HTMLからWordへのポイ

<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi</artifactId>
    <version>4.1.2</version>
</dependency>

<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi-ooxml</artifactId>
    <version>4.1.2</version>
</dependency>

import java.io.*;
import org.apache.poi.xwpf.usermodel.*;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

public class Main {
    public static void main(String[] args) {
        try {
            // 解析HTML文件
            File input = new File("input.html");
            Document doc = Jsoup.parse(input, "UTF-8");

            // 创建Word文档
            XWPFDocument docx = new XWPFDocument();
            FileOutputStream out = new FileOutputStream(new File("output.docx"));

            // 获取HTML文件中的段落
            Elements paras = doc.select("p");
            for (Element para : paras) {
                // 在Word文档中创建段落
                XWPFParagraph newPara = docx.createParagraph();
                // 将HTML内容添加到段落中
                newPara.createRun().setText(para.text());
            }

            // 保存Word文档
            docx.write(out);
            out.close();
            docx.close();

            System.out.println("HTML文件已成功转换为Word文档！");
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}