zoukankan      html  css  js  c++  java
  • 用SAX Parser(Simple API for XML)分析RSS

    用工厂方法产生一个SAXPareser实例:

    SAXParserFactory factory = SAXParserFactory.newInstance();

    SAXParser pareser = factory.newSAXParser();

    我们需要写一个事件处理类来驱动parser的Callback方法,只需要实现部分方法所以我们继承DefaultHandler类即可,DefaultHandler提供了ContentHandler的默认实现。我们需要实现一下方法:

    void characters(char[] ch, int start, int length)

    void endElement(String uri, String localName, String name)

    void startDocument()

    startElement(String uri, String localName, String name,
    Attributes attributes)

    startElement(String uri, String localName, String name, Attributes attributes)

    然后打开一个RSS的URL获得输入流

    InputStream inputStream = new URL(“http://…”).openConnection().getInputStream();

    分析feed

    pareser.parse(inputStream,handler);

    详细的实现代码:

    //定义一个接口,方便扩展,可以用其他的XML分析API

    import java.util.List;
    
    public interface FeedParser {
    	List<Message> parse();
    }
    
    

    import java.io.IOException;
    import java.io.InputStream;
    import java.net.MalformedURLException;
    import java.net.URL;
    
    public abstract class BaseFeedParser implements FeedParser {
    
    	// names of the XML tags
    	static final String CHANNEL = "channel";
    	static final String PUB_DATE = "pubDate";
    	static final  String DESCRIPTION = "description";
    	static final  String LINK = "link";
    	static final  String TITLE = "title";
    	static final  String ITEM = "item";
    	
    	private final URL feedUrl;
    
    	protected BaseFeedParser(String feedUrl){
    		try {
    			this.feedUrl = new URL(feedUrl);
    		} catch (MalformedURLException e) {
    			throw new RuntimeException(e);
    		}
    	}
    
    	protected InputStream getInputStream() {
    		try {
    			return feedUrl.openConnection().getInputStream();
    		} catch (IOException e) {
    			throw new RuntimeException(e);
    		}
    	}
    }
    

    import java.util.List;
    
    import javax.xml.parsers.SAXParser;
    import javax.xml.parsers.SAXParserFactory;
    
    public class SaxFeedParser extends BaseFeedParser {
    
    	protected SaxFeedParser(String feedUrl){
    		super(feedUrl);
    	}
    	
    	public List<Message> parse() {
    		SAXParserFactory factory = SAXParserFactory.newInstance();
    		try {
    			SAXParser parser = factory.newSAXParser();
    			RssHandler handler = new RssHandler();
    			parser.parse(this.getInputStream(), handler);
    			return handler.getMessages();
    		} catch (Exception e) {
    			throw new RuntimeException(e);
    		} 
    	}
    }
    

    import java.util.ArrayList;
    import java.util.List;
    
    import org.xml.sax.Attributes;
    import org.xml.sax.SAXException;
    import org.xml.sax.helpers.DefaultHandler;
    
    import static org.developerworks.android.BaseFeedParser.*;
    
    public class RssHandler extends DefaultHandler{
    	private List<Message> messages;
    	private Message currentMessage;
    	private StringBuilder builder;
    	
    	public List<Message> getMessages(){
    		return this.messages;
    	}
    	@Override
    	public void characters(char[] ch, int start, int length)
    			throws SAXException {
    		super.characters(ch, start, length);
    		builder.append(ch, start, length);
    	}
    
    	@Override
    	public void endElement(String uri, String localName, String name)
    			throws SAXException {
    		super.endElement(uri, localName, name);
    		if (this.currentMessage != null){
    			if (localName.equalsIgnoreCase(TITLE)){
    				currentMessage.setTitle(builder.toString());
    				System.out.println(builder.toString());
    			} else if (localName.equalsIgnoreCase(LINK)){
    				currentMessage.setLink(builder.toString());
    				System.out.println(builder.toString());
    			} else if (localName.equalsIgnoreCase(DESCRIPTION)){
    				currentMessage.setDescription(builder.toString());
    				System.out.println(builder.toString());
    			} else if (localName.equalsIgnoreCase(PUB_DATE)){
    				currentMessage.setDate(builder.toString());
    				System.out.println(builder.toString());
    			} else if (localName.equalsIgnoreCase(ITEM)){
    				messages.add(currentMessage);
    				System.out.println(builder.toString());
    			}
    			builder.setLength(0);	
    			
    		}
    	}
    
    	@Override
    	public void startDocument() throws SAXException {
    		super.startDocument();
    		messages = new ArrayList<Message>();
    		builder = new StringBuilder();
    	}
    
    	@Override
    	public void startElement(String uri, String localName, String name,
    			Attributes attributes) throws SAXException {
    		super.startElement(uri, localName, name, attributes);
    		if (localName.equalsIgnoreCase(ITEM)){
    			this.currentMessage = new Message();
    		}
    	}
    }
    

    public abstract class FeedParserFactory {
    	static String feedUrl = "http://www.androidster.com/android_news.rss";
    	
    	public static FeedParser getParser(){
    		return getParser(ParserType.SAX);
    	}
    	
    	public static FeedParser getParser(ParserType type){
    		switch (type){
    			case SAX:
    				return new SaxFeedParser(feedUrl);
    			case DOM:
    				return new DomFeedParser(feedUrl);
    			case ANDROID_SAX:
    				return new AndroidSaxFeedParser(feedUrl);
    			case XML_PULL:
    				return new XmlPullFeedParser(feedUrl);
    			default: return null;
    		}
    	}
    }
    

  • 相关阅读:
    Django admin 注册自己的路由
    django admin字段设置大全
    Python 装饰器原理
    css hack中遇到的一些问题
    阿里巴巴iconfont的正确使用方法
    css中position(absolute)与margin同时使用的情况
    关于IE浏览器不支持border-radius,box-shadow,text-shadow的解决方法
    大唐项目的总结
    js中的词法作用域
    easyui中datagrid自带loading效果
  • 原文地址:https://www.cnblogs.com/goodwin/p/1900039.html
Copyright © 2011-2022 走看看