Java 使用PDFBox对pdf文件进行相关操作

目录

创建空的PDF文件并报错到本地

加载已有的PDF文档 

设置PDF文档属性（包括作者、创建时间、修改时间等）

 查看PDF文档属性

往PDF页面中添加单行文字

往PDF页面中添加多行文字

读取PDF文档里的文字

往PDF文档里插入图片

加密PDF文档，即打开时需要输入密码

往PDF文档里添加javaScript脚本

将一个PDF文档拆成多个

将多个PDF文档合并成一个

提取PDF图像

添加矩形

---

创建空的PDF文件并报错到本地

package document;
 
import java.io.IOException;

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;

public class Adding_Pages {

   public static void main(String args[]) throws IOException {
       
      //创建 PDF 文档对象
      PDDocument document = new PDDocument();

      for (int i=0; i<10; i++) {
         //创建空白页
         PDPage blankPage = new PDPage();

         //将空白页添加到文档
         document.addPage( blankPage );
      } 
     
      //保存文档
      document.save("C:/PdfBox_Examples/my_doc.pdf");
      System.out.println("PDF created");
      
      //关闭文档
      document.close();

   }  
} 

加载已有的PDF文档 

import java.io.File;
import java.io.IOException;
 
import org.apache.pdfbox.pdmodel.PDDocument; 
import org.apache.pdfbox.pdmodel.PDPage;
public class LoadingExistingDocument {

   public static void main(String args[]) throws IOException {
   
      //加载现有文档
      File file = new File("C:/PdfBox_Examples/sample.pdf"); 
      PDDocument document = PDDocument.load(file); 
        
      System.out.println("PDF loaded"); 
        
      //在文档中添加空白页
      document.addPage(new PDPage());  

      //保存文档
      document.save("C:/PdfBox_Examples/sample.pdf");

      //关闭文档
      document.close(); 
        
   }  
}

设置PDF文档属性（包括作者、创建时间、修改时间等）

import java.io.IOException; 
import java.util.Calendar; 
import java.util.GregorianCalendar;
  
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDDocumentInformation;
import org.apache.pdfbox.pdmodel.PDPage;

public class AddingDocumentAttributes {
   public static void main(String args[]) throws IOException {

      //创建 PDF 文档对象
      PDDocument document = new PDDocument();

      //创建空白页
      PDPage blankPage = new PDPage();
       
      //将空白页添加到文档
      document.addPage( blankPage );

      //创建 PDDocumentInformation 对象
      PDDocumentInformation pdd = document.getDocumentInformation();

      //设置文档的作者
      pdd.setAuthor("Learnfk");
       
      //设置文档的标题
      pdd.setTitle("Sample document"); 
       
      //设置文档的创建者
      pdd.setCreator("PDF Examples"); 
       
      //设置文档的主题
      pdd.setSubject("Example document"); 
       
      //设置文档的创建日期
      Calendar date = new GregorianCalendar();
      date.set(2015, 11, 5); 
      pdd.setCreationDate(date);
      //设置文档的修改日期
      date.set(2016, 6, 5); 
      pdd.setModificationDate(date); 
       
      //为文档设置关键字
      pdd.setKeywords("sample, first example, my pdf"); 
 
      //保存文档
      document.save("C:/PdfBox_Examples/doc_attributes.pdf");

      System.out.println("Properties added successfully ");
       
      //关闭文档
      document.close();

   }
}

 查看PDF文档属性

import java.io.File; 
import java.io.IOException;

import org.apache.pdfbox.pdmodel.PDDocument; 
import org.apache.pdfbox.pdmodel.PDDocumentInformation;

public class RetrivingDocumentAttributes {
   public static void main(String args[]) throws IOException {
      
      //加载现有文档
      File file = new File("C:/PdfBox_Examples/doc_attributes.pdf")
      PDDocument document = PDDocument.load(file);
      //获取 PDDocumentInformation 对象
      PDDocumentInformation pdd = document.getDocumentInformation();

      //检索 PDF 文档的信息
      System.out.println("Author of the document is :"+ pdd.getAuthor());
      System.out.println("Title of the document is :"+ pdd.getTitle());
      System.out.println("Subject of the document is :"+ pdd.getSubject());

      System.out.println("Creator of the document is :"+ pdd.getCreator());
      System.out.println("Creation date of the document is :"+ pdd.getCreationDate());
      System.out.println("Modification date of the document is :"+ 
         pdd.getModificationDate()); 
      System.out.println("Keywords of the document are :"+ pdd.getKeywords()); 
       
      //关闭文档
      document.close();        
   }  
}  

往PDF页面中添加单行文字

import java.io.File; 
import java.io.IOException;
  
import org.apache.pdfbox.pdmodel.PDDocument; 
import org.apache.pdfbox.pdmodel.PDPage; 
import org.apache.pdfbox.pdmodel.PDPageContentStream; 
import org.apache.pdfbox.pdmodel.font.PDType1Font;
  
public class AddingContent {
   public static void main (String args[]) throws IOException {

