文档展示：IcePDF 将PDF转换为图片

上接 文档展示：PDFRender 将PDF转换为图片
[url]http://zhuyufufu.iteye.com/admin/blogs/2012236[/url]

PDFBox 与 PDFRender在转换时有清晰度与效率的问题，

PDFBox转换效果稍好，PDFRender更快，但是多线程操作不能大幅提高转换效率。

搜索这下找到IcePDF 他是开源的，但是字体支持要收费。

拿IcePDF自带的例子展示，上代码：

package com.zas.ice.test;
/*
 * Copyright 2006-2013 ICEsoft Technologies Inc.
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the
 * License. You may obtain a copy of the License at
 *
 *        http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing,
 * software distributed under the License is distributed on an "AS
 * IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either
 * express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */


import org.icepdf.core.exceptions.PDFException;
import org.icepdf.core.exceptions.PDFSecurityException;
import org.icepdf.core.pobjects.Document;
import org.icepdf.core.pobjects.PDimension;
import org.icepdf.core.pobjects.Page;
import org.icepdf.core.util.GraphicsRenderingHints;
import org.icepdf.ri.util.FontPropertiesManager;
import org.icepdf.ri.util.PropertiesManager;

import javax.imageio.ImageIO;

import java.awt.*;
import java.awt.image.BufferedImage;
import java.io.File;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.util.ArrayList;
import java.util.ResourceBundle;
import java.util.concurrent.Callable;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.ExecutorService;
import java.util.concurrent.Executors;

/**
 * The <code>PageCapture</code> class is an example of how to save page
 * captures to disk.  A file specified at the command line is opened and every
 * page in the document is captured as an image and saved to disk as a
 * PNG graphic file.
 *
 * @since 5.0
 */
public class PageCapture {
	static String outputFilePath = "D:\\pdf\\Linux命令行技术大全222222\\";

    public static void main(String[] args) {

        // Get a file from the command line to open
    	String filePath = "D:\\pdf\\面向对象软件构造(第二版)中英对照版.pdf";

        // read/store the font cache.
        ResourceBundle messageBundle = ResourceBundle.getBundle(
                PropertiesManager.DEFAULT_MESSAGE_BUNDLE);
        PropertiesManager properties = new PropertiesManager(System.getProperties(),
                ResourceBundle.getBundle(PropertiesManager.DEFAULT_MESSAGE_BUNDLE));
        new FontPropertiesManager(properties, System.getProperties(), messageBundle);

        // start the capture
        PageCapture pageCapture = new PageCapture();
        pageCapture.capturePages(filePath);

    }

    public void capturePages(String filePath) {
    	long beginTime = System.nanoTime();
        // open the url
        Document document = new Document();

        // setup two threads to handle image extraction.
        ExecutorService executorService = Executors.newFixedThreadPool(100);
        try {
            document.setFile(filePath);
            // create a list of callables.
            int pages = document.getNumberOfPages();
            java.util.List<Callable<Void>> callables = new ArrayList<Callable<Void>>(pages);
            for (int i = 0; i <= pages; i++) {
                callables.add(new CapturePage(document, i));
            }
            executorService.invokeAll(callables);
            executorService.submit(new DocumentCloser(document)).get();

        } catch (InterruptedException e) {
            System.out.println("Error parsing PDF document " + e);
        } catch (ExecutionException e) {
            System.out.println("Error parsing PDF document " + e);
        } catch (PDFException ex) {
            System.out.println("Error parsing PDF document " + ex);
        } catch (PDFSecurityException ex) {
            System.out.println("Error encryption not supported " + ex);
        } catch (FileNotFoundException ex) {
            System.out.println("Error file not found " + ex);
        } catch (IOException ex) {
            System.out.println("Error handling PDF document " + ex);
        }
        executorService.shutdown();
        long endTime = System.nanoTime();
		System.out.println("耗时: " + (endTime - beginTime) / 1000000000 + " 秒" );
    }

    /**
     * Captures images found in a page  parse to file.
     */
    public class CapturePage implements Callable<Void> {
        private Document document;
        private int pageNumber;
        private float scale = 1f;
        private float rotation = 0f;

        private CapturePage(Document document, int pageNumber) {
            this.document = document;
            this.pageNumber = pageNumber;
        }

        public Void call() {
            Page page = document.getPageTree().getPage(pageNumber);
            page.init();
            PDimension sz = page.getSize(Page.BOUNDARY_CROPBOX, rotation, scale);

            int pageWidth = (int) sz.getWidth();
            int pageHeight = (int) sz.getHeight();

            BufferedImage image = new BufferedImage(pageWidth,
                    pageHeight,
                    BufferedImage.TYPE_INT_RGB);
            Graphics g = image.createGraphics();

            page.paint(g, GraphicsRenderingHints.PRINT,
                    Page.BOUNDARY_CROPBOX, rotation, scale);
            g.dispose();
            // capture the page image to file
            try {
                System.out.println("Capturing page " + pageNumber);
                File file = new File(outputFilePath + "imageCapture_" + pageNumber + ".png");
                ImageIO.write(image, "png", file);

            } catch (Throwable e) {
                e.printStackTrace();
            }
            image.flush();
            return null;
        }
    }

    /**
     * Disposes the document.
     */
    public class DocumentCloser implements Callable<Void> {
        private Document document;

        private DocumentCloser(Document document) {
            this.document = document;
        }

        public Void call() {
            if (document != null) {
                document.dispose();
                System.out.println("Document disposed");
            }
            return null;
        }
    }
}

代码用到了JDK的线程池，也用到了任务callable，算是涨涨见识了

在转换的效果上比PDFRender略好，与PDFBox差不远；在转换的效率上，比PDFBox好很多，比PDFRender略差。

资料包是从一位Iteye用户那里下的，但是记不住他的链接了。

IcePdf官网 [url]http://www.icesoft.org/java/home.jsf[/url]