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
睿智的海鸥2 小时前
Markdown 语法大全详解
开发语言·前端·javascript·css·html
ZC跨境爬虫3 小时前
UI前端美化技能提升日志day8:(Watch专区字体优化+尺寸校准+视觉重构+结构分层)
前端·ui·重构·html
蒋胜山6 小时前
Word 练习题(3)
word
zhenxin01226 小时前
HTML头部元信息避坑指南
前端·html
sghuter6 小时前
HTML头部元信息避坑指南
c语言·前端·html·cocoa
ZC跨境爬虫1 天前
UI前端美化技能提升日志day7:(原生苹方字体全局适配+合规页脚完整像素级落地)
前端·javascript·ui·html·交互
爱上好庆祝1 天前
学习js的第2天
前端·css·学习·html·css3
小矮强1 天前
Word总页码减去首页
word
E_ICEBLUE1 天前
在 Python 中自动化转化 Markdown 为 HTML 【详细教程】
python·自动化·html
华科大胡子1 天前
HTML头部元信息
html