pdftohtml-example.php

<?php
// Standalone context.
define('PDFTOHTML_PATH', 'X:/PATH TO/workspace/_ouplayer_data/pdftohtml-0.39/pdftohtml.exe');  # Windows.
#define('PDFTOHTML_PATH', '/usr/bin/pdftohtml');  # Redhat 6.

require_once 'libraries/pdftohtml.php';

//( Or, CodeIgniter context. )
#$config['pdftohtml_path'] = '/usr/bin/pdftohtml';
#$this->load->library('pdftohtml');

$pdf = '/my/data/transcripts/l314audio2.pdf'; #Ok.
$xml = str_replace('.pdf', '.xml', $pdf);  //tmp file?
$ofile = str_replace('.pdf', '_transcript.html', $pdf);

try {
  $parser = new Pdftohtml();
  $out = $parser->parse($pdf, $xml, $delete_xml = TRUE);
  $by = file_put_contents($ofile, $out);
  echo "Ok, written $by bytes | $ofile".PHP_EOL;
}
catch(Exception $ex) {
  die('EX: '.$ex->getMessage().PHP_EOL);
}


/*
 pdftohtml binary install (Redhat Linux)

 $ yum info poppler
 $ yum install poppler
 $ pdftohtml -v
*/