PDFsharp & MigraDoc Foundation

using System;
using System.Collections.Generic;
using System.Diagnostics;
using System.IO;
using System.Linq;
using System.Text;
using System.Threading.Tasks;
using PdfSharp.Pdf;
using PdfSharp.Pdf.Advanced;
using PdfSharp.Pdf.IO;

namespace ReplaceRemoveImage
{
    class Program
    {
        static void Main(string[] args)
        {
            // Get a fresh copy of the sample PDF file
            string inFile = @"c:\in.pdf";
            string outFile = @"c:\out.pdf";
            File.Copy(inFile, outFile, true);

            // Read document into memory for modification
            PdfDocument document = PdfReader.Open(outFile);

            int imageCount = 0;
           
            PdfPage page = document.Pages[0];

            // Get resources dictionary
            PdfDictionary resources = page.Elements.GetDictionary("/Resources");
            if (resources != null)
            {
                // Get external objects dictionary
                PdfDictionary xObjects = resources.Elements.GetDictionary("/XObject");
                if (xObjects != null)
                {
                    ICollection<PdfItem> items = xObjects.Elements.Values;
                    // Iterate references to external objects
                    foreach (PdfItem item in items)
                    {
                        PdfReference reference = item as PdfReference;
                        if (reference != null)
                        {
                            PdfDictionary xObject = reference.Value as PdfDictionary;
                            // Is external object an image?
                            if (xObject != null && xObject.Elements.GetString("/Subtype") == "/Image")
                            {
                                //if (xObject.Stream.Value.Length)
                                Console.WriteLine("Found image with length of {0}", xObject.Stream.Value.Length);
                            }
                        }
                    }
                }
            }
           
            var pdfObjects = document.Internals.GetAllObjects();

            foreach (PdfObject pdfObject in pdfObjects)
            {
                Console.WriteLine("Found object {0}, {1} indirect:{2}",
                    pdfObject.Internals.ObjectID, pdfObject.Internals.ObjectNumber,
                    pdfObject.IsIndirect);
            }

            // Using PDFsharp we never deal with object numbers. We simply put the
            // objects together and PDFsharp does the rest.

            // Save the document...
            document.Save(outFile);

            Console.ReadKey();
            // ...and start a viewer.
            //Process.Start(outFile);
        }

        //static void ExportImage(PdfDictionary image, ref int count)
        //{
        //    string filter = image.Elements["/Filter"].ToString();

        //    // this filter value for my PDF always contained "[ /ASCII85Decode /FlateDecode /DCTDecode ]"
        //    // the subsequent saved image is unreadable
        //    if (filter.Contains("/DCTDecode"))
        //    {
        //        ExportJpegImage(image, ref count);
        //    }
        //    else if (filter.Contains("/FlateDecode"))
        //    {
        //        ExportAsPngImage(image, ref count);
        //    }
        //}

        //static void ExportJpegImage(PdfDictionary image, ref int count)
        //{
        //    // Fortunately JPEG has native support in PDF and exporting an image is just writing the stream to a file.
        //    byte[] stream = image.Stream.Value;
        //    FileStream fs = new FileStream(String.Format(@"c:\Image{0}.jpeg", count++), FileMode.Create, FileAccess.Write);
        //    BinaryWriter bw = new BinaryWriter(fs);
        //    bw.Write(stream);
        //    bw.Close();
        //}

        //static void ExportAsPngImage(PdfDictionary image, ref int count)
        //{
        //    int width = image.Elements.GetInteger(PdfImage.Keys.Width);
        //    int height = image.Elements.GetInteger(PdfImage.Keys.Height);
        //    int bitsPerComponent = image.Elements.GetInteger(PdfImage.Keys.BitsPerComponent);

        //    // TODO: You can put the code here that converts vom PDF internal image format to a Windows bitmap
        //    // and use GDI+ to save it in PNG format.
        //    // It is the work of a day or two for the most important formats. Take a look at the file
        //    // PdfSharp.Pdf.Advanced/PdfImage.cs to see how we create the PDF image formats.
        //    // We don't need that feature at the moment and therefore will not implement it.
        //    // If you write the code for exporting images I would be pleased to publish it in a future release
        //    // of PDFsharp.
        //}


    }
}