使用 Winsock 接收分块的 HTTP 数据

Posted

技术标签:

【中文标题】使用 Winsock 接收分块的 HTTP 数据【英文标题】:Receiving Chunked HTTP Data With Winsock 【发布时间】:2011-11-06 04:05:56 【问题描述】:

我在使用 winsock 读取一些分块的 HTTP 响应数据时遇到问题。 我发送请求很好并得到以下回复:

HTTP/1.1 200 OK
Server: LMAX/1.0
Content-Type: text/xml; charset=utf-8
Transfer-Encoding: chunked
Date: Mon, 29 Aug 2011 16:22:19 GMT

使用winsock recv。然而,此时它只是挂起。我让侦听器在无限循环中运行,但没有收到任何内容。

我认为这是一个 C++ 问题,但也可能与我通过 stunnel 推送连接以将其包裹在 HTTPS 中的事实有关。我有一个使用 C# 中的一些库的测试应用程序,它可以通过 stunnel 完美运行。我很困惑为什么我的循环在初始接收后没有接收到 C++ 分块数据。

这是有问题的循环...在上面的分块 ok 响应之后调用...

while(true)

    recvBuf= (char*)calloc(DEFAULT_BUFLEN, sizeof(char)); 
    iRes = recv(ConnectSocket, recvBuf, DEFAULT_BUFLEN, 0);
    cout << WSAGetLastError() << endl;
    cout << "Recv: " << recvBuf << endl;
    if (iRes==SOCKET_ERROR)
    
        cout << recvBuf << endl;
        err = WSAGetLastError();
        wprintf(L"WSARecv failed with error: %d\n", err);
        break;
         


有什么想法吗?

【问题讨论】:

我建议您将代码更改为不在循环中分配,否则您会泄漏内存,一次一个 DEFAULT_BUFLEN。另外,循环的停止条件是什么?您是否有可能在到达recv 之前消耗了数据? 是的,我知道它正在泄漏内存,但我现在对此并不太在意。我可以轻松地将其切换到 memset。每次接收后我都会进行打印,这表明数据永远不会到达。 如果您在此位之前发布代码可能会有所帮助,以查看您是否不小心使用了数据。另请注意,如果recv 返回错误,则永远不会修改recvBuf,因此打印毫无意义。 cout 【参考方案1】:

您需要更改阅读代码。您无法像尝试那样使用固定长度的缓冲区读取chunked 数据。数据以可变长度的块发送,其中每个块都有一个标头,以字节为单位指定块的实际长度,数据的最终块的长度为 0。您需要读取分块的标头才能正确处理块。请阅读RFC 2616 Section 3.6.1。你的逻辑需要更像下面的伪代码:

send request;

status = recv() a line of text until CRLF;
parse status as needed;
response-code = extract response-code from status;
response-version = extract response-version from status;

do

    line = recv() a line of text until CRLF;
    if (line is blank)
        break;
    store line in headers list;

while (true);

parse headers list as needed;

if ((response-code is not in [1xx, 204, 304]) and (request was not "HEAD"))

    if (Transfer-Encoding header is present and not "identity")
    
        do
        
            line = recv a line of text until CRLF;
            length = extract length from line;
            extensions = extract extensions from line;
            process extensions as needed; // optional
            if (length == 0)
                break;
            recv() length number of bytes into destination buffer;
            recv() and discard bytes until CRLF;
        
        while (true);

        do
        
            line = recv a line of text until CRLF;
            if (line is blank)
                break;
            store line in headers list as needed;
        
        while (true);

        re-parse headers list as needed;
    
    else if (Content-Length header is present)
    
        recv() Content-Length number of bytes into destination buffer;
    
    else if (Content-Type header starts with "multipart/")
    
        boundary = extract boundary from Content-Type's "boundary" attribute;
        recv() data into destination buffer until MIME termination boundary is reached;
    
    else
    
        recv() data into destination buffer until disconnected;
    


if (not disconnected)

    if (response-version is "HTTP/1.1")
    
        if (Connection header is "close")
            close connection;
    
    else
    
        if (Connection header is not "keep-alive")
            close connection;
    


check response-code for errors;
process destination buffer, per info in headers list;

【讨论】:

【参考方案2】:

确实,您没有收到分块,但内容是分块的。您必须为自己绘制一张图片,您收到的任何缓冲区可能看起来如何。这不像你当时收到一大块。有时你有前一个块的一些数据,表示新块大小的行,后面是一些块数据。其他时候,您只收到一点块数据。另一次是一些块数据和表示新块的行的一部分等。想象最坏的情况,这并不容易。阅读:http://www.jmarshall.com/easy/http/

