| career | drupal | java | mac | mysql | perl | scala | uml | unix  

What this is

This file is included in the "Java Source Code Warehouse" project. The intent of this project is to help you "Learn Java by Example" TM.

Other links

The source code

// $Header: /home/cvs/jakarta-jmeter/src/protocol/http/org/apache/jmeter/protocol/http/parser/,v 1.14 2004/03/25 03:19:18 sebb Exp $
 * Copyright 2003-2004 The Apache Software Foundation.
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * See the License for the specific language governing permissions and
 * limitations under the License.

package org.apache.jmeter.protocol.http.parser;

import java.util.Iterator;

import org.apache.jorphan.logging.LoggingManager;
import org.apache.log.Logger;

import org.htmlparser.Node;
import org.htmlparser.NodeReader;
import org.htmlparser.Parser;
import org.htmlparser.scanners.AppletScanner;
import org.htmlparser.scanners.BaseHrefScanner;
import org.htmlparser.scanners.BodyScanner;
import org.htmlparser.scanners.InputTagScanner;
import org.htmlparser.scanners.LinkScanner;
import org.htmlparser.scanners.LinkTagScanner;
import org.htmlparser.scanners.ScriptScanner;
import org.htmlparser.tags.AppletTag;
import org.htmlparser.tags.BaseHrefTag;
import org.htmlparser.tags.BodyTag;
import org.htmlparser.tags.ImageTag;
import org.htmlparser.tags.InputTag;
import org.htmlparser.tags.LinkTag;
import org.htmlparser.tags.LinkTagTag;
import org.htmlparser.tags.ScriptTag;
import org.htmlparser.util.DefaultParserFeedback;
import org.htmlparser.util.NodeIterator;
import org.htmlparser.util.ParserException;

 * HtmlParser implementation using SourceForge's HtmlParser.
 * @version $Revision: 1.14 $ updated on $Date: 2004/03/25 03:19:18 $
class HtmlParserHTMLParser extends HTMLParser
    /** Used to store the Logger (used for debug and error messages). */
    transient private static Logger log= LoggingManager.getLoggerForClass();

	protected HtmlParserHTMLParser(){

	protected boolean isReusable()
		return true;

    /* (non-Javadoc)
     * @see org.apache.jmeter.protocol.http.parser.HtmlParser#getEmbeddedResourceURLs(byte[],
    public Iterator getEmbeddedResourceURLs(byte[] html, URL baseUrl, URLCollection urls)
        throws HTMLParseException
        Parser htmlParser= null;
            String contents= new String(html);
            StringReader reader= new StringReader(contents);
            NodeReader nreader= new NodeReader(reader, contents.length());
            htmlParser= new Parser(nreader, new DefaultParserFeedback());
        catch (Exception e)
            throw new HTMLParseException(e);

        // Now parse the DOM tree

        // look for applets

        // This will only work with an Applet .class file.
        // Ideally, this should be upgraded to work with Objects (IE)
        //	and archives (.jar and .zip) files as well.

            // we start to iterate through the elements
            for (NodeIterator e= htmlParser.elements(); e.hasMoreNodes();)
                Node node= e.nextNode();
                String binUrlStr= null;

                // first we check to see if body tag has a
                // background set and we set the NodeIterator
                // to the child elements inside the body
                if (node instanceof BodyTag)
                    BodyTag body= (BodyTag)node;
                    binUrlStr= body.getAttribute("background");
                    // if the body tag exists, we get the elements
                    // within the body tag. if we don't we won't
                    // see the body of the page. The only catch
                    // with this is if there are images after the
                    // closing body tag, it won't get parsed. If
                    // someone puts it outside the body tag, it
                    // is probably a mistake. Plus it's bad to
                    // have important content after the closing
                    // body tag. Peter Lin 10-9-03
                    e= body.elements();
                else if (node instanceof BaseHrefTag)
                    BaseHrefTag baseHref= (BaseHrefTag)node;
                        baseUrl= new URL(baseUrl, baseHref.getBaseUrl()+"/");
                    catch (MalformedURLException e1)
                        throw new HTMLParseException(e1);
                else if (node instanceof ImageTag)
                    ImageTag image= (ImageTag)node;
                    binUrlStr= image.getImageURL();
                else if (node instanceof AppletTag)
                    AppletTag applet= (AppletTag)node;
                    binUrlStr= applet.getAppletClass();
                else if (node instanceof InputTag)
                    InputTag input= (InputTag)node;
                    // we check the input tag type for image
                    String strType= input.getAttribute("type");
                    if (strType != null && strType.equalsIgnoreCase("image"))
                        // then we need to download the binary
                        binUrlStr= input.getAttribute("src");
				} else if (node instanceof LinkTag){
					LinkTag link = (LinkTag)node;
					if (link.getChild(0) instanceof ImageTag){
						ImageTag img = (ImageTag)link.getChild(0);
						binUrlStr = img.getImageURL();
				} else if (node instanceof ScriptTag){
					ScriptTag script = (ScriptTag)node;
					binUrlStr = script.getAttribute("src");
				} else if (node instanceof LinkTagTag){
					LinkTagTag script = (LinkTagTag)node;
					binUrlStr = script.getAttribute("href");
                if (binUrlStr == null)

            log.debug("End   : parseNodes");
        catch (ParserException e)
            throw new HTMLParseException(e);

        return urls.iterator();

     * Returns a node representing a whole xml given an xml document.
     * @param text	an xml document
     * @return	a node representing a whole xml
     * @throws SAXException indicates an error parsing the xml document
    private static void addTagListeners(Parser parser)
        log.debug("Start : addTagListeners");
        // add body tag scanner
        parser.addScanner(new BodyScanner());
        // add BaseHRefTag scanner
        parser.addScanner(new BaseHrefScanner());
        // add ImageTag and BaseHrefTag scanners
        LinkScanner linkScanner= new LinkScanner(LinkTag.LINK_TAG_FILTER);
        // parser.addScanner(linkScanner);
                            // Taken from org.htmlparser.Parser
        // add input tag scanner
        parser.addScanner(new InputTagScanner());
        // add applet tag scanner
        parser.addScanner(new AppletScanner());
        parser.addScanner(new ScriptScanner());
        parser.addScanner(new LinkTagScanner());
... this post is sponsored by my books ...

#1 New Release!

FP Best Seller


new blog posts


Copyright 1998-2021 Alvin Alexander,
All Rights Reserved.

A percentage of advertising revenue from
pages under the /java/jwarehouse URI on this website is
paid back to open source projects.