      //加载现有文档
      File file = new File("C:/PdfBox_Examples/my_doc.pdf");
      PDDocument document = PDDocument.load(file);
       
      //检索文档的页面
      PDPage page = document.getPage(1);
      PDPageContentStream contentStream = new PDPageContentStream(document, page);
      
      //开始内容流
      contentStream.beginText(); 
       
      //将字体设置为内容流
      contentStream.setFont(PDType1Font.TIMES_ROMAN, 12);

      //设置线的位置
      contentStream.newLineAtOffset(25, 500);

      String text = "This is the sample document and we are adding content to it.";

      //以字符串形式添加文本 
      contentStream.showText(text);      

      //结束内容流
      contentStream.endText();

      System.out.println("Content added");

      //关闭内容流
      contentStream.close();

      //保存文档
      document.save(new File("C:/PdfBox_Examples/new.pdf"));

      //关闭文档
      document.close();
   }
}

往PDF页面中添加多行文字

import java.io.File;
import java.io.IOException;

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.PDPageContentStream;
import org.apache.pdfbox.pdmodel.font.PDType1Font;

public class AddMultipleLines {
   public static void main(String args[]) throws IOException {

      //加载现有文档
      File file = new File("C:/PdfBox_Examples/my_pdf.pdf");
      PDDocument doc = document.load(file);
       
      //创建PDF文档
      PDPage page = doc.getPage(1);  
       
      PDPageContentStream contentStream = new PDPageContentStream(doc, page); 
       
      //开始内容流
      contentStream.beginText(); 
       
      //将字体设置为内容流
      contentStream.setFont( PDType1Font.TIMES_ROMAN, 16 );
       
      //设置Lead
      contentStream.setLeading(14.5f);

      //设置Line的位置
      contentStream.newLineAtOffset(25, 725);

      String text1 = "This is an example of adding text to a page in the pdf document.
         we can add as many lines";
      String text2 = "as we want like this using the ShowText()  method of the
         ContentStream class";

      //以字符串的形式添加文本
      contentStream. ShowText(text1);
      contentStream.newLine();
      contentStream. ShowText(text2);
      //结束内容流
      contentStream.endText();

      System.out.println("Content added");

      //关闭内容流
      contentStream.close();

      //保存文档
      doc.save(new File("C:/PdfBox_Examples/new.pdf"));
            
      //关闭文档
      doc.close();
   }
}

读取PDF文档里的文字

import java.io.File;
import java.io.IOException;

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;
public class ReadingText {

   public static void main(String args[]) throws IOException {

      //加载现有文档
      File file = new File("C:/PdfBox_Examples/new.pdf");
      PDDocument document = PDDocument.load(file);

      //实例化PDFTextStropper类
      PDFTextStripper pdfStripper = new PDFTextStripper();

      //从PDF文档中检索文本
      String text = pdfStripper.getText(document);
      System.out.println(text);

      //关闭文件
      document.close();

   }
}

往PDF文档里插入图片

import java.io.File;
  
import org.apache.pdfbox.pdmodel.PDDocument; 
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.PDPageContentStream;
import org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject;

public class InsertingImage {

   public static void main(String args[]) throws Exception {
      //加载现有文档
      File file = new File("C:/PdfBox_Examples/sample.pdf");
      PDDocument doc = PDDocument.load(file);
        
      //检索页面
      PDPage page = doc.getPage(0);
       
      //创建PDImagexobject对象
      PDImageXObject pdImage = PDImageXObject.createFromFile("C:/PdfBox_Examples/logo.png",doc);
       
      //创建PDPageContentStream对象
      PDPageContentStream contents = new PDPageContentStream(doc, page);

      //在PDF文档中绘制图像
      contents.drawImage(pdImage, 70, 250);

      System.out.println("Image inserted");
      
      //关闭PDPageContentStream对象
      contents.close();		
		
      //保存文档
      doc.save("C:/PdfBox_Examples/sample.pdf");
            
      //关闭文件
      doc.close();
     
   }
}

加密PDF文档，即打开时需要输入密码

import java.io.File;
 
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.encryption.AccessPermission;
import org.apache.pdfbox.pdmodel.encryption.StandardProtectionPolicy;
public class EncriptingPDF {
  
   public static void main(String args[]) throws Exception {
      //加载现有文档
      File file = new File("C:/PdfBox_Examples/sample.pdf");
      PDDocument document = PDDocument.load(file);
   
      //创建访问权限对象
      AccessPermission ap = new AccessPermission();         

      //创建标准化的支持policy对象
      StandardProtectionPolicy spp = new StandardProtectionPolicy("1234", "1234", ap);

      //设置加密密钥的长度
      spp.setEncryptionKeyLength(128);

      //设置访问权限
      spp.setPermissions(ap);

      //保护文件
      document.protect(spp);

      System.out.println("Document encrypted");

      //保存文档
      document.save("C:/PdfBox_Examples/sample.pdf");
      //关闭文件
      document.close();

