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
xhxxx7 小时前
别再被 CSS 定位搞晕了!5 种 position 一图打尽 + 实战代码全公开
前端·css·html
wangbing11257 小时前
将swagger在线文档转为word
microsoft·c#·word
询问QQ688238868 小时前
基于偏最小二乘算法(PLS)的多输出数据回归预测
html
挫折常伴左右10 小时前
初见HTML
前端·html
kiki-bf1 天前
使用python把图片转为word
开发语言·python·word
一水鉴天1 天前
整体设计 定稿 之24 dashboard.html 增加三层次动态记录体系仪表盘 之2 程序 (Q208 之1)
前端·html
一水鉴天1 天前
整体设计 定稿 之22 dashboard.html 增加三层次动态记录体系仪表盘 之1
前端·html
开开心心_Every1 天前
Word转PDF工具,免费生成图片型文档
网络·笔记·pdf·word·powerpoint·excel·azure
dlhto1 天前
Markdown转Word操作指南
linux·centos·word
鹿衔`1 天前
StarRocks 2.5.22 混合部署实战文档(CDH环境)
starrocks·apache·paimon