Extract and Save an Attachment

Get All Attachments

With Aspose.PDF, it is possible to get all attachments from a PDF document. This is useful either when you want to save the documents separately from the PDF, or if you need to strip a PDF of attachments.

To get all attachments from a PDF file:

1. Loop through the Document object’s EmbeddedFiles collection. The EmbeddedFiles collection contains all attachments. Each element of this collection represents a FileSpecification object. Each iteration of the foreach loop through the EmbeddedFiles collection returns a FileSpecification object.
2. Once the object is available, retrieve either all the attached file’s properties or the file itself.

The following code snippets show how to get all the attachments from a PDF document.

The following code snippet also work with Aspose.PDF.Drawing library.

.NET Core 3.1

// For complete examples and data files, visit https://github.com/aspose-pdf/Aspose.PDF-for-.NET
private static void GetAllAttachments()
{
    // The path to the documents directory
    var dataDir = RunExamples.GetDataDir_AsposePdf_Attachments();

    // Open PDF document
    using (var document = new Aspose.Pdf.Document(dataDir + "GetAlltheAttachments.pdf"))
    {
        // Get embedded files collection
        Aspose.Pdf.EmbeddedFileCollection embeddedFiles = document.EmbeddedFiles;

        // Get count of the embedded files
        Console.WriteLine("Total files : {0}", embeddedFiles.Count);

        int count = 1;

        // Loop through the collection to get all the attachments
        foreach (Aspose.Pdf.FileSpecification fileSpecification in embeddedFiles)
        {
            Console.WriteLine("Name: {0}", fileSpecification.Name);
            Console.WriteLine("Description: {0}",
            fileSpecification.Description);
            Console.WriteLine("Mime Type: {0}", fileSpecification.MIMEType);

            // Check if parameter object contains the parameters
            if (fileSpecification.Params != null)
            {
                Console.WriteLine("CheckSum: {0}",
                fileSpecification.Params.CheckSum);
                Console.WriteLine("Creation Date: {0}",
                fileSpecification.Params.CreationDate);
                Console.WriteLine("Modification Date: {0}",
                fileSpecification.Params.ModDate);
                Console.WriteLine("Size: {0}", fileSpecification.Params.Size);
            }

            // Get the attachment and write to file or stream
            var fileContent = new byte[fileSpecification.Contents.Length];
            fileSpecification.Contents.Read(fileContent, 0, fileContent.Length);
            using (var fileStream = new FileStream(dataDir + count + "_out" + ".txt", FileMode.Create))
            {
                fileStream.Write(fileContent, 0, fileContent.Length);
            }
            count += 1;
        }
    }
}

.NET 8

// For complete examples and data files, visit https://github.com/aspose-pdf/Aspose.PDF-for-.NET
private static void GetAllAttachments()
{
    // The path to the documents directory
    var dataDir = RunExamples.GetDataDir_AsposePdf_Attachments();

    // Open PDF document
    using var document = new Aspose.Pdf.Document(dataDir + "GetAlltheAttachments.pdf");

    // Get embedded files collection
    Aspose.Pdf.EmbeddedFileCollection embeddedFiles = document.EmbeddedFiles;

    // Get count of the embedded files
    Console.WriteLine("Total files : {0}", embeddedFiles.Count);

    int count = 1;

    // Loop through the collection to get all the attachments
    foreach (Aspose.Pdf.FileSpecification fileSpecification in embeddedFiles)
    {
        Console.WriteLine("Name: {0}", fileSpecification.Name);
        Console.WriteLine("Description: {0}",
        fileSpecification.Description);
        Console.WriteLine("Mime Type: {0}", fileSpecification.MIMEType);

        // Check if parameter object contains the parameters
        if (fileSpecification.Params != null)
        {
            Console.WriteLine("CheckSum: {0}",
            fileSpecification.Params.CheckSum);
            Console.WriteLine("Creation Date: {0}",
            fileSpecification.Params.CreationDate);
            Console.WriteLine("Modification Date: {0}",
            fileSpecification.Params.ModDate);
            Console.WriteLine("Size: {0}", fileSpecification.Params.Size);
        }

        // Get the attachment and write to file or stream
        var fileContent = new byte[fileSpecification.Contents.Length];
        fileSpecification.Contents.Read(fileContent, 0, fileContent.Length);
        using var fileStream = new FileStream(dataDir + count + "_out" + ".txt", FileMode.Create);
        fileStream.Write(fileContent, 0, fileContent.Length);

        count += 1;
    }
}

Get Individual Attachment

In order to get an individual attachment, we can specify the index of attachment in EmbeddedFiles object of Document instance. Please try using following code snippet.

