doc与docx文档转html，格式样式不变（包含图片转换）

        最近做一个富文本的需求，要求把文档内容转换到富文本内，文档中的格式也好，样式也好，图片啥的都要一致展示；踩了不少坑，据说word文档其实是一个压缩包，我不是特别清楚但是也能理解，自己借鉴参考凑合看的，大佬勿喷

        啥都不说了看代码吧；其中关于图片的导出有两种方式比较大的那种是用的jdk8自带的base

64搞的，大小有差别同一个图片的话我这个实测的图片是差200k左右，有要求的你可以换着来引用；jar的引用pom中有

        
        
            org.apache.poi
            poi
            4.1.2
        
        
        
            org.apache.poi
            poi-scratchpad
            4.1.2
        
        
        
            org.apache.poi
            poi-ooxml
            4.1.2
        
       
            fr.opensagres.xdocreport
            fr.opensagres.poi.xwpf.converter.xhtml
            2.0.2
        

 
import fr.opensagres.poi.xwpf.converter.core.BasicURIResolver;
import fr.opensagres.poi.xwpf.converter.core.FileImageExtractor;
import fr.opensagres.poi.xwpf.converter.xhtml.XHTMLConverter;
import fr.opensagres.poi.xwpf.converter.xhtml.XHTMLOptions;
import lombok.extern.slf4j.Slf4j;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.converter.WordToHtmlConverter;
import org.apache.poi.hwpf.usermodel.PictureType;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.springframework.web.multipart.MultipartFile;
import org.w3c.dom.Document;
import sun.misc.BASE64Encoder;
 
import javax.imageio.ImageIO;
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.awt.image.BufferedImage;
import java.io.*;
import java.util.Base64;
 
/**
 * @author ：Xiaoning Fan
 * @date ：Created in 2023-10-16 下午 3:49
 * @description： 上传word文档并转换为html字符串返回，保持样式不变，图片替换为base64
 * @version: 1.0
 */
@Slf4j
public class WordToHtmlStringConverter {
 
    /**
     * wordToHtml
     *
     * @return
     * @throws IOException
     * @throws ParserConfigurationException
     * @throws TransformerException
     */
    public static String wordToHtml(MultipartFile file) {
//        提取出word文档名称和后缀
        String filename = file.getOriginalFilename();
        try {
            if (filename.endsWith(".docx")) {
                // 将上传的文件传入Document转换
                return new WordToHtmlStringConverter().docxToHtmlText(file);
            } else if (filename.endsWith(".doc")) {
                return new WordToHtmlStringConverter().docToHtmlText(file);
            } else {
                log.error("不支持的文件格式！");
                return null;
            }
        } catch (FileNotFoundException e) {
            log.error("文件找不到异常！");
            e.printStackTrace();
        } catch (IOException e) {
            log.error("io转换异常！");
            e.printStackTrace();
        } catch (Exception e) {
            log.error("文件转换异常！");
            e.printStackTrace();
        }
 
        return null;
    }
 
    /**
     * 上传Word文档，返回解析后的Html
     */
    public static String docToHtmlText(MultipartFile file) throws Exception {
        //使用字符数组流获取解析的内容
        ByteArrayOutputStream baos = new ByteArrayOutputStream();
        OutputStream outStream = new BufferedOutputStream(baos);
        try {
            //将上传的文件传入Document转换
            HWPFDocument wordDocument = new HWPFDocument(file.getInputStream());
            Document document = DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument();
            WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(document);
            //将读取到的图片上传并添加链接地址
            wordToHtmlConverter.setPicturesManager((imageStream, pictureType, name, width, height) -> {
                try {
                    //首先要判断图片是否能识别
                    if (pictureType.equals(PictureType.UNKNOWN)) {
                        return "[不能识别的图片]";
                    }
                    //此处转换图片文件为Base64
                    return Base64.getEncoder().encodeToString(imageStream).trim();
 
                } catch (Exception e) {
                    log.info("upload exception", e);
                }
                return "[图片上传失败]";
            });
            // word文档转Html文档
            wordToHtmlConverter.processDocument(wordDocument);
            Document htmlDocument = wordToHtmlConverter.getDocument();
            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);
            String content = baos.toString();
            log.info("docToHtmlText--->{}", content);
            return content;
        } catch (Exception e) {
            log.error("docToHtmlText 异常", e);
        } finally {
            baos.close();
            outStream.close();
        }
        return null;
    }
 
    /**
     * 上传docx文档，返回解析后的Html
     */
    public static String docxToHtmlText(MultipartFile file) throws Exception {
        ByteArrayOutputStream htmlStream = new ByteArrayOutputStream();
        ByteArrayOutputStream htmlImg = new ByteArrayOutputStream();
        String htmlStr = null;
        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 path = System.getProperty("java.io.tmpdir");
            String firstImagePathStr = path + "/" + System.currentTimeMillis();
            options.setExtractor(new FileImageExtractor(new File(firstImagePathStr)));
            options.URIResolver(new BasicURIResolver(firstImagePathStr));
            // 转换html
            docxDocument.createNumbering();
            XHTMLConverter.getInstance().convert(docxDocument, htmlStream, options);
            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()) {
                            log.info("处理图片开始。。。。。。。。");
                            // 处理图片成为Base64格式
                            // 读取图片字节数组
                            InputStream in = new FileInputStream(fileImage);
                            byte[] data = new byte[in.available()];
                            in.read(data);
                            String encode = new BASE64Encoder().encode(data);
                            log.info("处理图片结束。。。。。。。" + encode);
                            //修改文档中的图片信息
                            htmlStr = htmlStr.replace(oneImagePathStr, "data:image/png;base64,"+encode);
 
                           /* BufferedImage bi = ImageIO.read(fileImage);// 图片存储大小比较大
                            ByteArrayOutputStream baos = new ByteArrayOutputStream();
                            ImageIO.write(bi, "png", baos);
                            byte[] bytes = baos.toByteArray();
                            String sd =  Base64.getEncoder().encodeToString(bytes).trim();
                            log.info("处理图片结束。。。。。。。" + sd);
                            htmlStr = htmlStr.replace(oneImagePathStr, "data:image/png;base64,"+sd);*/
 
 
                        }
                    } catch (Exception e) {
                        log.info("upload docxToHtmlText exception", e);
                    }
                }
            }
            log.info("处理结果：{}", htmlStr);
        } catch (Exception e) {
            log.error("docxToHtmlText 解析异常", e);
        } finally {
            if (htmlStream != null) {
                htmlStream.close();
            }
            return htmlStr;
        }
    }
}

直接引用就行，但是有一点，一定要注意接口返回的时候，如果直接返回页面接口上要加

@ResponseBody不然就悲剧了；当然如果直接存库的那就无所谓了

这次就先这样，自娱自乐，手下留情勿喷！！