在您可以使用以下代码之前接收所有标题,直到空行。缓冲区中内容开始的位置是nContentStart。该代码使用了一些我无法共享的内部类,但您应该明白这一点;)据我测试,它按预期工作并且不会泄漏内存。虽然这并不容易,但我不能完全确定!

    if (bChunked)
    
        int nOffset = nContentStart;
        int nChunkLen = 0;
        int nCopyLen;

        while (true)
        
            if (nOffset >= nDataLen)
                pData->SetSize(0); Close(); ASSERTRETURN(false);

            // copy data of previous chunk to caller's buffer

            if (nChunkLen > 0)
            
                nCopyLen = min(nChunkLen, nDataLen - nOffset);
                n = pData->GetSize();
                pData->SetSize(n + nCopyLen);
                memcpy(pData->GetPtr() + n, buf.GetPtr() + nOffset, nCopyLen);
                nChunkLen -= nCopyLen;
                ASSERT(nChunkLen >= 0);

                nOffset += nCopyLen;
                if (nChunkLen == 0)
                    nOffset += strlen(lpszLineBreak);
                ASSERT(nOffset <= nDataLen);
            

            // when previous chunk is copied completely, process new chunk

            if (nChunkLen == 0 && nOffset < nDataLen)
            
                // chunk length is specified on first line

                p1 = buf.GetPtr() + nOffset;
                p2 = strstr(p1, lpszLineBreak);

                while (!p2) // if we can't find the line break receive more data until we do
                
                    buf.SetSize(nDataLen + RECEIVE_BUFFER_SIZE + 1);
                    nReceived = m_socket.Receive((BYTE*)buf.GetPtr() + nDataLen, RECEIVE_BUFFER_SIZE);

                    if (nReceived == -1)
                        pData->SetSize(0); Close(); ASSERTRETURN(false); // connection error
                    if (nReceived == 0)
                        pData->SetSize(0); Close(); ASSERTRETURN(false); // all data already received but did not find line break

                    nDataLen += nReceived;
                    buf[nDataLen] = 0;

                    p1 = buf.GetPtr() + nOffset; // address of buffer likely changed
                    p2 = strstr(p1, lpszLineBreak);
                

                *p2 = 0;
                p2 += strlen(lpszLineBreak);

                p3 = strchr(p1, ';');
                if (p3)
                    *p3 = 0;

                if (sscanf(p1, "%X", &nChunkLen) != 1)
                    pData->SetSize(0); Close(); ASSERTRETURN(false);

                if (nChunkLen < 0)
                    pData->SetSize(0); Close(); ASSERTRETURN(false);

                if (nChunkLen == 0)
                    break; // last chunk received

                // copy the following chunk data to caller's buffer

                nCopyLen = min(nChunkLen, buf.GetPtr() + nDataLen - p2);
                n = pData->GetSize();
                pData->SetSize(n + nCopyLen);
                memcpy(pData->GetPtr() + n, p2, nCopyLen);
                nChunkLen -= nCopyLen;
                ASSERT(nChunkLen >= 0);

                nOffset = (p2 - buf.GetPtr()) + nCopyLen;
                if (nChunkLen == 0)
                    nOffset += strlen(lpszLineBreak);

                if (nChunkLen == 0 && nOffset < nDataLen)
                    continue; // a new chunk starts in this buffer at nOffset, no need to receive more data
            

            // receive more data

            buf.SetSize(RECEIVE_BUFFER_SIZE + 1);
            nDataLen = m_socket.Receive((BYTE*)buf.GetPtr(), RECEIVE_BUFFER_SIZE);
            if (nDataLen == -1)
                pData->SetSize(0); Close(); ASSERTRETURN(false);
            if (nDataLen == 0)
                pData->SetSize(0); Close(); ASSERTRETURN(false);
            buf[nDataLen] = 0;

            nOffset = 0;
        

        // TODO: receive optional footers and add them to m_headers
    

【讨论】:

以上是关于使用 Winsock 接收分块的 HTTP 数据的主要内容,如果未能解决你的问题,请参考以下文章

WSARecv 钩子:防止数据包被可执行文件接收

#WEB安全基础 : HTTP协议 | 0x11 HTTP的分块传输模块

Azure函数通过http触发请求分块读取大文件

将 JavaScript WebSocket 连接到 C winsock

如何知道一个winsock已经完成接收文件?

vb以二进制打开excel后用winsock发送,结果接收后打开的是乱码,发送别的文件没问题,为啥?