一、依賴

<!--使用的是pdfbox計數總頁數與縮圖-->
<!-- 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、實現程式碼

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 {


    /**
     * 通過PDFbox獲取文章總頁數
     *
     * @param filePath:檔案路徑
     * @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;
        }
    }

    /**
     * 通過PDFbox獲取文章內容
     *
     * @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;
    }

    /**
     * 通過PDFbox生成檔案的縮圖
     *
     * @param filePath：檔案路徑
     * @param outPath：輸出圖片路徑
     * @throws IOException
     */
    public static void getThumbnails(String filePath, String outPath) throws IOException {
        // 利用PdfBox生成影象
        PDDocument pdDocument = PDDocument.load(new File(filePath));
        PDFRenderer renderer = new PDFRenderer(pdDocument);

        // 構造圖片
        BufferedImage img_temp = renderer.renderImageWithDPI(0, 30, ImageType.RGB);
        // 設定圖片格式
        Iterator<ImageWriter> it = ImageIO.getImageWritersBySuffix("png");
        // 將檔案寫出
        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 Document
        pdDocument.close();
    }
}
 

三、測試類--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>首先測試生成PDF檔案的頁碼，在控制檯可以看到

2>測試獲取PDF檔案的內容，在控制檯可以看到--你自己PDF檔案中的內容

3>測試生成PDF縮圖

縮圖的大小，可以在程式碼中修改