Extracting Embed Files from PDF using C# and VB.NET

Complete code

using System;
using System.IO;
using System.IO.Compression;
using SautinSoft.Pdf;

class Program
{
    /// <summary>
    /// Embed files to PDF document.
    /// </summary>
    /// <remarks>
    /// Details: https://sautinsoft.com/products/pdf/help/net/developer-guide/extract-embedded-files.php
    /// </remarks>
    static void Main()
    {
        // Before starting this example, please get a free 30-day trial key:
        // https://sautinsoft.com/start-for-free/

        // Apply the key here:
        // PdfDocument.SetLicense("...");

        // Add to zip archive all files embedded in the PDF document.
        using (var document = PdfDocument.Load(Path.GetFullPath(@"..\..\..\Embedded Files.pdf")))
        using (var archiveStream = File.Create("Embedded Files.zip"))
        using (var archive = new ZipArchive(archiveStream, ZipArchiveMode.Create, leaveOpen: true))
            foreach (var keyFilePair in document.EmbeddedFiles)
            {
                var fileSpecification = keyFilePair.Value;

                // Use the description or the name as the relative path of the entry in the zip archive.
                var entryFullName = fileSpecification.Description;
                if (entryFullName == null || !entryFullName.EndsWith(fileSpecification.Name, StringComparison.Ordinal))
                    entryFullName = fileSpecification.Name;

                var embeddedFile = fileSpecification.EmbeddedFile;

                // Create zip archive entry.
                // Zip archive entry is compressed if the embedded file's compressed size is less than its uncompressed size.
                bool compress = embeddedFile.Size == null || embeddedFile.CompressedSize < embeddedFile.Size.GetValueOrDefault();
                var entry = archive.CreateEntry(entryFullName, compress ? CompressionLevel.Optimal : CompressionLevel.NoCompression);

                // Set the modification date, if it is specified in the embedded file.
                var modificationDate = embeddedFile.ModificationDate;
                if (modificationDate != null)
                    entry.LastWriteTime = modificationDate.GetValueOrDefault();

                // Copy embedded file contents to the zip archive entry.
                using (var embeddedFileStream = embeddedFile.OpenRead())
                using (var entryStream = entry.Open())
                    embeddedFileStream.CopyTo(entryStream);
            }

        System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo("Embedded Files.zip") { UseShellExecute = true });
    }
}

Download


If you need a new code example or have a question: email us at support@sautinsoft.com or ask at Online Chat (right-bottom corner of this page) or use the Form below:



Questions and suggestions from you are always welcome!

We are developing .Net components since 2002. We know PDF, DOCX, RTF, HTML, XLSX and Images formats. If you need any assistance with creating, modifying or converting documents in various formats, we can help you. We will write any code example for you absolutely free.