XML约束schema和Jsoup使用

创建约束规则

<?xml version="1.0"?>
<xsd:schema xmlns="http://www.itcast.cn/xml"
        xmlns:xsd="http://www.w3.org/2001/XMLSchema"
        targetNamespace="http://www.itcast.cn/xml" elementFormDefault="qualified">


    <!--为跟结点student设置根约束-->
    <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>


    <!--为nage,age,sex,number设定格式-->
    <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="heima_\d{4}"/>
        </xsd:restriction>
    </xsd:simpleType>
</xsd:schema>

创建 student.xml,使用了上面的约束

<?xml version="1.0" encoding="UTF-8" ?>
<!-- 
	1.填写xml文档的根元素
	2.引入xsi前缀.  xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
	3.为每一个xsd约束声明一个前缀,作为标识  xmlns="http://www.itcast.cn/xml"
	4.引入xsd文件命名空间.  xsi:schemaLocation="http://www.itcast.cn/xml  student.xsd"

	
 -->
<students   xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
			xmlns="http://www.itcast.cn/xml"
			xsi:schemaLocation="http://www.itcast.cn/xml  student.xsd"
>
	<student number="heima_0001">
		<name>tom</name>
		<age>18</age>
		<sex>male</sex>
	</student>

</students>

2 Jsoup的使用

2-1 Jsoup简单入门

package cn.itcast.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;

/**
 * Jsoup快速入门
 */
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 = JsoupDemo1.class.getClassLoader().getResource("student.xml").getPath();
        //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");
        //3.获取元素对象 Element
        Elements elements = document.getElementsByTag("name");

        System.out.println(elements.size());
        //3.1获取第一个name的Element对象
        Element element = elements.get(0);
        //3.2获取数据
        String name = element.text();
        System.out.println(name);
    }

}

2-2 Jsoup可以解析的类型

File文档
html/xml
-网络的URL

package cn.itcast.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;
import java.net.URL;

/**
 * Jsoup对象功能
 */
public class JsoupDemo2 {
    public static void main(String[] args) throws IOException {
        //2.1获取student.xml的path
        String path = JsoupDemo2.class.getClassLoader().getResource("student.xml").getPath();
        //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)：解析xml或html字符串
       /* String str = "<?xml version=\"1.0\" encoding=\"UTF-8\" ?>\n" +
                "\n" +
                "<students>\n" +
                "\t<student number=\"heima_0001\">\n" +
                "\t\t<name>tom</name>\n" +
                "\t\t<age>18</age>\n" +
                "\t\t<sex>male</sex>\n" +
                "\t</student>\n" +
                "\t<student number=\"heima_0002\">\n" +
                "\t\t<name>jack</name>\n" +
                "\t\t<age>18</age>\n" +
                "\t\t<sex>female</sex>\n" +
                "\t</student>\n" +
                "\n" +
                "</students>";
        Document document = Jsoup.parse(str);
        System.out.println(document);*/

       //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://baike.baidu.com/item/jsoup/9012509?fr=aladdin");//代表网络中的一个资源路径
        Document document = Jsoup.parse(url, 10000);
        System.out.println(document);

    }

}

2-3 Jsoup得到document/element对象

package cn.itcast.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;
import java.net.URL;

/**
 * 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 = JsoupDemo3.class.getClassLoader().getResource("student.xml").getPath();
        //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("id");
        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", "heima_0001");
        System.out.println(elements2);

        System.out.println("-----------");
        //3.3获取id属性值的元素对象
        Element itcast = document.getElementById("itcast");
        System.out.println(itcast);
    }

}

2-4 element对象功能

package cn.itcast.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;

/**
 *Element对象功能
 */
public class JsoupDemo4 {
    public static void main(String[] args) throws IOException {
        //1.获取student.xml的path
        String path = JsoupDemo4.class.getClassLoader().getResource("student.xml").getPath();
        //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);
    }

}

2-5 选择器的查询

package cn.itcast.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;

/**
 *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 = JsoupDemo5.class.getClassLoader().getResource("student.xml").getPath();
        //2.获取Document对象
        Document document = Jsoup.parse(new File(path), "utf-8");

        //3.查询name标签
        /*
            div{

            }
         */
        Elements elements = document.select("name");
        System.out.println(elements);
        System.out.println("=----------------");
        //4.查询id值为itcast的元素
        Elements elements1 = document.select("#itcast");
        System.out.println(elements1);
        System.out.println("----------------");
        //5.获取student标签并且number属性值为heima_0001的age子标签
        //5.1.获取student标签并且number属性值为heima_0001
        Elements elements2 = document.select("student[number=\"heima_0001\"]");
        System.out.println(elements2);
        System.out.println("----------------");

        //5.2获取student标签并且number属性值为heima_0001的age子标签
        Elements elements3 = document.select("student[number=\"heima_0001\"] > age");
        System.out.println(elements3);

    }

}

2-6 Xpath语法查询

package cn.itcast.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 org.jsoup.select.Elements;

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 = JsoupDemo6.class.getClassLoader().getResource("student.xml").getPath();
        //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='itcast']");
        for (JXNode jxNode : jxNodes4) {
            System.out.println(jxNode);
        }
    }

}

posted @ 2020-03-14 13:11 姚狗蛋阅读(164) 评论(0) 编辑收藏举报

刷新页面返回顶部

王思雨

虽然辛苦，我还是选择滚烫的人生

XML约束schema和Jsoup使用

创建约束规则

创建 student.xml,使用了上面的约束

2 Jsoup的使用

2-1 Jsoup简单入门

2-2 Jsoup可以解析的类型

2-3 Jsoup得到document/element对象

2-4 element对象功能

2-5 选择器的查询

2-6 Xpath语法查询

公告