Android解析Rss,XML

通常Rss会是一个XML形式.所以也就是解析XML了,至于如何解析,到处都可以查到,在Android主要有三种,DOM,SAX,XMLPULL,当然如果把一些JAR弄进来也可以使用很简单的API来处理.因为Android内置了一些解析器,所以不会太有困难的. 
先定义一个RssBean,属性有 
private String title; 
    private String description; 
    private String link; 
    private String language; 
    private String pubDate;//Sun, 16 May 2010 10:18:46 +0800 
时间格式暂不转换,因为不需要 
然后解析一个XML把它解析成一个RssBean组成的List. 

public List<RssBean> rssList=new ArrayList<RssBean>();//只包含了item
    private StringBuilder sb=new StringBuilder();//处理节点中的文本串
    RssBean rb=null;
    boolean flag=false;//麻烦的是在<item></item>中有Link和Title而它前面也有,所以这是烂招了,如果有更好的处理方式,喜欢讨论.
解析方法:
public void parseRss(String urlString) throws ParserConfigurationException,SAXException,MalformedURLException,IOException{
        SAXParserFactory factory=SAXParserFactory.newInstance();
        SAXParser parser=factory.newSAXParser();
        URL url=new URL(urlString);
        /*HttpURLConnection connection=(HttpURLConnection)url.openConnection();
        if(connection.getResponseCode()==HttpURLConnection.HTTP_OK){
            parser.parse(connection.getInputStream(),this);
        }*/
        XMLReader xmlReader = parser.getXMLReader();
        InputSource is = new InputSource(url.openStream());
        xmlReader.setContentHandler(this);
        xmlReader.parse(is);
        //connection=null;
        factory=null;
        parser=null;
    }
由于xmlReader.setContentHandler(this);所以,这个解析类继承了extends DefaultHandler,当然覆盖了一些方法:
@Override
    public void startElement(String uri,String localName,String qName,
        Attributes attributes) throws SAXException{
        System.out.println("startElement:"+qName+"***"+localName);
//在J2SE中使用SAX,qName是有东西的.这里是空的.
        if(qName.equals("item")||"item".equals(localName)){   //检测到了一个Item就新建一个Bean.
            if(!flag){
                System.out.println("\n========================================");
            }
            flag=true;//防止检查前面的元素.
            //System.out.println(qName);
            rb=new RssBean();
        }
    }

    @Override
    public void characters(char[] ch,int start,int length) throws SAXException{
        //System.out.print(new String(ch,start,length));
        sb.append(new String(ch,start,length));
    }

    @Override
    public void endElement(String uri,String localName,String qName) throws SAXException{
        System.out.println("\nendElement***qName:"+qName);//因为DTD handlers aren't supported,所以qName为空?不是.
        System.out.println("localName:"+localName);
        if(qName.equals("item")||"item".equals(localName)){
            rssList.add(rb);
            //rb=null;
            System.out.println("endElement.rssList:"+rssList.size());
        }else if(qName.equals("title")||"title".equals(localName)){
            if(flag){
                rb.setTitle(sb.toString().trim());//这里需要去除空格.
                System.out.println("添加了title:"+sb.toString().trim());
//
            }
        }else if(qName.equals("description")||"description".equals(localName)){
            if(flag){
                rb.setDescription(sb.toString().trim());
                //System.out.println("添加了Description:"+sb.toString().trim());
            }
        }else if(qName.equals("link")||"link".equals(localName)){
            if(flag){
                rb.setLink(sb.toString().trim());
                System.out.println("添加了Link:"+sb.toString().trim());
            }
        }else if(qName.equals("language")||"language".equals(localName)){
            rb.setLanguage(sb.toString().trim());
            System.out.println("添加了language:"+sb.toString().trim());
        }else if(qName.equals("pubDate")||"pubDate".equals(localName)){
            rb.setPubDate(sb.toString().trim());
            System.out.println("添加了pubDate:"+sb.toString().trim());
        }
        sb.setLength(0);// 清除内容.
    }

    @Override
    public void startDocument() throws SAXException{
        System.out.println("startDocument");
    }

