To get text from a pdf, I use Text::FromAny.
To get text from a ppt, I use catppt from catdoc.

Prerequisites =>

wish from Tcl
catppt from catdoc

Module Prerequisites =>

#!/usr/bin/perl

use strict;
use warnings;
use CPAN;

CPAN::Shell->install(qw(
XML::Twig
Archive::Zip
File::Temp
Time::Local
IO::File
Any::Moose
Try::Tiny
Text::Extract::Word
OpenOffice::OODoc
File::LibMagic
RTF::Parser
HTML::FormatText::WithLinks
CAM::PDF
Text::FromAny));
[download]

Once the prereqs are satisfied, run this:

#!/usr/bin/perl

use strict;
use warnings;
use File::Fetch;
use Text::FromAny;

my $ff1 = File::Fetch->new( 
          uri => 'http://cpansearch.perl.org/src/KARMAN/SWISH-Filter-0
+.15/t/test.ppt');
my $ff2 = File::Fetch->new(
          uri => 'http://cpansearch.perl.org/src/KARMAN/SWISH-Filter-0
+.15/t/test.pdf');
 
my $where1 = $ff1->fetch( ) or die $ff1->error;
my $where2 = $ff2->fetch( ) or die $ff2->error;

my $tFromAny= Text::FromAny->new( file => 'test.pdf');
my $text = $tFromAny->text;
print $text, "\n";
system("/usr/local/bin/catppt -lV");
print "\n";
system("/usr/local/bin/catppt test.ppt");
[download]