Java

Avoid URLs Matching Any of a Set of Patterns

See more Spider Examples

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". Java

import com.chilkatsoft.*;

public class ChilkatExample {

  static {
    try {
        System.loadLibrary("chilkat");
    } catch (UnsatisfiedLinkError e) {
      System.err.println("Native code library failed to load.\n" + e);
      System.exit(1);
    }
  }

  public static void main(String argv[])
  {
    boolean success = false;

    CkSpider spider = new CkSpider();

    // 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.
    int i;
    for (i = 0; i <= 9; i++) {

        success = spider.CrawlNext();
        if (success == true) {
            // Show the URL of the page just spidered.
            System.out.println(spider.lastUrl());
            // 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) {
                System.out.println("No more URLs to spider");
                }
            else {
                System.out.println(spider.lastErrorText());
                }

            }

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