PDSL.PDFProcessor.java Source code

Introduction

Here is the source code for PDSL.PDFProcessor.java

Source

/*
 * To change this license header, choose License Headers in Project Properties.
 * To change this template file, choose Tools | Templates
 * and open the template in the editor.
 */
package PDSL;

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.PrintWriter;
import java.io.RandomAccessFile;
import org.apache.pdfbox.cos.COSDocument;
import org.apache.pdfbox.io.RandomAccessRead;
import org.apache.pdfbox.pdfparser.PDFParser;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;

/**
 * Processing PDF to text using pdfbox
 *
 * @author sidiksoleman
 */
public class PDFProcessor {

    public void pdfToText(String dirFrom, String dirTo) throws IOException {
        File pdfFolder = new File(dirFrom);
        File[] listOfPDF = pdfFolder.listFiles();
        for (File thePDF : listOfPDF) {
            PDDocument pdDoc = PDDocument.load(thePDF);
            PDFTextStripper pdfStripper = new PDFTextStripper();
            String parsedText = pdfStripper.getText(pdDoc);
            PrintWriter out = new PrintWriter(dirTo + "/" + thePDF.getName().replace(".pdf", ".txt"));
            out.write(parsedText);
            out.close();
        }
    }

    public static void main(String[] args) throws IOException {
        PDFProcessor ps = new PDFProcessor();
        ps.pdfToText("../testFrom", "../testTo");
    }
}