一种xml解析二次处理的方法（根据剔除规则仅保留部分二级节点）

最新推荐文章于 2022-09-25 22:17:17 发布

查查24

最新推荐文章于 2022-09-25 22:17:17 发布

阅读量6k

点赞数

分类专栏：笔记文章标签： xml dom操作 dom

本文链接：https://blog.csdn.net/m0_37611361/article/details/111213164

版权

笔记专栏收录该内容

27 篇文章 0 订阅

订阅专栏

处理前的xml文件：

<?xml version="1.0" encoding="UTF-8"?>
<product_set>
    <product>
        <product_id>614944313705</product_id>
        <click_sku_id>614944313705</click_sku_id>
        <product_name><![CDATA[oppo钢化水凝膜a3全屏覆盖a3s无白边a1防摔爆护眼抗蓝光膜oppoa3手机屏幕oqqo贴膜软膜oppoa3s保护膜oppoa1]]></product_name>
        <expiration_time>2022-12-14 01:12:14</expiration_time>
        <image_url><![CDATA[https://img.alicdn.com/imgextra/i1/2206948455447/O1CN01kkILjC1q6lxhX85iX_!!0-item_pic.jpg]]></image_url>
        <target_url_mobile><![CDATA[https://huodong.taobao.com/wow/z/usergrowth/outside/dpa_module?wh_biz=tm&force_no_smb=true&bc_fl_src=growth_dhh_3843640202_100-450957-2089633783&dpa_material_id=614944313705&dpa_material_type=1&dpa_source_code=10082&itemIds=614944313705&spm=2014.ugdhh.3843640202.100-450957-2089633783]]></target_url_mobile>
        <target_url_android><![CDATA[tbopen://m.taobao.com/tbopen/index.html?action=ali.open.nav&bc_fl_src=growth_dhh_3843640202_100-450957-2089633783&bootImage=0&dpa_material_id=614944313705&dpa_material_type=1&dpa_source_code=10082&itemIds=614944313705&module=h5&source=auto&spm=2014.ugdhh.3843640202.100-450957-2089633783&h5Url=https://huodong.taobao.com/wow/z/usergrowth/outside/dpa_module?wh_biz%3Dtm%26force_no_smb%3Dtrue%26bc_fl_src%3Dgrowth_dhh_3843640202_100-450957-2089633783%26dpa_material_id%3D614944313705%26dpa_material_type%3D1%26dpa_source_code%3D10082%26itemIds%3D614944313705%26spm%3D2014.ugdhh.3843640202.100-450957-2089633783]]></target_url_android>
        <target_url_ios><![CDATA[tbopen://m.taobao.com/tbopen/index.html?action=ali.open.nav&bc_fl_src=growth_dhh_3843640202_100-450957-2089633783&bootImage=0&dpa_material_id=614944313705&dpa_material_type=1&dpa_source_code=10082&itemIds=614944313705&module=h5&source=auto&spm=2014.ugdhh.3843640202.100-450957-2089633783&h5Url=https://huodong.taobao.com/wow/z/usergrowth/outside/dpa_module?wh_biz%3Dtm%26force_no_smb%3Dtrue%26bc_fl_src%3Dgrowth_dhh_3843640202_100-450957-2089633783%26dpa_material_id%3D614944313705%26dpa_material_type%3D1%26dpa_source_code%3D10082%26itemIds%3D614944313705%26spm%3D2014.ugdhh.3843640202.100-450957-2089633783]]></target_url_ios>
        <product_short_name><![CDATA[总副 oppo a3水凝膜]]></product_short_name>
        <third_category_id>50012587</third_category_id>
        <third_category_name><![CDATA[手机贴膜]]></third_category_name>
        <price>10</price>
        <sale_price>10</sale_price>
    </product>
    <product>
        <product_id>615130411096</product_id>
        <click_sku_id>615130411096</click_sku_id>
        <product_name><![CDATA[小白嘴山药铁棍山药新鲜蔬菜铁杆淮山药5斤装非河南焦作温县垆土]]></product_name>
        <expiration_time>2022-12-14 01:12:14</expiration_time>
        <image_url><![CDATA[https://img.alicdn.com/imgextra/i2/2207816494036/O1CN01FQQp1Q1fgX74GLegt_!!0-item_pic.jpg]]></image_url>
        <target_url_mobile><![CDATA[https://huodong.taobao.com/wow/z/usergrowth/outside/dpa_module?wh_biz=tm&force_no_smb=true&bc_fl_src=growth_dhh_3843640202_100-450957-2089633783&dpa_material_id=615130411096&dpa_material_type=1&dpa_source_code=10082&itemIds=615130411096&spm=2014.ugdhh.3843640202.100-450957-2089633783]]></target_url_mobile>
