Rss,Atom聚合规范的XML文件解析(Rome,rssutils)

1.通过Rome插件可以简化对这两种规范文件的解析难度！Rss,Atom一般用在网站订阅功能，可以实现网络资源共享，用户可以通过客户端软件直接浏览各大网站已订阅的文章。简单的来说，电子订阅的特点就是，可以将多个网站上频繁更新的内容如：博客，新闻，聚合到一个网页列表上。ff可以下载sage插件解析，IE7可以直接解析。以下是读写操作的代码示例： 

package rss;

 

import java.io.FileWriter;

import java.io.Writer;

import java.text.DateFormat;

import java.text.SimpleDateFormat;

import java.util.ArrayList;

import java.util.Date;

import java.util.List;

 

import com.sun.syndication.feed.synd.SyndContent;

import com.sun.syndication.feed.synd.SyndContentImpl;

import com.sun.syndication.feed.synd.SyndEntry;

import com.sun.syndication.feed.synd.SyndEntryImpl;

import com.sun.syndication.feed.synd.SyndFeed;

import com.sun.syndication.feed.synd.SyndFeedImpl;

import com.sun.syndication.io.SyndFeedOutput;

 

public class RssWrite {

 

public static void main(String[] args) throws Exception {

DateFormat dateParser = new SimpleDateFormat("yyyyMMddhhmmss");

 

SyndFeed feed = new SyndFeedImpl();

feed.setFeedType("atom_1.0");

feed.setTitle("Sample Feed (created with Rome)");

    feed.setLink("http://rome.dev.java.net");

    feed.setDescription("This feed has been created using Rome (Java syndication utilities");

    feed.setEncoding("utf-8");//默认是utf-8

 

    List entries = new ArrayList();

    SyndEntry entry;

    SyndContent description;

 

    entry = new SyndEntryImpl(); // feed其中的一个 entry, 即其中一篇文章

 

    entry.setTitle("Rome v1.0");  // 设置文章标题

    entry.setLink("http://wiki.java.net/bin/view/Javawsxml/Rome01");

    entry.setPublishedDate(new Date());

    description = new SyndContentImpl(); // 文章的描述

    description.setType("text/plain");

    description.setValue("hello caohaigang");

    entry.setDescription(description);

    entries.add(entry);

 

    entry = new SyndEntryImpl();

    entry.setTitle("Rome v1.0");

    entry.setLink("http://wiki.java.net/bin/view/Javawsxml/Rome01");

    entry.setPublishedDate(new Date());

    description = new SyndContentImpl();

    description.setType("text/plain");

    description.setValue("<img src=/"http://farm4.static.flickr.com/3026/2645744338_bf6a7e9c57_m.jpg/" />");

    entry.setDescription(description);

    entries.add(entry);

 

    feed.setEntries(entries); // 设置feed的文章列表

    String path = "c:/xml";

    File f = new File(path);       

        if(!f.exists()){

        f.mkdirs();  

        }

    String fileName = dateParser.format(new Date())+".xml";

    //FileWriter输出的XML文件为gb2312编码,这在linux下无法使用

    //Writer writer = new FileWriter(path + "/" + fileName);

    //要和正文编码设置一致

    Writer writer = new OutputStreamWriter(new FileOutputStream(fileName), "UTF-8");

    SyndFeedOutput output = new SyndFeedOutput();

    output.output(feed,writer); // 向客户端输出xml

    writer.close();

 

    System.out.println("The feed has been written to the file ["+fileName+"]");

}

}

 

import com.sun.syndication.feed.synd.SyndEntry;

import com.sun.syndication.feed.synd.SyndFeed;

import com.sun.syndication.fetcher.FeedFetcher;

import com.sun.syndication.fetcher.impl.FeedFetcherCache;

import com.sun.syndication.fetcher.impl.HashMapFeedInfoCache;

import com.sun.syndication.fetcher.impl.HttpURLFeedFetcher;

 

public class RssReader {

 

    public static void main(String[] args) throws Exception {

        FeedFetcherCache feedInfoCache = HashMapFeedInfoCache.getInstance();

        FeedFetcher feedFetcher = new HttpURLFeedFetcher(feedInfoCache);

 

        URL url = new URL("http://www.china-pub.com/rss/FeedPub.asp?id=3");

        //url是XML文件, 如http://feed.feedsky.com/xxx.xml

        SyndFeed feed = feedFetcher.retrieveFeed(url);

        List entryList = feed.getEntries();

        for (int i = 0; i < entryList.size(); i++) {

            SyndEntry entry = (SyndEntry) entryList.get(i);

            System.out.println("Published Date: " + entry.getPublishedDate());

            System.out.println("Title: " + entry.getTitle());

            System.out.println("Link: " + entry.getLink());

            SyndContent sc = entry.getDescription();

            if(sc!=null){

            System.out.println("Description: " + sc.getValue());

            }

            System.out.println("------------------------------");

        }

    }

}

 

 

其中FeedType为以下同种中的一种 :

public static final String RSS_090 = "rss_0.9";

public static final String RSS_092 = "rss_0.92";

public static final String RSS_093 = "rss_0.93";

public static final String RSS_094 = "rss_0.94";

public static final String RSS_091_Netscape = "rss_0.91";

public static final String RSS_091_Userland = "rss_0.91";

public static final String RSS_100 = "rss_1.0";

public static final String RSS_200 = "rss_2.0";

public static final String ATOM_030 = "atom_0.3";

public static final String ATOM_100 = "atom_1.0";

 

 

用ROME ,就可以很简单的生成rss, atom或者将rss转化成atom, 等操作.. 
这个插件需要3个jar包 jdom.jar rome-0.9.jar rome-fetcher-0.9.jar 

2.通过rssutils插件可以对RssXml进行读操作，引入jar包之后直接可以通过在jsp页写标签进行输出，优点：使用简单。缺点：仅仅只能对RssXml文件进行读取操作

 

<%@ page language="java" import="java.util.*" pageEncoding="utf-8"%>

<%@ taglib uri="/WEB-INF/rssutils.tld" prefix="rss" %>

 

<rss:feed

url="http://dev.csdn.net/rss/2.xml"

feedId="example1"/>

<b>Image: </b><rss:channelImage feedId="example1" asLink="true"/><br>

<b>Title: </b><rss:channelTitle feedId="example1"/><br>

<b>Link: </b><rss:channelLink feedId="example1" asLink="true"/><br>

<b>Description: </b><rss:channelDescription feedId="example1"/><br>

<ul>

  <rss:forEachItem feedId="example1">

    <li><rss:itemTitle feedId="example1"/><br>

    <rss:itemLink feedId="example1"/><br>

    <rss:itemDescription feedId="example1"/><br>

  </rss:forEachItem>

</ul>

 

需要rssutils.jar

 

http://dl.javaeye.com/topics/download/b2eccd4c-6cc8-368f-a46b-7bca286b9bd4

 

http://dl.javaeye.com/topics/download/8ef29618-2433-3d22-b218-2c2f66ba1b4f