java对word各种文件类型的转换

其中程序使用到了poi，jacob，openoffice，icepdf，iText包，可以在网上搜一下。

PS：在使用openoffice将pdf转成图片时，前提是本地安装了openoffice软件，并且要开启该服务：

安装完openoffice后

1.安装openoffice后进入默认的安装目录

cd C:\Program Files (x86)\OpenOffice 4\program

执行

soffice -headless -accept="socket,host=127.0.0.1,port=8100;urp;" -nofirststartwizard

2.查看是否安装成功

    2.1查看端口对应的pid

    netstat -ano|findstr "8100"

    2.2查看pid对应的服务程序名

    tasklist|findstr "ipd值"

不多说，直接上代码：

package com.officefileparser.utils;

import java.awt.image.BufferedImage;
import java.awt.image.RenderedImage;
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.net.ConnectException;
import java.net.MalformedURLException;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import javax.imageio.ImageIO;
import org.apache.commons.io.FilenameUtils;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.util.PDFTextStripper;
import org.apache.poi.hslf.HSLFSlideShow;
import org.apache.poi.hslf.extractor.PowerPointExtractor;
import org.apache.poi.hslf.model.Picture;
import org.apache.poi.hslf.model.Slide;
import org.apache.poi.hslf.model.TextRun;
import org.apache.poi.hslf.usermodel.PictureData;
import org.apache.poi.hslf.usermodel.SlideShow;
import org.apache.poi.hwpf.extractor.WordExtractor;
import org.apache.poi.poifs.filesystem.POIFSFileSystem;
import org.icepdf.core.pobjects.Document;
import org.icepdf.core.pobjects.Page;
import org.icepdf.core.util.GraphicsRenderingHints;
import com.artofsolving.jodconverter.DefaultDocumentFormatRegistry;
import com.artofsolving.jodconverter.DocumentConverter;
import com.artofsolving.jodconverter.DocumentFormat;
import com.artofsolving.jodconverter.openoffice.connection.OpenOfficeConnection;
import com.artofsolving.jodconverter.openoffice.connection.SocketOpenOfficeConnection;
import com.artofsolving.jodconverter.openoffice.converter.OpenOfficeDocumentConverter;
import com.jacob.activeX.ActiveXComponent;
import com.jacob.com.Dispatch;

public class OfficeFileParserUtils {
	
	/**
	 * 使用poi读取doc文件
	 * @param docUrl
	 * doc文件路径
	 * @return
	 * 代表doc文件内容的字符串
	 * @throws IOException
	 */
	public static void reaDoc(String docPath) throws IOException{
		FileInputStream in;
		in = new FileInputStream(docPath);
		WordExtractor extractor = new WordExtractor(in);
		//HWPFDocument hwpfDocument = new HWPFDocument(in);
		//一个元素就是一段内容
		String[] paraTexts = extractor.getParagraphText();
	      for (int i=0; i<paraTexts.length; i++) {
	    	  //一段一段的存入
	          System.out.println(/*"Paragraph " + (i+1) + " : " +*/ paraTexts[i]);  
	       } 
	}

	/**
     * 使用poi写word文档
     * @param destFile 目的地址
     * @param fileCon  待写入的字符串
     */
    public void exportDoc(String destFile,String fileCon){
        try {
            //doc content
            ByteArrayInputStream bais = new ByteArrayInputStream(fileCon.getBytes());
            POIFSFileSystem fs = new POIFSFileSystem();
            DirectoryEntry directory = fs.getRoot(); 
            directory.createDocument("WordDocument", bais);
            FileOutputStream ostream = new FileOutputStream(destFile);
            fs.writeFilesystem(ostream);
            bais.close();
            ostream.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

	/**
	 * 使用pdfbox读取pdf文档信息
	 * @param pdfPath pdf文件路径
	 * @return pdf信息字符串
	 * @throws Exception
	 */
	public static String getPdfText(String pdfPath) throws Exception {
		boolean sort = false;
		int startPage = 1;
		int endPage = 10;
		PDDocument document = null;
		File file = new File(pdfPath);
		if(!file.exists()){
			System.out.println(file.getAbsolutePath()+" 不存在！！！");
			return "";
		}
		System.out.println(file);
		try {
			try {
				document = PDDocument.load(file);
			} catch (MalformedURLException e) {
			}
			PDFTextStripper stripper = new PDFTextStripper();
			stripper.setSortByPosition(sort);
			stripper.setStartPage(startPage);
			stripper.setEndPage(endPage);
			return stripper.getText(document);
		} catch (Exception e) {
			e.printStackTrace();
			return "";
		} finally {
			if (document != null) {
				document.close();
			}
		}
	}
	