        <target_url_android><![CDATA[tbopen://m.taobao.com/tbopen/index.html?action=ali.open.nav&bc_fl_src=growth_dhh_3843640202_100-450957-2089633783&bootImage=0&dpa_material_id=615130411096&dpa_material_type=1&dpa_source_code=10082&itemIds=615130411096&module=h5&source=auto&spm=2014.ugdhh.3843640202.100-450957-2089633783&h5Url=https://huodong.taobao.com/wow/z/usergrowth/outside/dpa_module?wh_biz%3Dtm%26force_no_smb%3Dtrue%26bc_fl_src%3Dgrowth_dhh_3843640202_100-450957-2089633783%26dpa_material_id%3D615130411096%26dpa_material_type%3D1%26dpa_source_code%3D10082%26itemIds%3D615130411096%26spm%3D2014.ugdhh.3843640202.100-450957-2089633783]]></target_url_android>
        <target_url_ios><![CDATA[tbopen://m.taobao.com/tbopen/index.html?action=ali.open.nav&bc_fl_src=growth_dhh_3843640202_100-450957-2089633783&bootImage=0&dpa_material_id=615130411096&dpa_material_type=1&dpa_source_code=10082&itemIds=615130411096&module=h5&source=auto&spm=2014.ugdhh.3843640202.100-450957-2089633783&h5Url=https://huodong.taobao.com/wow/z/usergrowth/outside/dpa_module?wh_biz%3Dtm%26force_no_smb%3Dtrue%26bc_fl_src%3Dgrowth_dhh_3843640202_100-450957-2089633783%26dpa_material_id%3D615130411096%26dpa_material_type%3D1%26dpa_source_code%3D10082%26itemIds%3D615130411096%26spm%3D2014.ugdhh.3843640202.100-450957-2089633783]]></target_url_ios>
        <product_short_name><![CDATA[小白嘴山药铁棍山药新鲜蔬菜铁杆淮山药5斤]]></product_short_name>
        <third_category_id>50050721</third_category_id>
        <third_category_name><![CDATA[新鲜山药]]></third_category_name>
        <price>66</price>
        <sale_price>66</sale_price>
    </product>
    <product>
        <product_id>615818020475</product_id>
        <click_sku_id>615818020475</click_sku_id>
        <product_name><![CDATA[发光掏耳神器挖耳勺带灯宝宝儿童采耳掏耳朵淘扣工具套装可视耳屎]]></product_name>
        <expiration_time>2022-12-14 01:12:14</expiration_time>
        <image_url><![CDATA[https://img.alicdn.com/imgextra/i3/4185085665/O1CN017n2fTh1ricLAKCRgr_!!0-item_pic.jpg]]></image_url>
        <target_url_mobile><![CDATA[https://huodong.taobao.com/wow/z/usergrowth/outside/dpa_module?wh_biz=tm&force_no_smb=true&bc_fl_src=growth_dhh_3843640202_100-450957-2089633783&dpa_material_id=615818020475&dpa_material_type=1&dpa_source_code=10082&itemIds=615818020475&spm=2014.ugdhh.3843640202.100-450957-2089633783]]></target_url_mobile>
        <target_url_android><![CDATA[tbopen://m.taobao.com/tbopen/index.html?action=ali.open.nav&bc_fl_src=growth_dhh_3843640202_100-450957-2089633783&bootImage=0&dpa_material_id=615818020475&dpa_material_type=1&dpa_source_code=10082&itemIds=615818020475&module=h5&source=auto&spm=2014.ugdhh.3843640202.100-450957-2089633783&h5Url=https://huodong.taobao.com/wow/z/usergrowth/outside/dpa_module?wh_biz%3Dtm%26force_no_smb%3Dtrue%26bc_fl_src%3Dgrowth_dhh_3843640202_100-450957-2089633783%26dpa_material_id%3D615818020475%26dpa_material_type%3D1%26dpa_source_code%3D10082%26itemIds%3D615818020475%26spm%3D2014.ugdhh.3843640202.100-450957-2089633783]]></target_url_android>
        <target_url_ios><![CDATA[tbopen://m.taobao.com/tbopen/index.html?action=ali.open.nav&bc_fl_src=growth_dhh_3843640202_100-450957-2089633783&bootImage=0&dpa_material_id=615818020475&dpa_material_type=1&dpa_source_code=10082&itemIds=615818020475&module=h5&source=auto&spm=2014.ugdhh.3843640202.100-450957-2089633783&h5Url=https://huodong.taobao.com/wow/z/usergrowth/outside/dpa_module?wh_biz%3Dtm%26force_no_smb%3Dtrue%26bc_fl_src%3Dgrowth_dhh_3843640202_100-450957-2089633783%26dpa_material_id%3D615818020475%26dpa_material_type%3D1%26dpa_source_code%3D10082%26itemIds%3D615818020475%26spm%3D2014.ugdhh.3843640202.100-450957-2089633783]]></target_url_ios>
        <product_short_name><![CDATA[PROMISE/承诺 008]]></product_short_name>
        <third_category_id>50007005</third_category_id>
        <third_category_name><![CDATA[耳勺]]></third_category_name>
        <price>38</price>
        <sale_price>38</sale_price>
    </product>
</product_set>

