(PowerShell) 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.

Chilkat .NET Downloads Chilkat .NET Assemblies

Add-Type -Path "C:\chilkat\ChilkatDotNet47-9.5.0-x64\ChilkatDotNet47.dll"

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

$pdf = New-Object Chilkat.Pdf

$success = $pdf.LoadFile("qa_data/pdf/embedded_files/my_embedded_files_test.pdf")
if ($success -eq $false) {
    $($pdf.LastErrorText)
    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.NumEmbeddedFiles
$("Number of embedded files: " + $numFiles)

$json = New-Object Chilkat.JsonObject
$json.EmitCompact = $false

$bd = New-Object Chilkat.BinData

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

    $success = $pdf.GetEmbeddedFileInfo($i,$json)
    if ($success -eq $false) {
        $($pdf.LastErrorText)
        exit
    }

    $($json.Emit())

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

    # The filename SHOULD always be present..
    if ($json.HasMember("filename") -eq $true) {
        $filename = $json.StringOf("filename")
    }

    # Get the file data.
    $success = $pdf.GetEmbeddedFileBd($i,$bd)
    if ($success -eq $false) {
        $($pdf.LastErrorText)
        exit
    }

    # Save the contents of the bd to the filename (in the current working directory) in the filesystem.
    $success = $bd.WriteFile($filename)
    if ($success -eq $false) {
        $("Failed to write output file.")
    }

    $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'"
# }