XPath解析html和xml

最新推荐文章于 2024-07-10 06:14:25 发布

·yying·

最新推荐文章于 2024-07-10 06:14:25 发布

阅读量90

点赞数 1

分类专栏： java 文章标签： xml

本文链接：https://blog.csdn.net/weixin_56232016/article/details/130926526

版权

java 专栏收录该内容

49 篇文章 0 订阅

订阅专栏

java用xpath需要导入JsoupXpath-0.3.2.jar架包

解析html和xml

xpath语法变量

/ : 绝对路径

// : 相对路径

[] : 条件

@ ：指定属性（一般写于[]中或直接写在/后面表示将属性输出）

：通配符（匹配所有对象）

text(): 当前控件下的文本

JXDocument doc = new JXDocument("html/xml");
List<JXNode> list = doc.selN("xpath");	
//JXNode可以.sel()继续搜索下去，JXNode其toString方法为输出其内容
List<Object> list = doc.sel("xpath");

https://www.cnblogs.com/wanghaomiao/p/4899355.html

import cn.wanghaomiao.xpath.exception.XpathSyntaxErrorException;
import cn.wanghaomiao.xpath.model.JXDocument;
import cn.wanghaomiao.xpath.model.JXNode;

import java.util.List;

public class test {
    public static void main(String[] args) throws  XpathSyntaxErrorException {
        JXDocument doc = new JXDocument(
                "<?xml version="1.0" encoding="UTF-8"?>\n" +
                        "<apps>\n" +
                        "\t<app>\n" +
                        "\t\t<id>1</id>\n" +
                        "\t\t<name>Google</name>\n" +
                        "\t\t<version>1.0</version>\n" +
                        "\t</app>\n" +
                        "\t<app>\n" +
                        "\t\t<id>2</id>\n" +
                        "\t\t<name>Edge</name>\n" +
                        "\t\t<version>2.0</version>\n" +
                        "\t</app>\n" +
                        "</apps>"
        );
        List<JXNode> list = doc.selN("//app");
        System.out.println("------------");
        for (int i = 0; i < list.size(); i++) {
            JXNode app = list.get(i);
            System.out.println("id:"+app.sel("id/text()").get(0));
            System.out.println("name:"+app.sel("name/text()").get(0));
            System.out.println("version:"+app.sel("version/text()").get(0));
            System.out.println("------------");
        }
    }
}
/*
运行结果：
------------
id:1
name:Google
version:1.0
------------
id:2
name:Edge
version:2.0
------------
*/

import cn.wanghaomiao.xpath.exception.XpathSyntaxErrorException;
import cn.wanghaomiao.xpath.model.JXDocument;
import cn.wanghaomiao.xpath.model.JXNode;

import java.util.List;

public class test {
    public static void main(String[] args) throws  XpathSyntaxErrorException {
        JXDocument doc = new JXDocument(
                "<!DOCTYPE html>\n" +
                        "<html lang="en">\n" +
                        "<head>\n" +
                        "    <meta charset="UTF-8">\n" +
                        "    <title>Title</title>\n" +
                        "</head>\n" +
                        "<body>\n" +
                        "    <div class="apps">\n" +
                        "        <div class="app" style="color: red">\n" +
                        "            <p2 class="id">1</p2>\n" +
                        "            <p2 class="name">Google</p2>\n" +
                        "            <p2 class="version">1.0</p2>\n" +
                        "        </div>\n" +
                        "        <div class="app" style="color: blue">\n" +
                        "            <p2 class="id">2</p2>\n" +
                        "            <p2 class="name">Edge</p2>\n" +
                        "            <p2 class="version">2.1</p2>\n" +
                        "        </div>\n" +
                        "    </div>\n" +
                        "</body>\n" +
                        "</html>"
        );
        List<JXNode> list = doc.selN("//div[@class='app']");
        System.out.println("------------");
        for (int i = 0; i < list.size(); i++) {
            JXNode app = list.get(i);
            System.out.println("style"+app.sel("@style").get(0));
            System.out.println("id:"+app.sel("p2[@class='id']/text()").get(0));
            System.out.println("name:"+app.sel("p2[@class='name']/text()").get(0));
            System.out.println("version:"+app.sel("p2[@class='version']/text()").get(0));
            System.out.println("------------");
        }
    }
}
/*
运行结果：
------------
stylecolor: red
id:1
name:Google
version:1.0
------------
stylecolor: blue
id:2
name:Edge
version:2.1
------------
*/