使用poi将word转换为html

使用poi将word转换为html，支持doc,docx，转换后可以保持文字、表格、图片、样式

演示地址: https://www.xiaoyun.studio/app/preview.html

完整的源代码在http://git.oschina.net/xiaoyun_studio/xiaoyun-studio ，路径:src/main/java/studio/xiaoyun/file/tool/PoiTool.java

需要的jar(使用了Maven):

<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>

转换的代码：

import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.converter.WordToHtmlConverter;
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;

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));
        Document document = DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument();
        WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(document);
        // 保存图片，并返回图片的相对路径
        wordToHtmlConverter.setPicturesManager((content, pictureType, name, width, height) -> {
            try(FileOutputStream out = new FileOutputStream(imagePathStr + name)){
                 out.write(content);
            } catch (Exception e) {
                e.printStackTrace();
            }
            return "image/" + name;
        });
        wordToHtmlConverter.processDocument(wordDocument);
        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 = "D:\\ac\\00.docx";
        String targetFileName = "D:\\ac\\test.html";
        String imagePathStr = "D:\\ac\\image\\";
        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"));
            outputStreamWriter = new OutputStreamWriter(new FileOutputStream(targetFileName), "utf-8");
            XHTMLConverter xhtmlConverter = (XHTMLConverter) XHTMLConverter.getInstance();
            xhtmlConverter.convert(document, outputStreamWriter, options);
        } finally {
            if (outputStreamWriter != null) {
                outputStreamWriter.close();
            }
        }
    }