方法:1、文件轉換成pdf(采用openoffice或者jacob)
2、抓取pdf首頁圖
第一步:采用jacob:
a、下載jacob 注意區分32位,64位,否則不能用
將dll文件放在java bin目錄下即可
jar包引入項目
b、轉換pdf
package cn.bnsr.edu_yun.util; import java.io.File; import java.io.IOException; import com.jacob.activeX.ActiveXComponent; import com.jacob.com.ComThread; import com.jacob.com.Dispatch; import com.jacob.com.Variant; public class TestUtil { static final int wdFormatPDF = 17;// PDF 格式 public void wordToPDF(String sfileName,String toFileName){ System.out.println("啟動Word..."); long start = System.currentTimeMillis(); ActiveXComponent app = null; Dispatch doc = null; try { app = new ActiveXComponent("Word.Application"); app.setProperty("Visible", new Variant(false)); Dispatch docs = app.getProperty("Documents").toDispatch(); // doc = Dispatch.call(docs, "Open" , sourceFile).toDispatch(); doc = Dispatch.invoke(docs,"Open",Dispatch.Method,new Object[] { sfileName, new Variant(false),new Variant(true) }, new int[1]).toDispatch(); System.out.println("打開文檔..." + sfileName); System.out.println("轉換文檔到PDF..." + toFileName); File tofile = new File(toFileName); if (tofile.exists()) { tofile.delete(); } // Dispatch.call(doc, "SaveAs", destFile, 17); Dispatch.invoke(doc, "SaveAs", Dispatch.Method, new Object[] { toFileName, new Variant(17) }, new int[1]); long end = System.currentTimeMillis(); System.out.println("轉換完成..用時:" + (end - start) + "ms."); } catch (Exception e) { e.printStackTrace(); System.out.println("========Error:文檔轉換失敗:" + e.getMessage()); } finally { Dispatch.call(doc,"Close",false); System.out.println("關閉文檔"); if (app != null) app.invoke("Quit", new Variant[] {}); } //如果沒有這句話,winword.exe進程將不會關閉 ComThread.Release(); } public static void main(String[] args) { TestUtil d = new TestUtil(); d.wordToPDF("D:\\work\\1111.docx", "d:\\work\\1111.pdf"); } }
第二步:抓取首頁圖:
package cn.bnsr.edu_yun.util; 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.lang.reflect.Method; import java.nio.ByteBuffer; import java.nio.channels.FileChannel; import java.security.AccessController; import java.security.PrivilegedAction; import com.sun.image.codec.jpeg.JPEGCodec; import com.sun.image.codec.jpeg.JPEGImageEncoder; import com.sun.pdfview.PDFFile; import com.sun.pdfview.PDFPage; public class PdfImageUtil { // 將PDF格式的文件轉換為JPG格式的文件 public static void pdfToJPG(String inputFile)throws IOException { // load a pdf from a byte buffer File file = new File(inputFile); RandomAccessFile raf = new RandomAccessFile(file, "r"); FileChannel channel = raf.getChannel(); //這句代碼通道建立了map映射,如果要刪除file那么得接觸映射 ByteBuffer buf = channel.map(FileChannel.MapMode.READ_ONLY, 0, channel.size()); PDFFile pdffile = new PDFFile(buf); int totalpage =pdffile.getNumPages(); for (int i = 1; i <= totalpage; i++) { if (i == 1) { // draw the first page to an image // 以圖片的形式來描繪首頁 PDFPage page = pdffile.getPage(i); Rectangle rect = new Rectangle(0, 0, (int) page.getBBox().getWidth(), (int) page.getBBox().getHeight()); // generate the image // 生成圖片 Image img = page.getImage(rect.width, rect.height, // width & // height rect, // clip rect null, // null for the ImageObserver true, // fill background with white true // block until drawing is done ); BufferedImage tag = new BufferedImage(rect.width, rect.height, BufferedImage.TYPE_INT_RGB); tag.getGraphics().drawImage(img.getScaledInstance(rect.width, rect.height, Image.SCALE_SMOOTH), 0, 0, rect.width, rect.height,null); FileOutputStream out = new FileOutputStream( "D:\\work\\s111"+ ".jpg"); // 輸出到文件流 JPEGImageEncoder encoder = JPEGCodec.createJPEGEncoder(out); encoder.encode(tag); // JPEG編碼 // 關閉輸出流 out.close(); break; } } buf.clear(); channel.close(); raf.close(); unmap(buf); file.delete(); } //解除map映射 public static <T> void unmap(final Object buffer) { AccessController.doPrivileged(new PrivilegedAction<T>(){ @Override public T run() { try { Method getCleanerMethod = buffer.getClass().getMethod("cleaner", new Class[0]); getCleanerMethod.setAccessible(true); sun.misc.Cleaner cleaner = (sun.misc.Cleaner) getCleanerMethod.invoke(buffer, new Object[0]); cleaner.clean(); } catch(Exception e) { e.printStackTrace(); } return null; } }); } }
第三步、搞定,加入自己的業務邏輯,有問題歡迎提問。