/// <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);
var listener = new ImageRenderListener();
parser.ProcessContent(pageNumber, listener);
return(listener.Images.Count > 0);
}
}
/// <summary>Extrai todas as imagens de um arquivo PDF.</summary>
public string ExtractImage(string filePath, string language)
{
var tesseract = new OCR()
{
Language = language
};
var imagePath = String.Empty;
var imageText = String.Empty;
using (var reader = new PdfReader(filePath))
{
var parser = new PdfReaderContentParser(reader);
var listener = new ImageRenderListener();
for (var index = 1; index <= reader.NumberOfPages; index++)
{
parser.ProcessContent(index, listener);
if (listener.Images.Count > 0)
{
for (int count = 0; count < listener.Images.Count; count++)
{
imagePath = System.IO.Path.GetFullPath(AppDomain.CurrentDomain.BaseDirectory) + "temp.png";
tesseract.ImagePath = imagePath;
imageText += tesseract.FromImage();
}
}
}
if (!String.IsNullOrWhiteSpace(imagePath))
{
File.Delete(imagePath);
}
return(imageText);
}
}
