saxspider.java

JAVA与XML处理一个重要方法是SAX,该包提供了11个常用程序,下载后可以根据具体情况对改进.这11个程序都已调试过.包括对XML的各种处理.建议先下载这个.

import org.xml.sax.*;
import org.xml.sax.helpers.*;
import java.io.*;
import java.util.*;

public class SAXSpider extends DefaultHandler
{
	private List spideredURLs=new Vector();
	private LinkedList queue=new LinkedList();
	private String currentURL;
	private XMLReader parser;
	
	public SAXSpider(XMLReader parser, String url)
	{
		this.parser=parser;
		this.currentURL=url;
	}
	
	public void endDocument()
	{
		spideredURLs.add(currentURL);
		System.out.println("Visited"+currentURL);
		String url;
		try{
			url=(String)queue.removeLast();
		}
		catch(NoSuchElementException e){
			return;
		}
		this.currentURL=url;
		try{
			parser.parse(url);
		}
		catch(Exception ex){
			this.endDocument();
		}
	}

	public void startElement(String namespaceURI, String localName,
	String qualifiedName, Attributes atts)
	{
		String type
		 =atts.getValue("http://www.w3.org/1999/xlink","type");
		if(type!=null)
		{
			String href
			=atts.getValue("http://www3.w3.org/1999/xlink","href");
			if(href!=null)
			{
				if(!spideredURLs.contains(href))
				{
					queue.addFirst(href);
				}
			}
		}
	}	
	
	public static void main(String[] args)
	{
		if(args.length==0)
		{
			System.out.println("Usage:java SAXSpider URL1");
		}
		String url=args[0];
		
		try{
			XMLReader parser=XMLReaderFactory.createXMLReader(
				"org.apache.xerces.parsers.SAXParser"
			);
			ContentHandler spider= new SAXSpider(parser,url);
			parser.setContentHandler(spider);			
			parser.parse(url);
			}		
		catch(Exception e){
			System.err.println(e);
		}
	}
}