Jsoup的网页工具类

如果有相关问题，可以一起研究下

引入相关依赖

<!-- Html工具 -->
<dependency>
    <groupId>org.jsoup</groupId>
    <artifactId>jsoup</artifactId>
    <version>1.14.1</version>
</dependency>

代码片段

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

import java.io.*;
import java.nio.charset.StandardCharsets;

/**
 * @Author: Climbing-pit
 * @Date: 2022/4/19 9:56
 * @Description: 网页工具类
 */
public class HtmlUtil {

    /**
     *  读取本地HTML文件
     *  批量移除某个标签的某个属性
     *  重新写入
     * @param filePath  HTML文件路径
     * @param tagName   标签名，例如<div></div>、<img></img>、<p></p>等等
     * @param attrName  属性名，例如id, class, src, style等等
     * @throws IOException
     */
    public static void removeForTagAttr(String filePath, String tagName, String attrName) throws IOException {

        File in = new File(filePath);
        Document document = Jsoup.parse(in, "UTF-8");
        Elements imgs = document.getElementsByTag(tagName);
        for (Element img : imgs) {
            img.removeAttr(attrName);
        }
        write(in, document);
    }

    /**
     *  读取本地HTML文件
     *  批量修改某个标签的某个属性
     *  重新写入
     * @param filePath  HTML文件路径
     * @param tagName   标签名，例如<div></div>、<img></img>、<p></p>等等
     * @param attrName  属性名，例如id, class, src, style等等
     * @throws IOException
     */
    public static void editForTagAttr(String filePath, String tagName, String attrName, String attrValue) throws IOException {

        File in = new File(filePath);
        Document document = Jsoup.parse(in, "UTF-8");
        Elements imgs = document.getElementsByTag(tagName);
        for (Element img : imgs) {
            img.attr(attrName, attrValue);
        }
        write(in, document);
    }

    /**
     *  编辑完Document后写入
     * @param in    源文件
     * @param document  新的Document
     * @throws IOException
     */
    public static void write(File in, Document document) throws IOException {
        //重新写入
        FileOutputStream fos = new FileOutputStream(in, false);
        OutputStreamWriter osw = new OutputStreamWriter(fos, StandardCharsets.UTF_8);
        osw.write(document.html());
        osw.close();
    }

    public static void main(String[] args) {
        String filePath = "D:\\files\\practice\\testPaper\\1650335157835\\1650335157835.html";
        String tagName = "img";
        String attrName = "alt";
        try {
            HtmlUtil.removeForTagAttr(filePath, tagName, attrName);
        } catch (IOException e) {
            e.printStackTrace();
        }

    }
}

注意：jsoup是基于MIT协议发布的，可放心使用于商业项目。