基于Apach POI 实现Word 转换HTML 文件

Apache POI 简介：

Apache POI 简介是用Java编写的免费开源的跨平台的 Java API，Apache POI提供API给Java程式对Microsoft Office（Excel、WORD、PowerPoint、Visio等）格式档案读和写的功能。POI为“Poor Obfuscation Implementation”的首字母缩写，意为“可怜的模糊实现”。

官方主页： http://poi.apache.org/index.html 
API文档： http://poi.apache.org/apidocs/index.html

编写项目

1、项目依赖

2、核心代码
 

项目pom.xml 文件

<!--集成apache poi word 转html -->
		<dependency>
			<groupId>org.apache.poi</groupId>
			<artifactId>poi</artifactId>
			<version>3.10.1</version>
		</dependency>
		<dependency>
			<groupId>org.apache.poi</groupId>
			<artifactId>poi-scratchpad</artifactId>
			<version>3.9</version>
		</dependency>
		<dependency>
			<groupId>org.apache.poi</groupId>
			<artifactId>poi-ooxml</artifactId>
			<version>3.10.1</version>
		</dependency>
		<dependency>
			<groupId>org.apache.poi</groupId>
			<artifactId>poi-ooxml-schemas</artifactId>
			<version>3.10.1</version>
		</dependency>
		<dependency>
			<groupId>org.apache.poi</groupId>
			<artifactId>ooxml-schemas</artifactId>
			<version>1.1</version>
		</dependency>

		<!-- 集成 -->
		<dependency>
			<groupId>fr.opensagres.xdocreport</groupId>
			<artifactId>fr.opensagres.xdocreport.document</artifactId>
			<version>2.0.1</version>
		</dependency>
		<dependency>
			<groupId>fr.opensagres.xdocreport</groupId>
			<artifactId>org.apache.poi.xwpf.converter.xhtml</artifactId>
			<version>1.0.6</version>
		</dependency>
		<dependency>
			<groupId>fr.opensagres.xdocreport</groupId>
			<artifactId>org.apache.poi.xwpf.converter.core</artifactId>
			<version>1.0.6</version>
		</dependency>

2、核心代码：

package com.zzg.word.trans.html;

import java.io.File;
import java.io.InputStream;
import java.io.OutputStream;

import org.apache.poi.xwpf.converter.core.BasicURIResolver;
import org.apache.poi.xwpf.converter.core.FileImageExtractor;
import org.apache.poi.xwpf.converter.xhtml.XHTMLOptions;
import org.apache.poi.xwpf.usermodel.XWPFDocument;

public class WordTransHtml {
	
	/**
	 * 
	 * @Title: docxTransHtml   
	 * @Description: docx 转换 HTML  
	 * @param: @param inputStream: docx 文件输入流
	 * @param: @param outputStream: html 文件输出流
	 * @param: @param imageSaveDir：图片路径 
	 * @return: void      
	 * @throws
	 */
	public static void docxTransHtml(InputStream inputStream, OutputStream outputStream, String imageSaveDir){
		try{
			XWPFDocument document = new XWPFDocument(inputStream);
			
			XHTMLOptions options = XHTMLOptions.create();
			options.setExtractor(new FileImageExtractor(new File(imageSaveDir)));
			options.URIResolver(new BasicURIResolver(imageSaveDir));
			
			org.apache.poi.xwpf.converter.xhtml.XHTMLConverter.getInstance().convert(document, outputStream, options);
		}catch(Exception e){
			e.printStackTrace();
		}
	}

}

测试代码：

package com.zzg.word.trans.html.test;

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.io.OutputStream;

import com.zzg.word.trans.html.WordTransHtml;

public class WordTransHtmlTest {

	public static void main(String[] args) {
		// TODO Auto-generated method stub
		String imagePath = "C:\\image\\iamges";
		String docPath ="C:\\image\\1.docx";
		String htmlPath = "c:\\image\\1.html";
		File docFile = new File(docPath);
		File htmlFile = new File(htmlPath);
		File imageDir = new File(imagePath);
		// 判断文件夹是否存在，不存在则创建文件夹
		if(!imageDir.exists()){
			imageDir.mkdirs();
		}
		// 判断html 文件是否存在，不存在则创建
		if(!htmlFile.exists()){
			try {
				htmlFile.createNewFile();
			} catch (IOException e) {
				// TODO Auto-generated catch block
				e.printStackTrace();
			}
		}
		if(docFile.exists() && htmlFile.exists()){
			try {
				InputStream inputStream = new FileInputStream(docFile);
				OutputStream outputStream = new FileOutputStream(htmlFile);
				WordTransHtml.docxTransHtml(inputStream, outputStream, imagePath);
			} catch (FileNotFoundException e) {
				// TODO Auto-generated catch block
				e.printStackTrace();
			}
			
		}
		
	}

}

效果展示: