将PDF文件转换为图像

您可以轻松地将04-Request-
Headers.pdf
文件页面转换为图像格式。

使用PDF Box将所有pdf页面转换为Java中的图像格式。

Apache PDFBox 1.8。*版本的解决方案：

Jar需要pdfbox-1.8.3.jar

或Maven依赖

<dependency>    <groupId>org.apache.pdfbox</groupId>    <artifactId>pdfbox</artifactId>    <version>1.8.3</version></dependency>

解决方法如下：

package com.pdf.pdfbox.examples;import java.awt.image.BufferedImage;import java.io.File;import java.util.List;import javax.imageio.ImageIO;import org.apache.pdfbox.pdmodel.PDdocument;import org.apache.pdfbox.pdmodel.PDPage;@SuppressWarnings("unchecked")public class ConvertPDFPagesToImages {    public static void main(String[] args) {        try {        String sourceDir = "C:/documents/04-Request-Headers.pdf"; // Pdf files are read from this folder        String destinationDir = "C:/documents/Converted_PdfFiles_to_Image/"; // converted images from pdf document are saved here        File sourceFile = new File(sourceDir);        File destinationFile = new File(destinationDir);        if (!destinationFile.exists()) { destinationFile.mkdir(); System.out.println("Folder Created -> "+ destinationFile.getAbsolutePath());        }        if (sourceFile.exists()) { System.out.println("Images copied to Folder: "+ destinationFile.getName());   PDdocument document = PDdocument.load(sourceDir); List<PDPage> list = document.getdocumentCatalog().getAllPages(); System.out.println("Total files to be converted -> "+ list.size()); String fileName = sourceFile.getName().replace(".pdf", "");   int pageNumber = 1; for (PDPage page : list) {     BufferedImage image = page.convertToImage();     File outputfile = new File(destinationDir + fileName +"_"+ pageNumber +".png");     System.out.println("Image Created -> "+ outputfile.getName());     ImageIO.write(image, "png", outputfile);     pageNumber++; } document.close(); System.out.println("Converted Images are saved at -> "+ destinationFile.getAbsolutePath());        } else { System.err.println(sourceFile.getName() +" File not exists");        }    } catch (Exception e) {        e.printStackTrace();    }}}

图像可能转换为

jpg, jpeg, png, bmp, gif

注意： 我提到了主要使用的图像格式。

ImageIO.write(image , "jpg", new File( destinationDir +fileName+"_"+pageNumber+".jpg" ));ImageIO.write(image , "jpeg", new File( destinationDir +fileName+"_"+pageNumber+".jpeg" ));ImageIO.write(image , "png", new File( destinationDir +fileName+"_"+pageNumber+".png" ));ImageIO.write(image , "bmp", new File( destinationDir +fileName+"_"+pageNumber+".bmp" ));ImageIO.write(image , "gif", new File( destinationDir +fileName+"_"+pageNumber+".gif" ));

控制台输出：

Images copied to Folder: Converted_PdfFiles_to_ImageTotal files to be converted -> 13Aug 06, 2014 1:35:49 PM org.apache.pdfbox.util.PDFStreamEngine processOperatorINFO: unsupported/disabled operation: iImage Created -> 04-Request-Headers_1.pngAug 06, 2014 1:35:50 PM org.apache.pdfbox.util.PDFStreamEngine processOperatorINFO: unsupported/disabled operation: iImage Created -> 04-Request-Headers_2.pngAug 06, 2014 1:35:51 PM org.apache.pdfbox.util.PDFStreamEngine processOperatorINFO: unsupported/disabled operation: iImage Created -> 04-Request-Headers_3.pngAug 06, 2014 1:35:51 PM org.apache.pdfbox.util.PDFStreamEngine processOperatorINFO: unsupported/disabled operation: iImage Created -> 04-Request-Headers_4.pngAug 06, 2014 1:35:52 PM org.apache.pdfbox.util.PDFStreamEngine processOperatorINFO: unsupported/disabled operation: iImage Created -> 04-Request-Headers_5.pngAug 06, 2014 1:35:52 PM org.apache.pdfbox.util.PDFStreamEngine processOperatorINFO: unsupported/disabled operation: iImage Created -> 04-Request-Headers_6.pngAug 06, 2014 1:35:53 PM org.apache.pdfbox.util.PDFStreamEngine processOperatorINFO: unsupported/disabled operation: iImage Created -> 04-Request-Headers_7.pngAug 06, 2014 1:35:53 PM org.apache.pdfbox.util.PDFStreamEngine processOperatorINFO: unsupported/disabled operation: iImage Created -> 04-Request-Headers_8.pngAug 06, 2014 1:35:54 PM org.apache.pdfbox.util.PDFStreamEngine processOperatorINFO: unsupported/disabled operation: iImage Created -> 04-Request-Headers_9.pngAug 06, 2014 1:35:54 PM org.apache.pdfbox.util.PDFStreamEngine processOperatorINFO: unsupported/disabled operation: iImage Created -> 04-Request-Headers_10.pngAug 06, 2014 1:35:54 PM org.apache.pdfbox.util.PDFStreamEngine processOperatorINFO: unsupported/disabled operation: iImage Created -> 04-Request-Headers_11.pngAug 06, 2014 1:35:55 PM org.apache.pdfbox.util.PDFStreamEngine processOperatorINFO: unsupported/disabled operation: iImage Created -> 04-Request-Headers_12.pngAug 06, 2014 1:35:55 PM org.apache.pdfbox.util.PDFStreamEngine processOperatorINFO: unsupported/disabled operation: iImage Created -> 04-Request-Headers_13.pngConverted Images are saved at -> C:documentsConverted_PdfFiles_to_Image

