s, const void *buffer, int buflen)
{
    const char *pbuf = (const char*) buffer;
    while (buflen > 0)
    {
        int numSent = send(s, pbuf, buflen, 0);
        if (numSent == SOCKET_ERROR)
            return SOCKET_ERROR;
        pbuf += numSent;
        buflen -= numSent;
    }
    return 1;
}

int recvData(SOCKET s, void *buffer, int buflen)
{
    char *pbuf = (char*) buffer;
    while (buflen > 0)
    {
        int numRecv = recv(s, pbuf, buflen, 0);
        if (numRecv == SOCKET_ERROR)
            return SOCKET_ERROR;
        if (numRecv == 0)
            return 0;
        pbuf += numRecv;
        buflen -= numRecv;
    }
    return 1;
}

int main(void)
{
    //SOCKS5 info
    u_short sockPort = 45554;
    std::string sockIp = "xx.xx.xx.xx";

    //Destination info
    u_short destPort = 80;
    std::string destIPorHost = "checkip.dyndns.com";

    //Check to see if winsock2 is available
    WSADATA wsaData;
    if (WSAStartup(MAKEWORD(2,0), &wsaData) != 0)
    {
        cout << "WSA Startup Failed";
        return -1;
    }

    if (LOBYTE(wsaData.wVersion) < 2)
    {
        cout << "WSA Version error!";
        return -1;
    }

    ///////////////////////////////////////////////////////////////////////////////////////////
    //Init sockaddr for SOCKS5
    cout << "Initialize sock_addr for socks5 connection...";
    sockaddr_in sock;
    sock.sin_family = AF_INET;                      // host byte order
    sock.sin_port = htons(sockPort);                // short, network byte order
    if (!utils::getHostIP(sock.sin_addr.S_un.S_addr, sockIp)) // Write ip address in the right format
    {
        cout << "fail";
        return -1;
    }
    cout << "done" << endl;

    ////////////////////////////////////////////////////////////////////////////////////////////////
    //Time to connect to SOCKS5 server

    //Creating socket handler
    cout << "Creating socket handler...";
    SOCKET hSocketSock = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
    if (hSocketSock == INVALID_SOCKET)
    {
        cout << "fail";
        return -1;
    }
    cout << "done" << endl;

    cout << "Connecting to socks server...";
    if (connect(hSocketSock, reinterpret_cast<sockaddr *>(&sock), sizeof(sock)) != 0)
    {
        cout << "failed";
        closesocket(hSocketSock);
        return -1;
    }
    cout << "done" << endl;

    //Documentation: https://tools.ietf.org/html/rfc1928

    //We have to send first packet which tell to SOCKS5 to enter on
    //sub-negociation mode so we can connect to actual destination server

    //    The client connects to the server, and sends a version
    //    identifier/method selection message:
    //    +----+----------+----------+
    //    |VER | NMETHODS | METHODS  |
    //    +----+----------+----------+
    //    | 1  |    1     | 1 to 255 |
    //    +----+----------+----------+

    //Allocate space for the first initialize packet and his replay
    char initPacket1[3];        
    initPacket1[0] = 5;  //SOCKS Version. [VER]
    initPacket1[1] = 1;  //No. of methods [NMETHODS]
    initPacket1[2] = 0;  //No auth required [X’00’]

    //Now we are sending the packet we just created
    cout << "Sending first init packet...";
    if (sendData(hSocketSock, initPacket1, 3) < 0)
    {
        cout << "failed";
        closesocket(hSocketSock);
        return -1;
    }
    cout << "done" << endl;

    //And our expected replay format:
    //
    //    The server selects from one of the methods given in METHODS, and
    //    sends a METHOD selection message:
    //    +----+--------+
    //    |VER | METHOD |
    //    +----+--------+
    //    | 1  |   1    |
    //    +----+--------+

    //Receiving response from server

    char reply1[2];
    cout << "Waiting for response...";
    if (recvData(hSocketSock, reply1, 2) <= 0)
    {
        cout << "failed";
        closesocket(hSocketSock);
        return -1;
    }
    cout << "done" << endl;

    //reply[0] = our version
    //reply[1] = out method. [X’00’ NO AUTHENTICATION REQUIRED]
    if( !(reply1[0] == 5 && reply1[1] == 0) )
    {
        cout << "Error: bad result on reply:" << (int)reply1[0] << " " << (int)reply1[1] << endl;
        closesocket(hSocketSock);
        return -1;
    }

