B4X

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.

B4X

Dim success As Boolean = False

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

Dim pdf As ChilkatPdf
pdf.Initialize("pdf")

success = pdf.LoadFile("qa_data/pdf/embedded_files/my_embedded_files_test.pdf")
If success = False Then
    Log(pdf.LastErrorText)
    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?
Dim numFiles As Int = pdf.NumEmbeddedFiles
Log("Number of embedded files: " & numFiles)

Dim json As ChilkatJsonObject
json.Initialize
json.EmitCompact = False

Dim bd As ChilkatBinData
bd.Initialize

'  Get information about each file, and extract each to the filesystem.
Dim i As Int = 0
Do While i < numFiles

    success = pdf.GetEmbeddedFileInfo(i, json)
    If success = False Then
        Log(pdf.LastErrorText)
        Return
    End If


    Log(json.Emit)

    '  Get the filename from the JSON.
    Dim filename As String = "someFile.dat"

    '  The filename SHOULD always be present..
    If json.HasMember("filename") = True Then
        filename = json.StringOf("filename")
    End If


    '  Get the file data.
    success = pdf.GetEmbeddedFileBd(i, bd)
    If success = False Then
        Log(pdf.LastErrorText)
        Return
    End If


    '  Save the contents of the bd to the filename (in the current working directory) in the filesystem.
    success = bd.WriteFile(filename)
    If success = False Then
        Log("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'"
'  }