Perl Requires Chilkat v9.5.0.95+

Extract Embedded Files from PDF

Demonstrates how to get information about the embedded files (if any) contained within a PDF, and shows how to extract each file. Chilkat2 Perl

use strict;
use warnings;
use Chilkat2;

# This example requires the Chilkat API to have been previously unlocked.
# See Global Unlock Sample for sample code.

my $pdf = Chilkat2::Pdf->new;

my $success = $pdf->LoadFile('qa_data/pdf/embedded_files/my_embedded_files_test.pdf');
if (!$success) {
    print $pdf->LastErrorText, "\n";
    exit;
}

# How many embedded files exist within the opened PDF?
my $numFiles = $pdf->NumEmbeddedFiles;
print 'Number of embedded files: ', $numFiles, "\n";

my $json = Chilkat2::JsonObject->new;
$json->EmitCompact(0);

my $bd = Chilkat2::BinData->new;

# Get information about each file, and extract each to the filesystem.
my $i = 0;
while ($i < $numFiles) {
    $success = $pdf->GetEmbeddedFileInfo($i, $json);
    if (!$success) {
        print $pdf->LastErrorText, "\n";
        exit;
    }

    print $json->Emit(), "\n";

    # Get the filename from the JSON.
    my $filename = 'someFile.dat';

    # The filename SHOULD always be present..
    if ($json->HasMember('filename')) {
        $filename = $json->StringOf('filename');
    }

    # Get the file data.
    $success = $pdf->GetEmbeddedFileBd($i, $bd);
    if (!$success) {
        print $pdf->LastErrorText, "\n";
        exit;
    }

    # Save the contents of the bd to the filename (in the current working directory) in the filesystem.
    $success = $bd->WriteFile($filename);
    if (!$success) {
        print "Failed to write output file.\n";
    }

    $i = $i + 1;
}

# Sample output for the above code:

# Number of embedded files: 3
# {
#   "filename": "employees.json",
#   "desc": "JSON",
#   "subType": "application/json",
#   "size": 159,
#   "creationDate": "D:20230715170506-05'00'",
#   "modDate": "D:20160207153838-05'00'"
# }
#
# {
#   "filename": "rsaPubKey.pem",
#   "desc": "RSA Public Key PEM",
#   "size": 451,
#   "creationDate": "D:20230715170546-05'00'",
#   "modDate": "D:20150724133153-05'00'"
# }
#
# {
#   "filename": "starfish.jpg",
#   "desc": "Starfish JPG",
#   "subType": "image/jpeg",
#   "size": 6229,
#   "creationDate": "D:20230715170356-05'00'",
#   "modDate": "D:20080529103055-05'00'"
# }