	// function 检查文件是否为PPT
		public static boolean checkFile(File file) {
			boolean isppt = false;
			String filename = file.getName();
			String suffixname = null;
			if (filename != null && filename.indexOf(".") != -1) {
				suffixname = filename.substring(filename.indexOf("."));
				System.out.println(suffixname);
				if (suffixname.equals(".ppt")) {
					isppt = true;
				}
				return isppt;
			} else {
				return isppt;
			}
		}
		
	/**
	 * 使用poi抽取PPT的全部内容
	 * @param PPTPath
	 * @return
	 * @throws IOException
	 */
	public static String readPPTAll(String PPTPath) throws IOException{
		
		PowerPointExtractor powerPointExtractor = new PowerPointExtractor(PPTPath);
		System.out.println(powerPointExtractor.getText());
		return powerPointExtractor.getText();
	}
	
	/**
	 * 使用poi一张一张的抽取ppt内容
	 * @param pptPath
	 * @return
	 * @throws IOException
	 */
	public static HashMap readPPTOneByOne(String pptPath,String outPath) throws IOException{
		
		//StringBuffer content = new StringBuffer("");//store the content of ppt
		InputStream inputStream = new FileInputStream(pptPath);
		HashMap<Integer, String> contentPageMap =new HashMap<Integer, String>();  
		//Constructs a Powerpoint document from an input stream.
		SlideShow slideShow = new SlideShow(new HSLFSlideShow(inputStream));
		
		//获得每一张幻灯片,可认为一个slides元素就是一张ppt 
		Slide[] slides = slideShow.getSlides();
		for (int i = 0; i < slides.length; i++) {
			//获得ppt的页码pageNum
			int pageNum = slides[i].getSlideNumber();
			//读取一张幻灯片的内容(包括标题),为了取得幻灯片的文字内容,建立TextRun,TextRun代表一张ppt
			TextRun[] textRuns = slides[i].getTextRuns();
			System.out.println("第"+pageNum+"张");
			//读取一张幻灯片的标题
            String title=slides[i].getTitle();
/*            //获得系统换行符
            String lineSeparator = (String) java.security.AccessController.doPrivileged(
                    new sun.security.action.GetPropertyAction("line.separator"));
            System.out.print(lineSeparator);*/
			//如果一张ppt中没有标题,就将第一个文本框中的内容作为标题
            if(title == null){
            	title = textRuns[0].getText().replaceAll("[\n\r]", "");//去掉换行符
            }
            
            System.out.println("标题:"+title);
			for (int j = 0; j < textRuns.length; j++) {
				//获得一张ppt的一个文本框中的内容text
				String text = textRuns[j].getText().replaceAll("[\n\r]", "");
				contentPageMap.put(i, text);
				System.out.print(text);
				System.out.println();
			}	
		}
		// 提取ppt中的所有图片
		//获得ppt的页码pageNum
		File outDir = new File(outPath);
		if(!outDir.exists()){
			outDir.mkdir();
		}
		extractImageOfPPT(pptPath,outPath);
		return contentPageMap;
	}
	
	//使用poi抽取ppt中的图片
		private static void extractImageOfPPT(String pptPath,String outPath) throws IOException {
			//SlidesShow类代表一个ppt文件
			SlideShow ppt = new SlideShow(new HSLFSlideShow(pptPath));
			//sildes数组中的一个元素就代表一张ppt
			Slide[] slides = ppt.getSlides();
			// extract all pictures contained in the presentation
			PictureData[] pdata = ppt.getPictureData();
			for (int i = 0; i < pdata.length; i++) {
				PictureData pict = pdata[i];
				// picture data
				byte[] data = pict.getData();
				int type = pict.getType();
				String ext;
				switch (type) {
				case Picture.JPEG:
					ext = ".jpg";
					break;
				case Picture.PNG:
					ext = ".png";
					break;
				case Picture.WMF:
					ext = ".wmf";
					break;
				case Picture.EMF:
					ext = ".emf";
					break;
				case Picture.PICT:
					ext = ".pict";
					break;
				default:
					continue;
				}
				FileOutputStream out = new FileOutputStream(outPath+"pict_" + i + ext);
				out.write(data);
				out.close();
			}
		}
		
