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
清纯世纪17 小时前
word设置的正文样式,按回车后变成了样式格式
word
ELI_He99918 小时前
WPS制作论文三线表
word·论文
秋邱19 小时前
AR 技术团队搭建与规模化接单:从个人到团队的营收跃迁
前端·人工智能·后端·python·html·restful
OC溥哥99920 小时前
2D,MC像素风跑酷游戏用HTML实现
javascript·游戏·html
m0_7400437320 小时前
Element-UI 组件库的核心组件及其用法
前端·javascript·vue.js·ui·elementui·html
沧海寄馀生20 小时前
Apache Hadoop生态组件部署分享-Kafka
大数据·hadoop·分布式·kafka·apache
沧海寄馀生21 小时前
Apache Hadoop生态组件部署分享-Spark
大数据·hadoop·分布式·spark·apache
踢球的打工仔21 小时前
前端html(3)
前端·算法·html
沧海寄馀生1 天前
Apache Hadoop生态组件部署分享-Sqoop
大数据·hadoop·分布式·apache·sqoop
坚定信念,勇往无前1 天前
vue3图片,pdf,word,excel,ppt多格式文件预览组件Vue Doc Viewers Plus
pdf·word·excel