html抓取插件,浏览器插件获取网页内容

void GetHtmlContent()

{

//m_Explorer

HRESULT hr;

LPDISPATCH pDisp;

IHTMLDocument2* phd;//IHtmlDocument2接口指针

IHTMLElement* pBody;//网页中的元素

pDisp = m_Explorer.get_Document();

hr = pDisp->QueryInterface(IID_IHTMLDocument2, (LPVOID*)&phd);

pDisp->Release();

if (SUCCEEDED(hr))

{

BSTR bstrText;

hr = phd->get_body(&pBody); //BODY

if (SUCCEEDED(hr))

{

hr = pBody->get_innerText(&bstrText);

if (SUCCEEDED(hr))

{

//PrintBSTR(bstrText); // 处理得到的文本

char* lpszText2 = _com_util::ConvertBSTRToString(bstrText);

g_Log.print(LogLevel_Info,"[info] GetHtmlContent:%s.\n",lpszText2);

SysFreeString(bstrText);

//AfxMessageBox("获取成功");

}

}

SysFreeString(bstrText);

}

phd->Release();

pBody->Release();

}

原文：http://blog.csdn.net/loveheronly/article/details/38172487