Java 核心技术 卷II 高级特性 第3章XML

3.1 XML 概述

3.1.1 XML文档的结构

3.2 解析XML文档

3.3 验证XML文档

3.3.1 文档类型定义

3.4 使用XPath来定位信息

3.6 流机制解析器

3.6.1 使用SAX解析器

package sax;

import java.io.*;
import java.net.*;
import javax.xml.parsers.*;
import org.xml.sax.*;
import org.xml.sax.helpers.*;

/**
 * This program demonstrates how to use a SAX parser. The program prints all hyperlinks of an
 * XHTML web page. <br>
 * Usage: java sax.SAXTest URL
 * @version 1.00 2001-09-29
 * @author Cay Horstmann
 */
public class SAXTest
{
   public static void main(String[] args) throws Exception
   {
      String url;
      if (args.length == 0)
      {
         url = "http://www.w3c.org";
         System.out.println("Using " + url);
      }
      else url = args[0];

      DefaultHandler handler = new DefaultHandler()
         {
            public void startElement(String namespaceURI, String lname, String qname,
                  Attributes attrs)
            {
               if (lname.equals("a") && attrs != null)
               {
                  for (int i = 0; i < attrs.getLength(); i++)
                  {
                     String aname = attrs.getLocalName(i);
                     if (aname.equals("href")) System.out.println(attrs.getValue(i));
                  }
               }
            }
         };

      SAXParserFactory factory = SAXParserFactory.newInstance();
      factory.setNamespaceAware(true);
      factory.setFeature("http://apache.org/xml/features/nonvalidating/load-external-dtd", false);
      SAXParser saxParser = factory.newSAXParser();
      InputStream in = new URL(url).openStream();
      saxParser.parse(in, handler);
   }
}

3.6.2 使用StAX解析器

package stax;

import java.io.*;
import java.net.*;
import javax.xml.stream.*;

/**
 * This program demonstrates how to use a StAX parser. The program prints all hyperlinks links of an
 * XHTML web page. <br>
 * Usage: java stax.StAXTest URL
 * @author Cay Horstmann
 * @version 1.0 2007-06-23
 */
public class StAXTest
{
   public static void main(String[] args) throws Exception
   {
      String urlString;
      if (args.length == 0)
      {
         urlString = "http://www.w3c.org";
         System.out.println("Using " + urlString);
      }
      else urlString = args[0];
      URL url = new URL(urlString);
      InputStream in = url.openStream();
      XMLInputFactory factory = XMLInputFactory.newInstance();
      XMLStreamReader parser = factory.createXMLStreamReader(in);
      while (parser.hasNext())
      {
         int event = parser.next();
         if (event == XMLStreamConstants.START_ELEMENT)
         {
            if (parser.getLocalName().equals("a")) 
            {
               String href = parser.getAttributeValue(null, "href");
               if (href != null)
                  System.out.println(href);               
            }
         }
      }
   }
}