Get Base Domains

Demonstrates how to accumulate a list of unique domain names referenced from outbound URLs.

Download Chilkat C++ Libraries for VC++ 8.0 / Win32

Download Chilkat C++ Libraries for VC++ 7.0 / Win32

Download Chilkat C++ Libraries for VC++ 6.0 / Win32

#include <CkSpider.h>
#include <CkStringArray.h>
#include <CkString.h>

void ChilkatSample(void)
    {
    // The Chilkat Spider component/library is free.
    CkSpider spider;

    CkStringArray domainList;

    // Set the Unique property so that duplicates are not added.
    domainList.put_Unique(true);

    // Crawl the home page of joelonsoftware.com and get the outbound URLs
    spider.Initialize("www.joelonsoftware.com");
    spider.AddUnspidered("http://www.joelonsoftware.com/");

    bool success;
    success = spider.CrawlNext();

    // Build a list of unique domains.
    int i;
    CkString url;
    for (i = 0; i <= spider.get_NumOutboundLinks() - 1; i++) {
        url = spider.getOutboundLink(i);
        domainList.Append(spider.getDomain(url));
    }

    // Display the domains.
    for (i = 0; i <= domainList.get_Count() - 1; i++) {
        printf("%s\n",domainList.getString(i));
        printf("%s\n\n",spider.getBaseDomain(domainList.getString(i)));
    }

    }