java实现word文件转html文件

importjava.io.ByteArrayOutputStream;

importjava.io.File;

importjava.io.FileInputStream;

importjava.io.FileNotFoundException;

importjava.io.FileOutputStream;

importjava.io.IOException;

importjava.io.InputStream;

importjava.io.OutputStream;

importjavax.xml.parsers.DocumentBuilderFactory;

importjavax.xml.parsers.ParserConfigurationException;

importjavax.xml.transform.OutputKeys;

importjavax.xml.transform.Transformer;

importjavax.xml.transform.TransformerException;

importjavax.xml.transform.TransformerFactory;

importjavax.xml.transform.dom.DOMSource;

importjavax.xml.transform.stream.StreamResult;

importorg.apache.poi.hwpf.HWPFDocument;

importorg.apache.poi.hwpf.converter.PicturesManager;

importorg.apache.poi.hwpf.converter.WordToHtmlConverter;

importorg.apache.poi.hwpf.usermodel.PictureType;

importorg.apache.poi.xwpf.converter.core.BasicURIResolver;

importorg.apache.poi.xwpf.converter.core.FileImageExtractor;

importorg.apache.poi.xwpf.converter.core.FileURIResolver;

importorg.apache.poi.xwpf.converter.xhtml.XHTMLConverter;

importorg.apache.poi.xwpf.converter.xhtml.XHTMLOptions;

importorg.apache.poi.xwpf.usermodel.XWPFDocument;

importorg.w3c.dom.Document;

/**

 * word 转换成html 2017-2-27

 */

publicclassWordToHtml {

  /**

   * 将word2003转换为html文件 2017-2-27

   * @param wordPath word文件路径

   * @param wordName word文件名称无后缀

   * @param suffix  word文件后缀

   * @throws IOException

   * @throws TransformerException

   * @throws ParserConfigurationException

   */

  publicString  Word2003ToHtml(String wordPath,String wordName,String  suffix)throwsIOException, TransformerException,  ParserConfigurationException {

    String htmlPath = wordPath + File.separator + wordName +"_show"+ File.separator;

    String htmlName = wordName +".html";

    finalString imagePath = htmlPath +"image"+ File.separator;

    //判断html文件是否存在

    File htmlFile =newFile(htmlPath + htmlName);

    if(htmlFile.exists()){

      returnhtmlFile.getAbsolutePath();

    }

    //原word文档

    finalString file = wordPath + File.separator + wordName + suffix;

    InputStream input =newFileInputStream(newFile(file));

    HWPFDocument wordDocument =newHWPFDocument(input);

    WordToHtmlConverter  wordToHtmlConverter  =newWordToHtmlConverter(DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());

    //设置图片存放的位置

    wordToHtmlConverter.setPicturesManager(newPicturesManager() {

      publicString  savePicture(byte[] content, PictureType pictureType, String  suggestedName,floatwidthInches,floatheightInches) {

        File imgPath =newFile(imagePath);

        if(!imgPath.exists()){//图片目录不存在则创建

          imgPath.mkdirs();

        }

        File file =newFile(imagePath + suggestedName);

        try{

          OutputStream os =newFileOutputStream(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 =newFile(htmlPath);

    if(!folder.exists()){

      folder.mkdirs();

    }

    //生成html文件地址

    OutputStream outStream =newFileOutputStream(htmlFile);

    DOMSource domSource =newDOMSource(htmlDocument);

    StreamResult streamResult =newStreamResult(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);

    outStream.close();

    returnhtmlFile.getAbsolutePath();

  }

  /**

   * 2007版本word转换成html 2017-2-27

   * @param wordPath word文件路径

   * @param wordName word文件名称无后缀

   * @param suffix  word文件后缀

   * @return

   * @throws IOException

   */

  publicString Word2007ToHtml(String wordPath,String wordName,String suffix)throwsIOException {

    String htmlPath = wordPath + File.separator + wordName +"_show"+ File.separator;

    String htmlName = wordName +".html";

    String imagePath = htmlPath +"image"+ File.separator;

    //判断html文件是否存在

    File htmlFile =newFile(htmlPath + htmlName);

    if(htmlFile.exists()){

      returnhtmlFile.getAbsolutePath();

    }

    //word文件

    File wordFile =newFile(wordPath + File.separator + wordName + suffix);

    // 1) 加载word文档生成 XWPFDocument对象

    InputStream in =newFileInputStream(wordFile);

    XWPFDocument document =newXWPFDocument(in);

    // 2) 解析 XHTML配置 (这里设置IURIResolver来设置图片存放的目录)

    File imgFolder =newFile(imagePath);

    XHTMLOptions options = XHTMLOptions.create();

    options.setExtractor(newFileImageExtractor(imgFolder));

    //html中图片的路径 相对路径

    options.URIResolver(newBasicURIResolver("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 =newFile(htmlPath);

    if(!folder.exists()){

      folder.mkdirs();

    }

    OutputStream out =newFileOutputStream(htmlFile);

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

    returnhtmlFile.getAbsolutePath();

  }

}