通过XMLReader 读取服务器的xml 文件(通过sax2)

本文通过参考http://www.iteye.com/topic/763895 网站

通过读本地磁盘取得xml 可以参考 http://www.iteye.com/topic/763895网站 InputStream input = new FileInputStream(new File("D:\\test\\test.xml"));

有三类：TestRssTesteSax2.java| SaxRssTestService.java|RssItemDTO.java

第一类：

import java.io.File;

import java.io.FileInputStream;

import java.io.IOException;

import java.io.InputStream;

import java.io.InputStreamReader;

import java.net.URL;

import java.net.URLConnection;

import java.util.List;

import org.xml.sax.InputSource;

import org.xml.sax.XMLReader;

import org.xml.sax.helpers.XMLReaderFactory;

public class TestRssTesteSax2 {

public TestRssTesteSax2() {

// TODO Auto-generated constructor stub

}

/**

* @param args

* @throws Exception

*/

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

String Url = "http://blog.hiredmyway.com/feed";// Url 就是读这个网站的信息

SaxRssTestService sax = new SaxRssTestService();

try {

URL u = new URL(Url);

URLConnection UC = u.openConnection();

/*

* If we don't set the user-agent property sites like Google won't

* let you access their feeds.

*/

UC.setRequestProperty("User-agent", "www.hiredmyway.com");

InputStreamReader r = new InputStreamReader(UC.getInputStream());

List<RssItemDTO> blogs = sax.getBlogs(r);

for(RssItemDTO dto : blogs){

System.out.println(dto.toString());

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

}

System.out.println("count="+blogs.size());

} catch (Exception e) {

}

}

}

-----------------------------------------------------------------

第二类

import java.io.InputStreamReader;

import java.util.ArrayList;

import java.util.List;

import javax.xml.parsers.SAXParser;

import javax.xml.parsers.SAXParserFactory;

import org.xml.sax.Attributes;

import org.xml.sax.InputSource;

import org.xml.sax.SAXException;

import org.xml.sax.XMLReader;

import org.xml.sax.helpers.DefaultHandler;

import org.xml.sax.helpers.XMLReaderFactory;

public class SaxRssTestService extends DefaultHandler{

private List<RssItemDTO> blogs = null;

private RssItemDTO blog = null;

private String preTag = null;//作用是记录解析时的上一个节点名称

public List<RssItemDTO> getBlogs(InputStreamReader xmlStream) throws Exception{

SAXParserFactory factory = SAXParserFactory.newInstance();

// SAXParser parser = factory.newSAXParser();

SaxRssTestService handler = new SaxRssTestService();

XMLReader xr = XMLReaderFactory.createXMLReader();

xr.setContentHandler(handler);

xr.setErrorHandler(handler);

// xr.parse(xmlStream, handler);

xr.parse(new InputSource(xmlStream));

return handler.getBlogs();

}

public List<RssItemDTO> getBlogs() {

return blogs;

}

public void setBlogs(List<RssItemDTO> blogs) {

this.blogs = blogs;

}

@Override

public void startDocument() throws SAXException {

blogs = new ArrayList<RssItemDTO>();

}

@Override

public void startElement(String uri, String localName, String qName, Attributes attributes) throws SAXException {

if("item".equals(qName)){

blog = new RssItemDTO();

// blog.setId(Integer.valueOf(attributes.getValue(0)));

}

preTag = qName;//将正在解析的节点名称赋给preTag

}

@Override

public void endElement(String uri, String localName, String qName)

throws SAXException {

if("item".equals(qName)){

blogs.add(blog);

blog = null;

}

preTag = null;

}

@Override

public void characters(char[] ch, int start, int length) throws SAXException {

if (blog !=null) {

if(preTag!=null){

String content = "";

for (int i = start; i < start + length; i++) {

content += ch[i];

}

if("title".equals(preTag)){

blog.setTitle(content);

}else if("pubDate".equals(preTag)){

blog.setPubDate(content);

}else if ("link".equals(preTag)) {

//description

blog.setURL(content);

} else if ("description".equals(preTag)){

if (content !=null && !content.equals("\n")) {

blog.setDescription(content);

}

} else if ("content:encoded".equals(preTag)) {

if (content !=null && !content.equals("\n")) {

blog.setImageUrl(content);

}

}

}

}

}

}

====================================

第三个类：

package com.hiredmyway.index.sax2test;

import org.apache.commons.lang.StringUtils;

import com.hiredmyway.util.string.ShortTextSubString;

import com.hiredmyway.util.string.TitleSubString;

public class RssItemDTO {

private String Title = "";

private String URL = "";

private String description="";

private String pubDate="";

private String imageUrl = "";

private int id;

public int getId() {

return id;

}

public void setId(int id) {

this.id = id;

}

public String getDescription() {

if(StringUtils.isNotBlank(description)){

description = new ShortTextSubString().trimSubString(description);

}

return description;

}

public void setDescription(String description) {

this.description = description;

}

public void setTitle(String Title) {

if(StringUtils.isNotBlank(this.Title)){

this.Title = new TitleSubString().trimSubString(this.Title);

}

this.Title = Title;

}

public void setURL(String URL) {

this.URL = URL;

}

public String toString() {

return this.Title+":"+this.pubDate+":"+this.URL+":"+this.description+":"+this.getImageUrl();

}

public String getTitle() {

return Title;

}

public String getURL() {

return URL;

}

public String getPubDate() {

return pubDate;

}

public void setPubDate(String pubDate) {

this.pubDate = pubDate;

}

public String getImageUrl() {

return imageUrl;

}

public void setImageUrl(String imageUrl) {

this.imageUrl = imageUrl;

}

}