How to extract text from a PDF file with Apache PDFBox

Question

I would like to extract text from a given PDF file with Apache PDFBox.

I wrote this code:

PDFTextStripper pdfStripper = null;
PDDocument pdDoc = null         


        

Answer 1

This works fine to extract data from a PDF file that has text content using pdfbox 2.0.6

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

public class PDFTextExtractor {
   public static void main(String[] args) throws IOException {
       System.out.println(readParaFromPDF("C:\\sample1.pdf",3, "Enter Start Text Here", "Enter Ending Text Here"));
    //Enter FilePath, Page Number, StartsWith, EndsWith
   }
   public static String readParaFromPDF(String pdfPath, int pageNo, String strStartIndentifier, String strEndIdentifier) {
       String returnString = "";
       try {
           PDDocument document = PDDocument.load(new File(pdfPath));
           document.getClass();        
           if (!document.isEncrypted()) {
               PDFTextStripperByArea stripper = new PDFTextStripperByArea();
               stripper.setSortByPosition(true);
               PDFTextStripper tStripper = new PDFTextStripper();
               tStripper.setStartPage(pageNo);
               tStripper.setEndPage(pageNo);
               String pdfFileInText = tStripper.getText(document);
               String strStart = strStartIndentifier;
               String strEnd = strEndIdentifier;
               int startInddex = pdfFileInText.indexOf(strStart);
               int endInddex = pdfFileInText.indexOf(strEnd);
               returnString = pdfFileInText.substring(startInddex, endInddex) + strEnd;
           }
          } catch (Exception e) {
              returnString = "No ParaGraph Found";
       }
            return returnString;
   }
}