import java.net.*;
interface ISpiderReportable {
public boolean spiderFoundURL(URL base,URL url);
public void spiderURLError(URL url);
public void spiderFoundEMail(String email);
}

例3：可复用的蜘蛛类（Spider.java）

import java.util.*;
import java.net.*;
import java.io.*;
import javax.swing.text.*;
import javax.swing.text.html.*;
public class Spider {
/**
*导致错误的URL集合
*/
protected Collection workloadError = new ArrayList(3);
/**
*等待区URL集合
*/
protected Collection workloadWaiting = new ArrayList(3);
/**
*处理过的URL集合
*/
protected Collection workloadProcessed = new ArrayList(3);
protected ISpiderReportable report;
/**
*表明处理过程是否应取消的标志
*/
protected boolean cancel = false;
/**
*构造函数
*
*参数report为实现了ISpiderReportable接口的类
*/
public Spider(ISpiderReportable report)
{
this.report = report;
}
/**
*获取导致错误的URL
*/
public Collection getWorkloadError()
{
return workloadError;
}
/**
*获取在等待的URL
*应添加至少一个URL到此集合以启动蜘蛛
*/
public Collection getWorkloadWaiting()
{
return workloadWaiting;
}
/**
*获取被处理过的URL
*/
public Collection getWorkloadProcessed()
{
return workloadProcessed;
}
/**
*清空所有
*/
public void clear()
{
getWorkloadError().clear();
getWorkloadWaiting().clear();
getWorkloadProcessed().clear();
}
/**
*设置一标志，使begin方法在完成之前返回
*/
public void cancel()
{
cancel = true;
}
public void addURL(URL url)
{
if ( getWorkloadWaiting().contains(url) )
return;
if ( getWorkloadError().contains(url) )
return;
if ( getWorkloadProcessed().contains(url) )
return;
log("正添加到工作区：" + url );
getWorkloadWaiting().add(url);
}
public void processURL(URL url)
{
try {
log("正在处理：" + url );
//获取URL的内容
      URLConnection connection = url.openConnection();
if ( (connection.getContentType()!=null) &&
!connection.getContentType().toLowerCase().s
tartsWith("text/") ) {
getWorkloadWaiting().remove(url);
getWorkloadProcessed().add(url);
log("不会进行正理，因为类型为：" +
connection.getContentType() );
return;
}
//读取URL
      InputStream is = connection.getInputStream();
Reader r = new InputStreamReader(is);
//解析URL
      HTMLEditorKit.Parser parse = new HTMLParse().getParser();
parse.parse(r,new Parser(url),true);
} catch ( IOException e ) {
getWorkloadWaiting().remove(url);
getWorkloadError().add(url);
log("错误：" + url );
report.spiderURLError(url);
return;
}
//标记此URL已完成
    getWorkloadWaiting().remove(url);
getWorkloadProcessed().add(url);
log("已完成：" + url );
}
public void begin()
{
cancel = false;
while ( !getWorkloadWaiting().isEmpty() && !cancel ) {
Object list[] = getWorkloadWaiting().toArray();
for ( int i=0;(i<list.length)&&!cancel;i++ )
processURL((URL)list[i]);
}
}
/**
*HTML解析器回调函数
*/
protected class Parser
extends HTMLEditorKit.ParserCallback {
protected URL base;
public Parser(URL base)
{
this.base = base;
}
public void handleSimpleTag(HTML.Tag t,
MutableAttributeSet a,int pos)
{
String href = (String)a.getAttribute(HTML.Attribute.HREF);
if( (href==null) && (t==HTML.Tag.FRAME) )
href = (String)a.getAttribute(HTML.Attribute.SRC);
if ( href==null )
return;
int i = href.indexOf('#');
if ( i!=-1 )
href = href.substring(0,i);
if ( href.toLowerCase().startsWith("mailto:") ) {
report.spiderFoundEMail(href);
return;
}
handleLink(base,href);
}
public void handleStartTag(HTML.Tag t,
MutableAttributeSet a,int pos)
{
handleSimpleTag(t,a,pos);//以同样的方式处理

}
protected void handleLink(URL base,String str)
{
try {
URL url = new URL(base,str);
if ( report.spiderFoundURL(base,url) )
addURL(url);
} catch ( MalformedURLException e ) {
log("找到畸形URL：" + str );
}
}
}
/**
*由内部调用来记录信息
*仅是把日志写到标准输出
*
*参数entry为写到日志的信息
*/
public void log(String entry)
{
System.out.println( (new Date()) + ":" + entry );
}
}

例4：解析HTML（HTMLParse.java）

import javax.swing.text.html.*;
public class HTMLParse extends HTMLEditorKit {
public HTMLEditorKit.Parser getParser()
{
return super.getParser();
}
}