In This Topic
Programming / PDF / Extracting embedded files (attachments) from a PDF document

Extracting embedded files (attachments) from a PDF document

In This Topic

You can attach other files to a PDF document in two ways. That said, you can also extract those embedded files from your PDF document in two different ways. Here is how to do it using GdPicture.NET.

  • Embedded files can be included as a whole directly to a PDF document; these are named File Attachments. They should be located in the Attachments panel in viewer applications. This simple piece of code shows you how to find out the number of attached files and how to extract the first one into a single file.
    Copy Code 
    'We assume that GdPicture has been correctly installed and unlocked.

 Using oGdPicturePDF As GdPicturePDF = New GdPicturePDF()

     If oGdPicturePDF.LoadFromFile("test.pdf", False) = GdPictureStatus.OK Then

         Dim embeddedFileCount As Integer = oGdPicturePDF.GetEmbeddedFileCount()

         If oGdPicturePDF.GetStat() = GdPictureStatus.OK Then

             If embeddedFileCount > 0 Then

                 Dim FileName As String = oGdPicturePDF.GetEmbeddedFileName(0)

                 If oGdPicturePDF.GetStat() = GdPictureStatus.OK Then

                     Dim FileSize As Integer = oGdPicturePDF.GetEmbeddedFileSize(0)

                     If oGdPicturePDF.GetStat() = GdPictureStatus.OK Then

                         Dim FileData As Byte() = New Byte(FileSize) {}

                         Dim status As GdPictureStatus = oGdPicturePDF.ExtractEmbeddedFile(0, FileData)

                         If status = GdPictureStatus.OK Then

                             MessageBox.Show("The content of the first embedded file has been extracted successfully.", "Example: Emdedded files (Attachments)", MessageBoxButtons.OK, MessageBoxIcon.Information)

                             Dim oFileStream As System.IO.FileStream = Nothing

                             oFileStream = New System.IO.FileStream(FileName + "_content.dat", System.IO.FileMode.Create)

                             oFileStream.Write(FileData, 0, FileData.Length)

                             oFileStream.Close()

                             MessageBox.Show("The content of the embedded file has been saved successfully.", "Example: Emdedded files (Attachments)", MessageBoxButtons.OK, MessageBoxIcon.Information)

                         Else

                             MessageBox.Show("The embedded file has failed to extract. Status: " + status.ToString(), "Example: Emdedded files (Attachments)", MessageBoxButtons.OK, MessageBoxIcon.Error)

                         End If

                    Else

                         MessageBox.Show("An error occurred getting the file size. Status: " + oGdPicturePDF.GetStat().ToString(), "Example: Emdedded files (Attachments)", MessageBoxButtons.OK, MessageBoxIcon.Error)

                     End If

                 Else

                     MessageBox.Show("An error occurred getting the file name. Status: " + oGdPicturePDF.GetStat().ToString(), "Example: Emdedded files (Attachments)", MessageBoxButtons.OK, MessageBoxIcon.Error)

                 End If

             Else

                 MessageBox.Show("This PDF file does not contain embedded files.", "Example: Emdedded files (Attachments)", MessageBoxButtons.OK, MessageBoxIcon.Information)

             End If

         Else

             MessageBox.Show("An error occurred getting the number of embedded files. Status: " + oGdPicturePDF.GetStat().ToString(), "Example: Emdedded files (Attachments)", MessageBoxButtons.OK, MessageBoxIcon.Error)

         End If

     Else

         MessageBox.Show("The file can't be loaded.", "Example: Emdedded files (Attachments)", MessageBoxButtons.OK, MessageBoxIcon.Error)

     End If

 End Using
    Copy Code 
    //We assume that GdPicture has been correctly installed and unlocked.

 using (GdPicturePDF oGdPicturePDF = new GdPicturePDF())

 {

    if (oGdPicturePDF.LoadFromFile("test.pdf", false) == GdPictureStatus.OK)

     {

         int embeddedFileCount = oGdPicturePDF.GetEmbeddedFileCount();

         if (oGdPicturePDF.GetStat() == GdPictureStatus.OK)

         {

             if (embeddedFileCount > 0)

             {

                 string FileName = oGdPicturePDF.GetEmbeddedFileName(0);

                 if (oGdPicturePDF.GetStat() == GdPictureStatus.OK)

                 {

                     int FileSize = oGdPicturePDF.GetEmbeddedFileSize(0);

                     if (oGdPicturePDF.GetStat() == GdPictureStatus.OK)

                    {

                         byte[] FileData = new byte[FileSize + 1];

                         GdPictureStatus status = oGdPicturePDF.ExtractEmbeddedFile(0, ref FileData);

