[andyh2000]

Originally Posted by Cactus Chef

...

I do wish they were CBZ rather than PDF. Oh well.

I had some PDFs that were just collections of images and I wanted to have them in a different format so I whipped up a small C# .NET application to extract the images. It assumes that the PDF just consists of a collection of embedded JPG images (and some small miscellaneous stuff it ignores) and saves them out to individual files. Then you could add them to a new CBZ file.

using iText.Kernel.Exceptions;
using iText.Kernel.Pdf;

PdfDocument pdfDoc = new(new PdfReader("../../../pdfs/test.pdf"));
PdfObject obj;
List<int> streamLengths = new();
int imgNum = 0;
for (int i = 1; i <= pdfDoc.GetNumberOfPdfObjects(); i++)
{
    obj = pdfDoc.GetPdfObject(i);
    if (obj != null && obj.IsStream())
    {
        byte[] b;
        try
        {
            b = ((PdfStream)obj).GetBytes();
        }
        catch (PdfException)
        {
            b = ((PdfStream)obj).GetBytes(false);
        }
        if (b.Length > 2048 )
        {
            MemoryStream fos = new(b);
            string pageNum = ("0000" + imgNum++)[^4..];
            FileStream file = new($"../../../images/{pageNum}.jpg", FileMode.Create, System.IO.FileAccess.Write);
            fos.WriteTo(file);

            streamLengths.Add(b.Length);
            fos.Close();
            file.Close();
        }
    }
}
pdfDoc.Close();