Java word转html 支持(doc,docx) 完美保留格式与图片，处理图片路径。

将Word2003 Word2007成Html。

maven:

	<properties>
		<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
		<xdocreport-version>1.0.6</xdocreport-version>
	</properties>


	<dependencies>

		<dependency>
			<groupId>fr.opensagres.xdocreport</groupId>
			<artifactId>fr.opensagres.xdocreport.document</artifactId>
			<version>${xdocreport-version}</version>
		</dependency>
		<dependency>
			<groupId>fr.opensagres.xdocreport</groupId>
			<artifactId>org.apache.poi.xwpf.converter.xhtml</artifactId>
			<version>${xdocreport-version}</version>
		</dependency>
		<dependency>
			<groupId>fr.opensagres.xdocreport</groupId>
			<artifactId>org.apache.poi.xwpf.converter.pdf</artifactId>
			<version>${xdocreport-version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.poi</groupId>
			<artifactId>poi</artifactId>
			<version>3.13</version>
		</dependency>
		<dependency>
			<groupId>org.apache.poi</groupId>
			<artifactId>poi-scratchpad</artifactId>
			<version>3.13</version>
		</dependency>

	</dependencies>

package com.hessianhealth.system.utils.wkhtmltopdfUtils;

import java.io.*;

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 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.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;

/**
 * 将word以上版本转成Html
 *
 * @author lgn
 *
 */
public class WordToHtml {

    /**
     * 将Word2007+转成Html
     * docx
     * @throws Exception
     */
    public static void word2007ToHtml() throws Exception {
        String filePath = "C:\\Users\\XX\\Desktop\\";
        String fileName = "XX.docx";
        String htmlName = "XX.html";
        final String file = filePath + fileName;
        File f = new File(file);
        if (!f.exists()) {
            System.out.println("Sorry File does not Exists!");
        } else {
			/* 判断是否为docx文件 */
            if (f.getName().endsWith(".docx") || f.getName().endsWith(".DOCX")) {
                // 1)加载word文档生成XWPFDocument对象
                FileInputStream in = new FileInputStream(f);
                XWPFDocument document = new XWPFDocument(in);
                // 2)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);
                // 3)将XWPFDocument转换成XHTML
                FileOutputStream out = new FileOutputStream(new File(filePath + htmlName));
                XHTMLConverter.getInstance().convert(document, out, options);
            } else {
                System.out.println("Enter only as MS Office 2007+ files");
            }
        }
        System.exit(0);
    }

    /**
     * word2003转换成html
     * 对于doc，可以用下面这种方式:
     * @throws Exception
     */
    public static void word2003ToHtml() throws Exception {
        String filePath = "C:\\Users\\XX\\Desktop\\";
        String fileName = "CC.doc";
        String htmlName = "CC.html";
        final String imagePath = filePath + "/image/";
        final String file = filePath + fileName;
        InputStream input = new FileInputStream(new File(file));
        HWPFDocument wordDocument = new HWPFDocument(input);
        WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(
                DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());
        //设置图片存储位置
        wordToHtmlConverter.setPicturesManager(new PicturesManager() {

            public String savePicture(byte[] content, PictureType pictureType, String suggestedName, float widthInches,
                                      float heightInches) {
                File imgPath=new File(imagePath);
                if (!imgPath.exists()) {//目录不存在则创建目录
                    imgPath.mkdirs();
                }
                File file = new File(imagePath+suggestedName);
                try {
                    FileOutputStream os = new FileOutputStream(file);
                    os.write(content);
                    os.close();
                } catch (FileNotFoundException e) {
                    e.printStackTrace();
                } catch (IOException e) {
                    e.printStackTrace();
                }

                String newPath=imagePath+suggestedName;
                return newPath;
            }
        });

        //解析word文档
        wordToHtmlConverter.processDocument(wordDocument);
        Document htmlDocument = wordToHtmlConverter.getDocument();
        File htmlFile = new File(filePath+htmlName);
        FileOutputStream 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();
    }




    public static void main(String[] args) {

        try {
            word2003ToHtml();
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}

如果2007转换成html 的时候docx里面如果有图片，在生成html的时候路径问题会非常麻烦，会生成一个图片的文件夹，如果有在线预览服务器上的html的需要，可以采用把图片直接处理成base64格式直接把图片嵌入到html：

package com.hessianhealth.system.utils.wkhtmltopdfUtils;

import com.itextpdf.html2pdf.jsoup.Jsoup;
import com.itextpdf.html2pdf.jsoup.nodes.Document;
import com.itextpdf.html2pdf.jsoup.nodes.Element;
import com.itextpdf.html2pdf.jsoup.select.Elements;
import org.apache.commons.net.util.Base64;
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.apache.poi.xwpf.usermodel.XWPFPictureData;

import javax.xml.parsers.ParserConfigurationException;
import javax.xml.transform.TransformerException;
import java.io.*;
import java.util.ArrayList;
import java.util.List;


    /**
     * 2007转换成html
     * 对于docx，可以用下面这种方式:
     * @throws Exception
     */
    public static void docxToHtml() throws Exception {
        String filePath = "C:\\Users\\XX\\Desktop\\";
        String fileName = "可视化问题1.5.docx";
        String htmlName = "可视化问题1.5.html";

        String htmlPath=filePath + htmlName;
        String docPath=filePath + fileName;

        InputStream input = new FileInputStream(new File(docPath));

        XWPFDocument document = new XWPFDocument(input);
        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);
        System.out.println(s);

        PrintStream printStream = new PrintStream(new FileOutputStream(htmlPath));
        //将HTML文件内容写入文件中
        printStream.println(s.toString());

        document.close();
    }


    /**
     * 处理文档中的图片，转化成字节流支持在线预览
     * @param html
     * @param list
     * @return
     */
    private static 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();
    }
    public static void main(String[] args) {
        try {
            docxToHtml();
        } catch (Exception e) {
            e.printStackTrace();
        }
    }