使用java将doc/docx转换成html

需要使用的maven依赖

        <!--注意版本保持一致 poi poi-ooxml  poi-scratchpad-->
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi</artifactId>
            <version>4.1.2</version>
        </dependency>
        <!-- 操作doc ppt xls  -->
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-scratchpad</artifactId>
            <version>4.1.2</version>
        </dependency>
        <!-- 操作docx pptx xlsx  -->
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-ooxml</artifactId>
            <version>4.1.2</version>
        </dependency>
 
        <dependency>
            <groupId>fr.opensagres.xdocreport</groupId>
            <artifactId>fr.opensagres.poi.xwpf.converter.xhtml</artifactId>
            <version>2.0.2</version>
        </dependency>

工具类：

package com.bxkc.utils;


import cn.hutool.core.io.FileUtil;
import fr.opensagres.poi.xwpf.converter.xhtml.XHTMLConverter;
import fr.opensagres.poi.xwpf.converter.xhtml.XHTMLOptions;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.converter.WordToHtmlConverter;
import org.apache.poi.xwpf.usermodel.XWPFDocument;

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

/**
 * word文档转html工具类
 *
 * @author sgz
 * @version 1.0.0
 * @since 2023/7/5
 */

public class WordToHtmlUtil {

    /**
     * doc转换为html
     *
     * @param inputStream 输入流
     * @return html文本
     * @throws TransformerException         TransformerException
     * @throws IOException                  IOException
     * @throws ParserConfigurationException ParserConfigurationException
     */
    public static String convertDoc(InputStream inputStream) throws TransformerException, IOException, ParserConfigurationException {
        HWPFDocument wordDocument = new HWPFDocument(inputStream);
        WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(
                DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());

        wordToHtmlConverter.processDocument(wordDocument);
        org.w3c.dom.Document htmlDocument = wordToHtmlConverter.getDocument();

        // 写入到输出流中
        ByteArrayOutputStream byteOut = new ByteArrayOutputStream();
        OutputStream outStream = new BufferedOutputStream(byteOut);

        DOMSource domSource = new DOMSource(htmlDocument);
        StreamResult streamResult = new StreamResult(outStream);
        TransformerFactory factory = TransformerFactory.newInstance();
        Transformer serializer = factory.newTransformer();
        serializer.setOutputProperty(OutputKeys.ENCODING, "utf-8");
        serializer.setOutputProperty(OutputKeys.INDENT, "yes");
        serializer.setOutputProperty(OutputKeys.METHOD, "html");
        serializer.transform(domSource, streamResult);


        wordToHtmlConverter.processDocument(wordDocument);
        // 有图片需要进行图片处理， 保存图片
//        wordToHtmlConverter.setPicturesManager(new PicturesManager() {
//            public String savePicture(byte[] content, PictureType pictureType, String suggestedName, float widthInches, float heightInches) {
//                return "test/" + suggestedName;
//            }
//        });
//        wordToHtmlConverter.processDocument(wordDocument);
//        // 保存图片
//        List<Picture> pics = wordDocument.getPicturesTable().getAllPictures();
//        if (pics != null) {
//            for (int i = 0; i < pics.size(); i++) {
//                Picture pic = (Picture) pics.get(i);
//                System.out.println();
//                try {
//                    pic.writeImageContent(new FileOutputStream(tempPath + pic.suggestFullFileName()));
//                } catch (FileNotFoundException e) {
//                    e.printStackTrace();
//                }
//            }
//        }
        String byteOutString = byteOut.toString();
        inputStream.close();
        wordDocument.close();
        outStream.close();
        byteOut.close();
        return byteOutString;
    }

    /**
     * doc转换为html
     *
     * @param inputStream 输入流
     * @param outFile     输出文件
     * @throws TransformerException         TransformerException
     * @throws IOException                  IOException
     * @throws ParserConfigurationException ParserConfigurationException
     */
    public static void convertDoc(InputStream inputStream, File outFile) throws TransformerException, IOException, ParserConfigurationException {
        String htmlDoc = convertDoc(inputStream);
        FileUtil.writeString(htmlDoc, outFile, "utf-8");
    }

    /**
     * docx转换为html
     *
     * @param inputStream 输入流
     * @return html文本
     * @throws IOException IOException
     */
    public static String convertDocx(InputStream inputStream) throws IOException {
        XWPFDocument document = new XWPFDocument(inputStream);
        XHTMLOptions options = XHTMLOptions.create().indent(4);
        // 导出图片
//        File imageFolder = new File(tempPath);
//        options.setExtractor(new FileImageExtractor(imageFolder));
//        // URI resolver
//        options.URIResolver(new FileURIResolver(imageFolder));

        // 写入到输出流中
        ByteArrayOutputStream byteOut = new ByteArrayOutputStream();
        OutputStream outStream = new BufferedOutputStream(byteOut);

        XHTMLConverter.getInstance().convert(document, outStream, options);

        String byteOutString = byteOut.toString();
        inputStream.close();
        outStream.close();
        document.close();
        return byteOutString;
    }

    /**
     * docx转换为html
     *
     * @param inputStream 输入流
     * @param outFile     输出文件
     * @throws IOException IOException
     */
    public static void convertDocx(InputStream inputStream, File outFile) throws IOException {
        String htmlDoc = convertDocx(inputStream);
        FileUtil.writeString(htmlDoc, outFile, "utf-8");
    }

}

亲测可以使用