使用Apache POI将Word转HTML

java 复制代码
package com.shengun.utils;


import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.converter.WordToHtmlConverter;
import org.w3c.dom.Document;

import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;
import java.io.*;

public class WordToHtmlTable {


    public static void main(String[] args) throws Exception {
        String path = "C:/Users/28916/Desktop/aaa/";
        try {
            convertToHtml(path + "a.doc", path + "sample.html");
            System.out.println("Word to HTML conversion successful!");
        } catch (Exception e) {
            e.printStackTrace();
        }
    }

    /**
     * 使用Apache POI将Word转HTML
     * @param docFilePath
     * @param htmlFilePath
     * @throws Exception
     */
    public static void convertToHtml(String docFilePath, String htmlFilePath) throws Exception {
        InputStream input = new FileInputStream(new File(docFilePath));
        HWPFDocument wordDocument = new HWPFDocument(input);
        WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(
                DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());
        wordToHtmlConverter.processDocument(wordDocument);

        Document htmlDocument = wordToHtmlConverter.getDocument();
        ByteArrayOutputStream out = new ByteArrayOutputStream();
        DOMSource domSource = new DOMSource(htmlDocument);
        StreamResult streamResult = new StreamResult(out);

        TransformerFactory tf = TransformerFactory.newInstance();
        Transformer serializer = tf.newTransformer();
        serializer.setOutputProperty("encoding", "UTF-8");
        serializer.setOutputProperty("indent", "yes");
        serializer.setOutputProperty("method", "html");
        serializer.transform(domSource, streamResult);

        out.close();

        OutputStream outputStream = new FileOutputStream(htmlFilePath);
        outputStream.write(out.toByteArray());
        outputStream.close();
    }




}
相关推荐
LaughingZhu20 小时前
Product Hunt 每日热榜 | 2026-05-21
前端·人工智能·经验分享·chatgpt·html
顧棟1 天前
Apache-doris 集群扩缩容迁移方案
apache
苦逼的猿宝1 天前
仓储管理系统设计与实现
python·word·markdown
顧棟1 天前
Apache-doris-2.0.2原地滚动升级3.1.4方案
apache
ZC跨境爬虫1 天前
跟着 MDN 学CSS day_5:掌握属性选择器的存否匹配与子字符串匹配
前端·javascript·css·ui·html
ew452181 天前
【Java】Apache POI 终极封装:支持多表格循环、图片插入、日期格式化的Word导出工具类(兼容POI3.17+)
java·word·apache
拉里呱唧1 天前
在线可视化HTML编辑器横评:8款拖拽式工具的实测对比
前端·编辑器·html
小皮蛋儿子1 天前
mac 微信双开
linux·服务器·apache
三乐2282 天前
简单定位布局
html
Zzzzmo_2 天前
【HTML+CSS+JavaScript】01 HTML标签
html