java Word转Html

第一步：maven导入jar包

<dependency>
  <groupId>org.apache.poigroupId>
  <artifactId>poi-scratchpadartifactId>
  <version>3.14version>
dependency>

<dependency>
  <groupId>org.apache.poigroupId>
  <artifactId>poi-ooxmlartifactId>
  <version>3.14version>
dependency>

<dependency>
  <groupId>fr.opensagres.xdocreportgroupId>
  <artifactId>xdocreportartifactId>
  <version>1.0.6version>
dependency>

<dependency>
  <groupId>org.apache.poigroupId>
  <artifactId>poi-ooxml-schemasartifactId>
  <version>3.14version>
dependency>

<dependency>
  <groupId>org.apache.poigroupId>
  <artifactId>ooxml-schemasartifactId>
  <version>1.3version>
dependency>

<dependency>
  <groupId>org.jsoupgroupId>
  <artifactId>jsoupartifactId>
  <version>1.11.3version>
dependency>

转换方法：

/**
 * 将word2003转换为html文件  
 * 
 * @param wordPath word文件路径
 * @param wordName word文件名称无后缀
 * @param suffix   word文件后缀
 * @param htmlPath html存储地址
 * @throws IOException
 * @throws TransformerException
 * @throws ParserConfigurationException
 */
public static String Word2003ToHtml(String wordPath, String wordName, String suffix, String htmlPath)
    throws IOException, TransformerException, ParserConfigurationException {
  String htmlName = wordName + ".html";
  final String imagePath = htmlPath + "image" + File.separator;
  // 判断html文件是否存在
  File htmlFile = new File(htmlPath + htmlName);
  if (htmlFile.exists()) {
    return htmlFile.getAbsolutePath();
  }
  // 原word文档
  final String file = wordPath + File.separator + wordName + suffix;
  InputStream input = new FileInputStream(new File(file));
  HWPFDocument wordDocument = new HWPFDocument(input);
  WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(
      DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());
  // 设置图片存放的位置
  wordToHtmlConverter.setPicturesManager(new PicturesManager() {
    public String savePicture(byte[] content, PictureType pictureType, String suggestedName, float widthInches,
        float heightInches) {
      File imgPath = new File(imagePath);
      if (!imgPath.exists()) {// 图片目录不存在则创建
        imgPath.mkdirs();
      }
      File file = new File(imagePath + suggestedName);
      try {
        OutputStream os = new FileOutputStream(file);
        os.write(content);
        os.close();
      } catch (FileNotFoundException e) {
        e.printStackTrace();
      } catch (IOException e) {
        e.printStackTrace();
      }
      // 图片在html文件上的路径 相对路径
      return "image/" + suggestedName;
    }
  });
  // 解析word文档
  wordToHtmlConverter.processDocument(wordDocument);
  Document htmlDocument = wordToHtmlConverter.getDocument();
  // 生成html文件上级文件夹
  File folder = new File(htmlPath);
  if (!folder.exists()) {
    folder.mkdirs();
  }
  OutputStream outStream = new FileOutputStream(htmlFile);
  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);
  return htmlFile.getAbsolutePath();
}
/**
 * 
 * 2007版本word转换成html  
 * 
 * @param wordPath  word文件路径
 * @param wordName word文件名称无后缀
 * @param suffix   word文件后缀
 * @param htmlPath html存储地址
 * @return
 * @throws IOException
 */
public static String Word2007ToHtml(String wordPath, String wordName, String suffix, String htmlPath)
    throws IOException {
  String htmlName = wordName + ".html";
  String imagePath = htmlPath + "image" + File.separator;
  // 判断html文件是否存在
  File htmlFile = new File(htmlPath + htmlName);
  if (htmlFile.exists()) {
    return htmlFile.getAbsolutePath();
  }
  // word文件
  File wordFile = new File(wordPath + File.separator + wordName + suffix);
  // 1) 加载word文档生成 XWPFDocument对象
  InputStream in = new FileInputStream(wordFile);
  XWPFDocument document = new XWPFDocument(in);
  // 2) 解析 XHTML配置 (这里设置IURIResolver来设置图片存放的目录)
  File imgFolder = new File(imagePath);
  XHTMLOptions options = XHTMLOptions.create();
  options.setExtractor(new FileImageExtractor(imgFolder));
  // html中图片的路径 相对路径
  options.URIResolver(new BasicURIResolver("image"));
  options.setIgnoreStylesIfUnused(false);
  options.setFragment(true);
  // 3) 将 XWPFDocument转换成XHTML
  // 生成html文件上级文件夹
  File folder = new File(htmlPath);
  if (!folder.exists()) {
    folder.mkdirs();
  }
  OutputStream out = new FileOutputStream(htmlFile);
  XHTMLConverter.getInstance().convert(document, out, options);
  return htmlFile.getAbsolutePath();
}

第三步：具体调用

public static void main(String[] args) {
  try {
    Word2007ToHtml("C:\\", "1", ".docx", "c://wordToHtml/");
  } catch (Exception e) {
    e.printStackTrace();
  }
}

 

转自：https://blog.csdn.net/weixin_41889524/article/details/88988256