Java word文档转HTML 使用poi（版本：4.1.2）

最新推荐文章于 2024-08-13 08:49:27 发布

yi_sao

最新推荐文章于 2024-08-13 08:49:27 发布

阅读量1.7k

点赞数 2

文章标签： java poi html 后端 intellij idea

本文链接：https://blog.csdn.net/qq_39744247/article/details/110493894

版权

各种找不到类找不到方法的错误，都是版本不对，建议打开External Libraries检查一下各个包的版本是否正确

1、maven依赖

        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi</artifactId>
            <version>4.1.2</version>
        </dependency>

        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-scratchpad</artifactId>
            <version>4.1.2</version>
        </dependency>

        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-ooxml</artifactId>
            <version>4.1.2</version>
        </dependency>

        <dependency>
            <groupId>fr.opensagres.xdocreport</groupId>
            <artifactId>xdocreport</artifactId>
            <version>2.0.2</version>
        </dependency>

        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>ooxml-schemas</artifactId>
            <version>1.4</version>
        </dependency>

2、java代码

 /**
     * docx格式转html
     * @param document
     * @return
     */
    public String docxToHtml(XWPFDocument document){
        String value = "";
        try {
            ByteArrayOutputStream outputStream = new ByteArrayOutputStream();
            XHTMLConverter.getInstance().convert(document, outputStream, null);

            value = new String(outputStream.toByteArray());
        } catch (Exception e){
            e.printStackTrace();
        }
        return value;
    }

    /**
     * doc格式转html
     * @param wordDocument
     * @return
     */
    public String docToHtml(HWPFDocument wordDocument) {
        String content = null;
        ByteArrayOutputStream baos = null;
        try {
            WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());
            wordToHtmlConverter.processDocument(wordDocument);
            Document htmlDocument = wordToHtmlConverter.getDocument();
            DOMSource domSource = new DOMSource(htmlDocument);
            baos = new ByteArrayOutputStream();
            StreamResult streamResult = new StreamResult(baos);

            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);

        } catch (Exception e) {
            e.printStackTrace();
        } finally {
            try {
                if (baos != null) {
                    content = new String(baos.toByteArray(), "utf-8");
                    baos.close();
                }
            } catch (Exception e) {
                e.printStackTrace();
            }
        }
        return content;
    }