Jsoup采集百度新闻内容，网页显示并实时更新

太过爱你忘了你带给我的痛 2022-06-12 11:59 93阅读 0赞

采集目标：

![Center][]

代码：

PaChong.java(采集的业务逻辑)

package com.jsoup;
    
    import java.net.URL;
    import java.util.ArrayList;
    import java.util.List;
    
    import org.jsoup.Jsoup;
    import org.jsoup.nodes.Document;
    import org.jsoup.nodes.Element;
    import org.jsoup.select.Elements;
    
    import com.bean.News;
    import com.dao.NewsDao;
    
    public class PaChong {
        
    	public static List<News> PaChongData(){
    		 List<News> list = new ArrayList<News>();
        try {
    	  	  Document doc = Jsoup.connect("http://news.baidu.com/n?cmd=4&class=enternews&pn=1").get();
    	  	  //System.out.println(doc);
    	  	  Element e = doc.getElementsByClass("p2").first();
    	  	  Elements es = e.children();   //不包含外层div
    	  	  for(int i=0; i<es.size(); i++){
    	  		Element nodes = es.get(i);    //获取一个div段
    	  		String  from = nodes.getElementsByClass("c").first().text();   //获取新闻来源
    	  		Element content = nodes.getElementsByTag("a").first();
    	  		String title = content.text();     //获取链接和题目
    	  		String url = content.attr("href");
    	  		News neww = new News();
    	  		neww.setFroms(from);
    	  		neww.setTitle(title);
    	  		neww.setUrl(url);
    	  		NewsDao dao =new NewsDao();
    	  		dao.insert(neww);
    	  		list.add(neww);
    	  	}
    	 } catch (Exception e) {
    	  		// TODO Auto-generated catch block
    	  		e.printStackTrace();
    	  }
        return list;
    	}
    	
    	//测试类
    	public static void main(String[] args) {
    		// TODO Auto-generated method stub
    		 List<News> lists = PaChongData();    //采集数据
    		 for(int i=0 ; i<lists.size(); i++){
    			 News news = lists.get(i);
    			 System.out.println(news.getFroms()+"\n"+news.getTitle()+"\n"+news.getUrl()+"\n");
    		 }
    	}
    
    }

News.java

package com.bean;
    
    public class News {
      private Integer id;     //新闻ID
      private String froms;   //新闻来源
      private String title;   //新闻标题
      private String url;     //新闻路径
    public Integer getId() {
    	return id;
    }
    public void setId(Integer id) {
    	this.id = id;
    }
    public String getFroms() {
    	return froms;
    }
    public void setFroms(String froms) {
    	this.froms = froms;
    }
    public String getTitle() {
    	return title;
    }
    public void setTitle(String title) {
    	this.title = title;
    }
    public String getUrl() {
    	return url;
    }
    public void setUrl(String url) {
    	this.url = url;
    }
      
      
    }

NewsDao.java(数据访问层)

package com.dao;
    
    import java.sql.ResultSet;
    import java.sql.SQLException;
    import java.util.ArrayList;
    import java.util.List;
    
    import com.bean.News;
    import com.mysql.jdbc.Connection;
    import com.mysql.jdbc.PreparedStatement;
    import com.util.DButil;
    
    public class NewsDao {
    	public void insert(News news) {
    		// TODO Auto-generated method stub
    		Connection conn=null;
    		PreparedStatement ps=null;
    		try {
    			conn = DButil.open();
    			String sql="insert into news(froms,title,url) values(?,?,?)"; 
    			ps=(PreparedStatement) conn.prepareStatement(sql);
    			ps.setString(1, news.getFroms());
    			ps.setString(2, news.getTitle());
    			ps.setString(3, news.getUrl());
    			ps.executeUpdate();
    			System.out.println("数据库读写成功!");
    		} catch (SQLException e) {
    			// TODO Auto-generated catch block 
    			System.out.println("数据库读写失败!");
    			e.printStackTrace();
    		}
    		finally {
    			DButil.close(conn);
    		}
    	}
    	
    	public List<News> findAllNews() {
    		// TODO Auto-generated method stub
    		String sql="select * from news";
    		Connection conn=DButil.open(); 
    		List<News> list = new ArrayList<News>();
    		try {  
    			PreparedStatement pstmt=(PreparedStatement) conn.prepareStatement(sql);  
                ResultSet rs=pstmt.executeQuery(sql);//执行查询该表  
                while(rs.next())  
                {  
                	int id =rs.getInt(1);
                	String froms = rs.getString(2);
                	String title = rs.getString(3);
                	String url = rs.getString(4);
                    News newss = new News();
                    newss.setId(id);
                    newss.setFroms(froms);
                    newss.setTitle(title);
                    newss.setUrl(url);
                    list.add(newss);
                    System.out.println("查询数据成功！");
                }  
            } catch (SQLException e) {  
                // TODO Auto-generated catch block  
                e.printStackTrace(); 
                System.out.println("查询数据失败！");
            }  
            finally {  
                DButil.close(conn);  
            }  
    		return list;
    	}
    }

PaChong.jsp(采集的新闻头条用网页展示，可点击查看新闻)

<%@page import="com.bean.News"%>
    <%@page import="java.util.List"%>
    <%@page import="com.dao.NewsDao"%>
    <%@ page language="java" contentType="text/html; charset=UTF-8"
        pageEncoding="UTF-8"%>
    <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
    <html>
    <head>
    <meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
    <title>新闻头条</title>
    </head>
    <body>
    <center>
    <h1>新闻头条</h1>
    <hr/>
    <table border="0" width="700px">
    <tr>
      <td align="left">新闻标题</td>
      <td align="right">新闻来源</td>
    </tr>
    <%
      NewsDao dao = new NewsDao();
      List<News> list = dao.findAllNews();
      for(int i=0 ; i<list.size(); i++){
    	  News news = list.get(i);
    %>
      <tr>
         <td><a href="<%=news.getUrl()%>"><%=news.getTitle() %></a></td>
         <td align="right"><b><%=news.getFroms() %></b></td>
      </tr>
    <%} %>
    </table>
    </center>
    </body>
    </html>

截图：

采集到的数据存储在数据库中

![Center 1][]

采集的数据形成新闻链接，可点击访问

![Center 2][]

点击第一条新闻，即可查看新闻

![Center 3][]

[Center]: /images/20220612/11b694c346b34f5a8a8e7e2718212b03.png
[Center 1]: /images/20220612/b5921b54fb2f4aec81fbe58b63e70cfd.png
[Center 2]: /images/20220612/28a50b0769ec4033b3047c8cc6741203.png
[Center 3]: /images/20220612/518ebb20d3414ffda3304c2b2a8f5e49.png