		/**
		 *使用openoffice将doc的各种类型文件转成pdf格式
		 * @param docPath
		 * @param pdfPath
		 * @throws ConnectException
		 */
		 public static void doc2Pdf(String docPath, String pdfPath) throws ConnectException {  
	         File inputFile = new File(docPath);//预转文件  
	         File outputFile = new File(pdfPath);//pdf文件  
	         OpenOfficeConnection connection = new SocketOpenOfficeConnection(8100);  
	         connection.connect();//建立连接  
	         DocumentConverter converter = new OpenOfficeDocumentConverter(connection);  
	         DefaultDocumentFormatRegistry formatReg = new DefaultDocumentFormatRegistry();     
	         DocumentFormat txt = formatReg.getFormatByFileExtension("odt") ;//设定文件格式  
	         DocumentFormat pdf = formatReg.getFormatByFileExtension("pdf") ;//设定文件格式  
	         converter.convert(inputFile, txt, outputFile, pdf);//文件转换  
	         connection.disconnect();//关闭连接  
	      } 
		
		/**
		  * 使用openoffice将doc文档转成图片，效果不错,思路：先将doc文档转成pdf，然后将pdf转成图片
		  * @param docPath
		  * @param imgDirPath
		  */
		public static void doc2Imags(String docPath, String imgDirPath){
		    String pdfPath =String.format("%s%s.pdf",  FilenameUtils.getFullPath(docPath), FilenameUtils.getBaseName(docPath));  
		    try {  
		    	System.out.println(FilenameUtils.getFullPath(docPath)+"   "+FilenameUtils.getBaseName(docPath));
		        doc2Pdf(docPath, pdfPath);
		        pdf2Imgs(pdfPath, imgDirPath);  
		        File pdf =  new File(pdfPath);  
		        if(pdf.isFile()){  
		           // pdf.delete();  
		        }  
		  
		    } catch (ConnectException e) {  
		        e.printStackTrace();  
		    } catch (Exception e) {  
		        e.printStackTrace();  
		    }  
		   }
	
	/** 
	  * 使用icepdf将pdf转换成图片 ,并返回图片名称 
	  * @param pdfPath 
	  * @param imagePath 
	  * @return 返回转换后图片的名字 
	  * @throws Exception 
	  */  
	 public static List<String> pdf2Imgs(String pdfPath, String imgDirPath) throws Exception {  
	     Document document = new Document();  
	     document.setFile(pdfPath);  
	     float scale = 5f;//放大倍数  
	     float rotation = 0f;//旋转度数  
	     List<String> imgNames = new ArrayList<String>();  
	     int pageNum = document.getNumberOfPages();  
	     File imgDir = new File(imgDirPath);  
	     if (!imgDir.exists()) { 
	         imgDir.mkdirs();  
	     }  
	     for (int i = 0; i < pageNum; i++) {  
	         BufferedImage image = (BufferedImage) document.getPageImage(i, GraphicsRenderingHints.SCREEN,  
	                 Page.BOUNDARY_CROPBOX, rotation, scale);
	         RenderedImage rendImage = image;  
	         try {  
	             String filePath = imgDirPath + File.separator + i + ".jpg";  
	             File file = new File(filePath);  
	             ImageIO.write(rendImage, "jpg", file);  
	             imgNames.add(FilenameUtils.getName(filePath));  
	         } catch (IOException e) {  
	             e.printStackTrace();  
	             return null;  
	         }  
	         image.flush();  
	     }  
	     document.dispose();  
	     return imgNames;  
	 }
	 
	 /**
	  * 使用jacob将ppt转成图片
	  * @param inputFile
	  * @param ImgFilePath
	  */
		public static synchronized void ppt2Img(String inputFile,String ImgFilePath){
	        System.out.println("ppt2PDF==========进入");
	        ActiveXComponent app = null;
	        try {
	             app = new ActiveXComponent("PowerPoint.Application");
	        } catch (Exception e) {
	            e.printStackTrace();
	        }
	        System.out.println("--------------------");
	        app.setProperty("Visible", true);
	        Dispatch ppts = app.getProperty("Presentations").toDispatch();
	        System.out.println("ppt2PDF==========准备打开ppt文档");
	        System.out.println(new File(inputFile).exists());
	        Dispatch ppt = Dispatch.call(ppts,
	                                    "Open",
	                                    inputFile,
	                                    true,//ReadOnly
	                                    true,//Untitled指定文件是否有标题
	                                    true//WithWindow指定文件是否可见
	                                    ).toDispatch();
	        System.out.println("ppt2PDF==========准备转换ppt文档");
	        Dispatch.call(ppt,"SaveCopyAs",ImgFilePath,17);//转换成jpg
	                    
	        System.out.println("ppt2PDF==========准备关闭ppt文档");       
	        Dispatch.call(ppt, "Close");
	        app.invoke("Quit");
	    }
}