Extracting text from PDF file using iText and qualifying the document for OCR processing

PdfText

/*
Extracts text from PDF using iText libraries.
If no text is found, it could be a document with images or may be a scanned pdf
NOTE: This logic works for SINGLE PAGE PDF
*/

import com.itextpdf.text.pdf.PdfReader;
import com.itextpdf.text.pdf.parser.PdfTextExtractor;

public class PdfText {
  
	public static void main(String args[]){
	  
		try{

			PdfReader reader = new PdfReader("/path/pdffilename.pdf");
			
			String text=PdfTextExtractor.getTextFromPage(reader, 1);
			System.out.println(text);
			
			//Check if the document is scanned pdf
			if(text.isEmpty()){
			  System.out.println("Eligible for Ocr");
			}else{
				System.out.println("Not Eligible for Ocr");
			}
			
		}catch(Exception e){
			e.printStackTrace();
		}
		
	}