void LoadDocument()
{
MemoryStream memory = new MemoryStream(convertDocToByteArray(@"D:\Code Project\Subrip\Document\HSK Book.pdf"));
BinaryReader BRreader = new BinaryReader(memory);
StringBuilder text = new StringBuilder();
iText.Kernel.Pdf.PdfReader iTextReader = new iText.Kernel.Pdf.PdfReader(memory);
iText.Kernel.Pdf.PdfDocument pdfDoc = new iText.Kernel.Pdf.PdfDocument(iTextReader);
int numberofpages = pdfDoc.GetNumberOfPages();
List <Tuple <int, string> > Contents = new List <Tuple <int, string> >();
for (int page = 1; page <= numberofpages; page++)
{
iText.Kernel.Pdf.Canvas.Parser.Listener.ITextExtractionStrategy strategy = new iText.Kernel.Pdf.Canvas.Parser.Listener.LocationTextExtractionStrategy();
string currentText = iText.Kernel.Pdf.Canvas.Parser.PdfTextExtractor.GetTextFromPage(pdfDoc.GetPage(page), strategy);
currentText = Encoding.UTF8.GetString(UTF8Encoding.Convert(
Encoding.UTF8, Encoding.UTF8, Encoding.UTF8.GetBytes(currentText)));
text.Append(currentText);
Tuple <int, string> tuple = new Tuple <int, string>(page, currentText);
Contents.Add(tuple);
}
document = Contents;
}
/// <summary>
/// Reads PDF file by a given path.
/// </summary>
/// <param name="path">The path to the file</param>
/// <param name="pageCount">The number of pages to read (0=all, 1 by default) </param>
/// <returns></returns>
public static DocumentTree PdfToText(string path, int pageCount = 1)
{
var pages = new DocumentTree();
using (iText.Kernel.Pdf.PdfReader reader = new iText.Kernel.Pdf.PdfReader(path))
{
using (iText.Kernel.Pdf.PdfDocument pdfDocument = new iText.Kernel.Pdf.PdfDocument(reader))
{
var strategy = new iText.Kernel.Pdf.Canvas.Parser.Listener.LocationTextExtractionStrategy();
// set up pages to read
int pagesToRead = 1;
if (pageCount > 0)
{
pagesToRead = pageCount;
}
if (pagesToRead > pdfDocument.GetNumberOfPages() || pageCount == 0)
{
pagesToRead = pdfDocument.GetNumberOfPages();
}
// for each page to read...
for (int i = 1; i <= pagesToRead; ++i)
{
// get the page and save it
var page = pdfDocument.GetPage(i);
var txt = iText.Kernel.Pdf.Canvas.Parser.PdfTextExtractor.GetTextFromPage(page, strategy);
pages.Add(txt);
}
pdfDocument.Close();
reader.Close();
}
}
return(pages);
}