    @Override
    public void endDocument() throws SAXException{
        System.out.println("endDocument\n===================================");
        /*for(int i=0;i<rssList.size();i++){
            RssBean tmpBean=rssList.get(i);
            System.out.println("标题:"+tmpBean.getTitle());
            System.out.println("日期:"+tmpBean.getPubDate());
            System.out.println("链接"+tmpBean.getLink());
            System.out.println("语言:"+tmpBean.getLanguage());
        }*/
    }
这样解析就完成了.使用DOM似乎更简单些.不过它需要载入整个文档才通解析,耗费内存多些.
public void parseRss(String urlStr){
        DocumentBuilderFactory builderFactory=null;
        DocumentBuilder docBuilder=null;
        Document doc=null;
        URL url;
        try{
            url=new URL(urlStr);
            URLConnection connection=url.openConnection();
            HttpURLConnection httpURLConnection=(HttpURLConnection)connection;
            int responseCode=httpURLConnection.getResponseCode();
            if(responseCode==HttpURLConnection.HTTP_OK){
                InputStream in=httpURLConnection.getInputStream();
builderFactory=DocumentBuilderFactory.newInstance();
docBuilder=builderFactory.newDocumentBuilder();
    //xml file 放到 assets目录中的
    //doc=docBuilder.parse(new File(url));
    doc=docBuilder.parse(in);
    //rootE element
    Element rootE=doc.getDocumentElement();
    //Do something here get a NodeList by tagname
    Element element;
    //System.out.println("channel node:"+ele);
Element channelEle=(Element)rootE.getElementsByTagName("channel").item(0);
//parseChannel(channelEle);
NodeList itemList=channelEle.getElementsByTagName("item");
int len2=itemList.getLength();
rssItemList.clear();
for(int j=0;j<len2;j++){
    element=(Element)itemList.item(j);
    RssBean rb=new RssBean();
    NodeList titleNodeList=element.getElementsByTagName("title");
    parseTitle(titleNodeList,rb);
    titleNodeList=element.getElementsByTagName("description");
    parseDescription(titleNodeList,rb);
    titleNodeList=element.getElementsByTagName("link");
    parseLink(titleNodeList,rb);
    titleNodeList=element.getElementsByTagName("pubDate");
    parsePubDate(titleNodeList,rb);
    System.out.println(rb.getTitle()+"**"+rb.getLink());
    rssItemList.add(rb);
//而这些都是简单的方法.
    System.out.println("parseRss:"+rssItemList.size());
    }
}
}catch(MalformedURLException e){
            e.printStackTrace();
        }catch(IOException e){
            e.printStackTrace();
        }catch(SAXException e){
            e.printStackTrace();
        }catch(ParserConfigurationException e){
            e.printStackTrace();
        }finally{
            doc=null;
            docBuilder=null;
            builderFactory=null;
        }
    }
//在J2Se中有GetTextContent,而这里就没有了.在文档里也写了根据节点的类型来处理getNodeValue(),节点类型为3时表示是文本节点,取之有值,其它的为Null.并且成了子节点,nodeName为#text.
private void parseTitle(NodeList titleNodeList,RssBean rb) throws DOMException{
        rb.setTitle(titleNodeList.item(0).getFirstChild().getNodeValue());
    }

    /**
     * 处理描述
     * @param titleNodeList 节点列表
     * @param rb RssBean
     * @throws DOMException
     */
    private void parseDescription(NodeList titleNodeList,RssBean rb) throws DOMException{
        rb.setDescription(titleNodeList.item(0).getFirstChild().getNodeValue());
    }

    /**
     * 处理链接
     * @param linkList 节点列表
     * @param rb RssBean
     * @throws DOMException
     */
    private void parseLink(NodeList linkList,RssBean rb) throws DOMException{
        rb.setLink(linkList.item(0).getFirstChild().getNodeValue());
    }

    /**
     * 处理发布日期
     * @param titleNodeList 节点列表
     * @param rb RssBean
     * @throws DOMException
     */
    private void parsePubDate(NodeList titleNodeList,RssBean rb) throws DOMException{
        rb.setPubDate(titleNodeList.item(0).getFirstChild().getNodeValue());
    }