使用poi将word转换为html

import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.converter.WordToHtmlConverter;
import org.apache.poi.hwpf.usermodel.Picture;
import org.apache.poi.xwpf.converter.core.BasicURIResolver;
import org.apache.poi.xwpf.converter.core.FileImageExtractor;
import org.apache.poi.xwpf.converter.xhtml.XHTMLConverter;
import org.apache.poi.xwpf.converter.xhtml.XHTMLOptions;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
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.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.OutputStreamWriter;
import java.util.List;

public class Test {
    //doc转换为html
    void docToHtml() throws Exception {
        String sourceFileName = "C:\\doc\\test.doc";
        String targetFileName = "C:\\html\\test.html";
        String imagePathStr = "C:\\html\\image\\";
        HWPFDocument wordDocument = new HWPFDocument(new FileInputStream(sourceFileName));
        WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());
        //设置图片的相对路径
        wordToHtmlConverter.setPicturesManager((a, b, suggestedName, d, e) -> "image" + File.separator + suggestedName);
        wordToHtmlConverter.processDocument(wordDocument);
        List<Picture> pics = wordDocument.getPicturesTable().getAllPictures();
        for (Picture pic : pics) {
            //生成图片
            pic.writeImageContent(new FileOutputStream(imagePathStr + pic.suggestFullFileName()));
        }
        Document htmlDocument = wordToHtmlConverter.getDocument();
        DOMSource domSource = new DOMSource(htmlDocument);
        StreamResult streamResult = new StreamResult(new File(targetFileName));

        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);
    }

    //docx转换为html
    public void docxToHtml() throws Exception {
        String sourceFileName = "C:\\doc\\test.doc";
        String targetFileName = "C:\\html\\test.html";
        String imagePathStr = "C:\\html\\image\\";
        FileOutputStream fileOutputStream = null;
        OutputStreamWriter outputStreamWriter = null;
        try {
            XWPFDocument document = new XWPFDocument(new FileInputStream(sourceFileName));
            XHTMLOptions options = XHTMLOptions.create();
            //存放图片的文件夹
            options.setExtractor(new FileImageExtractor(new File(imagePathStr)));
            //html中图片的路径
            options.URIResolver(new BasicURIResolver("image"));
            fileOutputStream = new FileOutputStream(targetFileName);
            outputStreamWriter = new OutputStreamWriter(fileOutputStream, "utf-8");
            XHTMLConverter xhtmlConverter = (XHTMLConverter) XHTMLConverter.getInstance();
            xhtmlConverter.convert(document, outputStreamWriter, options);
        } finally {
            if (outputStreamWriter != null) {
                outputStreamWriter.close();
            }
            if (fileOutputStream != null) {
                fileOutputStream.close();
            }
        }
    }
}