xml学习

最新推荐文章于 2024-10-17 10:27:13 发布

快乐的一只小青娃

最新推荐文章于 2024-10-17 10:27:13 发布

阅读量85

点赞数

分类专栏：学习笔记文章标签： java xml

本文链接：https://blog.csdn.net/m0_57054441/article/details/118736553

版权

学习笔记专栏收录该内容

8 篇文章 0 订阅

订阅专栏

需要的jar包

1.xml内容：

<?xml version="1.0" encoding="UTF-8"?>
<contacts xmlns="http://xiaochen.com" xmlns:xs="http://www.w3.org/2001/XMLSchema-instance" xs:schemaLocation="http://xiaochen.com  contactsSchema.xsd">
  <linkman id="69"> 
    <name>gg</name>  
    <email>gg@xiaochen.com</email>  
    <address>武汉</address>  
    <group>小陈</group> 
  </linkman>  
  <linkman id="96"> 
    <name>mm</name>  
    <email>mm@qq.com</email>  
    <address>光谷</address>  
    <group>光谷mm</group> 
  </linkman>  
  <linkman id="11">
    <name>mm</name>
    <email>mm@qq.com</email>
    <address>光谷</address>
    <group>光谷dd</group>
  </linkman>
  <linkman id="55">
    <name>mm</name>
    <email>mm@qq.com</email>
    <address>光谷</address>
    <group>光谷dd</group>
  </linkman>
<linkman id="55"><name>mm</name><email>mm@qq.com</email><address>光谷</address><group>光谷dd</group></linkman><linkman id="55"><name>mm</name><email>mm@qq.com</email><address>光谷</address><group>光谷dd</group></linkman></contacts>

添加内容

package com.softeem.dom4j;

import org.dom4j.Document;
import org.dom4j.Element;
import org.dom4j.io.OutputFormat;
import org.dom4j.io.SAXReader;
import org.dom4j.io.XMLWriter;

import java.io.FileWriter;
import java.util.List;

public class dom4j_add_01 {
    public static void main(String[] args) throws Exception {
        SAXReader reader = new SAXReader();
        //得到document 对象
//        Document document = reader.read(dom4j_del_01.class.getResourceAsStream("/b/contacts.xml"));
        Document document = reader.read(dom4j_add_01.class.getClassLoader().getResourceAsStream("b/contacts.xml"));
        //得到根节点对象
        Element contacts = document.getRootElement();

        //得到根节点下面的节点
        List<Element> linkmans = contacts.elements();
        Element linkman = linkmans.get(linkmans.size() - 1);

        //contacts节点下面添加添加一个linkman节点


        Element linkman1 = contacts.addElement("linkman");
        linkman1.addAttribute("id","55");
        linkman1.addElement("name").addText("mm");
        linkman1.addElement("email").addText("mm@qq.com");
        linkman1.addElement("address").addText("光谷");
        linkman1.addElement("group").addText("光谷dd");
        //添加后还没完，添加的只是内存中的数据，将内存中的数据保存到文件中
        //创建一个文件流，参数为xml文件的路径
        FileWriter fw = new FileWriter("resouces/b/contacts.xml");
        document.write(fw);

        OutputFormat of = new OutputFormat().createPrettyPrint();
        XMLWriter xml = new XMLWriter(fw,of);
        xml.write(linkman1);
        fw.close();

    }
}

删除

package com.softeem.dom4j;

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

import javax.print.Doc;
import java.io.FileWriter;
import java.io.IOException;
import java.io.Writer;
import java.util.List;

public class dom4j_del_01 {
    public static void main(String[] args) throws Exception {
        SAXReader reader = new SAXReader();
        //得到document 对象
//        Document document = reader.read(dom4j_del_01.class.getResourceAsStream("/b/contacts.xml"));
        Document document = reader.read(dom4j_del_01.class.getClassLoader().getResourceAsStream("b/contacts.xml"));
        //得到根节点对象
        Element contacts = document.getRootElement();

        //得到根节点下面的节点
        List<Element> linkmans = contacts.elements();
        Element linkman = linkmans.get(linkmans.size() - 1);
        //通过父节点删除子节点
        contacts.remove(linkman);
        //删除后还没完，删除的只是内存中的数据，将内存中的数据保存到文件中
        //创建一个文件流，参数为xml文件的路径
        FileWriter fw = new FileWriter("resouces/b/contacts.xml");
        document.write(fw);
        //关闭流
        fw.close();





        //显示出下面节点的属性值
        /*for (Element e :linkman){
            List<Element> elist = e.elements();
            for (Element el : elist){
                System.out.println(el.getText());
            }
        }*/


    }
}

查看节点

public static void main(String[] args) throws Exception {
        SAXReader reader = new SAXReader();
        //得到document 对象
//        Document document = reader.read(dom4j_del_01.class.getResourceAsStream("/b/contacts.xml"));
        Document document = reader.read(dom4j_work.class.getClassLoader().getResourceAsStream("b/contacts.xml"));
        //得到根节点对象
        Element contacts = document.getRootElement();

        //得到根节点下面的节点
        List<Element> linkmans = contacts.elements();
 //显示出下面节点的属性值
        for (Element e :linkman){
            List<Element> elist = e.elements();
            for (Element el : elist){
                System.out.println(el.getText());
            }
        }
}

jsoup 网络爬虫

package com.softeem.jsoup;

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.select.Elements;

import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.net.MalformedURLException;
import java.net.URL;
import java.net.URLConnection;
import java.util.Date;

public class jsoup01 {
    public static void main(String[] args) throws Exception {
        URL url = new URL("https://www.baidu.com/");
        Document parse = Jsoup.parse(url, 10000);
        Elements imgs = parse.getElementsByTag("img");
        System.out.println(imgs.size());
        for (int i=0;i<=imgs.size()-1;i++){
            String src = imgs.get(i).attr("src");
            System.out.println(src);
            downLoad(src);
        }
    }

    public static void downLoad(String url){
        //封装url为URL对象。
        try {
            URL u = new URL(url);
//这个方法有时候拿不到流,因为有反爬虫机制，看请求头，是不是有浏览器标识。
//            u.openStream()
            // 反反爬虫，，，模拟正常人操作，欺骗电脑，设置机制中需要识别的参数，
            //设置浏览器请求头。
//            User-agent: Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36
            URLConnection uc = u.openConnection();
            uc.setRequestProperty("User-agent","Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36");
            InputStream is = uc.getInputStream();

            //复制文件操作
            FileOutputStream fos = new FileOutputStream(new Date().getTime() + ".png");
            int len;
            byte[] by = new byte[1024];
            while ((len=is.read(by))!=-1){
                fos.write(by);
            }
            fos.close();
            is.close();

        } catch (MalformedURLException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }

    }
}