WORD转html带base64图片，解决转换后乱码问题

最新推荐文章于 2022-07-26 15:09:50 发布

浮_雲

最新推荐文章于 2022-07-26 15:09:50 发布

阅读量843

点赞数

分类专栏： java

本文链接：https://blog.csdn.net/qq_31275085/article/details/121164696

版权

word转html java word转html jword转html带图片

java 专栏收录该内容

41 篇文章 0 订阅

订阅专栏

package jxfgw.util;
import org.apache.poi.hwpf.HWPFDocumentCore;
import org.apache.poi.hwpf.converter.WordToHtmlConverter;
import org.apache.poi.hwpf.converter.WordToHtmlUtils;
import org.apache.poi.hwpf.usermodel.Picture;
import org.w3c.dom.Document;
import org.w3c.dom.Element;

import com.sun.org.apache.xerces.internal.impl.dv.util.Base64;

import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.transform.*;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;
import java.io.*;
import java.util.Properties;
public class DocToHtml{
    public static void main(String[] args) throws ParserConfigurationException, TransformerException, IOException {
    	HWPFDocumentCore wordDocument = WordToHtmlUtils.loadDoc(new FileInputStream("D:\\1.doc"));
    	DocToHtml docToHtml = new DocToHtml();
        docToHtml.docToHtml(wordDocument);
    }
    public String docToHtml(HWPFDocumentCore wordDocument) throws IOException, ParserConfigurationException, TransformerException {
        WordToHtmlConverter wordToHtmlConverter = new ImageConverter(
                DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument()
        );
        wordToHtmlConverter.processDocument(wordDocument);
        Document htmlDocument = wordToHtmlConverter.getDocument();
        ByteArrayOutputStream out = new ByteArrayOutputStream();
        DOMSource domSource = new DOMSource(htmlDocument);
        StreamResult streamResult = new StreamResult(out);
        TransformerFactory transformerFactory = TransformerFactory.newInstance();
        Transformer serializer = transformerFactory.newTransformer();
      //判断操作系统是windows，还是Linux的SUSE系统
  		if(isWindows()){
  			serializer.setOutputProperty(OutputKeys.ENCODING, "gb2312");
  		}else{
  			serializer.setOutputProperty(OutputKeys.ENCODING, "utf-8");
  		}
//        serializer.setOutputProperty(OutputKeys.ENCODING, "GB2312");  
        serializer.setOutputProperty(OutputKeys.INDENT, "yes");  
        serializer.setOutputProperty(OutputKeys.METHOD, "html");  
        serializer.transform(domSource, streamResult);  
        out.close();
        String result = new String(out.toByteArray());
        return result;
//        writeFile(new String(out.toByteArray()), "D://1.html"); 
    }
    
    public class ImageConverter extends WordToHtmlConverter{

        public ImageConverter(Document document) {
            super(document);
        }
        @Override
        protected void processImageWithoutPicturesManager(Element currentBlock, boolean inlined, Picture picture){
            Element imgNode = currentBlock.getOwnerDocument().createElement("img");
            StringBuffer sb = new StringBuffer();
//           java8用这个 Base64.getMimeEncoder().encodeToString(picture.getRawContent())
            sb.append(Base64.encode(picture.getRawContent()));
            sb.insert(0, "data:" + picture.getMimeType() + ";base64,");
            imgNode.setAttribute("src", sb.toString());
            currentBlock.appendChild(imgNode);
        }
    }
    public static boolean isWindows(){
	    boolean flag = false;
	    if (System.getProperties().getProperty("os.name").toUpperCase().indexOf("WINDOWS") != -1) {
	    flag = true;
	    }
	    return flag;
	}

    public static void writeFile(String content, String path) {  
        FileOutputStream fos = null;  
        BufferedWriter bw = null;  
        try {  
            File file = new File(path);  
            fos = new FileOutputStream(file);  
            bw = new BufferedWriter(new OutputStreamWriter(fos,"GB2312"));  
            bw.write(content);  
        } catch (FileNotFoundException fnfe) {  
            fnfe.printStackTrace();  
        } catch (IOException ioe) {  
            ioe.printStackTrace();  
        } finally {  
            try {  
                if (bw != null)  
                    bw.close();  
                if (fos != null)  
                    fos.close();  
            } catch (IOException ie) {  
            }  
        }  
    }  
}

需要用到的包poi3.9或者poi3.8等

乱码问题一般是window环境下用GB2316 linux下用utf-8编码，如此可解决乱码问题