从网页中读数据的问题？多谢

[dciw]

朋友想做一个能从网页上抓数据存起来的东西
我应该能用findwindow找到ie的句炳，然后用什么能读取它的html值呢？

[ruanyuping]

up

[henryzc]

findwindow会找到很多IE窗口吧。通过com组件，在右键菜单中，实现保存功能

[generalz]

不懂，我也很想知道啊！
高手快来啊！

[brilliancechen]

用 request.form("varname ") 不行吗？

[hotness28]

很好的一个办法就是：
把网页保存下来，然后读取
如果不这样，那用findwindow(),但是还要找到控件
我认为会很麻烦

[liuchengdan]

给出获取网页源代码的函数。

BOOL GetSourceByURL(CString sURL, CString &fileContent)
{
CInternetSession internetSession;
CHttpConnection* pHttpConnection = NULL;
CHttpFile* pHttpFile = NULL;
CString strServer, strObject;
DWORD dwServiceType = 0;
DWORD dwHttpRequestFlags = INTERNET_FLAG_EXISTING_CONNECT | INTERNET_FLAG_NO_AUTO_REDIRECT;
TCHAR szHeaders[] = _T("Accept: text/*\r\nUser-Agent: LCD's Sample Http Client\r\n");
INTERNET_PORT nPort;
int nRet = 0;

nRet = AfxParseURL( (LPCTSTR)sURL, dwServiceType, strServer, strObject, nPort );
if( !nRet || dwServiceType != INTERNET_SERVICE_HTTP )
{
fileContent.Empty();
AfxMessageBox( "不能保存请求保存的网页的源代码。原因可能如下：\r\n\r\n1)请求不是一个HTTP请求。\r\n\r\n2)所请求的URL无法到达。" );
return FALSE;
}

pHttpConnection = internetSession.GetHttpConnection( strServer, nPort );
pHttpFile = pHttpConnection->OpenRequest( CHttpConnection::HTTP_VERB_GET, strObject, NULL, 1, NULL, NULL, dwHttpRequestFlags);
pHttpFile->AddRequestHeaders( szHeaders );
pHttpFile->SendRequest();

DWORD dwRet = 0;
pHttpFile->QueryInfoStatusCode( dwRet );
if( dwRet == HTTP_STATUS_DENIED )
{
AfxMessageBox( "连接被拒绝" );
return FALSE;
}

CString string, prefix, suffix, path, sCopy, sTemp, strFilePath;
int iStart = 0, iEnd = 0;

strFilePath = sURL.Left( ( sURL.ReverseFind( '/' ) ) );

fileContent.Empty();
while( pHttpFile->ReadString( string ) )
{
fileContent += "\r\n" + string;
}

pHttpFile->Close();
pHttpConnection->Close();
delete pHttpFile;
delete pHttpConnection;

return TRUE;
}

[smch]

呵呵，楼上的说的很对，你那样是把事情复杂化了。极大的复杂化。

[xsc2001]

CHttpFile* fileGet;
CException* e;
TRY
{
fileGet=(CHttpFile*)sess.OpenURL((char*)strURL);//Open file
}
CATCH_ALL(e)
{
fileGet = 0;
}
END_CATCH_ALL

if(fileGet)
{
DWORD dwStatus;
DWORD dwBuffLen = sizeof(dwStatus);
BOOL bSuccess = fileGet->QueryInfo(
HTTP_QUERY_STATUS_CODE|HTTP_QUERY_FLAG_NUMBER,
&dwStatus, &dwBuffLen);

if( bSuccess && dwStatus>= 200&& dwStatus<300 )
{
while(fileGet->ReadString(strSentence))
m_FileContent+=strSentence;
}// if bSuccess.
fileGet->Close();
delete fileGet;
}
sess.Close();