word转html

先添加maven依赖

<dependency>
    <groupId>fr.opensagres.xdocreport</groupId>
    <artifactId>fr.opensagres.xdocreport.document</artifactId>
    <version>1.0.5</version>
</dependency>
<dependency>
    <groupId>fr.opensagres.xdocreport</groupId>
    <artifactId>org.apache.poi.xwpf.converter.xhtml</artifactId>
    <version>1.0.5</version>
</dependency>
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi-scratchpad</artifactId>
    <version>3.12</version>
</dependency>
​​​​​​​<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi</artifactId>
    <version>3.13</version>
</dependency>
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi-ooxml</artifactId>
    <version>3.13</version>
</dependency>

上代码

package com.safeneeds.commana.web;

import com.safeneeds.commana.ser.IUploadService;
import com.safeneeds.filemana.entity.TFileInfo;
import com.safeneeds.util.base.BaseAction;
import com.safeneeds.util.base.RetType;
import org.apache.commons.fileupload.FileItem;
import org.apache.commons.fileupload.FileItemFactory;
import org.apache.commons.fileupload.disk.DiskFileItemFactory;
import org.apache.commons.io.FileUtils;
import org.apache.poi.xwpf.converter.core.BasicURIResolver;
import org.apache.poi.xwpf.converter.core.FileImageExtractor;
import org.apache.poi.xwpf.converter.xhtml.XHTMLConverter;
import org.apache.poi.xwpf.converter.xhtml.XHTMLOptions;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.springframework.beans.factory.annotation.Value;
import org.springframework.mock.web.MockMultipartFile;
import org.springframework.stereotype.Controller;
import org.springframework.web.bind.annotation.RequestMapping;
import org.springframework.web.bind.annotation.ResponseBody;
import org.springframework.web.bind.annotation.RestController;
import org.springframework.web.multipart.MultipartFile;
import org.springframework.web.multipart.commons.CommonsMultipartFile;

import javax.annotation.Resource;
import java.io.*;
import java.util.UUID;

/**
 * @description
 * @author: czw
 * @create: 2021-08-23 15:24
 **/
@RestController
@RequestMapping("/wordToHtml")
public class WordToHtmlAction extends BaseAction {

    private static final Logger logger = LoggerFactory.getLogger(WordToHtmlAction.class);

    @Resource(name="uploadService")
    private IUploadService uploadService;

    @Value("${FILEBASEPATH}")
    private String FILEBASEPATH;

    @Value("${FileSavePath}")
    private String FILE_SAVE_PATH;


    /**
     * 上传docx文档，返回解析后的Html
     */
    @RequestMapping("/getWordHtmlInfo.idop")
    public RetType docxToHtmlText(MultipartFile file) throws IOException {
        RetType rt = new RetType();
        ByteArrayOutputStream htmlStream = new ByteArrayOutputStream();
        try {
            // 将上传的文件传入Document转换
            XWPFDocument docxDocument = new XWPFDocument(file.getInputStream());
            XHTMLOptions options = XHTMLOptions.create();
            // 设置图片存储路径
            String firstImagePathStr = FILE_SAVE_PATH;
            options.setExtractor(new FileImageExtractor(new File(firstImagePathStr)));
            options.URIResolver(new BasicURIResolver(firstImagePathStr));
            // 转换html
            docxDocument.createNumbering();
            XHTMLConverter.getInstance().convert(docxDocument, htmlStream, options);
            String htmlStr = htmlStream.toString();
            String middleImageDirStr = "/word/media";
            String imageDirStr = firstImagePathStr + middleImageDirStr;
            File imageDir = new File(imageDirStr);
            String[] imageList = imageDir.list();
            if (imageList != null) {
                for (int i = 0; i < imageList.length; i++) {
                    try {
                        String oneImagePathStr = imageDirStr + "/" + imageList[i];
                        File fileImage = new File(oneImagePathStr);
                        if (fileImage.exists()) {
                            String name = fileImage.getName();
                            //此处上传到自己的文件服务器
                            InputStream inputStream = new FileInputStream(fileImage);
                            MultipartFile multipartFile = new MockMultipartFile(name, inputStream);
                            RetType retType = uploadService.uplaodFile(multipartFile, name,UUID.randomUUID().toString().replaceAll("-",""));
                            if (!retType.isSuccess()) {
                                continue;
                            } else {
                                TFileInfo fileInfo = (TFileInfo) retType.getData();
                                //修改文档中的图片信息
                                htmlStr = htmlStr.replace(oneImagePathStr, FILEBASEPATH + fileInfo.getFilePath());
                            }
                        }
                    } catch (Exception e) {
                        logger.info("upload docxToHtmlText exception", e);
                        rt.doError(e.toString());
                        return rt;
                    }
                }
            }
            //删除图片路径
            File firstImagePath = new File(firstImagePathStr);
            FileUtils.deleteDirectory(firstImagePath);
            rt.doSuccess(htmlStr);
            return rt;
        } catch (Exception e) {
            logger.error("docxToHtmlText 解析异常", e);
            rt.doError(e.toString());
            return rt;
        } finally {
            if (htmlStream != null) {
                htmlStream.close();
            }
        }
    }

    /**
     * 获取MultipartFile文件
     *
     * @param picPath
     * @return
     */
    private MultipartFile getMulFileByPath(String picPath) {
        FileItem fileItem = createFileItem(picPath);
        MultipartFile mfile = new CommonsMultipartFile(fileItem);
        return mfile;
    }

    private FileItem createFileItem(String filePath) {
        FileItemFactory factory = new DiskFileItemFactory(16, null);
        String textFieldName = "textField";
        int num = filePath.lastIndexOf(".");
        String extFile = filePath.substring(num);
        FileItem item = factory.createItem(textFieldName, "text/plain", true,
                "MyFileName" + extFile);
        File newfile = new File(filePath);
        int bytesRead = 0;
        byte[] buffer = new byte[8192];
        try {
            FileInputStream fis = new FileInputStream(newfile);
            OutputStream os = item.getOutputStream();
            while ((bytesRead = fis.read(buffer, 0, 8192))
                    != -1) {
                os.write(buffer, 0, bytesRead);
            }
            os.close();
            fis.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
        return item;
    }

    public static void main(String[] args) {
        WordToHtmlAction action = new WordToHtmlAction();
        try {
            String content = action.docxToHtmlText(action.getMulFileByPath("F:\\test.docx")).getData().toString();
            System.out.println(content);
        } catch (Exception e) {
            e.printStackTrace();
        }
    }

}