word转html

Maven依赖

<dependency>
    <groupId>com.itextpdf</groupId>
    <artifactId>itextpdf</artifactId>
    <version>5.5.9</version>
</dependency>
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi-scratchpad</artifactId>
    <version>3.8</version>
</dependency>

import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.converter.PicturesManager;
import org.apache.poi.hwpf.converter.WordToHtmlConverter;
import org.apache.poi.hwpf.usermodel.PictureType;
import org.w3c.dom.Document;

import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.transform.OutputKeys;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;
import java.io.ByteArrayOutputStream;
import java.io.InputStream;

/**
 * @author: 木杉
 * @email: 819236727@qq.com
 * @Date: 2019/7/23 9:01
 * @describe:
 */
public class Test {
    public static void main(String[] args) throws Exception{
        //word的文件流
        InputStream inputStream = null;
        HWPFDocument wordDocument = new HWPFDocument(inputStream);
        WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(
                DocumentBuilderFactory.newInstance().newDocumentBuilder()
                        .newDocument());

        //获取word中的图片信息
        wordToHtmlConverter.setPicturesManager(new PicturesManager() {
            public String savePicture(byte[] content,
                                      PictureType pictureType, String suggestedName,
                                      float widthInches, float heightInches) {
                //content 图片的二进制
                //pictureType 通过该对象里面的属性getExtension可以获取word图片的类型
                //suggestedName 图片的名称
                //widthInches 宽   heightInches高

                //当转成html时候 <img src=""/> src里面保存的地址
                return "http://xxxxxxx.jpg";
            }
        });

        wordToHtmlConverter.processDocument(wordDocument);
        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);

        //里面即是word转成html的字符串
        String html = new String(out.toByteArray());
        out.close();
    }
}