DataFlex

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.

DataFlex

Use ChilkatAx-win32.pkg

Procedure Test
    Boolean iSuccess
    Handle hoPdf
    Integer iNumFiles
    Variant vJson
    Handle hoJson
    Variant vBd
    Handle hoBd
    Integer i
    String sFilename
    String sTemp1
    Boolean bTemp1

    Move False To iSuccess

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

    Get Create (RefClass(cComChilkatPdf)) To hoPdf
    If (Not(IsComObjectCreated(hoPdf))) Begin
        Send CreateComObject of hoPdf
    End

    Get ComLoadFile Of hoPdf "qa_data/pdf/embedded_files/my_embedded_files_test.pdf" To iSuccess
    If (iSuccess = False) Begin
        Get ComLastErrorText Of hoPdf To sTemp1
        Showln sTemp1
        Procedure_Return
    End

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

    // How many embedded files exist within the opened PDF?
    Get ComNumEmbeddedFiles Of hoPdf To iNumFiles
    Showln "Number of embedded files: " iNumFiles

    Get Create (RefClass(cComChilkatJsonObject)) To hoJson
    If (Not(IsComObjectCreated(hoJson))) Begin
        Send CreateComObject of hoJson
    End
    Set ComEmitCompact Of hoJson To False

    Get Create (RefClass(cComChilkatBinData)) To hoBd
    If (Not(IsComObjectCreated(hoBd))) Begin
        Send CreateComObject of hoBd
    End

    // Get information about each file, and extract each to the filesystem.
    Move 0 To i
    While (i < iNumFiles)

        Get pvComObject of hoJson to vJson
        Get ComGetEmbeddedFileInfo Of hoPdf i vJson To iSuccess
        If (iSuccess = False) Begin
            Get ComLastErrorText Of hoPdf To sTemp1
            Showln sTemp1
            Procedure_Return
        End

        Get ComEmit Of hoJson To sTemp1
        Showln sTemp1

        // Get the filename from the JSON.
        Move "someFile.dat" To sFilename

        // The filename SHOULD always be present..
        Get ComHasMember Of hoJson "filename" To bTemp1
        If (bTemp1 = True) Begin
            Get ComStringOf Of hoJson "filename" To sFilename
        End

        // Get the file data.
        Get pvComObject of hoBd to vBd
        Get ComGetEmbeddedFileBd Of hoPdf i vBd To iSuccess
        If (iSuccess = False) Begin
            Get ComLastErrorText Of hoPdf To sTemp1
            Showln sTemp1
            Procedure_Return
        End

        // Save the contents of the bd to the filename (in the current working directory) in the filesystem.
        Get ComWriteFile Of hoBd sFilename To iSuccess
        If (iSuccess = False) Begin
            Showln "Failed to write output file."
        End

        Move (i + 1) To i
    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'"
    // }


End_Procedure