#!/usr/bin/perl -w
use strict;
use CAM::PDF;
use CAM::PDF::PageText;
use File::Spec::Functions;
use File::Find::Rule;

#1. Specify directory 

my $dirPath= 'F:/project_italia/firm_files';
my $src_fmt='*.*';

#2 retrieve all sub-dirs from the directory
my @allDir = File::Find::Rule->maxdepth(1)->directory->in($dirPath);

open(LIST, ">>", 'F:/project_italia/firmList_pdf.txt' ) or die "Can't open destination.fil $!";

foreach (@allDir)
{
    my $src_path = catfile($_, $src_fmt);
    my @filings = glob($src_path);
    
    foreach (@filings)
    {
       my $fileName=$_;
       my $pdf = CAM::PDF->new($_);
          
       #split path name       
       my @textName = split(/\\/, $_);
       
       #Create new text file
       open(DEST, ">>", 'F:/project_italia/firm_text/'.$textName[4].'.txt' ) or die "Can't open destination.fil $!";
       
       #keeps track on whether the pdf to text conversion was successful
       my $conv=0;
       my $count=0;
       
        #Get total page number of the pdf
        my $pageNum=$pdf->numPages();
               
        for (1..$pageNum)
        {
            my $pageConv = $pdf->getPageContentTree($_);
            
            #if conversion fails move to the next file
            print DEST CAM::PDF::PageText->render($pageConv) or do
            {
                warn "PDF->new failed on $_\n";
                next;
            };
            
            $count++;     
            #conversion is successful only when all pages have been converted
            $conv=1 if ($count==$pageNum); 
        }
        
        #close text file
        close DEST;
        
        #keep track of which files converted successfully
        print LIST "$textName[4] | $conv \n";
    }
        
}    
close LIST;