word转html并将图片上传oss

将word转html之后并将word中的图片转换为oss链接。先加入maven依赖：

<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi</artifactId>
    <version>3.15</version>
</dependency>
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi-ooxml</artifactId>
    <version>3.15</version>
</dependency>
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi-ooxml-schemas</artifactId>
    <version>3.15</version>
</dependency>
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi-scratchpad</artifactId>
    <version>3.15</version>
</dependency>
<dependency>
    <groupId>fr.opensagres.xdocreport</groupId>
    <artifactId>xdocreport</artifactId>
    <version>1.0.6</version>
</dependency>
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>ooxml-schemas</artifactId>
    <version>1.3</version>
</dependency>

poi版本都到4.X版本了，为啥还要用3.15版本呢？因为下面的代码如果使用高版本的poi会出现ClassNotFound的异常。其实根本的原因是不清楚高版本poi转换html的方法（笑）

• word2007版本

public String docxToHtml(InputStream in) {
        String imagePath = "./word-images";
        File imageFile = new File(imagePath);
        if (!imageFile.exists()) {
            imageFile.mkdir();
        }
        try {
            XWPFDocument document = new XWPFDocument(in);
            //存储图片
            XHTMLOptions options = XHTMLOptions.create().URIResolver(new FileURIResolver(imageFile));
            options.setExtractor(new FileImageExtractor(imageFile));
            options.URIResolver((uri) -> {
                log.info("docx 图片地址：{}", uri);
                File imgFile = new File(imagePath +"\\" + uri);//获取图片
                String imgName = System.currentTimeMillis() + "_" + imgFile.getName();//设置图片文件名
                InputStream is = null;
                try {
                    is = new FileInputStream(imgFile);
                    return OSSUploadUtil.upload(imgName, is);
                } catch (IOException e) {
                    e.printStackTrace();
                }
                return "#";
            });
            ByteArrayOutputStream out = new ByteArrayOutputStream();
            XHTMLConverter converter = new XHTMLConverter();
            converter.convert(document, out, options);
            return new String(out.toByteArray(), StandardCharsets.UTF_8);
        } catch (IOException e) {
            e.printStackTrace();
            return "#";
        }
    }

• word2003转换

  public String docToHtml(InputStream in) {
          //加载word文档生成XWPF对象
          try {
              HWPFDocument doc = new HWPFDocument(in);
              org.w3c.dom.Document document = DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument();
              WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(document);
              //保存图片，并返回图片的相对路径
              //将图片上传,调用上传的方法
              wordToHtmlConverter.setPicturesManager((content, pictureType, name, width, height) -> {
                  try {
                      String upload = OSSUploadUtil.upload(name, new ByteArrayInputStream(content));
                      return upload;
                  } catch (UnsupportedEncodingException | FileNotFoundException e) {
                      return "#";
                  }
              });
              wordToHtmlConverter.processDocument(doc);
              org.w3c.dom.Document htmlDocument = wordToHtmlConverter.getDocument();
              DOMSource domSource = new DOMSource(htmlDocument);
              ByteArrayOutputStream byteArrayOutputStream = new ByteArrayOutputStream();
              StreamResult streamResult = new StreamResult(byteArrayOutputStream);
              TransformerFactory tf = TransformerFactory.newInstance();
              Transformer serializer = tf.newTransformer();
              serializer.setOutputProperty(OutputKeys.ENCODING, "utf-8");
              serializer.setOutputProperty(OutputKeys.INDENT, "yes");
              serializer.setOutputProperty(OutputKeys.METHOD, "html");
              serializer.transform(domSource, streamResult);
              return new String(byteArrayOutputStream.toByteArray(), "UTF-8");
          } catch (IOException | ParserConfigurationException | TransformerException e) {
              log.error("", e);
          }
          return null;
      }
  

注意：本文归作者所有，未经作者允许，不得转载