vc 网络编程VC网络编程问题：读取网页后，如何将<br />、<span>、</div> 等等无关英文去掉？

vc 网络编程时间:2022-02-27 阅读:()

VC网络编程问题：读取网页后，如何将<br />、<span>、</div> 等等无关英文去掉？

#include #include OLECHAR szHTML[] = OLESTR("

百度寻人
齐心协力，让孩子早日回家

"); int __stdcall WinMain(HINSTANCE hInst, HINSTANCE hPrev, LPSTR lpCmdLine, int nShowCmd) { 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 *pMS = NULL; pPersist->InitNew(); pPersist->Release(); pDoc->QueryInterface(IID_IMarkupServices, (LPVOID *) &pMS); if (pMS) { IMarkupContainer *pMC = NULL; IMarkupPointer *pMkStart = NULL; IMarkupPointer *pMkFinish = NULL; pMS->CreateMarkupPointer(&pMkStart); pMS->CreateMarkupPointer(&pMkFinish); pMS->ParseString(szHTML, 0, &pMC, pMkStart, pMkFinish); if (pMC) { IHTMLDocument2 *pNewDoc = NULL; pMC->QueryInterface(IID_IHTMLDocument, (LPVOID *) &pNewDoc); if (pNewDoc) { // do anything with pNewDoc, in this case // get the body innerText. IHTMLElement *pBody; pNewDoc-gt;get_body(&pBody); if (pBody) { BSTR strText; pBody->get_innerText(&strText); pBody->Release(); SysFreeString(strText); } pNewDoc->Release(); } pMC->Release(); } if (pMkStart) pMkStart->Release(); if (pMkFinish) pMkFinish->Release(); pMS->Release(); } } pDoc->Release(); } CoUninitialize(); return TRUE; }

展开全文