JavaWeb12.4【XML：Jsoup解析器对象的使用】

 

 

<?xml version="1.0" encoding="UTF-8" ?>
<students>
    <student number="itcast_0001">
        <!--<name id="itcast">tom</name>-->
        <name id="itcast">
            <xing>张</xing>
            <ming>三</ming>
        </name>
        <age>9999</age>
        <sex>male</sex>
    </student>
    <student number="itcast_0002">
        <name>sam</name>
        <age>20</age>
        <sex>female</sex>
    </student>
</students>

package com.haifei.jsoup;

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

import java.io.File;
import java.io.IOException;
import java.net.URL;

/**
 * Jsoup对象功能
 */
public class JsoupDemo2 {
    public static void main(String[] args) throws IOException {
        //1 parse​(File in, String charsetName)：解析xml或html文件
        String path = JsoupDemo1.class.getClassLoader().getResource("student.xml").getPath();
        Document document = Jsoup.parse(new File(path), "utf-8");
//        System.out.println(document); //返回字符串形式的xml文档内容

        //2 parse​(String html)：解析xml或html字符串
        String str = "<?xml version=\"1.0\" encoding=\"UTF-8\" ?>\n" +
                "<students>\n" +
                "\t<student number=\"itcast_0001\">\n" +
                "\t\t<name>tom</name>\n" +
                "\t\t<age>9999</age>\n" +
                "\t\t<sex>male</sex>\n" +
                "\t</student>\n" +
                "\t<student number=\"itcast_0002\">\n" +
                "\t\t<name>sam</name>\n" +
                "\t\t<age>20</age>\n" +
                "\t\t<sex>female</sex>\n" +
                "\t</student>\n" +
                "</students>";
        Document document1 = Jsoup.parse(str);
//        System.out.println(document1);

        //3 parse​(URL url, int timeoutMillis)：通过网络路径获取指定的html或xml的文档对象，可爬虫
        URL url = new URL("https://baike.baidu.com/item/jsoup/9012509?fr=aladdin");
        Document document2 = Jsoup.parse(url, 10000);
//        System.out.println(document2); //html网页代码-字符串形式
    }
}

package com.haifei.jsoup;

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

import java.io.File;
import java.io.IOException;

/**
 * Document/Element对象功能
 */
public class JsoupDemo3 {
    public static void main(String[] args) throws IOException {
        String path = JsoupDemo1.class.getClassLoader().getResource("student.xml").getPath();
        Document document = Jsoup.parse(new File(path), "utf-8");

        //1 获取所有student对象
        Elements elements = document.getElementsByTag("student");
//        System.out.println(elements);
        /*
        <student number="itcast_0001">
         <name>
          tom
         </name>
         <age>
          9999
         </age>
         <sex>
          male
         </sex>
        </student>
        <student number="itcast_0002">
         <name>
          sam
         </name>
         <age>
          20
         </age>
         <sex>
          female
         </sex>
        </student>
         */

        //2 获取属性名为id的元素对象
        Elements elements1 = document.getElementsByAttribute("id");
//        System.out.println(elements1);
        /*
        <name id="itcast">
         tom
        </name>
         */

        //3 获取number属性值为itcast_0002的元素对象
        Elements elements2 = document.getElementsByAttributeValue("number", "itcast_0002");
//        System.out.println(elements2);
        /*
        <student number="itcast_0002">
         <name>
          sam
         </name>
         <age>
          20
         </age>
         <sex>
          female
         </sex>
        </student>
         */

        //4 根据id获取值为itcast的元素对象
        Element element = document.getElementById("itcast");
        System.out.println(element);
        /*
        <name id="itcast">
         tom
        </name>
         */
    }
}

package com.haifei.jsoup;

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

import java.io.File;
import java.io.IOException;

/**
 * Element对象功能
 */
public class JsoupDemo4 {
    public static void main(String[] args) throws IOException {
        String path = JsoupDemo1.class.getClassLoader().getResource("student.xml").getPath();
        Document document = Jsoup.parse(new File(path), "utf-8");

        //通过Document对象获取name标签，获取所有的name标签
        Elements elements = document.getElementsByTag("name");
        System.out.println(elements.size()); //2

        Element element_student = document.getElementsByTag("student").get(0);
        Elements element_name = element_student.getElementsByTag("name");
        System.out.println(element_name.size()); //1

        //获取student对象的属性值
        String number = element_student.attr("number");
        System.out.println(number); //itcast_0001

        //获取文本内容
        String text = element_name.text(); //仅获取文本内容
        String html = element_name.html(); //获取标签体的所有内容(包括子标签的字符串内容)
        System.out.println(text); //tom
        System.out.println(html); //tom
        /*
        张 三

        <xing>
         张
        </xing>
        <ming>
         三
        </ming>
         */
    }
}