   }
}

往PDF文档里添加javaScript脚本

import java.io.File;
  
import org.apache.pdfbox.pdmodel.PDDocument; 
import org.apache.pdfbox.pdmodel.interactive.action.PDActionJavaScript;

public class AddJavaScript {

   public static void main(String args[]) throws Exception {

      //加载现有文件
      File file = new File("C:/PdfBox_Examples/new.pdf");
      PDDocument document = PDDocument.load(file);

      String javaScript = "app.alert( {cMsg: 'this is an example', nIcon: 3,"
         + " nType: 0, cTitle: 'PDFBox Javascript example'} );";

      //创建PDActionjavascript对象
      PDActionJavaScript PDAjavascript = new PDActionJavaScript(javaScript);

      //嵌入JavaScript
      document.getDocumentCatalog().setOpenAction(PDAjavascript);

      //保存文档
      document.save( new File("C:/PdfBox_Examples/new.pdf") );
      System.out.println("Data added to the given PDF"); 

      //关闭文件
      document.close();

   }
}

将一个PDF文档拆成多个

import org.apache.pdfbox.multipdf.Splitter; 
import org.apache.pdfbox.pdmodel.PDDocument;

import java.io.File; 
import java.io.IOException; 
import java.util.List; 
import java.util.Iterator;
  
public class SplitPages {
   public static void main(String[] args) throws IOException {

      //加载现有的PDF文档
      File file = new File("C:/PdfBox_Examples/sample.pdf");
      PDDocument document = PDDocument.load(file); 

      //实例化Splitter类
      Splitter splitter = new Splitter();

      //分割PDF文档的页面
      List Pages = splitter.split(document);

      //创建迭代器
      Iterator iterator = Pages.listIterator();

      //将每个页面保存为单个文档
      int i = 1;
      while(iterator.hasNext()) {
         PDDocument pd = iterator.next();
         pd.save("C:/PdfBox_Examples/sample"+ i++ +".pdf");
      }
      System.out.println("Multiple PDF's created");
      document.close();
   }
}

将多个PDF文档合并成一个

import org.apache.pdfbox.multipdf.PDFMergerUtility;
import org.apache.pdfbox.pdmodel.PDDocument;
  
import java.io.File; 
import java.io.IOException;

public class MergePDFs {
   public static void main(String[] args) throws IOException {

      //加载现有的PDF文档
      File file1 = new File("C:/PdfBox_Examples/sample1.pdf");
      PDDocument doc1 = PDDocument.load(file1);
       
      File file2 = new File("C:/PdfBox_Examples/sample2.pdf");
      PDDocument doc2 = PDDocument.load(file2);
         
      //实例化PDFmergerutility类
      PDFMergerUtility PDFmerger = new PDFMergerUtility();

      //设置目标文件
      PDFmerger.setDestinationFileName("C:/PdfBox_Examples/merged.pdf");

      //添加源文件
      PDFmerger.addSource(file1);
      PDFmerger.addSource(file2);

      //合并两份文件
      PDFmerger.mergeDocuments();

      System.out.println("Documents merged");
      //关闭文件
      doc1.close();
      doc2.close();
   }

}

提取PDF图像

import java.awt.image.BufferedImage;
import java.io.File;

import javax.imageio.ImageIO;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.rendering.PDFRenderer;
public class PdfToImage {

   public static void main(String args[]) throws Exception {

      //加载现有的PDF文档
      File file = new File("C:/PdfBox_Examples/sample.pdf");
      PDDocument document = PDDocument.load(file);
       
      //实例化PDFRenderer类
      PDFRenderer renderer = new PDFRenderer(document);

      //从PDF文档渲染图像
      BufferedImage image = renderer.renderImage(0);

      //将图像写入文件
      ImageIO.write(image, "JPEG", new File("C:/PdfBox_Examples/myimage.jpg"));
       
      System.out.println("Image created");
       
      //Closing the document
      document.close();

   }
}

添加矩形

import java.awt.Color;
import java.io.File;
  
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.PDPageContentStream;
public class ShowColorBoxes {

   public static void main(String args[]) throws Exception {

      //加载现有文档
      File file = new File("C:/PdfBox_Examples/BlankPage.pdf");
      PDDocument document = PDDocument.load(file);
        
      //检索PDF文件的页面
      PDPage page = document.getPage(0);

      //实例化PDPAGEContentStream类
      PDPageContentStream contentStream = new PDPageContentStream(document, page);
       
      //设置NonStroking颜色
      contentStream.setNonStrokingColor(Color.DARK_GRAY);

      //绘制一个矩形
      contentStream.addRect(200, 650, 100, 100);

      //绘制一个矩形
      contentStream.fill();

      System.out.println("rectangle added");

      //关闭contentStream对象
      contentStream.close();

      //保存文档
      File file1 = new File("C:/PdfBox_Examples/colorbox.pdf");
      document.save(file1);

      //关闭文件
      document.close();
   }
}