Java第四十一天，XML系列（三），解析XML（二）—— Jsoup

一、步骤

• 导入 jar 包
• 获取 Document 对象
• 获取对应的标签(Element)
• 获取标签数据

二、用到的类

• Jsoup：工具类，可以解析html或xml文档，返回 Document
• Document：文档对象。代表内存中的dom树
• Elements：元秦E1ement对象的集合。可以当做 ArrayList< Element>来使用
• Node：节点对象

三、实战

1. student.xsd 约束文件

<?xml version="1.0"?>
<xsd:schema xmlns="http://www.lanyue.cn/xml"
        xmlns:xsd="http://www.w3.org/2001/XMLSchema"
        targetNamespace="http://www.lanyue.cn/xml" elementFormDefault="qualified">
    <xsd:element name="students" type="studentsType"/>
    <xsd:complexType name="studentsType">
        <xsd:sequence>
            <xsd:element name="student" type="studentType" minOccurs="0" maxOccurs="unbounded"/>
        </xsd:sequence>
    </xsd:complexType>
    <xsd:complexType name="studentType">
        <xsd:sequence>
            <xsd:element name="name" type="xsd:string"/>
            <xsd:element name="age" type="ageType" />
            <xsd:element name="sex" type="sexType" />
        </xsd:sequence>
        <xsd:attribute name="number" type="numberType" use="required"/>
    </xsd:complexType>
    <xsd:simpleType name="sexType">
        <xsd:restriction base="xsd:string">
            <xsd:enumeration value="male"/>
            <xsd:enumeration value="female"/>
        </xsd:restriction>
    </xsd:simpleType>
    <xsd:simpleType name="ageType">
        <xsd:restriction base="xsd:integer">
            <xsd:minInclusive value="0"/>
            <xsd:maxInclusive value="256"/>
        </xsd:restriction>
    </xsd:simpleType>
    <xsd:simpleType name="numberType">
        <xsd:restriction base="xsd:string">
            <xsd:pattern value="d{4}"/>
        </xsd:restriction>
    </xsd:simpleType>
</xsd:schema> 

2. student.xml 文件

<?xml version="1.0" encoding="UTF-8" ?>
<students   xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
			xmlns="http://www.lanyue.cn/xml"
			xsi:schemaLocation="http://www.lanyue.cn/xml  student.xsd"
>
	<student number="0001">
		<name>小红</name>
		<age>18</age>
		<sex>male</sex>
	</student>

	<student number="0002">
		<name>小明</name>
		<age>18</age>
		<sex>female</sex>
	</student>

</students>

3.jar离线包

https://download.csdn.net/download/ITlanyue/12710441

4.测试入口类

（1）入门

package cn.lanyue.xml.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;

public class JsoupDemo1 {
    public static void main(String[] args) throws IOException {
        //2.获取Document对象，根据xml文档获取
        //2.1获取student.xml的path
        String path = "G:\火狐下载\day32_xml\src\resources\student.xml";
        //2.2解析xml文档，加载文档进内存，获取dom树--->Document
        // 字符集必须和文件编码格式一致
        Document document = Jsoup.parse(new File(path), "utf-8");
        //3.获取元素对象 Element 的 name 标签
        Elements elements = document.getElementsByTag("name");
        for(Element e: elements){
            System.out.println(e.text());
        }
    }

}

（2）Jsoup parse 构造函数

package cn.lanyue.xml.jsoup;

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import java.io.File;
import java.io.IOException;
import java.net.URL;

/**
 * parse 的构造方法
 */
public class JsoupDemo2 {
    public static void main(String[] args) throws IOException {
//        2.1获取student.xml的path
        String path = "G:\火狐下载\day32_xml\src\resources\student.xml";
//        2.2解析xml文档，加载文档进内存，获取dom树--->Document
        Document document = Jsoup.parse(new File(path), "utf-8");
        System.out.println(document);

//        2.parse​(String html)：参数为html或xml文档的内容
//
//        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

        URL url = new URL("https://www.baidu.com");
        // 参数为超时时间
        Document documentUrl = Jsoup.parse(url, 10000);
        System.out.println(documentUrl);

    }

}

（3）Document /Element 对象的使用

package cn.lanyue.xml.jsoup;

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
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 {
        //1.获取student.xml的path
        String path = "G:\火狐下载\day32_xml\src\resources\student.xml";
        //2.获取Document对象
        Document document = Jsoup.parse(new File(path), "utf-8");

        //3.获取元素对象了。
        //3.1获取所有student对象
        Elements elements = document.getElementsByTag("student");
        System.out.println(elements);
        System.out.println("-----------");

        //3.2 获取属性名为id的元素对象们
        Elements elements1 = document.getElementsByAttribute("number");
        System.out.println(elements1);
        System.out.println("-----------");