.NET Core 3.1

// For complete examples and data files, visit https://github.com/aspose-pdf/Aspose.PDF-for-.NET
private static void GetIndividualAttachment()
{
    // The path to the documents directory
    var dataDir = RunExamples.GetDataDir_AsposePdf_Attachments();

    // Open PDF document
    using (var document = new Aspose.Pdf.Document(dataDir + "GetIndividualAttachment.pdf"))
    {
        // Get particular embedded file
        Aspose.Pdf.FileSpecification fileSpecification = document.EmbeddedFiles[1];

        // Get the file properties
        Console.WriteLine("Name: {0}", fileSpecification.Name);
        Console.WriteLine("Description: {0}", fileSpecification.Description);
        Console.WriteLine("Mime Type: {0}", fileSpecification.MIMEType);

        // Check if parameter object contains the parameters
        if (fileSpecification.Params != null)
        {
            Console.WriteLine("CheckSum: {0}",
            fileSpecification.Params.CheckSum);
            Console.WriteLine("Creation Date: {0}",
            fileSpecification.Params.CreationDate);
            Console.WriteLine("Modification Date: {0}",
            fileSpecification.Params.ModDate);
            Console.WriteLine("Size: {0}", fileSpecification.Params.Size);
        }

        // Get the attachment and write to file or stream
        var fileContent = new byte[fileSpecification.Contents.Length];
        fileSpecification.Contents.Read(fileContent, 0, fileContent.Length);

        using (var fileStream = new FileStream(dataDir + "test_out" + ".txt", FileMode.Create))
        {
            fileStream.Write(fileContent, 0, fileContent.Length);
        }
    }
}

.NET 8

// For complete examples and data files, visit https://github.com/aspose-pdf/Aspose.PDF-for-.NET
private static void GetIndividualAttachment()
{
    // The path to the documents directory
    var dataDir = RunExamples.GetDataDir_AsposePdf_Attachments();

    // Open PDF document
    using var document = new Aspose.Pdf.Document(dataDir + "GetIndividualAttachment.pdf");

    // Get particular embedded file
    Aspose.Pdf.FileSpecification fileSpecification = document.EmbeddedFiles[1];

    // Get the file properties
    Console.WriteLine("Name: {0}", fileSpecification.Name);
    Console.WriteLine("Description: {0}", fileSpecification.Description);
    Console.WriteLine("Mime Type: {0}", fileSpecification.MIMEType);

    // Check if parameter object contains the parameters
    if (fileSpecification.Params != null)
    {
        Console.WriteLine("CheckSum: {0}",
        fileSpecification.Params.CheckSum);
        Console.WriteLine("Creation Date: {0}",
        fileSpecification.Params.CreationDate);
        Console.WriteLine("Modification Date: {0}",
        fileSpecification.Params.ModDate);
        Console.WriteLine("Size: {0}", fileSpecification.Params.Size);
    }

    // Get the attachment and write to file or stream
    var fileContent = new byte[fileSpecification.Contents.Length];
    fileSpecification.Contents.Read(fileContent, 0, fileContent.Length);

    using var fileStream = new FileStream(dataDir + "test_out" + ".txt", FileMode.Create);
    fileStream.Write(fileContent, 0, fileContent.Length);
}

Get Attachments that contains in FileAttachmentAnnotation objects

In addition to the Document object’s EmbeddedFiles collection, Attachments can also be contained in FileAttachmentAnnotation objects. Below is the code for viewing the number and details of such Attachments.

.NET Core 3.1

// For complete examples and data files, visit https://github.com/aspose-pdf/Aspose.PDF-for-.NET
private static void ViewAttachmentsInFileAttachmentAnnotations()
{
    // The path to the documents directory
    var dataDir = RunExamples.GetDataDir_AsposePdf_Attachments();

    // Open PDF document
    using (var document = new Aspose.Pdf.Document(dataDir + "GetAlltheAttachments.pdf"))
    {
        for (int i = 1; i <= document.Pages.Count; i++)
        {
            foreach (Aspose.Pdf.Annotations.Annotation annotation in document.Pages[i].Annotations)
            {
                var fileAttachmentAnnotation = annotation as Aspose.Pdf.Annotations.FileAttachmentAnnotation;
                if (fileAttachmentAnnotation != null)
                {
                    Aspose.Pdf.FileSpecification file = fileAttachmentAnnotation.File;
                    if (file != null && file.Name != null)
                    {
                        Console.WriteLine($"Name: {file.Name} on page {i}");
                    }
                }
            }
        }
    }
}

.NET 8

// For complete examples and data files, visit https://github.com/aspose-pdf/Aspose.PDF-for-.NET
private static void ViewAttachmentsInFileAttachmentAnnotations()
{
    // The path to the documents directory
    var dataDir = RunExamples.GetDataDir_AsposePdf_Attachments();

    // Open PDF document
    using var document = new Aspose.Pdf.Document(dataDir + "GetAlltheAttachments.pdf");

    for (int i = 1; i <= document.Pages.Count; i++)
    {
        foreach (Aspose.Pdf.Annotations.Annotation annotation in document.Pages[i].Annotations)
        {
            var fileAttachmentAnnotation = annotation as Aspose.Pdf.Annotations.FileAttachmentAnnotation;
            if (fileAttachmentAnnotation != null)
            {
                Aspose.Pdf.FileSpecification file = fileAttachmentAnnotation.File;
                if (file != null && file.Name != null)
                {
                    Console.WriteLine($"Name: {file.Name} on page {i}");
                }
            }
        }
    }
}