JavaFX: Parse HTML content with DOMParser R

I have started an interesting project. I will illustrate a crawler based on JavaFX scripting. Though there is no specific reason beyond using JavaFX except to enhance my knowledge on JavaFX scripting.

Here is some preliminary code that I have already written:

Import statement and package declaration –

———————————————————

package com.we4tech.linkcrawler.fx.script;

import java.lang.*;

import java.io.*;

import java.net.*;

import java.util.*;

import org.xml.sax.SAXException;

import org.w3c.dom.Document;

import org.w3c.dom.NodeList;

import org.w3c.dom.Node;

import org.w3c.dom.NamedNodeMap;

import com.sun.org.apache.xerces.internal.parsers.DOMParser;

Sample class skeleton –

————————————————————–

/**

* Define structure for Crawler class.

* @author hasan (hasan -AT- somewherein.net)

*/

public class Crawler {

/**

* Define the target url.

*/

public attribute url: String;

public attribute debug: Boolean;

private attribute foundLinks: String*;

/**

* Start crawling process.

*/

public operation start();

private operation followupLink(link: String);

/**

* Return a list of all available links.

*/

public function getLinks(): String*;

/**

* Print out debug output without timestamp and [LEVEL] prefix.

*/

private operation debug(message: String);

private operation error(message: String);

}

Implementation –

————————————————————————-

operation Crawler.start() {

debug(”Initiating crawler process..”);

debug(”URL is set to - {url}”);

debug(”Crawling just initiated.”);

followupLink(url);

}

operation Crawler.followupLink(link: String) {

debug(”Follow up link - {link}”);

if (link == null or link.length() == 0) {

error(”URL is empty”);

return;

} else {

try {

// Run in background thread through EDT.

do {

var parse = new DOMParser();

parse.parse(link);

var document = parse.getDocument();

var nodes = document.getElementsByTagName(”a”);

for (i in [0..nodes.getLength()]) {

var node = nodes.item(i);

var attributes = node.getAttributes();

if (attributes <> null) {

for (j in [0..attributes.getLength()]) {

var attr = attributes.item(j);

if (attr <> null) {

var nodeName = attr.getNodeName();

if (”href” == nodeName) {

var nodeValue = attr.getNodeValue();

debug(”{nodeName} link - {nodeValue}”);

insert nodeValue into foundLinks;

// start new follow up process.

followupLink(

}

}

}

}

}

}

} catch (e) {

error(”Error found during opening up new URLConnection - {e}”);

}

}

}

operation Crawler.debug(message: String) {

if (debug) {

System.out.println(”[DEBUG] - [{new Date()}] - {message}”);

}

}

operation Crawler.error(message: String) {

System.out.println(”[ERROR] - [{new Date()}] - {message}”);

}

function Crawler.getLinks() {

return foundLinks;

}

NOTE: I have published these codes to make some sense to those people who have started learning JavaFX. This might help other people to know more on it.

Best wishes,