处理后的xml文件：

<?xml version="1.0" encoding="UTF-8"?>

<product_set>
    <product>
        <product_id>614944313705</product_id>
        <click_sku_id>614944313705</click_sku_id>
        <product_name><![CDATA[oppo钢化水凝膜a3全屏覆盖a3s无白边a1防摔爆护眼抗蓝光膜oppoa3手机屏幕oqqo贴膜软膜oppoa3s保护膜oppoa1]]></product_name>
        <expiration_time>2022-12-14 01:12:14</expiration_time>
        <image_url><![CDATA[https://img.alicdn.com/imgextra/i1/2206948455447/O1CN01kkILjC1q6lxhX85iX_!!0-item_pic.jpg]]></image_url>
        <target_url_mobile><![CDATA[https://huodong.taobao.com/wow/z/usergrowth/outside/dpa_module?wh_biz=tm&force_no_smb=true&bc_fl_src=growth_dhh_3843640202_100-450957-2089633783&dpa_material_id=614944313705&dpa_material_type=1&dpa_source_code=10082&itemIds=614944313705&spm=2014.ugdhh.3843640202.100-450957-2089633783]]></target_url_mobile>
        <target_url_android><![CDATA[tbopen://m.taobao.com/tbopen/index.html?action=ali.open.nav&bc_fl_src=growth_dhh_3843640202_100-450957-2089633783&bootImage=0&dpa_material_id=614944313705&dpa_material_type=1&dpa_source_code=10082&itemIds=614944313705&module=h5&source=auto&spm=2014.ugdhh.3843640202.100-450957-2089633783&h5Url=https://huodong.taobao.com/wow/z/usergrowth/outside/dpa_module?wh_biz%3Dtm%26force_no_smb%3Dtrue%26bc_fl_src%3Dgrowth_dhh_3843640202_100-450957-2089633783%26dpa_material_id%3D614944313705%26dpa_material_type%3D1%26dpa_source_code%3D10082%26itemIds%3D614944313705%26spm%3D2014.ugdhh.3843640202.100-450957-2089633783]]></target_url_android>
        <target_url_ios><![CDATA[tbopen://m.taobao.com/tbopen/index.html?action=ali.open.nav&bc_fl_src=growth_dhh_3843640202_100-450957-2089633783&bootImage=0&dpa_material_id=614944313705&dpa_material_type=1&dpa_source_code=10082&itemIds=614944313705&module=h5&source=auto&spm=2014.ugdhh.3843640202.100-450957-2089633783&h5Url=https://huodong.taobao.com/wow/z/usergrowth/outside/dpa_module?wh_biz%3Dtm%26force_no_smb%3Dtrue%26bc_fl_src%3Dgrowth_dhh_3843640202_100-450957-2089633783%26dpa_material_id%3D614944313705%26dpa_material_type%3D1%26dpa_source_code%3D10082%26itemIds%3D614944313705%26spm%3D2014.ugdhh.3843640202.100-450957-2089633783]]></target_url_ios>
        <product_short_name><![CDATA[总副 oppo a3水凝膜]]></product_short_name>
        <third_category_id>50012587</third_category_id>
        <third_category_name><![CDATA[手机贴膜]]></third_category_name>
        <price>10</price>
        <sale_price>10</sale_price>
    </product>
</product_set>

