Sunday, November 5, 2017

Read PDF file by using PDFBOX Java


Download PFD Box from here:  https://pdfbox.apache.org/download





package MyPackage;

import java.io.File;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;

public class ReadPDF
       {

public void readP() throws Exception
{
File filepath=new File("PDF file path");
PDDocument document = PDDocument.load(filepath);

int pages=document.getNumberOfPages();

System.out.println("Total Number of Pages in Document :"+pages);
     
//Instantiate PDFTextStripper class
      PDFTextStripper pdfStripper = new PDFTextStripper();

      //Retrieving text from PDF document
      String text = pdfStripper.getText(document);
      System.out.println(text);      
     
      //Closing the document
      document.close();

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

ReadPDF p=new ReadPDF();
p.readP();

}

}


No comments:

Post a Comment