C++ 提取网页内容系列之一

标题: C++ 提取网页内容系列
作者: itdef
链接: http://www.cnblogs.com/itdef/p/4171179.html

欢迎转帖请保持文本完整并注明出处

首先分析网页就要下载网页内容这里给出了两种方案

一种是使用MFC自带函数

代码如下:

int GetHttpFileData(CString strUrl,char* szDownloadHtmFileName)
{
    CInternetSession Session("Internet Explorer", 0);
    CHttpFile *pHttpFile = NULL;
    CString strData;
    CString strClip;
    int iRet = -1;
 
    if(szDownloadHtmFileName == NULL)
    {   
        cerr << "DownloadHtmFileName is NULL" << endl;
        Session.Close();
        return iRet;
    }
 
    ofstream of(szDownloadHtmFileName);
    if (of.bad())
    {
        cerr << "of create file error" << endl;
        Session.Close();
        return iRet;
    }
 
    try
    {
        pHttpFile = (CHttpFile*)Session.OpenURL(strUrl);
        while ( pHttpFile->ReadString(strClip) )
        {
            of << strClip;
        }
    }catch(CInternetException* pEx)
    {
        TCHAR pszError[64];
        pEx->GetErrorMessage(pszError, 64);
        cerr << __FUNCTION__ << pszError << endl;
        goto GetHttpFileData_EXIT;
    }
 
    iRet = 0;
 
GetHttpFileData_EXIT:
    Session.Close();
    of.close();
 
    return iRet;
}

这里我将下载内容写入了一个文件存入硬盘。另外还需要注意的是网页文件下载的格式可能是宽字节使用UTF8格式，这里需要将其转换为GBK多字节。

int UTF8Str2GBK(const string& strUTF8,string& strGBK)
{
    int i = MultiByteToWideChar(CP_UTF8, 0, strUTF8.c_str(), -1, NULL, 0);
    WCHAR *wsz = NULL;
    TCHAR *tsz = NULL;
    int iRet = -1;
 
    wsz = new WCHAR[i+1];
    if( NULL == wsz)
    {
        goto UTF8Str2GBK_EXIT;
    }
    MultiByteToWideChar(CP_UTF8, 0, strUTF8.c_str(), -1, wsz, i);
 
    i = WideCharToMultiByte(CP_ACP, 0, wsz, -1, NULL, 0, NULL, NULL);
    tsz = new TCHAR[i+1];
    if( NULL == tsz)
    {
        goto UTF8Str2GBK_EXIT;
    }
    WideCharToMultiByte(CP_ACP, 0, wsz, -1, tsz, i, NULL, NULL);
     
    strGBK = string(tsz);
 
    iRet = 0;
UTF8Str2GBK_EXIT:
 
    delete []wsz;
    delete []tsz;
 
    return iRet;
}