Java使用PDFBox操作PDF文件获取页码、文章内容、缩略图

一、依赖

<!--使用的是pdfbox计数总页数与缩略图-->
<!-- https://mvnrepository.com/artifact/com.sleepycat/je -->
<dependency><groupId>com.sleepycat</groupId><artifactId>je</artifactId><version>5.0.73</version>
</dependency><!--pdf-->
<!-- https://mvnrepository.com/artifact/org.apache.pdfbox/pdfbox -->
<dependency><groupId>org.apache.pdfbox</groupId><artifactId>pdfbox</artifactId><version>2.0.8</version>
</dependency>

二、实现代码

import lombok.extern.slf4j.Slf4j;
import org.apache.pdfbox.pdfparser.PDFParser;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.rendering.ImageType;
import org.apache.pdfbox.rendering.PDFRenderer;
import org.apache.pdfbox.text.PDFTextStripper;import javax.imageio.IIOImage;
import javax.imageio.ImageIO;
import javax.imageio.ImageWriter;
import javax.imageio.stream.ImageOutputStream;
import java.awt.image.BufferedImage;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.util.Iterator;
@Slf4j
public class PdfUtil {/*** 通过PDFbox获取文章总页数** @param filePath:文件路径* @return* @throws IOException*/public static int getNumberOfPages(String filePath) throws IOException, InterruptedException {File file = new File(filePath);PDDocument pdDocument = PDDocument.load(new File(filePath));int pages = pdDocument.getNumberOfPages();pdDocument.close();return pages;}}/*** 通过PDFbox获取文章内容** @param filePath* @return*/public static String getContent(String filePath) throws IOException {PDFParser pdfParser = new PDFParser(new org.apache.pdfbox.io.RandomAccessFile(new File(filePath), "rw"));pdfParser.parse();PDDocument pdDocument = pdfParser.getPDDocument();String text = new PDFTextStripper().getText(pdDocument);pdDocument.close();return text;}/*** 通过PDFbox生成文件的缩略图** @param filePath：文件路径* @param outPath：输出图片路径* @throws IOException*/public static void getThumbnails(String filePath, String outPath) throws IOException {// 利用PdfBox生成图像PDDocument pdDocument = PDDocument.load(new File(filePath));PDFRenderer renderer = new PDFRenderer(pdDocument);// 构造图片BufferedImage img_temp = renderer.renderImageWithDPI(0, 30, ImageType.RGB);// 设置图片格式Iterator<ImageWriter> it = ImageIO.getImageWritersBySuffix("png");// 将文件写出ImageWriter writer = (ImageWriter) it.next();ImageOutputStream imageout = ImageIO.createImageOutputStream(new FileOutputStream(outPath));writer.setOutput(imageout);writer.write(new IIOImage(img_temp, null, null));img_temp.flush();imageout.flush();imageout.close();//Warning: You did not close a PDF DocumentpdDocument.close();}
}

三、测试类--Main

import java.io.IOException;
/*** @author Mr.lu* @Title: Main* @ProjectName DocCloud* @Description: TODO* @date 2018/11/6:22:17*/
public class Main {public static void main(String[] args) throws IOException, InterruptedException {int numberOfPages = getNumberOfPages("D:\\Desktop\\DocCloud\\testDir\\hadoopClientCode.pdf");System.out.println(numberOfPages);String content = getContent("");System.out.println(content);getThumbnails("D:\\Desktop\\DocCloud\\testDir\\hadoopClientCoed.pdf","D:\\Desktop\\DocCloud\\testDir\\hadoopClientCoed.pdf.png");}
}

1>首先测试生成PDF文件的页码，在控制台可以看到

2>测试获取PDF文件的内容，在控制台可以看到--你自己PDF文件中的内容

3>测试生成PDF缩略图

缩略图的大小，可以在代码中修改