VC 获取网页数据时，如何解决乱码问题

网页编码格式有：UTF-8，GBK，gb2312等，而VC是Unicode编码格式，获取网页数据直接显示会有乱码问题，那么就需要将其他编码格式转换成Unicode格式。

//取网页标题  
void CGetWebTitleDlg::OnBnClickedBtnGetTitle()  
{  
    m_HtmlCode.SetWindowText(_T(""));//clear  
  
    CInternetSession mySession(NULL,0);  
    CHttpFile* htmlFile=NULL;  
    CString strLine,url,strHtml;  
    TCHAR sRecv[1024];  
    UINT CodePage=65001;//CP_UTF8:65001 CP_ACP:0  
    m_Url.GetWindowText(url);  
  
    TRY   
    {  
        htmlFile=(CHttpFile*)mySession.OpenURL(url);//打开连接  
          
        //获取网页编码  
        while(htmlFile->ReadString(sRecv,1024))  
        {  
            //先用UTF8来进行转换，如果html页面编码是gbk或gb2312，转换后中文字符为  
            //乱码，但英文字符显示正常，我们判断html页码编码，通过寻找英文就可以了  
            int nBufferSize = MultiByteToWideChar(CP_UTF8, 0, (LPCSTR)sRecv, -1, NULL, 0);  
            wchar_t *pBuffer = new wchar_t[nBufferSize+1];  
            memset(pBuffer,0,(nBufferSize+1)*sizeof(wchar_t));   
            MultiByteToWideChar(CP_UTF8, 0, (LPCSTR)sRecv, -1 , pBuffer, nBufferSize*sizeof(wchar_t));   
            strHtml=pBuffer;  
            if (-1!=strHtml.Find(_T("charset=gbk")))  
            {  
                CodePage=0;  
                delete pBuffer;  
                break;  
            }  
            if (-1!=strHtml.Find(_T("charset=GBK")))//http://www.sohu.com  
            {  
                CodePage=0;  
                delete pBuffer;  
                break;  
            }  
            if (-1!=strHtml.Find(_T("charset=gb2312")))  
            {  
                CodePage=0;  
                delete pBuffer;  
                break;  
            }  
            if (-1!=strHtml.Find(_T("charset=GB2312")))  
            {  
                CodePage=0;  
                delete pBuffer;  
                break;  
            }  
            if (-1!=strHtml.Find(_T("charset=utf-8")))  
            {  
                CodePage=65001;  
                delete pBuffer;  
                break;  
            }  
            if (-1!=strHtml.Find(_T("charset=UTF-8")))  
            {  
                CodePage=65001;  
                delete pBuffer;  
                break;  
            }  
            delete pBuffer;  
        }  
        strHtml=_T("");  
          
        //获取网页源码  
      <span style="color:#ff9966;">  htmlFile=(CHttpFile*)mySession.OpenURL(url);//重新打开连接  
        while(htmlFile->ReadString(sRecv,1024))  
        {  
  
            // 编码转换，可解决中文乱码问题  
            //gb2312转为unicode,则用CP_ACP  
            //gbk转为unicode,也用CP_ACP  
            //utf-8转为unicode,则用CP_UTF8  
            int nBufferSize = MultiByteToWideChar(CodePage, 0, (LPCSTR)sRecv, -1, NULL, 0);  
          
            wchar_t *pBuffer = new wchar_t[nBufferSize];  
            memset(pBuffer,0,(nBufferSize+1)*sizeof(wchar_t));   
      
            //gb2312转为unicode,则用CP_ACP  
            //gbk转为unicode,也用CP_ACP  
            //utf-8转为unicode,则用CP_UTF8  
            MultiByteToWideChar(CodePage, 0, (LPCSTR)sRecv, -1 , pBuffer, nBufferSize*sizeof(wchar_t));   
  
            strHtml+=pBuffer;  
            strHtml+="\r\n";  
            delete pBuffer;  
        }  </span>
        htmlFile->Close();  
        mySession.Close() ;  
        delete htmlFile;  
  
        m_HtmlCode.SetWindowText(strHtml);//显示网页源码  
  
        //获取网页标题   
        CString szTitle=strHtml.GetString();  
        int nStart=szTitle.Find(_T("<title>"));  
        int nEnd=szTitle.Find(_T("</title>"));  
        szTitle=szTitle.Mid(nStart+7,nEnd-nStart-7);  
        this->SetWindowText(_T("获取到的网页标题为【")+szTitle+_T("】   By︶风不冷丶"));  
  
    }  
    CATCH (CException, e)  
    {  
        TCHAR err[1024];  
        e->GetErrorMessage(err,1024);  
        m_HtmlCode.SetWindowText(err);  
    }  
    END_CATCH  
}