Java word转HTML文件，汉字由Ascii转为Utf-8

Java word转成HTML文件、文本打开Html文件汉字由Ascii转为Utf-8

1、Maven

<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>

        <dependency>
            <groupId>org.jsoup</groupId>
            <artifactId>jsoup</artifactId>
            <version>1.11.3</version>
        </dependency>

        <dependency>
            <groupId>net.sf.json-lib</groupId>
            <artifactId>json-lib</artifactId>
            <version>2.4</version>
            <classifier>jdk15</classifier>
        </dependency>
        <!--Ascii转为Utf8-->
        <dependency>
            <groupId>org.apache.commons</groupId>
            <artifactId>org.apache.commons.lang</artifactId>
            <version>2.4.0</version>
        </dependency>

下面是代码测试

package com.test.controller;


import org.apache.commons.lang.StringEscapeUtils;
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.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.parsers.ParserConfigurationException;
import javax.xml.transform.OutputKeys;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerException;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;
import java.io.*;

public class docxToHtml {

    public static void main(String[] args) {
        try {
            WordToHtml1();
        } catch (Exception e) {
            e.printStackTrace();
        }
    }

    public static String WordToHtml1() throws IOException {
        String wordPath = "C:\\upload\\";
        String wordName = "s";
        String suffix =".docx";
        String htmlPath = wordPath + File.separator + wordName + "-file"
                + File.separator;
        String htmlName = wordName + ".html";
        String imagePath = htmlPath + "image" + File.separator;

// 判断html文件是否存在
        File htmlFile = new File(htmlPath + htmlName);
        if (htmlFile.exists()) {
            return htmlFile.getAbsolutePath();
        }

// word文件
        File wordFile = new File(wordPath + File.separator + wordName + suffix);

// 加载word文档生成 XWPFDocument对象
        InputStream in = new FileInputStream(wordFile);
        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 imgFolder = new File(imagePath);
        XHTMLOptions options = XHTMLOptions.create();
        options.setExtractor(new FileImageExtractor(imgFolder));
// html中图片的路径 相对路径
        options.URIResolver(new BasicURIResolver("image"));
        options.setIgnoreStylesIfUnused(false);
        options.setFragment(true);


// 将 XWPFDocument转换成XHTML
// 生成html文件上级文件夹
        File folder = new File(htmlPath);
        if (!folder.exists()) {
            folder.mkdirs();
        }
        OutputStream out = new FileOutputStream(htmlFile);
        //XHTMLConverter.getInstance().convert(document, out, options);
// 使用字符数组流获取解析的内容
 	ByteArrayOutputStream baos = new ByteArrayOutputStream();
 	XHTMLConverter.getInstance().convert(document, baos, options);
 	//转为字符后，转义编码、然后转为数组写入。
 	String contents = baos.toString();
 	contents = StringEscapeUtils.unescapeHtml(contents);
    byte[] b_gbk = contents.getBytes();
    out.write(b_gbk);
 	System.out.println("2007-docx"+contents);
 	baos.close();

        return htmlFile.getAbsolutePath();
    }


    /**
     * 将word2003转换为html文件
     *
     * @param wordPath
     *            word文件路径
     * @param wordName
     *            word文件名称无后缀
     * @param suffix
     *            word文件后缀
     * @throws IOException
     * @throws TransformerException
     * @throws ParserConfigurationException
     */
    public static String WordToHtml2003(String wordPath, String wordName,
                                        String suffix) throws IOException, TransformerException,
            ParserConfigurationException {
        String htmlPath = wordPath + File.separator + wordName + "-file"
                + File.separator;
        String htmlName = wordName + ".html";
        final String imagePath = htmlPath + "image" + File.separator;


// 判断html文件是否存在
        File htmlFile = new File(htmlPath + htmlName);
        if (htmlFile.exists()) {
            return htmlFile.getAbsolutePath();
        }


// 原word文档
        final String file = wordPath + File.separator + wordName + suffix;
        InputStream input = new FileInputStream(new File(file));


        HWPFDocument wordDocument = new HWPFDocument(input);
        WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(
                DocumentBuilderFactory.newInstance().newDocumentBuilder()
                        .newDocument());
// 设置图片存放的位置
        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()) {// 图片目录不存在则创建
                    imgPath.mkdirs();
                }
                File file = new File(imagePath + suggestedName);
                try {
                    OutputStream os = new FileOutputStream(file);
                    os.write(content);
                    os.close();
                } catch (FileNotFoundException e) {
                    e.printStackTrace();
                } catch (IOException e) {
                    e.printStackTrace();
                }
// 图片在html文件上的路径 相对路径
                return "image/" + suggestedName;
            }
        });


// 解析word文档
        wordToHtmlConverter.processDocument(wordDocument);
        Document htmlDocument = wordToHtmlConverter.getDocument();


// 生成html文件上级文件夹
        File folder = new File(htmlPath);
        if (!folder.exists()) {
            folder.mkdirs();
        }


// 生成html文件地址
// 也可以使用字符数组流获取解析的内容
// ByteArrayOutputStream baos = new ByteArrayOutputStream();
// OutputStream outStream = new BufferedOutputStream(baos);


        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);


// 也可以使用字符数组流获取解析的内容
// String content = baos.toString();
// System.out.println(content);
// baos.close();
// System.out.println("2003-doc"+content);
        return htmlFile.getAbsolutePath();
    }

}