pb text extraction

[david guede]

Hi guys,

I try to extract some text from a pdf document. The basic of this step is
not too complicated and works well, but, I do not manage to extract the
text from a section. In my program, I manage to print the bookmarks, for
example:

Sample
   1. Introduction
       1.1 IntroductionPart1
        1.2 IntroductionPart2
   2.Section 1
        2.1 Section1Part1
        2.2Section1Part2

What I would like to do is to create a .txt file for each section with the
corresponding text in it.

Can somebody help me with my code or give me an example ?

This is my code:


 import org.apache.pdfbox.exceptions.InvalidPasswordException;
  import org.apache.pdfbox.pdfparser.PDFParser;
 import org.apache.pdfbox.pdmodel.PDDocument;
 import
org.apache.pdfbox.pdmodel.interactive.documentnavigation.outline.PDDocumentOutline;
import
org.apache.pdfbox.pdmodel.interactive.documentnavigation.outline.PDOutlineItem;
 import
org.apache.pdfbox.pdmodel.interactive.documentnavigation.outline.PDOutlineNode;
import org.apache.pdfbox.util.PDFTextStripper;
import org.apache.pdfbox.util.PDFTextStripperByArea;

import java.io.BufferedWriter;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStreamWriter;

public class PrintBookmarks{

    public static void main( String[] args ) throws Exception
    {
        PDDocument document = PDDocument.load("C:/sample.pdf");
        PrintBookmarks meta = new PrintBookmarks();
        PDDocumentOutline outline =
document.getDocumentCatalog().getDocumentOutline();
        meta.printBookmark( outline, "" );
     }


     public void printBookmark( PDOutlineNode bookmark, String indentation
) throws IOException
     {
         PDOutlineItem current = bookmark.getFirstChild();
         while( current != null )
         {
             System.out.println( indentation + current.getTitle() );
             printBookmark( current, indentation + "    " );
             PDDocument doc = PDDocument.load("C:/sample.pdf");
             File output = new File("C:/"+current.getTitle()+".txt");
             BufferedWriter wr = new BufferedWriter(new
OutputStreamWriter(new FileOutputStream(output)));
             PDFTextStripperByArea  stripper = new PDFTextStripperByArea();
             stripper.setStartBookmark(current);
             stripper.setEndBookmark(current.getNextSibling());
             stripper.;
             current = current.getNextSibling();
        }
      }

}