(Node.js) 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".

Install Chilkat for Node.js and Electron using npm at Chilkat npm packages for Node.js Chilkat npm packages for Electron on Windows, Linux, MacOS

var os = require('os');
if (os.platform() == 'win32') {  
  var chilkat = require('@chilkat/ck-node23-win64'); 
} else if (os.platform() == 'linux') {
    if (os.arch() == 'arm') {
        var chilkat = require('@chilkat/ck-node23-linux-arm');
    } else if (os.arch() == 'arm64') {
        var chilkat = require('@chilkat/ck-node23-linux-arm64');
    } else {
        var chilkat = require('@chilkat/ck-node23-linux-x64');
    }
} else if (os.platform() == 'darwin') {
  var chilkat = require('@chilkat/ck-node23-mac-universal');
}

function chilkatExample() {

    var spider = new chilkat.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.
    var i;
    for (i = 0; i <= 9; i++) {
        var success;
        success = spider.CrawlNext();
        if (success == true) {
            // Show the URL of the page just spidered.
            console.log(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.NumUnspidered == 0) {
                console.log("No more URLs to spider");
            }
            else {
                console.log(spider.LastErrorText);
            }

        }

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


}

chilkatExample();