Chilkat HOME .NET Core C# Android™ AutoIt C C# C++ Chilkat2-Python CkPython Classic ASP DataFlex Delphi ActiveX Delphi DLL Go Java Lianja Mono C# Node.js Objective-C PHP ActiveX PHP Extension Perl PowerBuilder PowerShell PureBasic Ruby SQL Server Swift 2 Swift 3,4,5... Tcl Unicode C Unicode C++ VB.NET VBScript Visual Basic 6.0 Visual FoxPro Xojo Plugin
(Unicode C) Extract HTML Title, Description, KeywordsThis example expands on the "getting started" example by showing how to access the HTML title, description, and keywords within each page spidered. These are the contents of the META tags for keywords, description, and title found in the HTML header.
#include <C_CkSpiderW.h> void ChilkatSample(void) { HCkSpiderW spider; int i; BOOL success; spider = CkSpiderW_Create(); // The spider object crawls a single web site at a time. As you'll see // in later examples, you can collect outbound links and use them to // crawl the web. For now, we'll simply spider 10 pages of chilkatsoft.com CkSpiderW_Initialize(spider,L"www.chilkatsoft.com"); // Add the 1st URL: CkSpiderW_AddUnspidered(spider,L"http://www.chilkatsoft.com/"); // Begin crawling the site by calling CrawlNext repeatedly. for (i = 0; i <= 9; i++) { success = CkSpiderW_CrawlNext(spider); if (success == TRUE) { // Show the URL of the page just spidered. wprintf(L"%s\n",CkSpiderW_lastUrl(spider)); // The HTML META keywords, title, and description are available in these properties: wprintf(L"%s\n",CkSpiderW_lastHtmlTitle(spider)); wprintf(L"%s\n",CkSpiderW_lastHtmlDescription(spider)); wprintf(L"%s\n",CkSpiderW_lastHtmlKeywords(spider)); // The HTML is available in the LastHtml property } else { // Did we get an error or are there no more URLs to crawl? if (CkSpiderW_getNumUnspidered(spider) == 0) { wprintf(L"No more URLs to spider\n"); } else { wprintf(L"%s\n",CkSpiderW_lastErrorText(spider)); } } // Sleep 1 second before spidering the next URL. CkSpiderW_SleepMs(spider,1000); } CkSpiderW_Dispose(spider); } |
© 2000-2024 Chilkat Software, Inc. All Rights Reserved.