PowerBuilder

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.

PowerBuilder

integer li_rc
integer li_Success
oleobject loo_Pdf
integer li_NumFiles
oleobject loo_Json
oleobject loo_Bd
integer i
string ls_Filename

li_Success = 0

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

loo_Pdf = create oleobject
li_rc = loo_Pdf.ConnectToNewObject("Chilkat.Pdf")
if li_rc < 0 then
    destroy loo_Pdf
    MessageBox("Error","Connecting to COM object failed")
    return
end if

li_Success = loo_Pdf.LoadFile("qa_data/pdf/embedded_files/my_embedded_files_test.pdf")
if li_Success = 0 then
    Write-Debug loo_Pdf.LastErrorText
    destroy loo_Pdf
    return
end if

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

// How many embedded files exist within the opened PDF?
li_NumFiles = loo_Pdf.NumEmbeddedFiles
Write-Debug "Number of embedded files: " + string(li_NumFiles)

loo_Json = create oleobject
li_rc = loo_Json.ConnectToNewObject("Chilkat.JsonObject")

loo_Json.EmitCompact = 0

loo_Bd = create oleobject
li_rc = loo_Bd.ConnectToNewObject("Chilkat.BinData")

// Get information about each file, and extract each to the filesystem.
i = 0
do while i < li_NumFiles

    li_Success = loo_Pdf.GetEmbeddedFileInfo(i,loo_Json)
    if li_Success = 0 then
        Write-Debug loo_Pdf.LastErrorText
        destroy loo_Pdf
        destroy loo_Json
        destroy loo_Bd
        return
    end if

    Write-Debug loo_Json.Emit()

    // Get the filename from the JSON.
    ls_Filename = "someFile.dat"

    // The filename SHOULD always be present..
    if loo_Json.HasMember("filename") = 1 then
        ls_Filename = loo_Json.StringOf("filename")
    end if

    // Get the file data.
    li_Success = loo_Pdf.GetEmbeddedFileBd(i,loo_Bd)
    if li_Success = 0 then
        Write-Debug loo_Pdf.LastErrorText
        destroy loo_Pdf
        destroy loo_Json
        destroy loo_Bd
        return
    end if

    // Save the contents of the bd to the filename (in the current working directory) in the filesystem.
    li_Success = loo_Bd.WriteFile(ls_Filename)
    if li_Success = 0 then
        Write-Debug "Failed to write output file."
    end if

    i = i + 1
loop

// 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'"
// }


destroy loo_Pdf
destroy loo_Json
destroy loo_Bd