    //We have to build initialize packet. This will transmit to SOCKS5 server
    //the web server we want to connect to.
    //
    //    The SOCKS request is formed as follows:
    //
    //    +----+-----+-------+------+----------+----------+
    //    |VER | CMD |  RSV  | ATYP | DST.ADDR | DST.PORT |
    //    +----+-----+-------+------+----------+----------+
    //    | 1  |  1  | X’00’ |   1  | Variable |    2     |
    //    +----+-----+-------+------+----------+----------+
    //
    //    Where:
    //    o VER protocol version: X’05’
    //    o CMD
    //    o CONNECT X’01’
    //    o BIND X’02’
    //    o UDP ASSOCIATE X’03’
    //    o RSV RESERVED
    //    o ATYP address type of following address
    //    o IP V4 address: X’01’
    //    o DOMAINNAME: X’03’
    //    o IP V6 address: X’04’
    //    o DST.ADDR desired destination address
    //    o DST.PORT desired destination port in network octet
    //    order

    int hostlen = max(destIPorHost.size(), 255);

    //Building that packet
    char *initPacket2 = new char[7+hostlen];
    initPacket2[0] = 5; //SOCKS Version;
    initPacket2[1] = 1; //1 = CONNECT, 2 = BIND, 3 = UDP ASSOCIATE;
    initPacket2[2] = 0; //Reserved byte
    initPacket2[3] = 3; //1 = IPv4, 3 = DOMAINNAME, 4 = IPv6
    initPacket2[4] = (char) hostlen;
    memcpy(&initPacket2[5], destIPorHost.c_str(), hostlen);
    *((u_short*) &(initPacket2[5+hostlen])) = htons(destPort);

    //Send the second init packet to server. This will inform the SOCKS5 server
    //what is our target.
    cout << "Sending second init packet...";
    if (sendData(hSocketSock, initPacket2, 7+hostlen) < 0)
    {
        cout << "failed";
        delete[] initPacket2;
        closesocket(hSocketSock);
        return -1;
    }
    cout << "done" << endl;

    delete[] initPacket2;

    //Reading the response
    //Expected response format:

    //    The SOCKS request information is sent by the client as soon as it has
    //    established a connection to the SOCKS server, and completed the
    //    authentication negotiations. The server evaluates the request, and
    //    returns a reply formed as follows:

    //    +----+-----+-------+------+----------+----------+
    //    |VER | REP |  RSV  | ATYP | BND.ADDR | BND.PORT |
    //    +----+-----+-------+------+----------+----------+
    //    | 1  |  1  | X’00’ |  1   | Variable |   2      |
    //    +----+-----+-------+------+----------+----------+
    //                              Where:
    //    o VER protocol version: X’05’
    //    o REP Reply field:
    //        o X’00’ succeeded
    //        o X’01’ general SOCKS server failure
    //        o X’02’ connection not allowed by ruleset
    //        o X’03’ Network unreachable
    //        o X’04’ Host unreachable
    //        o X’05’ Connection refused
    //        o X’06’ TTL expired
    //        o X’07’ Command not supported
    //        o X’08’ Address type not supported
    //        o X’09’ to X’FF’ unassigned
    //    ......................................

    char reply2[262];
    cout << "Waiting for response...";
    if (recvData(hSocketSock, reply2, 4) <= 0)
    {
        cout << "failed";
        closesocket(hSocketSock);
        return -1;
    }

    if (!(reply2[0] == 5 && reply2[1] == 0))
    {
        cout << "failed";
        closesocket(hSocketSock);
        return -1;
    }

    int replylen = 4;
    switch (reply2[3])
    {
        case 1:
        {
            if (recvData(hSocketSock, &reply2[replylen], 4) <= 0)
            {
                cout << "failed";
                closesocket(hSocketSock);
                return -1;
            }
            replylen += 4;
            break;
        }

        case 3:
        {
            if (recvData(hSocketSock, &reply2[replylen], 1) <= 0)
            {
                cout << "failed";
                closesocket(hSocketSock);
                return -1;
            }

            hostlen = reply2[replylen];
            ++replylen;

            if (recvData(hSocketSock, &reply2[replylen], hostlen) <= 0)
            {
                cout << "failed";
                closesocket(hSocketSock);
                return -1;
            }

            replylen += hostlen;
            break;
        }

        case 4:
        {
            if (recvData(hSocketSock, &reply2[replylen], 16) <= 0)
            {
                cout << "failed";
                closesocket(hSocketSock);
                return -1;
            }
            replylen += 16;
            break;
        }
    }

    if (recvData(hSocketSock, &reply2[replylen], 2) <= 0)
    {
        cout << "failed";
        closesocket(hSocketSock);
        return -1;
    }

    cout << "done" << endl;

    // use hSocketSock as needed for subsequent traffic...

    closesocket(hSocketSock);
    return 0;
}