利用poi 把（word）doc、docx转html

最新推荐文章于 2021-01-16 19:44:54 发布

bbenst

最新推荐文章于 2021-01-16 19:44:54 发布

阅读量7.7k

点赞数 1

CC 4.0 BY-SA版权

本文链接：https://blog.youkuaiyun.com/bbenst/article/details/86079395

本文介绍了一种将Microsoft Word的Doc和Docx格式文件转换为HTML的方法，包括处理图片和使用不同转换策略的过程。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

/**
     * doc转换为html
     *
     * @param fileName
     * @param outPutFile
     * @throws TransformerException
     * @throws IOException
     * @throws ParserConfigurationException
     */
    public static void doc2Html(String fileName, String outPutFile) throws TransformerException, IOException, ParserConfigurationException {
        long startTime = System.currentTimeMillis();
        HWPFDocument wordDocument = new HWPFDocument(new FileInputStream(fileName));
        WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());
        wordToHtmlConverter.setPicturesManager(new PicturesManager() {
            public String savePicture(byte[] content, PictureType pictureType, String suggestedName, float widthInches, float heightInches) {
                return suggestedName;
            }
        });
        wordToHtmlConverter.processDocument(wordDocument);
        // 保存图片
        List<Picture> pics = wordDocument.getPicturesTable().getAllPictures();
        if (pics != null) {
            for (int i = 0; i < pics.size(); i++) {
                Picture pic = (Picture) pics.get(i);
                try {
                    pic.writeImageContent(new FileOutputStream("E://temp//" + pic.suggestFullFileName()));
                } catch (FileNotFoundException e) {
                    e.printStackTrace();
                }
            }
        }
        Document htmlDocument = wordToHtmlConverter.getDocument();
        ByteArrayOutputStream out = new ByteArrayOutputStream();
        DOMSource domSource = new DOMSource(htmlDocument);
        StreamResult streamResult = new StreamResult(out);

        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);
        out.close();
        writeFile(new String(out.toByteArray()), outPutFile);
        System.out.println("Generate " + outPutFile + " with " + (System.currentTimeMillis() - startTime) + " ms.");
    }
/**
     * 写文件
     *
     * @param content
     * @param path
     */
    public static void writeFile(String content, String path) {
        FileOutputStream fos = null;
        BufferedWriter bw = null;
        try {
            File file = new File(path);
            fos = new FileOutputStream(file);
            bw = new BufferedWriter(new OutputStreamWriter(fos, "utf-8"));
            bw.write(content);
        } catch (FileNotFoundException fnfe) {
            fnfe.printStackTrace();
        } catch (IOException ioe) {
            ioe.printStackTrace();
        } finally {
            try {
                if (bw != null)
                    bw.close();
                if (fos != null)
                    fos.close();
            } catch (IOException ie) {
            }
        }
    }

 /**
     * docx格式word转换为html
     *
     * @param fileName   docx文件路径
     * @param outPutFile html输出文件路径
     * @throws TransformerException
     * @throws IOException
     * @throws ParserConfigurationException
     */
    public static void docx2Html(String fileName, String outPutFile) throws IOException {
        String fileOutName = outPutFile;
        long startTime = System.currentTimeMillis();
        XWPFDocument document = new XWPFDocument(new FileInputStream(fileName));
        XHTMLOptions options = XHTMLOptions.create().indent(4);
        // 导出图片
        File imageFolder = new File("E:/temp/images");
        options.setExtractor(new FileImageExtractor(imageFolder));
        // URI resolver  word的html中图片的目录路径
        options.URIResolver(new BasicURIResolver("images"));
        File outFile = new File(fileOutName);
        outFile.getParentFile().mkdirs();
        OutputStream out = new FileOutputStream(outFile);
        XHTMLConverter.getInstance().convert(document, out, options);
        System.out.println("Generate " + fileOutName + " with " + (System.currentTimeMillis() - startTime) + " ms.");

    }