Java在线预览（word转html）--强势推荐

Java--Word在线预览（word转html）--强势推荐

一、新建一个maven项目

二、pom文件

  4.0.0
  com.maven
  online-preview
  war
  0.0.1-SNAPSHOT
  online-preview Maven Webapp
  http://maven.apache.org
  
    
      junit
      junit
      4.12
      test
    
     
     org.apache.poi 
     poi 
     3.14 
     
     
     org.apache.poi 
     poi-scratchpad 
     3.14 
     
     
     org.apache.poi 
     poi-ooxml 
     3.14 
     
     
     fr.opensagres.xdocreport 
     xdocreport 
     1.0.6 
     
     
     org.apache.poi 
     poi-ooxml-schemas 
     3.14 
     
     
     org.apache.poi 
     ooxml-schemas 
     1.3 
     
    

    org.apache.directory.studio
    org.apache.commons.io
    2.4

    
  
  
    online-preview
  

三、Word2007ToHtml.java区分word2007和word2003

/**
 * 
 */
package com.maven.controller;

import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.InputStream;
import java.util.List;

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.commons.io.FileUtils;
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;

/**
* 
Title:Word2007ToHtml 
* 
Company: 
 
* @author 
* @date 2018年4月11日下午2:21:30
* Description: 
*/
public class Word2007ToHtml {
	/*@Test
    public void word2007ToHtml() throws Exception {
        String filepath = "D:\\Tomcat8.0\\File\\";
        String sourceFileName =filepath+"1.docx"; 
        String targetFileName = filepath+"1496717486420.html"; 
        String imagePathStr = filepath+"/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(); 
          } 
        }
      } */
	
	public static void main(String[] args) throws Throwable {
		  final String path = "C:\\Users\\Administrator\\Desktop\\My\\船员培训\\doxc\\题库\\船员用表\\";
		  final String file = "1.doc";
		  InputStream input = new FileInputStream(path + file);
		  HWPFDocument wordDocument = new HWPFDocument(input);
		  WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(
		    DocumentBuilderFactory.newInstance().newDocumentBuilder()
		      .newDocument());
		  wordToHtmlConverter.setPicturesManager(new PicturesManager() {
		   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();
		  String content = new String(outStream.toByteArray());
		  FileUtils.writeStringToFile(new File(path, "1.html"), content, "utf-8");
		 }
}

注意：pyth：本地地址。转换完之后，又在pyth的地址中保存的html文件

不懂在下面留言即可

欢迎订阅关注公众号（JAVA和人工智能）

                                       

                                                           获取更多免费书籍、资源、视频资料