word文档转为html文档解决方案

前言：项目中，遇到需要将 word 文档转为 html 文档的需求，下面整理一下用到的两种方式：

• 方案一：
  使用 aspose.words.jar 工具，代码如下(这个工具其他使用方法，详见：word文档转pdf并在任意浏览器预览打印一体化方案)：

	/**
	 * word转html文本
	 * @param doc 需要转换的doc文件对象
	 * @return
	 */
	public String parseWord2Html(Document doc){
		HtmlSaveOptions saveOptions = new HtmlSaveOptions();
		saveOptions.setExportHeadersFootersMode(ExportHeadersFootersMode.NONE); // HtmlSaveOptions的其他设置信息请参考相关API
		ByteArrayOutputStream htmlStream = new ByteArrayOutputStream();
		String htmlText = "";
		try {
			doc.save(htmlStream, saveOptions);
			htmlText = new String(htmlStream.toByteArray(),"UTF-8");
			htmlStream.close();
		} catch (Exception e) {
			LOG.error("word文件转换失败，详细错误信息：{}",e.getMessage());
		}
		return htmlText;
	}

• 方案二
  使用 apache 的 poi 进行转换。

package test.poi;

import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
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.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 test {
	
	public static synchronized String getOnlyId(){
		long curL = System.currentTimeMillis();
		if(curL>curL){
			cacheInt = 0;
		}else{
			cacheInt += 1;
		}
		return String.valueOf(curL)+String.valueOf(cacheInt);
	}	
	
	private static int cacheInt = 0;
	
	private static String projectUrl = "http://192.168.1.1:8080/test/";
	
	private static String projectPath = "D:/test/piccache/";
	
	/**
	 * 处理word2003
	 * @param inFile
	 * @return
	 */
	public static String doWord(File inFile) {
		ByteArrayOutputStream out = new ByteArrayOutputStream();  
		String randomName = "PIC"+getOnlyId();
		//转换后html中图片src的链接
		final String baseUrl = projectUrl+"wordpic/"+randomName+"/";
		//转换后图片存放的位置
		String dir = projectPath+"/wordpic/"+randomName+"/";
		File dirF = new File(dir);
		if(!dirF.exists()||!dirF.isDirectory()){
			dirF.mkdir();
		}
		try{
			HWPFDocument wordDocument = new HWPFDocument(new FileInputStream(inFile));
	        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 baseUrl+suggestedName;  
	             }  
	         } );  
	        wordToHtmlConverter.processDocument(wordDocument);  
	        List<Picture> 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(dir + pic.suggestFullFileName()));  
	                } catch (FileNotFoundException e) {  
	                    e.printStackTrace();  
	                }    
	            }  
	        }  
	        Document htmlDocument = wordToHtmlConverter.getDocument();  
	        
	        DOMSource domSource = new DOMSource(htmlDocument);  
	        StreamResult streamResult = new StreamResult(out);  
	  
	        TransformerFactory tf = TransformerFactory.newInstance();  
	        Transformer serializer = tf.newTransformer();  
	        serializer.setOutputProperty(OutputKeys.ENCODING, "GB2312");  
	        serializer.setOutputProperty(OutputKeys.INDENT, "yes");  
	        serializer.setOutputProperty(OutputKeys.METHOD, "html");  
	        serializer.transform(domSource, streamResult);  
	        out.close();  
		}catch(Exception e){
			e.printStackTrace();
		}
        return new String(out.toByteArray());
	}  
	
	/**
	 * 处理word2007
	 * @param inFile
	 * @return
	 */
	public static String doWord2007(File inFile) {
		ByteArrayOutputStream out = new ByteArrayOutputStream();  
		String randomName = "PIC"+getOnlyId();
		//转换后html中图片src的链接
		final String baseUrl = projectUrl+"wordpic/"+randomName+"/";
		//转换后图片存放的位置
		String dir = projectPath+"/wordpic/"+randomName+"/";
		File dirF = new File(dir);
		if(!dirF.exists()||!dirF.isDirectory()){
			dirF.mkdir();
		}
		try{
			XWPFDocument wordDocument = new XWPFDocument(new FileInputStream(inFile));
			XHTMLOptions options = XHTMLOptions.create().URIResolver(new BasicURIResolver(baseUrl));
			File imageFolderFile = new File(dir);
			options.setExtractor(new FileImageExtractor(imageFolderFile));
			XHTMLConverter.getInstance().convert(wordDocument, out, options);
	        out.close();  
		}catch(Exception e){
			e.printStackTrace();
		}
        return new String(out.toByteArray());
	}
	
	
	public static void main(String[] args) {
		File word2003 = new File("e:/文书系统2.0版本设计.doc");
		File word2007 = new File("e:/test.docx");
		
		/** 打印出word2003转换后的html内容*/
		System.out.println(doWord(word2003));
		
		/** 打印出word2007转换后的html内容*/
		System.out.println(doWord2007(word2007));
	}

}

用到的jar包：

完整源码及 jar 包：
https://download.youkuaiyun.com/download/CDWLX/12028495