word转html

最新推荐文章于 2025-08-16 13:36:16 发布

原创最新推荐文章于 2025-08-16 13:36:16 发布 · 568 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#java

本文介绍了一种使用Apache POI库将Word文档转换为HTML的方法。通过引入相关依赖，如poi、poi-ooxml等，创建一个工具类WordToHtmlUtil，利用WordToHtmlConverter处理Word文档，并保存图片，最终将处理后的文档转换成HTML格式。

本文章使用的组件为poi

温馨提示：如果是freemaker生成的word文档，是无法使用该方法转换html的，因为freemaker生成的不是标准格式的word文档。关于word文档转换html方法，我在另一篇文章有提到，是通过freemaker转换的html。有需要的小伙伴可以去看看.
链接: Freemaker导出word文档并实现预览.

一、poi依赖

		<dependency>
            <groupId>dom4j</groupId>
            <artifactId>dom4j</artifactId>
            <version>1.6.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi</artifactId>
            <version>3.14</version>
        </dependency>
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-scratchpad</artifactId>
            <version>3.14</version>
        </dependency>
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-ooxml</artifactId>
            <version>3.14</version>
        </dependency>
        <dependency>
            <groupId>fr.opensagres.xdocreport</groupId>
            <artifactId>xdocreport</artifactId>
            <version>1.0.6</version>
        </dependency>
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-ooxml-schemas</artifactId>
            <version>3.14</version>
        </dependency>
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>ooxml-schemas</artifactId>
            <version>1.3</version>
        </dependency>

二、工具类

package com.test.util;


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.Picture;
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.*;
import java.util.List;

/**
 * @author: zyx
 * @version: 1.0
 * @date:2021/11/9 上午 9:40
 */
public class WordToHtmlUtil {

    public static void wordToHtml() throws Exception {
    	//本地文件地址
        final String path = "C:\\Users\\Administrator\\Desktop\\";
        final String file = "xxx.doc";
        InputStream input = new FileInputStream(path + file);
        HWPFDocument wordDocument = new HWPFDocument(input);
        WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(
                DocumentBuilderFactory.newInstance().newDocumentBuilder()
                        .newDocument());
        wordToHtmlConverter.setPicturesManager(new PicturesManager() {
            @Override
            public String savePicture(byte[] content, PictureType pictureType,
                                      String suggestedName, float widthInches, float heightInches) {
                return suggestedName;
            }
        });
        wordToHtmlConverter.processDocument(wordDocument);
        List pics = wordDocument.getPicturesTable().getAllPictures();
        if (pics != null) {
            for (int i = 0; i < pics.size(); i++) {
                Picture pic = (Picture) pics.get(i);
                try {
                    pic.writeImageContent(new FileOutputStream(path
                            + pic.suggestFullFileName()));
                } catch (FileNotFoundException e) {
                    e.printStackTrace();
                }
            }
        }
        Document htmlDocument = wordToHtmlConverter.getDocument();
        ByteArrayOutputStream outStream = new ByteArrayOutputStream();
        DOMSource domSource = new DOMSource(htmlDocument);
        StreamResult streamResult = new StreamResult(outStream);
        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);
        outStream.close();
        //文本内容
        String content = new String(outStream.toByteArray());
        System.out.println(content);
    }
}