                         if (status == GdPictureStatus.OK)

                         {

                             MessageBox.Show("The content of the first embedded file has been extracted successfully.", "Example: Emdedded files (Attachments)", MessageBoxButtons.OK, MessageBoxIcon.Information);

                             System.IO.FileStream oFileStream = default(System.IO.FileStream);

                             oFileStream = new System.IO.FileStream(FileName + "_content.dat", System.IO.FileMode.Create);

                             oFileStream.Write(FileData, 0, FileData.Length);

                             oFileStream.Close();

                             MessageBox.Show("The content of the embedded file has been saved successfully.", "Example: Emdedded files (Attachments)", MessageBoxButtons.OK, MessageBoxIcon.Information);

                         }

                         else

                             MessageBox.Show("The embedded file has failed to extract. Status: " + status.ToString(), "Example: Emdedded files (Attachments)", MessageBoxButtons.OK, MessageBoxIcon.Error);

                     }

                     else

                         MessageBox.Show("An error occurred getting the file size. Status: " + oGdPicturePDF.GetStat().ToString(), "Example: Emdedded files (Attachments)", MessageBoxButtons.OK, MessageBoxIcon.Error);

                 }

                 else

                     MessageBox.Show("An error occurred getting the file name. Status: " + oGdPicturePDF.GetStat().ToString(), "Example: Emdedded files (Attachments)", MessageBoxButtons.OK, MessageBoxIcon.Error);

             }

             else

                 MessageBox.Show("This PDF file does not contain embedded files.", "Example: Emdedded files (Attachments)", MessageBoxButtons.OK, MessageBoxIcon.Information);

         }

         else

             MessageBox.Show("An error occurred getting the number of embedded files. Status: " + oGdPicturePDF.GetStat().ToString(), "Example: Emdedded files (Attachments)", MessageBoxButtons.OK, MessageBoxIcon.Error);

     }

     else

         MessageBox.Show("The file can't be loaded.", "Example: Emdedded files (Attachments)", MessageBoxButtons.OK, MessageBoxIcon.Error);

 }
  • Embedded files can also be attached as File Attachment Annotations as part of a particular comment located somewhere on the page. Such a comment appears on that page with a file attachment icon, and you should find the corresponding file in the Comments panel in viewer applications. This example demonstrates how to find out attached files in comments and how to extract them subsequently.
    Copy Code 
    'We assume that GdPicture has been correctly installed and unlocked.

 Using oGdPicturePDF As GdPicturePDF = New GdPicturePDF()

     If oGdPicturePDF.LoadFromFile("test.pdf", False) = GdPictureStatus.OK Then

         Dim pageCount As Integer = oGdPicturePDF.GetPageCount()

         If oGdPicturePDF.GetStat() = GdPictureStatus.OK Then

             Dim message As String = ""

             For page As Integer = 1 To pageCount

                 message = message + "Page nr." + page.ToString()

                 If oGdPicturePDF.SelectPage(page) = GdPictureStatus.OK Then

                     Dim annotCount As Integer = oGdPicturePDF.GetAnnotationCount()

                     If oGdPicturePDF.GetStat() = GdPictureStatus.OK Then

                         Dim subtype As String = ""

                         For annotID As Integer = 0 To annotCount - 1

                             subtype = oGdPicturePDF.GetAnnotationSubType(annotID)

                             If oGdPicturePDF.GetStat() = GdPictureStatus.OK Then

                                 If subtype.Equals("FileAttachment") Then

                                     message = message + vbCrLf + "AnnotID: " + annotID.ToString()

                                     Dim filedata As Byte() = Nothing

                                     Dim filesize As Integer = 0

                                     Dim filename As String = oGdPicturePDF.GetFileAttachmentAnnotFileName(annotID)

                                     If oGdPicturePDF.GetStat() = GdPictureStatus.OK Then filesize = oGdPicturePDF.GetFileAttachmentAnnotFileSize(annotID)

                                     If (oGdPicturePDF.GetStat() = GdPictureStatus.OK) AndAlso

                                        (oGdPicturePDF.GetFileAttachmentAnnotEmbeddedFile(annotID, filedata) = GdPictureStatus.OK) Then

                                         Using file As System.IO.Stream = System.IO.File.OpenWrite(filename)

                                             file.Write(filedata, 0, filesize)

                                         End Using

                                         message = message + "The embedded file has been extracted successfully."

