java 实现 PDF 转 TIF【黑白版】

一时失言乱红尘 2023-03-04 06:34 105阅读 0赞

## 先看效果 ##

原pdf文件11页 473kb  
转换后变成11个tif文件 共503kb  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MDYyMzczNg_size_16_color_FFFFFF_t_70]

## 实现代码 ##

**maven依赖**

<dependency>
       <groupId>org.apache.pdfbox</groupId>
        <artifactId>pdfbox</artifactId>
        <version>1.8.9</version>
        <scope>compile</scope>
    </dependency>
    <dependency>
        <groupId>javax.media</groupId>
        <artifactId>jai_imageio</artifactId>
        <version>1.1</version>
    </dependency>

**实现工具类**

import java.awt.image.BufferedImage;
    import java.io.*;
    import java.util.ArrayList;
    import java.util.List;
    import javax.imageio.*;
    import javax.imageio.metadata.IIOMetadata;
    import javax.imageio.metadata.IIOMetadataNode;
    import javax.imageio.stream.ImageOutputStream;
    import com.sun.media.imageioimpl.plugins.tiff.TIFFImageWriterSpi;
    import org.apache.pdfbox.pdmodel.PDDocument;
    import org.apache.pdfbox.pdmodel.PDPage;
    
    /** * Pdf2Tif * @Author chenqi * @Date 15:54 2020/8/1 **/
    public class Pdf2TiffUtil { 
    
        /** 打印精度设置 图片的像素 */
        public static final int DPI = 160;
    
        public static List<byte[]> pdf2tifList(InputStream inputStream) { 
            List<byte[]> b = new ArrayList<>();
            try{ 
                PDDocument pdf = PDDocument.load(inputStream);
                BufferedImage[] images = new BufferedImage[pdf.getNumberOfPages()];
                ByteArrayOutputStream out = new ByteArrayOutputStream(OmsConstants.Number.ONE_MB);
                for (int i = 0; i < images.length; i++) { 
                    PDPage page = (PDPage) pdf.getDocumentCatalog().getAllPages().get(i);
                    BufferedImage image;
                    image = page.convertToImage(BufferedImage.TYPE_BYTE_BINARY, DPI);
                    images[i] = image;
                    TIFFImageWriterSpi tiffWriter = new TIFFImageWriterSpi();
                    ImageWriter writer = tiffWriter.createWriterInstance();
                    ImageWriteParam param = writer.getDefaultWriteParam();
                    ImageTypeSpecifier typeSpecifier = ImageTypeSpecifier.createFromBufferedImageType(BufferedImage.TYPE_INT_ARGB);
                    param.setCompressionMode(ImageWriteParam.MODE_EXPLICIT);
                    param.setCompressionType("CCITT T.6");
                    param.setCompressionQuality(1);
                    IIOMetadata metadata = writer.getDefaultImageMetadata(typeSpecifier, param);
                    IIOMetadataNode hps = new IIOMetadataNode("HorizontalPixelSize");
                    hps.setAttribute("value", Double.toString(1d / 300d * 25.4d));
                    IIOMetadataNode vps = new IIOMetadataNode("VerticalPixelSize");
                    vps.setAttribute("value", Double.toString(1d / 300d * 25.4d));
                    IIOMetadataNode dim = new IIOMetadataNode("Dimension");
                    dim.appendChild(hps);
                    dim.appendChild(vps);
                    IIOMetadataNode root = new IIOMetadataNode("javax_imageio_1.0");
                    root.appendChild(dim);
                    metadata.mergeTree("javax_imageio_1.0", root);
                    ImageOutputStream ios = ImageIO.createImageOutputStream(out);
                    writer.setOutput(ios);
                    writer.write(metadata, new IIOImage(image, null, metadata), param);
                    out.reset();
                    ios.close();
                    b.add(out.toByteArray());
                }
                out.close();
                pdf.close();
                return b;
            } catch (IOException e) { 
                e.printStackTrace();
                return new ArrayList<>();
            }
        }
    
        public static void main(String[] args) { 
            File file = new File("D:/PDF/aa.pdf");
            try { 
                List<byte[]> list = pdf2tifList(new FileInputStream(file));
                int i = 1;
                for(byte[] b : list){ 
                    FileOutputStream ou = new FileOutputStream(new File("D:/PDF/" + i + ".tif"));
                    ou.write(b);
                    ou.flush();
                    i++;
                }
            }catch (Exception e){ 
                e.printStackTrace();
            }
        }
    
    
    
    }

参考博客：https://www.cnblogs.com/JohnsonLiu/p/11759267.html

实现不容易，也是参考了很多资料，如有帮助，就留言点个赞吧！  
另外调试过程中以下这句代码执行时间有点长，如果有知道怎么优化的兄弟，欢迎留言分享讨论。

image = page.convertToImage(BufferedImage.TYPE_BYTE_BINARY, DPI);

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MDYyMzczNg_size_16_color_FFFFFF_t_70]: /images/20230208/5d4e1517fc1645fea32717df64cbe4f4.png