        //3.2获取 number属性值为heima_0001的元素对象
        Elements elements2 = document.getElementsByAttributeValue("number", "0001");
        System.out.println(elements2);
    }

}

（4）Document详细属性

package cn.lanyue.xml.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;

/**
 * 获取Document对象的各种属性值
 */
public class JsoupDemo4 {
    public static void main(String[] args) throws IOException {
        //1.获取student.xml的path
        String path = "G:\火狐下载\day32_xml\src\resources\student.xml";
        //2.获取Document对象
        Document document = Jsoup.parse(new File(path), "utf-8");
        /*
        Element：元素对象
				1. 获取子元素对象
					* getElementById​(String id)：根据id属性值获取唯一的element对象
					* getElementsByTag​(String tagName)：根据标签名称获取元素对象集合
					* getElementsByAttribute​(String key)：根据属性名称获取元素对象集合
					* getElementsByAttributeValue​(String key, String value)：根据对应的属性名和属性值获取元素对象集合

				2. 获取属性值
					* String attr(String key)：根据属性名称获取属性值
				3. 获取文本内容
					* String text():获取所有字标签的纯文本内容
					* String html():获取标签体的所有内容(包括子标签的标签和文本内容)




         */
        //通过Document对象获取name标签，获取所有的name标签，可以获取到两个
        Elements elements = document.getElementsByTag("name");
        System.out.println(elements.size());
        System.out.println("-----------");
        //通过Element对象获取子标签对象
        Element element_student = document.getElementsByTag("student").get(0);
        Elements ele_name = element_student.getElementsByTag("name");
        System.out.println(ele_name.size());

        //获取student对象的属性值
        String number = element_student.attr("NUMBER");
        System.out.println(number);
        System.out.println("-----------");
        //获取文本内容
        String text = ele_name.text();
        String html = ele_name.html();
        System.out.println(text);
        System.out.println(html);
    }

}

5.选择器查询

package cn.lanyue.xml.jsoup;

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.select.Elements;
import java.io.File;
import java.io.IOException;

/**
 * 选择器查询
 */
public class JsoupDemo5 {
    public static void main(String[] args) throws IOException {
        //1.获取student.xml的path
        String path = "G:\火狐下载\day32_xml\src\resources\student.xml";
        //2.获取Document对象
        Document document = Jsoup.parse(new File(path), "utf-8");

        //3.查询name标签
        Elements elements = document.select("name");
        System.out.println(elements);
        System.out.println("=----------------");

        //4.查询id值为的元素
        Elements elements1 = document.select("#0001");
        System.out.println(elements1);
        System.out.println("----------------");

        //5.获取student标签并且number属性值为0001的age子标签
        //5.1.获取student标签并且number属性值为0001
        Elements elements2 = document.select("student[number="0001"]");
        System.out.println(elements2);
        System.out.println("----------------");

        //5.2获取student标签并且number属性值为0001的age子标签
        Elements elements3 = document.select("student[number="0001"] > age");
        System.out.println(elements3);

    }

}

6.Xpath查询

package cn.lanyue.xml.jsoup;

import cn.wanghaomiao.xpath.exception.XpathSyntaxErrorException;
import cn.wanghaomiao.xpath.model.JXDocument;
import cn.wanghaomiao.xpath.model.JXNode;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import java.io.File;
import java.io.IOException;
import java.util.List;

/**
 *XPath查询
 */
public class JsoupDemo6 {
    public static void main(String[] args) throws IOException, XpathSyntaxErrorException {
        //1.获取student.xml的path
        String path = "G:\火狐下载\day32_xml\src\resources\student.xml";
        //2.获取Document对象
        Document document = Jsoup.parse(new File(path), "utf-8");

        //3.根据document对象，创建JXDocument对象
        JXDocument jxDocument = new JXDocument(document);

        //4.结合xpath语法查询
        //4.1查询所有student标签
        List<JXNode> jxNodes = jxDocument.selN("//student");
        for (JXNode jxNode : jxNodes) {
            System.out.println(jxNode);
        }

        System.out.println("--------------------");

        //4.2查询所有student标签下的name标签
        List<JXNode> jxNodes2 = jxDocument.selN("//student/name");
        for (JXNode jxNode : jxNodes2) {
            System.out.println(jxNode);
        }

        System.out.println("--------------------");

        //4.3查询student标签下带有id属性的name标签
        List<JXNode> jxNodes3 = jxDocument.selN("//student/name[@id]");
        for (JXNode jxNode : jxNodes3) {
            System.out.println(jxNode);
        }
        System.out.println("--------------------");
        //4.4查询student标签下带有id属性的name标签 并且id属性值为itcast

        List<JXNode> jxNodes4 = jxDocument.selN("//student/name[@id='0001']");
        for (JXNode jxNode : jxNodes4) {
            System.out.println(jxNode);
        }
    }

}