Jsoup解析Xml{详解}

* 代码：
//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);

<?xml version="1.0" encoding="UTF-8"?>
<users>
    <user id=‘1‘>
        <name>zhangsan</name>
        <age>23</age>
        <gender>male</gender>
        <address>环湖中路36</address>
    </user>

    <user id=‘2‘>
        <name>lisi</name>
        <age>24</age>
        <gender>female</gender>
    </user>
</users>

public class ParseFromStudent {

    public static void main(String[] args) throws IOException {
        String path = "E:\\GItHubRepository\\Lear-Java\\java-growing\\src\\main\\java\\xml_jsoup\\Student.xml";
        Document dom = Jsoup.parse(new File(path), "UTF-8");
        class Student {
            String name;
            int age;
            String gender;

            public Student(String name, int age, String gender) {
                super();
                this.name = name;
                this.age = age;
                this.gender = gender;
            }

            @Override
            public String toString() {
                return "Student [name=" + name + ", age=" + age + ", gender=" + gender + "]";
            }
        }
        Elements element = dom.getElementsByTag("user");

        ArrayList<Student> slist = new ArrayList<>();
        // element.forEach(v->System.out.println(v));
        Iterator<Element> it = element.iterator();
        while (it.hasNext()) {
            Element next = it.next();
            Elements childrens = next.children();
            Iterator<Element> it_child = childrens.iterator();
            String name = null;
            int age = 0;
            String gender = null;
            while (it_child.hasNext()) {
                Element child_node = it_child.next();
                switch (child_node.nodeName()) {
                case "name":
                    name=child_node.text();
                    break;
                case "age":
                    age=Integer.parseInt(child_node.text());
                    break;
                case "gender":
                    gender=child_node.text();
                    break;
                }
            }
            slist.add(new Student(name, age, gender));
        }
        System.out.println(slist);
    }
}

public class ParseFromStudent2 {

    public static void main(String[] args) throws IOException {
        String path = "E:\\GItHubRepository\\Lear-Java\\java-growing\\src\\main\\java\\xml_jsoup\\Student.xml";
        Document dom = Jsoup.parse(new File(path), "UTF-8");
        class Student {
            String name;
            int age;
            String gender;

            public Student(String name, int age, String gender) {
                super();
                this.name = name;
                this.age = age;
                this.gender = gender;
            }

            @Override
            public String toString() {
                return "Student [name=" + name + ", age=" + age + ", gender=" + gender + "]";
            }
        }
        ArrayList<Student> list = new ArrayList<>();
        Elements element = dom.getElementsByTag("user");
        Iterator<Element> it = element.iterator();
        Student stu=null;
        /**
         * 1: 这里是有局限性的 如果我们要的数据 中间穿插几个不需要的数据,或者xml文档以后变化 了 那么我们还得需要改代码
         * 2: 最好的方式就行是使用匹配的方式, 无论 xml源文件 怎么发生变化, 最初的解析版本还是能够使用的
         */
        while(it.hasNext()) {
            Element next = it.next();
            String[] split = next.text().split(" ");
            stu=new Student(split[0], Integer.parseInt(split[1]), split[2]);
            list.add(stu);
        }
        System.out.println(list);
    }
}

2. XPath：XPath即为XML路径语言，它是一种用来确定XML（标准通用标记语言的子集）文档中某部分位置的语言
            * 使用Jsoup的Xpath需要额外导入jar包。
            * 查询w3cshool参考手册，使用xpath的语法完成查询
            * 代码：
                //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);
                }