Xbase++

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.

Xbase++

LOCAL nSuccess
LOCAL oPdf
LOCAL nNumFiles
LOCAL oJson
LOCAL oBd
LOCAL i
LOCAL cFilename

nSuccess := 0

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

oPdf := CreateObject("Chilkat.Pdf")

nSuccess := oPdf:LoadFile("qa_data/pdf/embedded_files/my_embedded_files_test.pdf")
IF (nSuccess == 0)
    ? oPdf:LastErrorText
    oPdf:destroy()
    RETURN
ENDIF

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

//  How many embedded files exist within the opened PDF?
nNumFiles := oPdf:NumEmbeddedFiles
? "Number of embedded files: " + Str(nNumFiles)

oJson := CreateObject("Chilkat.JsonObject")
oJson:EmitCompact := 0

oBd := CreateObject("Chilkat.BinData")

//  Get information about each file, and extract each to the filesystem.
i := 0
DO WHILE i < nNumFiles

    nSuccess := oPdf:GetEmbeddedFileInfo(i, oJson)
    IF (nSuccess == 0)
        ? oPdf:LastErrorText
        oPdf:destroy()
        oJson:destroy()
        oBd:destroy()
        RETURN
    ENDIF

    ? oJson:Emit()

    //  Get the filename from the JSON.
    cFilename := "someFile.dat"

    //  The filename SHOULD always be present..
    IF (oJson:HasMember("filename") == 1)
        cFilename := oJson:StringOf("filename")
    ENDIF

    //  Get the file data.
    nSuccess := oPdf:GetEmbeddedFileBd(i, oBd)
    IF (nSuccess == 0)
        ? oPdf:LastErrorText
        oPdf:destroy()
        oJson:destroy()
        oBd:destroy()
        RETURN
    ENDIF

    //  Save the contents of the bd to the filename (in the current working directory) in the filesystem.
    nSuccess := oBd:WriteFile(cFilename)
    IF (nSuccess == 0)
        ? "Failed to write output file."
    ENDIF

    i := i + 1
ENDDO

//  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'"
//  }

oPdf:destroy()
oJson:destroy()
oBd:destroy()