poi 将word文档转HTML格式

利用POI工具将word文档转成html

1，导入对应的jar

      

2，编写相应的代码，直接上图

     1)、

     a,在src目录下创建helper目录

     b,在helper目录下创建PoiHelperFactory.java文件

     

package helper;

import service.IDocHelper;
import service.impl.DocHeplerImpl;


/**
 * 
 * @author yanzz
 * poi静态工厂类
 * 
 */
public class PoiHelperFactory {
   
	public static IDocHelper createDocHelper(){

	   return new DocHeplerImpl();
   }
}

      2）、

      a, src目录下创建service目录以及在service目录下创建impl目录，

      b, 分别创建出IDocHelper.java 以及 DocHelperImpl.java文件

package service;

public interface IDocHelper {

	public String transformHtml(String sourceFilePath);
	
}

package service.impl;

import org.apache.log4j.Logger;

import service.IDocHelper;
import util.PoiUtil;

public class DocHeplerImpl implements IDocHelper {
	//poi控制器类的日志
   	private static Logger logger = Logger.getLogger(DocHeplerImpl.class);
	
	public String transformHtml(String sourceFilePath){		
		String xxName = PoiUtil.getVersion(sourceFilePath);
		String result = "";
	    if("doc".equals(xxName)){
	    	result = PoiUtil.docTransformHtml(sourceFilePath);
	    }else if("docx".equals(xxName)){
	    	result = PoiUtil.docxTransformHtml(sourceFilePath);
	    }else{
	    	logger.info("word文档的格式错误，，，请检查是否是word文档");
	    }   
		    return result;	
	}

}

      3)、

      a,src目录下创建util目录，并创建PoiUtil.java

package util;

import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
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.log4j.Logger;
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.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;

public class PoiUtil {
	
	//poi控制器类的日志
   	private static Logger logger = Logger.getLogger(PoiUtil.class);
	/**
	 * 这边先写死, 真正开发的时候可以将此处改成
	 * properties文件或者
	 * 数据局数据字典进行存储。
	 */
	public static final String IMAGEPATH ="D:/doc/images/";
	
	/**
	  * 动态的生成picture的名称通过 UUID
	  */
	private static  String getRandom(){
		  long curL = System.currentTimeMillis();
		  return String.valueOf(curL);
	}
	
	
	/**
	 * 对传入的文件的版本号进行判断
	 * 看返回的是docx
	 * 还是 doc
	 */
	public static String getVersion(String sourceFilePath){
		int index = sourceFilePath.lastIndexOf(".");
		sourceFilePath = sourceFilePath.substring(index+1);
		return sourceFilePath;
	}
	
    /**
     * 根据目标doc文件路径地址将word的内容打散成html格式的字符串 。
     * @param sourceFilePath
     *        源文件地址vg
     */
	public static String docTransformHtml(String sourceFilePath){
		//doc文档的html字符串
		String htmlContent ="";
	 try{	
		//创建inputStream
		 InputStream input = new FileInputStream(sourceFilePath);
		//创建HWPFDocument对象
		 HWPFDocument wordDocument = new HWPFDocument(input);
		//获取WordToHtmlConverter对象
		 WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(
				    DocumentBuilderFactory.newInstance().newDocumentBuilder()
				      .newDocument());		 
		 //保存路径这个路径也是html中 的图片引用路径
		 //<img src ="。。。。。。">
		 wordToHtmlConverter.setPicturesManager(new PicturesManager() {
			   public String savePicture(byte[] content, PictureType pictureType,
			     String suggestedName, float widthInches, float heightInches) {
			     return IMAGEPATH + suggestedName;
			   }
			  });
	    //设置processDocument
		 wordToHtmlConverter.processDocument(wordDocument);
		//获取图片table列表
		 List pics = wordDocument.getPicturesTable().getAllPictures();
		//将图片文件存入文件夹内 
		 if(pics != null){
		   for(int i = 0; i < pics.size(); i ++){
			   Picture pic = (Picture)pics.get(i);
			   pic.writeImageContent(new FileOutputStream(IMAGEPATH+pic.suggestFullFileName()));
		   }
		 }
		//获取html的document对象
		 Document docHtml = wordToHtmlConverter.getDocument();
		//创建DOMSource对象
		 DOMSource domSource = new DOMSource(docHtml);
		//创建StreamResult对象
		 ByteArrayOutputStream outStream = new ByteArrayOutputStream(); 
		 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();
		 htmlContent = new String(outStream.toByteArray(),"utf-8");
		 logger.debug("转化html字符串成功...");
	 }catch(Exception e){
		 e.printStackTrace();
	 }
	     return htmlContent;
	}
	
	/**
	  * 将docx文档打散成html格式的字符串
	  */
	 public static String docxTransformHtml(String sourceFilePath){  
		     String htmlContent = "";
		 try {
			 
			 ByteArrayOutputStream outStream = new ByteArrayOutputStream();
			 
			 File docxFile = new File(sourceFilePath);
			 XWPFDocument wordDocument = 
					      new XWPFDocument(new FileInputStream(docxFile));
			 XHTMLOptions options = XHTMLOptions.create()
					                .URIResolver(new BasicURIResolver(IMAGEPATH));
			 File imageFolderFile = new File(IMAGEPATH);
			 
			 options.setExtractor(new FileImageExtractor(imageFolderFile));
			 
			 XHTMLConverter.getInstance().convert(wordDocument, outStream, options);
			 
			 //返回字符串
			 htmlContent = new String(outStream.toByteArray(),"utf-8");
			 
		   } catch (FileNotFoundException e) {
		        logger.error("该路径下没有获取到文件，请检查路径是否正确");		
				e.printStackTrace();
		   } catch (IOException e) {
			   logger.error("后台报错...");
				e.printStackTrace();
		   } 
			 
			 return htmlContent;
	 }
	 		
}

这边的对应的word文档以及文件目录可以修改自己的对应的word以及目录，根据具体的实际情况而定。

ps:
      代码的百度网盘地址：https://pan.baidu.com/s/1o84UvKQ

      个人微信号： 一起学习注明csdn博客就可以了