Extracting HTML from PDFs

build.sbt

name := "pdftohtml"

version := "0.1"

scalaVersion := "2.12.8"

libraryDependencies += "org.apache.pdfbox" % "pdfbox" % "2.0.13"
libraryDependencies += "org.apache.pdfbox" % "pdfbox-tools" % "2.0.13"

PDFtoHTML.scala

package me

import java.io.{File, FileInputStream}

import org.apache.pdfbox.pdmodel.PDDocument
import org.apache.pdfbox.tools.PDFText2HTML

object PDFtoHTML {
  def main(args: Array[String]): Unit = {
    val stream = new FileInputStream(new File("/Users/me/Downloads/example.pdf"))
    val document = PDDocument.load(stream)
    val converter = new PDFText2HTML()
    val html = converter.getText(document)
    println(html)
    document.close()
    stream.close()
  }
}