Tcl

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.

Tcl

load ./chilkat.dll

set success 0

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

set pdf [new_CkPdf]

set success [CkPdf_LoadFile $pdf "qa_data/pdf/embedded_files/my_embedded_files_test.pdf"]
if {$success == 0} then {
    puts [CkPdf_lastErrorText $pdf]
    delete_CkPdf $pdf
    exit
}

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

# How many embedded files exist within the opened PDF?
set numFiles [CkPdf_get_NumEmbeddedFiles $pdf]
puts "Number of embedded files: $numFiles"

set json [new_CkJsonObject]

CkJsonObject_put_EmitCompact $json 0

set bd [new_CkBinData]

# Get information about each file, and extract each to the filesystem.
set i 0
while {$i < $numFiles} {

    set success [CkPdf_GetEmbeddedFileInfo $pdf $i $json]
    if {$success == 0} then {
        puts [CkPdf_lastErrorText $pdf]
        delete_CkPdf $pdf
        delete_CkJsonObject $json
        delete_CkBinData $bd
        exit
    }

    puts [CkJsonObject_emit $json]

    # Get the filename from the JSON.
    set filename "someFile.dat"

    # The filename SHOULD always be present..
    if {[CkJsonObject_HasMember $json "filename"] == 1} then {
        set filename [CkJsonObject_stringOf $json "filename"]
    }

    # Get the file data.
    set success [CkPdf_GetEmbeddedFileBd $pdf $i $bd]
    if {$success == 0} then {
        puts [CkPdf_lastErrorText $pdf]
        delete_CkPdf $pdf
        delete_CkJsonObject $json
        delete_CkBinData $bd
        exit
    }

    # Save the contents of the bd to the filename (in the current working directory) in the filesystem.
    set success [CkBinData_WriteFile $bd $filename]
    if {$success == 0} then {
        puts "Failed to write output file."
    }

    set i [expr $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'"
# }

delete_CkPdf $pdf
delete_CkJsonObject $json
delete_CkBinData $bd