用poi實現doc轉html

廢話，不多說直接上代碼。

一、doc轉html，并且帶文件夾

    / * word轉html
     * html轉圖片
     * @param tagPath   轉換html文件之后，所帶的圖片附件文件夾
 * @param sourceFileName 源文件
 * @param outPath  輸出文件xx.html
 * @return 
 * @throws Exception
     */
public static String docToHtml(String tagPath,  
        String sourceFileName, String outPath) throws Exception {
        File file = new File(tagPath);
        if(!file.exists()) {
                file.mkdirs();
        }
        HWPFDocument wordDocument = new HWPFDocument(new FileInputStream(sourceFileName));
        org.w3c.dom.Document document = DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument();
        WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(document);
        //保存圖片，并返回圖片的相對路徑
        wordToHtmlConverter.setPicturesManager((content, pictureType, name, width, height) -> {
                try (FileOutputStream out = new FileOutputStream(tagPath + name)) {
                        out.write(content);
                } catch (Exception e) {
                        e.printStackTrace();
                }
                return "image/" + name;
        });
        wordToHtmlConverter.processDocument(wordDocument);
        org.w3c.dom.Document htmlDocument = wordToHtmlConverter.getDocument();
        DOMSource domSource = new DOMSource(htmlDocument);
        StreamResult streamResult = new StreamResult(new File(outPath));
        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 outPath;
}

調用：

/**doc
             * 轉html
             */
            String tagPath = "D:\\red_ant_file\\20180915\\image\\";
            String sourcePath = "D:\\red_ant_file\\20180915\\RedAnt的實驗作業.doc";
            String outPath = "D:\\red_ant_file\\20180915\\123.html";
            try {
                AllServiceIsHere.docToHtml(tagPath, sourcePath, outPath);
            } catch (Exception e) {
                // TODO Auto-generated catch block
                e.printStackTrace();
            }

演示：

走你：