Read Password Protected PDF through Apache PDFBox

We can parse PDF files using Apache PDFBox
Just Add the dependency of Apache PDFBox  in pom.xml
        <dependency>
            <groupId>org.apache.pdfbox</groupId>
            <artifactId>pdfbox</artifactId>
            <version>2.0.9</version>
        </dependency>



Sometimes if you are getting error download following dependencies as well

        <dependency>
            <groupId>org.bouncycastle</groupId>
            <artifactId>bcpkix-jdk15on</artifactId>
            <version>1.54</version>
        </dependency>
        <dependency>
            <groupId>org.bouncycastle</groupId>
            <artifactId>bcprov-jdk15on</artifactId>
            <version>1.54</version>
        </dependency>

        <dependency>
            <groupId>org.bouncycastle</groupId>
            <artifactId>bcmail-jdk15on</artifactId>
            <version>1.54</version>
        </dependency>
        <dependency>
            <groupId>org.apache.pdfbox</groupId>
            <artifactId>pdfbox</artifactId>
            <version>2.0.9</version>
        </dependency>

Run the Sample below program to read the PDF (Unprotected)

 package com.neeraj.test.neeraj;  
 import java.io.File;  
 import java.io.IOException;  
 import org.apache.pdfbox.pdmodel.PDDocument;  
 import org.apache.pdfbox.pdmodel.encryption.InvalidPasswordException;  
 import org.apache.pdfbox.text.PDFTextStripper;  
 import org.apache.pdfbox.text.PDFTextStripperByArea;  
 public class PDFParser {  
   public static void main(String[] args) throws InvalidPasswordException, IOException {  
      try (PDDocument document = PDDocument.load(new File("C:\\Users\\bakhtani\\Downloads\\ticket_3057779845.pdf"))) {  
         document.getClass();  
         if (!document.isEncrypted()) {  
           PDFTextStripperByArea stripper = new PDFTextStripperByArea();  
           stripper.setSortByPosition(true);  
           PDFTextStripper tStripper = new PDFTextStripper();  
           String pdfFileInText = tStripper.getText(document);  
           //System.out.println("Text:" + st);  
           // split by whitespace  
           String lines[] = pdfFileInText.split("\\r?\\n");  
           for (String line : lines) {  
             System.out.println(line);  
             if(line.contains("Neeraj")){  
               System.out.println("Neeraj is there");  
                 System.out.println(line);  
               }  
           }  
         }  
       }  
     }  
   }  

Output


E-Ticket
Paytm Booking ID : 4134491696
Booked on: 14 Nov 2017 09:35 PM
Customer Care
7053111905
Paytm Flight Support
7053111905
24X7 Care
paytm.com/care
*Always carry ticket and your ID proof while travelling
One97 Communications Limited, B 121, Sector 5, Noida - 201301


How to Read Password Encrypted PDF (Protected PDF)

 package com.neeraj.test.neeraj;  
 import java.io.File;  
 import java.io.IOException;  
 import org.apache.pdfbox.pdmodel.PDDocument;  
 import org.apache.pdfbox.pdmodel.encryption.InvalidPasswordException;  
 import org.apache.pdfbox.text.PDFTextStripper;  
 public class PDFParser {  
   public static void main(String[] args) throws InvalidPasswordException, IOException {  
     try (PDDocument document = PDDocument.load(new File("C:\\Users\\bakhtani\\Downloads\\EAadhaar_285091794512_07122017141237_873152.pdf"), "password")) {  
       document.setAllSecurityToBeRemoved(true);  
       PDFTextStripper reader = new PDFTextStripper();  
       String pageText = reader.getText(document);  
       System.out.println(pageText);  
     } catch (IOException e){  
       System.err.println("Exception while trying to read pdf document - " + e);  
     }  
     }  
   }