java读取xml

妖狐艹你老母 2022-05-09 15:42 243阅读 0赞

用dom4j来解析xml文件的操作

package test;

import java.net.MalformedURLException;  
import java.net.URL;  
import java.util.Iterator;

import org.dom4j.Document;  
import org.dom4j.DocumentException;  
import org.dom4j.Element;  
import org.dom4j.io.SAXReader;

public class TestXml \{  
 String link = "";

String tit = "";

String pubdate = "";

String image = "";

String date = "";

String source = "";

String description;

String Docid;

String Server;

String Samenum;

String Interfixnum;

//获得整个xml文档  
 public Document readxml(URL url) throws MalformedURLException,  
   DocumentException \{

SAXReader reader = new SAXReader();  
  Document document = reader.read(url);  
  //System.out.println("ok");  
  return document;  
 \}

//获得根元素  
 public Element root(Document doc) \{  
  return doc.getRootElement();  
 \}

//遍历节点并取得其值  
 /\*\*  
  \* @param root  
  \*/  
 public  void node( Element root)  
    \{  
//   String link="";  
//   String tit="";  
//   String pubdate="";  
//   String image="";  
//   String date="";  
//   String source="";  
//   String description;  
//   String Docid;  
//   String Server;  
//   String Samenum;  
//   String  Interfixnum;  
    
   for ( Iterator i = root.elementIterator(); i.hasNext(); )  
    \{  
    Element element1 = (Element) i.next();//遍历出每个接点成功  
    for(Iterator it=element1.elementIterator();it.hasNext();)  
    \{    
     Element element=(Element)it.next();  
                 if (element.getName().equals("link"))//获得节点链接地址  
                  \{  
                   link=element.getText();//获得节点内容  
                   System.out.println(link);  
                  \}  
                 else if(element.getName().equals("tit") )//获得新闻标题  
                  \{  
                   tit=element.getText();  
                   System.out.println(tit);  
                  \}  
                 else if(element.getName().equals("pubdate"))//检索结果的时间  
                  \{  
                   pubdate=element.getText();  
                   System.out.println(pubdate);  
                  \}  
                else if(element.getName().equals("date"))//检索结果的日期  
                \{  
                 date=element.getText();  
                \}  
                else if(element.getName().equals("image"))//新闻相关图片的地址  
                \{  
                 image=element.getText();  
                \}  
                else if(element.getName().equals("source"))//检索结果的来源  
                \{  
                 source=element.getText();  
                \}  
                else if(element.getName().equals("description"))//检索结果的简介  
                \{  
                 description=element.getText();  
                \}  
                else if(element.getName().equals("Docid"))//检索结果的id  
                \{  
                 Docid=element.getText();  
                \}  
                else if(element.getName().equals("Server"))//检索结果的服务器  
                \{  
                 Server=element.getText();  
                \}  
                else if(element.getName().equals("Samenum"))//检索结果的相同新闻个数  
                \{  
                 Samenum=element.getText();  
                \}  
                else if(element.getName().equals("Interfixnum"))//检索结果的相关新闻个数  
                \{  
                 Interfixnum=element.getText();  
                \}  
                
    \}  
      
      
   \}  
    
    \}

public static void main(String\[\] args) \{  
  TestXml testxml = new TestXml();  
  try \{  
   URL fileurl = new URL(  
     "[http://202.108.2.45//news/news\_xml/xml/allnews.cgi?word=mm&nd=1][http_202.108.2.45_news_news_xml_xml_allnews.cgi_word_mm_nd_1]");  
   //BufferedReader filedata = new BufferedReader(new InputStreamReader(fileurl.openStream()));  
   Document doc = testxml.readxml(fileurl);

Element root = testxml.root(doc);

testxml.node(root);

\} catch (Exception e) \{  
   System.out.println(e.getMessage());  
  \}

[http_202.108.2.45_news_news_xml_xml_allnews.cgi_word_mm_nd_1]: http://202.108.2.45//news/news_xml/xml/allnews.cgi?word=mm&amp;nd=1