具体步骤

1、引入jar

<dependency>
    <groupId>dom4j</groupId>
    <artifactId>dom4j</artifactId>
    <version>1.1</version>
    <scope>test</scope>
</dependency>

2、核心代码

package com.shiyu.test;

import com.alibaba.fastjson.JSON;
import org.dom4j.Attribute;
import org.dom4j.Document;
import org.dom4j.DocumentHelper;
import org.dom4j.Element;
import org.dom4j.io.OutputFormat;
import org.dom4j.io.SAXReader;
import org.dom4j.io.XMLWriter;

import java.io.*;
import java.util.*;

/**
 * @author shiyu
 * @since 2020/12/14
 */
public class MyTest {
	private static final String LABEL_LIST = "其他配件,剃须刀,口罩,台历,咸鸭蛋,围裙,地垫,地毯,垃圾桶,垃圾袋,定制窗帘,居家鞋,山核桃,成品窗帘,扇子,手机贴膜,护发素,护目镜,挂钟,松子,柠檬,椅垫,榴莲,沐浴球,沐浴露,沙发垫,洗发水,洗手液,洗护套装,浴巾,浴帘杆,海参,海绵擦,湿巾,漱口水,牙膏,牛排,番茄,百洁布,眼罩,眼霜,移动电源,管道疏通器,糖果,纽扣,芒果,芒果干,苹果,隔音耳塞,面膜,鞋垫,飘窗垫,餐垫,香皂";
	
	public static void main(String[] args) {
		try {
			test();
		} catch(Exception e) {
			e.printStackTrace();
		}
	}
	
	public static void test() throws Exception {
		File source = new File("resources/test.xml");
		long time = System.currentTimeMillis();
		File target = new File("resources/test_" + time + ".xml");
		
		int sum = 0, available = 0;
		String[] keywords = LABEL_LIST.split(",");
		Map<String, Integer> map = new HashMap<>();
		
		//1.创建Reader对象
		SAXReader reader = new SAXReader();
		//2.加载xml
		Document doc = reader.read(source);
		//3.获取根节点
		Element root = doc.getRootElement();
		
		Document newDoc = DocumentHelper.createDocument();
		Element newRoot = newDoc.addElement(root.getQName());
		
		//4.遍历所有子节点
		Iterator iterator = root.elementIterator();
		while(iterator.hasNext()) {
			sum++;
			Element stu = (Element) iterator.next();
			List<Attribute> attributes = stu.attributes();
			for(Attribute attribute : attributes) {
				System.out.println(attribute.getValue());
			}
			Iterator iterator1 = stu.elementIterator();
			while(iterator1.hasNext()) {
				Element stuChild = (Element) iterator1.next();
				//System.out.println("节点名：" + stuChild.getName() + "---节点值：" + stuChild.getStringValue());
				if(stuChild.getStringValue().length() > 1) {
					for(String keyword : keywords) {
						if(stuChild.getStringValue().contains(keyword)) {
							if(map.containsKey(keyword)) {
								if(map.get(keyword) > 20){
									continue;
								}
								map.put(keyword, map.get(keyword)+1);
							} else {
								map.put(keyword, 1);
							}
							newRoot.add((Element) stu.clone());
							available++;
						}
					}
				}
			}
			// 限制上限2000
			if(available > 200) break;
		}
		
		// xml格式化样式
		OutputFormat format = OutputFormat.createPrettyPrint(); // 默认样式
		format.setIndentSize(4);                                // 行缩进重置
		
		// 输出xml文件
		XMLWriter writer = new XMLWriter(new FileOutputStream(target), format);
		writer.write(newDoc);
		System.out.println("共:" + sum + ", 符合:" + available);
		System.out.println("匹配详情: " + JSON.toJSONString(map));
	}
}