public IEnumerable <StockAdvice> ReadStockAdvice(FileInfo file)
{
var stockAdvices = new List <StockAdvice>();
var reader = new iText.Kernel.Pdf.PdfReader(file);
var doc = new iText.Kernel.Pdf.PdfDocument(reader);
var pageCount = doc.GetNumberOfPages();
if (pageCount > 0)
{
for (int pageNum = 1; pageNum < pageCount; pageNum++)
{
var page = doc.GetPage(pageNum);
var pageData = page.GetContentBytes();
string pageContent = Encoding.UTF8.GetString(pageData);
var folder = file.Directory;
var fileName = Path.Combine(folder.FullName, file.Name + "_Page_" + pageNum + ".txt");
WritePageContentToFile(fileName, pageContent);
}
}
doc.Close();
reader.Close();
return(stockAdvices);
}
/// <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);
}
public override BookatHome GetPocoBook(string filepath)
{
iText.Kernel.Pdf.PdfReader reader = null;
iText.Kernel.Pdf.PdfDocument pDoc = null;
try
{
if (File.Exists(filepath))
{
reader = new iText.Kernel.Pdf.PdfReader(filepath);
pDoc = new iText.Kernel.Pdf.PdfDocument(reader);
int nPages = pDoc.GetNumberOfPages();
int maxsearch = nPages < 15 ? nPages : 10;
for (int i = 1; i <= maxsearch; i++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string currentText = PdfTextExtractor.GetTextFromPage(pDoc.GetPage(i), strategy);
currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
if (currentText.ToLower().Contains("isbn", System.StringComparison.InvariantCulture))
{
string pattern = @"ISBN(-1(?:(0)|3))?:?\x20(\s)*[0-9]+[- ][0-9]+[- ][0-9]+[- ][0-9]*[- ]*[xX0-9]";
Match m = Regex.Match(currentText.Replace(":", "").Replace("-", " "), pattern);
if (m.Success)
{
PocoBook retBook = base.GetPocoBook(filepath) as PocoBook;
retBook.Isbnsearch = m.Value;
return(retBook);
}
}
}
reader.Close();
}
}
catch (IOException)
{
return(new PocoBook(filepath));
}
finally
{
((IDisposable)reader)?.Dispose();
((IDisposable)pDoc)?.Dispose();
}
return(base.GetPocoBook(filepath));
}