POM依赖

<dependency>
            <groupId>fr.opensagres.xdocreport</groupId>
            <artifactId>fr.opensagres.xdocreport.document</artifactId>
            <version>2.0.1</version>
        </dependency>

        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi</artifactId>
            <version>3.15</version>
        </dependency>
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-scratchpad</artifactId>
            <version>3.15</version>
        </dependency>
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-ooxml</artifactId>
            <version>3.15</version>
        </dependency>
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-ooxml-schemas</artifactId>
            <version>3.15</version>
        </dependency>

        <dependency>
            <groupId>fr.opensagres.xdocreport</groupId>
            <artifactId>org.apache.poi.xwpf.converter.xhtml</artifactId>
            <version>1.0.6</version>
        </dependency>

        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>ooxml-schemas</artifactId>
            <version>1.3</version>
        </dependency>
        <dependency>
            <groupId>org.jsoup</groupId>
            <artifactId>jsoup</artifactId>
            <version>1.13.1</version>
        </dependency>

Doc转Html

@Test
public void Word2003ToHtml() throws IOException, ParserConfigurationException, TransformerException {
    FileInputStream is = new FileInputStream(new File("D:\\BHFAE\\国金所\\MQ\\Websphere-MQ入门经典教程---经典.doc"));
    HWPFDocument wordDocument = new HWPFDocument(is);
    WordToHtmlConverter converter = new WordToHtmlConverter(DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());
    //对HWPFDocument进行转换
    converter.setPicturesManager(new PicturesManager() {
        @Override
        public String savePicture(byte[] content, PictureType pictureType, String suggestedName, float widthInches, float heightInches) {
            String type = pictureType.name();
            return "data:image/" + type + ";base64," + new String(Base64.encodeBase64(content));
        }
    });
    converter.processDocument(wordDocument);

    Transformer transformer = TransformerFactory.newInstance().newTransformer();
    transformer.setOutputProperty(OutputKeys.ENCODING, "utf-8");
    //是否添加空格
    transformer.setOutputProperty(OutputKeys.INDENT, "yes");
    transformer.setOutputProperty(OutputKeys.METHOD, "html");
    File file = new File("H:/testDocToHtml.html");
    FileOutputStream fileOutputStream = new FileOutputStream(file);
    transformer.transform(
            new DOMSource(converter.getDocument()),
            new StreamResult(fileOutputStream));
    fileOutputStream.flush();
    fileOutputStream.close();
    wordDocument.close();
}

Docx转Html

@Test
public void Word2007ToHtml() throws IOException {
    FileInputStream is = new FileInputStream(new File("D:\\BHFAE\\国金所\\MQ\\Websphere-MQ入门经典教程---经典.docx"));
    XWPFDocument document = new XWPFDocument(is);
    List<XWPFPictureData> list = document.getAllPictures();
    ByteArrayOutputStream outputStream = new ByteArrayOutputStream();
    XHTMLConverter.getInstance().convert(document, outputStream, null);
    String s = new String(outputStream.toByteArray());
    s = setImg(s, list);
    File file = new File("H:/testDocxToHtml.html");
    FileOutputStream fileOutputStream = new FileOutputStream(file);
    fileOutputStream.write(s.getBytes());
    fileOutputStream.flush();
    fileOutputStream.close();
    document.close();
}
private String setImg(String html, List<XWPFPictureData> list){
    Document doc = Jsoup.parse(html);
    Elements elements = doc.getElementsByTag("img");
    if (elements != null && elements.size() > 0 && list != null){
        for(Element element : elements){
            String src = element.attr("src");
            for (XWPFPictureData data: list){
                if (src.contains(data.getFileName())){
                    String type = src.substring(src.lastIndexOf(".") + 1);
                    String base64 = "data:image/" + type + ";base64," + new String(Base64.encodeBase64(data.getData()));
                    element.attr("src", base64);
                    break;
                }
            }
        }
    }
    return doc.toString();
}