Perl

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.

Note: This example requires Chilkat v9.5.0.95 or greater.

Perl

use chilkat();

$success = 0;

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

$pdf = chilkat::CkPdf->new();

$success = $pdf->LoadFile("qa_data/pdf/embedded_files/my_embedded_files_test.pdf");
if ($success == 0) {
    print $pdf->lastErrorText() . "\r\n";
    exit;
}

# Note: The embedded file functionality was added in Chilkat v9.5.0.95

# How many embedded files exist within the opened PDF?
$numFiles = $pdf->get_NumEmbeddedFiles();
print "Number of embedded files: " . $numFiles . "\r\n";

$json = chilkat::CkJsonObject->new();
$json->put_EmitCompact(0);

$bd = chilkat::CkBinData->new();

# Get information about each file, and extract each to the filesystem.
$i = 0;
while ($i < $numFiles) {

    $success = $pdf->GetEmbeddedFileInfo($i,$json);
    if ($success == 0) {
        print $pdf->lastErrorText() . "\r\n";
        exit;
    }

    print $json->emit() . "\r\n";

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

    # The filename SHOULD always be present..
    if ($json->HasMember("filename") == 1) {
        $filename = $json->stringOf("filename");
    }

    # Get the file data.
    $success = $pdf->GetEmbeddedFileBd($i,$bd);
    if ($success == 0) {
        print $pdf->lastErrorText() . "\r\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 == 0) {
        print "Failed to write output file." . "\r\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'"
# }