/// <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 static bool PageContainsImages(string filename, int pageNumber)
{
using (var reader = new PdfReader(filename))
{
var 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 PDF file.</summary>
public static Dictionary <string, System.Drawing.Image> ExtractImages(string filename)
{
var images = new Dictionary <string, System.Drawing.Image>();
using (var reader = new PdfReader(filename))
{
#region Trash
//FileStream fos = new FileStream(@"C:\PDFA\Meta.txt",FileMode.Create);
////FileOutputStream fos = new FileOutputStream(dest);
//byte[] b = reader.Metadata;
//fos.Write(b, 0, b.Length);
//fos.Flush();
//fos.Close();
//XmlDocument doc = new XmlDocument();
//MemoryStream ms = new MemoryStream(b);
//doc.Load(ms);
//XmlNode node = doc.DocumentElement;
//for (int i = 0; i < node.InnerXml.Length; i++)
//{
// string val = node.InnerXml[i].ToString();
//}
#endregion
try
{
var parser = new PdfReaderContentParser(reader);
ImageRenderListener listener = null;
for (var i = 1; i <= reader.NumberOfPages; i++)
{
parser.ProcessContent(i, (listener = new ImageRenderListener()));
var index = 1;
if (listener.Images.Count > 0)
{
Console.WriteLine("Found {0} images on page {1}.", listener.Images.Count, i);
foreach (var pair in listener.Images)
{
images.Add(string.Format("{0}{1}", System.IO.Path.GetFileNameWithoutExtension(filename), i.ToString()), pair.Key);//DS
index++;
}
}
}
}
catch (Exception ex)
{
throw ex;
}
return(images);
}
}
/// <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 static 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}",
System.IO.Path.GetFileNameWithoutExtension(filename), pageNumber.ToString("D4"), index.ToString("D4"), pair.Value), pair.Key);
index++;
}
}
return(images);
}
