Word文档或PDF转图片

首先把Word文档转为pdf，方法网上很多，比如用jacob、poi、pdfbox、xpdf、OpenOffice+JodConverter(Openoffice)等。

 

现在主要讲pdf转图片方法：

1、  Icepdf(http://www.icepdf.org/)

功能强大，转图片，直接搜索pdf，提取文本等。

例子，其中包在官方下载：

package com.test;

 

import java.awt.image.BufferedImage;

import java.awt.image.RenderedImage;

import java.io.File;

import java.io.IOException;

 

import javax.imageio.ImageIO;

 

import org.icepdf.core.pobjects.Document;

import org.icepdf.core.pobjects.Page;

import org.icepdf.core.util.GraphicsRenderingHints;

 

 

public class TestPdfToGif3 {

    public static void main(String[] args) {

 

    String p=System.getProperty("user.dir") + "/"+"333.pdf";     

        String filePath = p;

 

        Document document = new Document();

        try {

            document.setFile(filePath);

        } catch (Exception ex) {

        }

 

        // save page caputres to file.

        float scale = 1.3f;

        float rotation = 0f;

 

        // Paint each pages content to an image and write the image to file

        for (int i = 0; i < document.getNumberOfPages(); i++) {

            BufferedImage image = (BufferedImage)

            document.getPageImage(i,GraphicsRenderingHints.SCREEN,Page.BOUNDARY_CROPBOX, rotation, scale);

            RenderedImage rendImage = image;

            // capture the page image to file

            try {

                System.out.println("/t capturing page " + i);

                File file = new File("imageCapture1_" + i + ".png");

                ImageIO.write(rendImage, "png", file);

 

            } catch (IOException e) {

                e.printStackTrace();

            }

            image.flush();

        }

        // clean up resources

        document.dispose();

    }

}

 

2、  pdf-renderer(https://pdf-renderer.dev.java.net/)

转图片例子，其中包官方下载：

package com.test;

 

import java.awt.Color;

import java.awt.Image;

import java.awt.Rectangle;

import java.awt.image.BufferedImage;

import java.io.File;

import java.io.FileOutputStream;

import java.io.IOException;

import java.io.RandomAccessFile;

import java.nio.ByteBuffer;

import java.nio.channels.FileChannel;

 

import javax.imageio.ImageIO;

 

import org.apache.log4j.Logger;

 

import com.sun.pdfview.PDFFile;

import com.sun.pdfview.PDFPage;

 

/**

 * 测试pdf转图片，https://pdf-renderer.dev.java.net/

 */

public class TestPdfToGif2 {

 

    private static Logger log = Logger.getLogger(TestPdfToGif2.class);

 

    private String pdfName;

 

    public String getPdfName() {

       return pdfName;

    }

 

    public void setPdfName(String pdfName) {

       this.pdfName = pdfName;

    }

 

    public String getBasePath() {

       return basePath;

    }

 

    public void setBasePath(String basePath) {

       this.basePath = basePath;

    }

 

    private String fileNameNoExtMD5;

 

    private String basePath;

 

    /**

     * 测试

     *

     * @param args

     */

    public static void main(String[] args) {

 

       try {

 

           TestPdfToGif2 pg = new TestPdfToGif2();

 

           pg.setPdfName("333");

           pg.setBasePath(System.getProperty("user.dir") + "/");

           pg.fileNameNoExtMD5 = pg.basePath + pg.getPdfName();

 

           pg.pdfToGIF("gif");

 

       } catch (Exception e) {

           e.printStackTrace();

       }

 

       log.info("程序运行完了！");

 

    }

 

   

    /**

     * 建立PDF文档读取类

     *

     * @param filePath

     *            PDF文件的路径

     * @return null 或者PDFFile instance

     */

    private static PDFFile getPdfFile(String filePath) {

       try {

           File file = new File(filePath);

           RandomAccessFile raf = new RandomAccessFile(file, "r");

           FileChannel channel = raf.getChannel();

           ByteBuffer buf = channel.map(FileChannel.MapMode.READ_ONLY, 0,

                  channel.size());

           PDFFile pdffile = new PDFFile(buf);

           return pdffile;

       } catch (Exception ex) {

           ex.printStackTrace();

       }

       return null;

    }

   

    /**

     * pdf文件转成gif文件 转换成功后一定要记得写磁盘

     *

     * @throws IOException

     */

    private void pdfToGIF(String suff) throws IOException {

       PDFFile pdffile =getPdfFile(fileNameNoExtMD5 + ".pdf");

       int pages = pdffile.getNumPages();

       File gifFile = null;

       BufferedImage contImage = null;

       FileOutputStream fos = null;

       String giffilename = "";

       for (int i = 0; i < pages; i++) {

           try {

              giffilename = fileNameNoExtMD5 + "." + i + ".gif";

              gifFile = new File(giffilename);

              if (gifFile.exists()) {

                  continue;

              }

 

              fos = new FileOutputStream(gifFile);

              PDFPage page = pdffile.getPage(i);

 

              Rectangle rect = new Rectangle(0, 0, (int) page.getBBox()

