通过sax2写Action() 调用来读http://...xml 信息（sax2）
和上一个很类似：只是通过不通的方法：
第一通过前台action调用写了三个类：FeaturedBlogAction.java | RssReader.java继承 DefaultHandler 实现四个接口
implements EntityResolver, DTDHandler, ContentHandler, ErrorHandler |BlogCrainInfo.java 继承RssItemDTO
package com.hiredmyway.action.crain;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import org.apache.log4j.Logger;
import com.hiredmyway.action.DefaultAction;
import com.hiredmyway.dto.BlogCrainInfo;
import com.hiredmyway.dto.common.SelectDTO;
import com.hiredmyway.service.OrgService;
import com.hiredmyway.service.ServiceFactory;
import com.hiredmyway.util.RssReader;
public class FeaturedBlogAction extends DefaultAction {
/**
*
*/
private static final long serialVersionUID = 1L;
private Logger logger = Logger.getLogger(FeaturedBlogAction.class);
private String rssURL;
private OrgService orgService;
private String number;// 从前台传得参数就是有几个要显示在页面上比如有8条记录
public String getRssURL() {
return rssURL;
}
public void setRssURL(String rssURL) {
this.rssURL = rssURL;
}
public String getNumber() {
return number;
}
public void setNumber(String number) {
this.number = number;
}
@Override
public String execute() throws Exception {
logger.info(super.getRemoteInfo()+"get blog items from site:"+rssURL);
RssReader MyRSSParser = new RssReader(getRssURL(),Integer.valueOf(getNumber()),new BlogCrainInfo());
String results="no results found";
try {
results = MyRSSParser.parse();
} catch (Exception e) {
logger.error(super.getRemoteInfo()+"get blog items error"+e.getMessage());
results = e.getMessage();
}
response.setContentType("text/html");
response.setCharacterEncoding("UTF-8");
response.getWriter().write(results);
return null;
}
}
==============================================
package com.hiredmyway.util;
import java.io.InputStreamReader;
import java.net.URL;
import java.net.URLConnection;
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import org.apache.commons.lang.StringUtils;
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;
import com.hiredmyway.dto.BlogCrainInfo;//这个类是我本人做的
import com.hiredmyway.dto.BlogInfo;
import com.hiredmyway.dto.EmploymentItem;
import com.hiredmyway.dto.RssItemDTO;
public class RssReader extends DefaultHandler {
// How many RSS news items should we load before stopping.
private int maximumResults =6;
//get element form "item".
private boolean isbegin=false;
/*
* How many elements should we allow before stopping the parse this stops
* giant files from breaking the server.
*/
private static final int MAX_ELEMENTS = 500;
// Keep track of the current element count.
private int ecount = 0;
// Keep track of the current news item count.
private int rcount =0;
private String Url = "http://blog.hiredmyway.com/feed";// Url to parse.
// String to store parsed data to.
private String output = "";
// Current string being parsed.
private String currentText = "";
// Current RSS News Item.
private RssItemDTO NI = null;
private RssItemDTO rssItem=null;
// ArrayList of all current News Items.
private ArrayList News = new ArrayList();
// Has the RSS feed's description been set yet?
boolean dSet = false;
//BLOGSITEM or EMPLOYMENTITEM
private String type="BLOGSITEM";
private String imageUrl;
// Constructor.
/**
* @param Url the feed source
* @param maximumResults the number of results
* @param RssItemDTO Object
*/
public RssReader(String Url, int maximumResults,RssItemDTO rssItem) {
super();
this.Url = Url;
this.maximumResults = maximumResults;
this.rssItem=rssItem;
}
/**
* Returns an HTML representation of the news feed being parsed.
*/
public synchronized String parse() throws Exception{
Exception ex = null;
try {
XMLReader xr = XMLReaderFactory.createXMLReader();
xr.setContentHandler(this);
xr.setErrorHandler(this);
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());
xr.parse(new InputSource(r));
} catch (Exception e) {
ex = e;
}
// Output all the parsed news items as HTML.
for (int i = 0; News.size() >0 && i < News.size(); i++) {
output += ((RssItemDTO) News.get(i)).toString(i,News.size());
}
if(StringUtils.isEmpty(output)){
if(ex != null){
throw ex;
}
}
return (output);
}
// //////////////////////////////////////////////////////////////////
// Event handlers.