Apache PDFBox 2.0。*版本的解决方案：

所需的Jars
pdfbox-2.0.16.jar，fontbox-2.0.16.jar，commons-
logging-1.2.jar

或来自pom.xml依赖项

<!-- https://mvnrepository.com/artifact/org.apache.pdfbox/pdfbox --><dependency>    <groupId>org.apache.pdfbox</groupId>    <artifactId>pdfbox</artifactId>    <version>2.0.16</version></dependency><!-- https://mvnrepository.com/artifact/org.apache.pdfbox/fontbox --><dependency>    <groupId>org.apache.pdfbox</groupId>    <artifactId>fontbox</artifactId>    <version>2.0.16</version></dependency><!-- https://mvnrepository.com/artifact/commons-logging/commons-logging --><dependency>    <groupId>commons-logging</groupId>    <artifactId>commons-logging</artifactId>    <version>1.2</version></dependency>

2.0.16版本的解决方案：

package com.pdf.pdfbox.examples;import java.awt.image.BufferedImage;import java.io.File;import javax.imageio.ImageIO;import org.apache.pdfbox.pdmodel.PDdocument;import org.apache.pdfbox.rendering.ImageType;import org.apache.pdfbox.rendering.PDFRenderer;public class ConvertPDFPagesToImages {    public static void main(String[] args) {        try { String sourceDir = "C:\Users\venkataudaykiranp\Downloads-Request-Headers.pdf"; // Pdf files are read from this folder String destinationDir = "C:\Users\venkataudaykiranp\Downloads\Converted_PdfFiles_to_Image/"; // converted images from pdf document are saved here File sourceFile = new File(sourceDir); File destinationFile = new File(destinationDir); if (!destinationFile.exists()) {     destinationFile.mkdir();     System.out.println("Folder Created -> "+ destinationFile.getAbsolutePath()); } if (sourceFile.exists()) {     System.out.println("Images copied to Folder Location: "+ destinationFile.getAbsolutePath());       PDdocument document = PDdocument.load(sourceFile);     PDFRenderer pdfRenderer = new PDFRenderer(document);     int numberOfPages = document.getNumberOfPages();     System.out.println("Total files to be converting -> "+ numberOfPages);     String fileName = sourceFile.getName().replace(".pdf", "");       String fileExtension= "png";          int dpi = 300;// use less dpi for to save more space in harddisk. For professional usage you can use more than 300dpi     for (int i = 0; i < numberOfPages; ++i) {         File outPutFile = new File(destinationDir + fileName +"_"+ (i+1) +"."+ fileExtension);         BufferedImage bImage = pdfRenderer.renderImageWithDPI(i, dpi, ImageType.RGB);         ImageIO.write(bImage, fileExtension, outPutFile);     }     document.close();     System.out.println("Converted Images are saved at -> "+ destinationFile.getAbsolutePath()); } else {     System.err.println(sourceFile.getName() +" File not exists"); }        } catch (Exception e) { e.printStackTrace();        }    }}