Avoid URLs Matching Any of a Set of Patterns

Demonstrates how to use "avoid patterns" to prevent spidering any URL that matches a wildcarded pattern. This example avoids URLs containing the substrings "java", "python", or "perl".

Download Chilkat C/C++ Libraries for VC++ 9.0 / Win32

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

Download Chilkat C/C++ 64-bit Libraries for VC++ 8.0 / x64

Download Chilkat Visual Studio 2005 C/C++ Libs for Windows Mobile, Pocket PC, SmartPhone, WinCE

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

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

Download Chilkat C/C++ Libraries for VC++ 6.0, Win 95/98/NT4 Compatible

// Needs #include <CkSpider.h>

    CkString strOut;

    //  The Chilkat Spider component/library is free.
    CkSpider spider;

    //  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
    spider.Initialize("www.chilkatsoft.com");

    //  Add the 1st URL:
    spider.AddUnspidered("http://www.chilkatsoft.com/");

    //  Avoid URLs matching these patterns:
    spider.AddAvoidPattern("*java*");
    spider.AddAvoidPattern("*python*");
    spider.AddAvoidPattern("*perl*");

    //  Begin crawling the site by calling CrawlNext repeatedly.
    long i;
    for (i = 0; i <= 9; i++) {
        bool success;
        success = spider.CrawlNext();
        if (success == true) {
            //  Show the URL of the page just spidered.
            strOut.append(spider.lastUrl());
            strOut.append("\r\n");
            //  The HTML is available in the LastHtml property
        }
        else {
            //  Did we get an error or are there no more URLs to crawl?
            if (spider.get_NumUnspidered() == 0) {
                strOut.append("No more URLs to spider\r\n");
            }
            else {
                strOut.append(spider.lastErrorText());
                strOut.append("\r\n");
            }

        }

        //  Sleep 1 second before spidering the next URL.
        spider.SleepMs(1000);
    }



    SetDlgItemText(IDC_EDIT1,strOut.getUnicode());