Simple PDFTextExtractor

PDFTextExtractor.scala

import java.io.File

import org.apache.pdfbox.cos.COSDocument
import org.apache.pdfbox.io.{RandomAccessBuffer, RandomAccessFile}
import org.apache.pdfbox.pdfparser.PDFParser
import org.apache.pdfbox.pdmodel.PDDocument
import org.apache.pdfbox.text.PDFTextStripper

object PDFTextExtractor extends App {
  //val reader = new PDFReader(new File("my.pdf"))
  var pdfStripper: PDFTextStripper = null
  var pdDoc: PDDocument = null
  var cosDoc: COSDocument  = null
  val file = new File("/home/master/Desktop/RDD.pdf")
  val parser:PDFParser = new PDFParser(new RandomAccessFile(file, "r"))
  // val parser:PDFParser = new PDFParser(new RandomAccessBuffer(PDFTextExtractor.getClass.getResourceAsStream("/pdf-sample.pdf")))
  parser.parse()
  cosDoc = parser.getDocument()
  pdfStripper = new PDFTextStripper()
  pdDoc = new PDDocument(cosDoc)
  pdfStripper.setStartPage(1)
  pdfStripper.setEndPage(5)
  var parsedText = pdfStripper.getText(pdDoc)
  println(parsedText)
}