                     .getWidth(), (int) page.getBBox().getHeight());

 

              // generate the image

              Image img = page.getImage(rect.width, rect.height, rect, null,

                     true, true);

 

              contImage = new BufferedImage(rect.width, rect.height,

                     BufferedImage.TYPE_INT_ARGB);

              contImage.getGraphics().drawImage(img, 0, 0, Color.WHITE, null);

              ImageIO.write(contImage, suff, fos);

           } catch (Exception e) {

              e.printStackTrace();

           } finally {

              fos.flush();

              fos.close();

           }

       }

    }

}

 

 

3、  jpedal(http://www.jpedal.org/)

有些问题，比如一些字生成图片是一块黑的。不过还是附上例子和jar包jpedal_gpl.jar(把上传的图片后缀改一下jar)，可能用到的其他包请另外下载可能用到的其他包：

commons-cli-1.2.jar

 commons-io-1.4.jar

 FontBox-0.1.0-dev.jar

juh.jar

 jurt.jar

 PDFBox-0.7.3.jar

 poi-3.5-beta6-20090622.jar

 poi-contrib-3.5-beta6-20090622.jar

 poi-ooxml-3.5-beta6-20090622.jar

 poi-scratchpad-3.5-beta6-20090622.jar

 ridl.jar

 unoil.jar

 xmlbeans-2.3.0.jar

 xstream-1.3.1.jar

 

package com.test;

 

import java.awt.Color;

import java.awt.image.BufferedImage;

import java.io.File;

import java.io.FileOutputStream;

 

import javax.imageio.ImageIO;

 

import org.apache.log4j.Logger;

import org.jpedal.PdfDecoder;

 

 

public class TestPdfToGif1 {

 

    private static Logger log = Logger.getLogger(TestPdfToGif1.class);

   

    private String pdfName;

   

    public String getPdfName() {

       return pdfName;

    }

 

    public void setPdfName(String pdfName) {

       this.pdfName = pdfName;

    }

 

    public String getBasePath() {

       return basePath;

    }

 

    public void setBasePath(String basePath) {

       this.basePath = basePath;

    }

 

    private String fileNameNoExtMD5;

   

    private String basePath;

   

    /**

     * 测试

     * @param args

     */

    public static void main(String[] args) {

      

       try {

            

           TestPdfToGif1 pg = new TestPdfToGif1();

          

          

           pg.setPdfName("333");

           pg.setBasePath(System.getProperty("user.dir") + "/");

           pg.fileNameNoExtMD5 = pg.basePath + pg.getPdfName();

 

           pg.pdfToGIF();

          

       } catch (Exception e) {

           e.printStackTrace();

       }

      

       log.info("程序运行完了！");

 

    }  

   

 

    private void pdfToGIF() {

       StringBuffer errorpages = new StringBuffer();

       int pages = 0;

       String giffilename = "";

       PdfDecoder decodePdf = new PdfDecoder(true);

       BufferedImage imageToSave = null;

       BufferedImage contImage = null;

       FileOutputStream fos = null;

       File gifFile = null;

       int i = 0;

       try {

           decodePdf.openPdfFile(fileNameNoExtMD5 + ".pdf");

           //decodePdf

           pages = decodePdf.getPageCount();

           int h = decodePdf.getPDFHeight();

           int w = decodePdf.getPDFWidth();

           log.info("h = " + h);

           log.info("w = " + w);

           for (; i < pages; i++) {

              try {

                  giffilename = fileNameNoExtMD5 + "." + i + "_.gif";

                  gifFile = new File(giffilename);

                  if (!gifFile.exists()) {

                     int tmpw, tmph;

                     fos = new FileOutputStream(gifFile);

                     imageToSave = decodePdf.getPageAsImage(i + 1);

                     tmpw = imageToSave.getWidth();

                     tmph = imageToSave.getHeight();

                      log.info("h = " + tmph);

                     log.info("w = " + tmpw);

                     contImage = new BufferedImage(tmpw, tmph,

                            BufferedImage.TYPE_INT_ARGB);

                     contImage.getGraphics().drawImage(imageToSave, 0, 0,

                            Color.WHITE, null);

                     ImageIO.write(contImage, "gif", fos);

                     fos.flush();

                     fos.close();

                     //convertInfo.setTotalPage(i + 1);

                     // savestatus();// 不要每次都写磁盘

                  }

              } catch (Exception e) {

                  errorpages.append(i).append(",");

              }

           }

           if (errorpages.length() > 1) {

              errorpages.setLength(errorpages.length() - 1);

           }

           //convertInfo.setErrorpages(errorpages.toString());

           if (errorpages.length() > 0) {

           //  convertInfo.setErrorcode(3);

           } else {

              //convertInfo.setErrorcode(2);

           }

       } catch (Exception e) {

           log.error(e.getMessage());

           //convertInfo.setErrorcode(6);

       } finally {

           fos = null;

           decodePdf.closePdfFile();

           contImage = null;

           imageToSave = null;

           decodePdf = null;

           gifFile = null;

       }

    }

}

 附件： http://hi.csdn.net/attachment/201005/28/0_12750380531542.gif