poi将word转html

依赖：

        <!-- 针对2007以上版本的库 -->
        <dependency>
            <groupId>fr.opensagres.xdocreport</groupId>
            <artifactId>org.apache.poi.xwpf.converter.xhtml</artifactId>
            <version>1.0.6</version>
        </dependency>
        <!-- 针对2003版本的库 -->
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-scratchpad</artifactId>
            <version>4.1.2</version>
        </dependency>
        <dependency>
            <groupId>fr.opensagres.xdocreport</groupId>
            <artifactId>fr.opensagres.poi.xwpf.converter.xhtml</artifactId>
            <version>2.0.2</version>
        </dependency>

工具类：

package com.hnzie.config;

import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.converter.WordToHtmlConverter;
import org.apache.poi.xwpf.converter.core.FileImageExtractor;
import org.apache.poi.xwpf.converter.core.FileURIResolver;
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.*;

public class WordToHtmlUtil {
    /**
     * word2003转html
     * @throws Exception
     */
    public void word2003toHtm() throws Exception{
        String filePath = "d:/test";
        String fileName = "test.doc";
        String htmlname = "test.html";
        File file = new File(filePath + File.separator + fileName);
        InputStream input = new FileInputStream(file);
        HWPFDocument wordDocument = new HWPFDocument(input);
        WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());
        // 解析word文档
        wordToHtmlConverter.processDocument(wordDocument);
        Document htmlDocument = wordToHtmlConverter.getDocument();
        File htmlFile = new File(filePath +File.separator+ htmlname);
        OutputStream outStream = new FileOutputStream(htmlFile);
        DOMSource domSource = new DOMSource(htmlDocument);
        StreamResult streamResult = new StreamResult(outStream);
        TransformerFactory factory = TransformerFactory.newInstance();
        Transformer serializer = factory.newTransformer();
        serializer.setOutputProperty(OutputKeys.ENCODING, "utf-8");
        serializer.setOutputProperty(OutputKeys.INDENT, "yes");
        serializer.setOutputProperty(OutputKeys.METHOD, "html");
        serializer.transform(domSource, streamResult);
        outStream.close();
    }

    /**
     * word2007转html
     * @throws Exception
     */
    public void word2007toHtm() throws Exception{
        String filePath = "d:/test";
        String fileName = "test.doc";
        String htmlname = "test.html";
        File file = new File(filePath + File.separator + fileName);
        InputStream in = new FileInputStream(file);
        XWPFDocument document = new XWPFDocument(in);
        // 解析 XHTML配置 (这里设置IURIResolver来设置图片存放的目录)
        File imageFolderFile = new File(filePath);
        XHTMLOptions options = XHTMLOptions.create().URIResolver(new FileURIResolver(imageFolderFile));
        options.setExtractor(new FileImageExtractor(imageFolderFile));
        options.setIgnoreStylesIfUnused(false);
        options.setFragment(true);
        // 将 XWPFDocument转换成XHTML
        File htm = new File(filePath +File.separator+ htmlname);
        OutputStream out = new FileOutputStream(htm);
        XHTMLConverter.getInstance().convert(document, out, options);
    }

}