/// <summary>
/// Extracts all images from a specified page of a PDF file.
/// </summary>
/// <param name="pdf">The PDF stream.</param>
/// <param name="password">The password used to protect the document.</param>
/// <returns>Returns an array of images
/// 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(Stream pdf, string password = "")
{
byte[] pass = null;
iTextSharp.text.pdf.PdfReader pdfReader = null;
var images = new Dictionary <string, System.Drawing.Image>();
try
{
// If no password.
if (String.IsNullOrEmpty(password))
{
pdfReader = new iTextSharp.text.pdf.PdfReader(pdf);
}
else
{
pass = Encoding.Default.GetBytes(password);
pdfReader = new iTextSharp.text.pdf.PdfReader(pdf, pass);
}
// Create the pdf parser.
var parser = new PdfReaderContentParser(pdfReader);
ImageRenderListener listener = null;
for (var i = 1; i <= pdfReader.NumberOfPages; i++)
{
// Parse the pdf stream.
parser.ProcessContent(i, (listener = new ImageRenderListener()));
var index = 1;
// If images exist.
if (listener.Images.Count > 0)
{
// For each image extracted.
foreach (var pair in listener.Images)
{
// Add the image.
images.Add(string.Format("Page_{ 1} Image_{ 2} { 3}", i.ToString("D4"), index.ToString("D4"), pair.Value), pair.Key);
index++;
}
}
}
}
catch (Exception)
{
throw;
}
finally
{
if (pdfReader != null)
{
pdfReader.Close();
}
}
// Return the images.
return(images);
}
/// <summary>
/// Extracts all images from a specified page of a PDF file.
/// </summary>
/// <param name="pdf">The PDF stream.</param>
/// <param name="pageNumber">The page number to look for images.</param>
/// <param name="password">The password used to protect the document.</param>
/// <returns>Returns an array of images
/// 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(Stream pdf, int pageNumber, string password = "")
{
byte[] pass = null;
iTextSharp.text.pdf.PdfReader pdfReader = null;
Dictionary <string, System.Drawing.Image> images = new Dictionary <string, System.Drawing.Image>();
try
{
// If no password.
if (String.IsNullOrEmpty(password))
{
pdfReader = new iTextSharp.text.pdf.PdfReader(pdf);
}
else
{
pass = Encoding.Default.GetBytes(password);
pdfReader = new iTextSharp.text.pdf.PdfReader(pdf, pass);
}
// Create the content reader.
PdfReaderContentParser parser = new PdfReaderContentParser(pdfReader);
ImageRenderListener listener = null;
// Parse the content.
parser.ProcessContent(pageNumber, (listener = new ImageRenderListener()));
int index = 1;
// If images have been found.
if (listener.Images.Count > 0)
{
// Add each image to the list.
foreach (KeyValuePair <System.Drawing.Image, string> pair in listener.Images)
{
// Add the image.
images.Add(string.Format("Page_{ 1} Image_{ 2} { 3}", pageNumber.ToString("D4"), index.ToString("D4"), pair.Value), pair.Key);
index++;
}
}
}
catch (Exception)
{
throw;
}
finally
{
if (pdfReader != null)
{
pdfReader.Close();
}
}
// Return the images.
return(images);
}
/// <summary>
/// Checks whether a specified page of a PDF file contains images.
/// </summary>
/// <param name="pdf">The PDF stream.</param>
/// <param name="pageNumber">The page number to look for images.</param>
/// <param name="password">The password used to protect the document.</param>
/// <returns>True if the page contains at least one image; false otherwise.</returns>
public bool PageContainsImages(Stream pdf, int pageNumber, string password = "")
{
bool result = false;
ImageRenderListener listener = null;
byte[] pass = null;
iTextSharp.text.pdf.PdfReader pdfReader = null;
try
{
// If no password.
if (String.IsNullOrEmpty(password))
{
pdfReader = new iTextSharp.text.pdf.PdfReader(pdf);
}
else
{
pass = Encoding.Default.GetBytes(password);
pdfReader = new iTextSharp.text.pdf.PdfReader(pdf, pass);
}
// Parse the stream.
var parser = new PdfReaderContentParser(pdfReader);
parser.ProcessContent(pageNumber, (listener = new ImageRenderListener()));
result = (listener.Images.Count > 0 ? true : false);
}
catch (Exception)
{
throw;
}
finally
{
if (pdfReader != null)
{
pdfReader.Close();
}
}
return(result);
}
