如何使用IHTMLDocument直接分析由idhttp下载回来的源码?

meCAD 2006-08-17 10:48:44

...全文

333 3 打赏收藏转发到动态举报

写回复

用AI写文章

3 条回复

切换为时间正序

请发表友善的回复…

发表回复

meCAD 2006-08-17

打赏
举报

要直接分析html代码,求速度

ly_liuyang 2006-08-17

打赏
举报

例子很多的
用TInternetExplorer对象读取文本,分析即可

ccrun.com 2006-08-17

打赏
举报

给你个例子，将取回来的HTML内容代替szHTML就可以了。

利用IHTMLDocument2分析HTML文本内容

#include <mshtml.h>
void __fastcall Tfrm::Button1Click(TObject *Sender)
{
OLECHAR szHTML[] = OLESTR("<HTML><BODY>Hello World!</BODY></HTML>");

IHTMLDocument2 *pDoc = NULL;
CoInitialize(NULL);
CoCreateInstance(CLSID_HTMLDocument,
NULL,
CLSCTX_INPROC_SERVER,
IID_IHTMLDocument2,
(LPVOID *)&pDoc);
if(pDoc)
{
IPersistStreamInit *pPersist = NULL;
pDoc->QueryInterface(IID_IPersistStreamInit, (LPVOID *) &pPersist);
if(pPersist)
{
IMarkupServices *pMarkSvr = NULL;
pPersist->InitNew();
pPersist->Release();
pDoc->QueryInterface(IID_IMarkupServices, (LPVOID *)&pMarkSvr);
if(pMarkSvr)
{
IMarkupContainer *pMkContainer = NULL;
IMarkupPointer *pMkStart = NULL;
IMarkupPointer *pMkFinish = NULL;
pMarkSvr->CreateMarkupPointer(&pMkStart);
pMarkSvr->CreateMarkupPointer(&pMkFinish);
pMarkSvr->ParseString(szHTML, 0, &pMkContainer, pMkStart, pMkFinish);
if(pMkContainer)
{
IHTMLDocument2 *pNewDoc = NULL;
pMkContainer->QueryInterface(IID_IHTMLDocument, (LPVOID *)&pNewDoc);
if(pNewDoc)
{
// do anything with pNewDoc, in this case
// get the body innerText.
IHTMLElement *pBody;
pNewDoc->get_body(&pBody);
if(pBody)
{
BSTR strText;
pBody->get_innerText(&strText);
ShowMessage(strText);
pBody->Release();
SysFreeString(strText);
}
pNewDoc->Release();
}
pMkContainer->Release();
}
if(pMkStart)
pMkStart->Release();
if(pMkFinish)
pMkFinish->Release();
pMarkSvr->Release();
}
}
pDoc->Release();
}
CoUninitialize();
}