java 用PDFBox 删除 PDF文件中的某一页

依赖：

<dependency>
      <groupId>org.apache.pdfbox</groupId>
      <artifactId>pdfbox-app</artifactId>
      <version>1.8.10</version>
 </dependency>

java 用PDFBox 删除 PDF文件中的某一页，前n页，后n页，效率低，不推荐使用

 

package com.everjiankang;

import java.io.File;

import org.apache.pdfbox.pdmodel.PDDocument;

/**运行效率很慢，因为每次删除一页就读取和保存一次文件,初始文件名格式：xxxx0.pdf*/
public class Test {
    static String  name_pre = "C:\\log\\jvm";    //文件名前缀
    static String  name_after = ".pdf";//文件名后缀
    public static void main(String[] args) {
        //1.刪除前n頁
//        cutPdfPreNPage(2);
        //2.刪除后n頁
        cutPdfAfterNPage(5);
        //3.刪除第n頁
        cutPdf(name_pre + 0 + name_after,name_pre + (0+1) + name_after,7);//删除第n页
    }
    
    /**
     * 删除前n页
     * @param n
     */
    public static void cutPdfPreNPage(int n) {
        for(int i = 0; i < n; i++)
            cutPdf(name_pre + i + name_after,name_pre + (i+1) + name_after,0);
    }
    
    /**
     * 删除后n页
     * @param n
     */
    public static void cutPdfAfterNPage(int n) {
        for(int i = 0; i < n; i++)
            cutPdf(name_pre + i + name_after,name_pre + (i+1) + name_after,1);
    }
    
    /**
     * 
     * @param pdfPath        旧路径
     * @param newPdfPath    新路径
     * @param flag            0：第一页；1：最后一页 ；else : 要删除的页码
     */
    public static void cutPdf(String pdfPath,String newPdfPath, int flag)
    {
        File file = new File(pdfPath);
        PDDocument document = new PDDocument();
        try{
            document = PDDocument.load(file);
        }catch(Exception e){
            e.printStackTrace();
        }
        int noOfPages = document.getNumberOfPages();
        System.out.println(noOfPages);
        if(flag == 0) 
            document.removePage(0);
        else if(flag == 1) {
            document.removePage(noOfPages-1);
        } else {
            document.removePage(flag-1);
        }
        try{
            document.save(newPdfPath);
            document.close();
        }catch(Exception e){
            e.printStackTrace();
        }
        System.out.println("已经转完了哦");
        
    }
}

 

 

 

抽取任意范围的PDF页作为新的PDF. 效率高

依赖

<dependency>
    <groupId>com.itextpdf</groupId>
    <artifactId>itextpdf</artifactId>
    <version>5.5.13</version>
</dependency>

 

代码

 /** 
     * 截取pdfFile的第from页至第end页，组成一个新的文件名 
     * @param pdfFile  需要分割的PDF
     * @param savepath  新PDF
     * @param from  起始页
     * @param end  结束页
     */  
    public static void splitPDFFile(String respdfFile,  
            String savepath, int from, int end) {  
        Document document = null;  
        PdfCopy copy = null;          
        try {  
            PdfReader reader = new PdfReader(respdfFile);            
            int n = reader.getNumberOfPages();            
            if(end==0){  
                end = n;  
            }  
            ArrayList<String> savepaths = new ArrayList<String>();  
            String staticpath = respdfFile.substring(0, respdfFile.lastIndexOf("\\")+1);  
            //String savepath = staticpath+ newFile;  
            savepaths.add(savepath);  
            document = new Document(reader.getPageSize(1));  
            copy = new PdfCopy(document, new FileOutputStream(savepaths.get(0)));  
            document.open();  
            for(int j=from; j<=end; j++) {  
                document.newPage();   
                PdfImportedPage page = copy.getImportedPage(reader, j);  
                copy.addPage(page);  
            }  
            document.close();  

        } catch (IOException e) {  
            e.printStackTrace();  
        } catch(DocumentException e) {  
            e.printStackTrace();  
        }  
    }