                                     End If

                                     If oGdPicturePDF.GetStat() <> GdPictureStatus.OK Then message = message + "Extracting embedded file has failed. Status: " + oGdPicturePDF.GetStat().ToString()

                                 End If

                             Else

                                 message = message + "An error occurred getting the annotation subtype. Status: " + oGdPicturePDF.GetStat().ToString()

                             End If

                         Next

                     Else

                         message = message + "An error occurred getting the annotation count. Status: " + oGdPicturePDF.GetStat().ToString()

                     End If

                 Else

                     message = message + "An error occurred selecting the page. Status: " + oGdPicturePDF.GetStat().ToString()

                 End If

                 message += vbCrLf

             Next

             If message.Contains("error") Then

                 MessageBox.Show(message, "Example: Annotation's file attachments", MessageBoxButtons.OK, MessageBoxIcon.Error)

             Else

                 MessageBox.Show(message, "Example: Annotation's file attachments", MessageBoxButtons.OK, MessageBoxIcon.Information)

             End If

         Else

             MessageBox.Show("An error occurred getting the page count. Status: " + oGdPicturePDF.GetStat().ToString(), "Example: Annotation's file attachments", MessageBoxButtons.OK, MessageBoxIcon.Error)

         End If

     Else

         MessageBox.Show("The file can't be loaded.", "Example: Annotation's file attachments", MessageBoxButtons.OK, MessageBoxIcon.Error)

     End If

 End Using
    Copy Code 
    //We assume that GdPicture has been correctly installed and unlocked.

 using (GdPicturePDF oGdPicturePDF = new GdPicturePDF())

 {

    if (oGdPicturePDF.LoadFromFile("test.pdf", false) == GdPictureStatus.OK)

     {

         int pageCount = oGdPicturePDF.GetPageCount();

         if (oGdPicturePDF.GetStat() == GdPictureStatus.OK)

         {

             string message = "";

             for (int page = 1; page <= pageCount; page++)

             {

                 message = message + "Page nr." + page.ToString();

                 if (oGdPicturePDF.SelectPage(page) == GdPictureStatus.OK)

                 {

                     int annotCount = oGdPicturePDF.GetAnnotationCount();

                     if (oGdPicturePDF.GetStat() == GdPictureStatus.OK)

                     {

                         string subtype = "";

                         for (int annotID = 0; annotID < annotCount; annotID++)

                         {

                             subtype = oGdPicturePDF.GetAnnotationSubType(annotID);

                             if (oGdPicturePDF.GetStat() == GdPictureStatus.OK)

                             {

                                 if (subtype.Equals("FileAttachment"))

                                 {

                                     message = message + "\nAnnotID: " + annotID.ToString();

                                     byte[] filedata = null;

                                     int filesize = 0;

                                     string filename = oGdPicturePDF.GetFileAttachmentAnnotFileName(annotID);

                                     if (oGdPicturePDF.GetStat() == GdPictureStatus.OK)

                                         filesize = oGdPicturePDF.GetFileAttachmentAnnotFileSize(annotID);

                                     if ((oGdPicturePDF.GetStat() == GdPictureStatus.OK) &&

                                         (oGdPicturePDF.GetFileAttachmentAnnotEmbeddedFile(annotID, ref filedata) == GdPictureStatus.OK))

                                     {

                                         using (System.IO.Stream file = File.OpenWrite(filename))

                                         {

                                             file.Write(filedata, 0, filesize);

                                         }

                                         message = message + "The embedded file has been extracted successfully.";

                                     }

                                     if (oGdPicturePDF.GetStat() != GdPictureStatus.OK)

                                         message = message + "Extracting embedded file has failed. Status: " + oGdPicturePDF.GetStat().ToString();

                                 }

                             }

                             else message = message + "An error occurred getting the annotation subtype. Status: " + oGdPicturePDF.GetStat().ToString();

                         }

                     }

                     else

                         message = message + "An error occurred getting the annotation count. Status: " + oGdPicturePDF.GetStat().ToString();

                 }

                 else

                     message = message + "An error occurred selecting the page. Status: " + oGdPicturePDF.GetStat().ToString();

                 message += "\n";

             }

             if (message.Contains("error"))

                 MessageBox.Show(message, "Example: Annotation's file attachments", MessageBoxButtons.OK, MessageBoxIcon.Error);

             else

                 MessageBox.Show(message, "Example: Annotation's file attachments", MessageBoxButtons.OK, MessageBoxIcon.Information);

         }

         else

             MessageBox.Show("An error occurred getting the page count. Status: " + oGdPicturePDF.GetStat().ToString(), "Example: Annotation's file attachments", MessageBoxButtons.OK, MessageBoxIcon.Error);

     }

     else

         MessageBox.Show("The file can't be loaded.", "Example: Annotation's file attachments", MessageBoxButtons.OK, MessageBoxIcon.Error);

 }