// //////////////////////////////////////////////////////////////////
// Called when the XML file begins.
public void startDocument() {
}
// Called when the end of the XML file is reached.
public void endDocument() {
/*
* If we have a partially parsed news item throw it into our array.
*/
if (NI != null) {
rcount++;
News.add(NI);
}
}
// Called when we begin parsing the XML file.
public void startElement(String uri, String name, String qName,
Attributes atts) throws SAXException {
// qName contains the non-URI name of the XML element.
if (qName.equals("item")) {
isbegin=true;
if (NI != null) {
// We've fetched another news item.
if (rcount >= maximumResults) {
// Maximum results have been reached.
throw new SAXException("\nLimit reached.");
}else{
rcount++;
// Add it to our ArrayList.
News.add(NI);
}
}
// Create a new NewsItem to add data to.
NI=rssItem;
if(NI instanceof BlogInfo)
NI = new BlogInfo();
else if(NI instanceof EmploymentItem)
NI = new EmploymentItem();
else if (NI instanceof BlogCrainInfo)
NI = new BlogCrainInfo();
}
}
// We've reached the end of an XML element.
public void endElement(String uri, String name, String qName)
throws SAXException {
if(!isbegin){
currentText = "";
return;
}
if(NI!=null){
if (qName.equals("link"))
NI.setURL(currentText);
else if (qName.equals("description"))
NI.setDescription(currentText);
if(NI instanceof EmploymentItem){
if (qName.equals("title")) {
NI.setTitle(currentText);
}else if(qName.equals("pubDate")){
NI.setPubDate(SysUtil.convertDateStringToString(currentText));
}
}else if(NI instanceof BlogInfo){
if(qName.equals("title")){
currentText=SysUtil.subString(currentText, 0, 50);
NI.setTitle(currentText);
}
} else if (NI instanceof BlogCrainInfo) {
if (qName.equals("title")){
currentText = SysUtil.subString(currentText, 0, 50);
NI.setTitle(currentText);
}
if (qName.equals("description")){
NI.setDescription(currentText);
}
if (qName.equals("content:encoded")) {
List list = getImageUrl(currentText);
if (list != null && list.size() > 0) {
for (int i = 0; i < list.size();) {
this.imageUrl = getImageUrl(currentText).get(i);
NI.setImageUrl(imageUrl);
break;
}
}
}
}
}
// Make sure we don't attempt to parse too long of a document.
currentText = "";
ecount++;
if (ecount > MAX_ELEMENTS)
throw new SAXException("\nLimit reached");
}
// Parse characters from the current element we're parsing.
public void characters(char ch[], int start, int length) {
for (int i = start; i < start + length; i++) {
currentText += ch[i];
}
}
// 用正则表达式来获得<img src="xxxx">
private List<String> getImageUrl(String content) {
String img = "";
Pattern p_image;
Matcher m_image;
List<String> pics = new ArrayList<String>();
String regex_img = "<img.*src\\s*=\\s*(.*?)[^>]*?>";
p_image = Pattern.compile(regex_img, Pattern.CASE_INSENSITIVE);
m_image = p_image.matcher(content);
while (m_image.find()) {
img = img + "," + m_image.group();
Matcher m = Pattern.compile("src\\s*=\\s*\"?(.*?)(\"|>|\\s+)").matcher(img);
while (m.find()) {
pics.add(m.group(1));
}
}
return pics;
}
}
=====================================================
package com.hiredmyway.dto;
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 = "";
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(int currentItem,int itemAmount) {
return "";
}
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;
}
}
==================================
public class BlogCrainInfo extends RssItemDTO{
//通过toString()方法输出在页面上
@Override
public String toString(int currentItem,int itemAmount) {
String returnMe = "";
returnMe +="<div class=\"title_infor_5\"><a href=\"" + getURL() + "\" target=\"_parent\">" + getTitle() +"</a></div>"
+"<div class=\"daily_blog_title\" > <img src=\""+getImageUrl()+"\" width=\"72px\" height=\"67px\" /> <span>"+getDescription()+"</span> </div>"+"|";
return (returnMe);
}
}