/// <summary>
/// Checks whether a specified page of a PDF file contains images.
/// </summary>
/// <returns>True if the page contains at least one image; false otherwise.</returns>
public bool PageContainsImages(string filename, int pageNumber)
{
PdfReader reader = new PdfReader(filename);
PdfReaderContentParser parser = new PdfReaderContentParser(reader);
ImageRenderListener listener = null;
parser.ProcessContent(pageNumber, (listener = new ImageRenderListener()));
return listener.Images.Count > 0;
}
/// <summary>
/// Extracts all images (of types that iTextSharp knows how to decode)
/// from a specified page of a PDF file.
/// </summary>
/// <returns>Returns a generic <see cref="Dictionary<string, System.Drawing.Image>",
/// where the key is a suggested file name, in the format: PDF filename without extension,
/// page number and image index in the page./></returns>
public Dictionary<string, System.Drawing.Image> ExtractImages(string filename, int pageNumber)
{
Dictionary<string, System.Drawing.Image> images = new Dictionary<string, System.Drawing.Image>();
PdfReader reader = new PdfReader(filename);
PdfReaderContentParser parser = new PdfReaderContentParser(reader);
ImageRenderListener listener = null;
parser.ProcessContent(pageNumber, (listener = new ImageRenderListener()));
int index = 1;
if (listener.Images.Count > 0)
{
//Console.WriteLine("Found {0} images on page {1}.", listener.Images.Count, pageNumber);
foreach (KeyValuePair<System.Drawing.Image, string> pair in listener.Images)
{
images.Add(string.Format("{0}_Page_{1}_Image_{2}{3 Path.GetFileNameWithoutExtension(filename)", pageNumber.ToString("D4"), index.ToString("D4"), pair.Value), pair.Key);
index++;
}
}
return images;
}
