I have a PDF file in my System drive. I want to write a program in C# using iTextSharp to search for a particular word in that PDF.
Say I want to search "StackOverFlow": If the PDF contains the Word "StackOverFlow", it should return true, else it should return false.
What I have tried till now is:
public string ReadPdfFile(string fileName)
{
StringBuilder text = new StringBuilder();
if (File.Exists(fileName))
{
PdfReader pdfReader = new PdfReader(fileName);
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string currentText = "2154/MUM/2012 A";// PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
text.Append(currentText);
}
pdfReader.Close();
}
return text.ToString();
}
The following method works fine. It gives the list of pages in which the text is found.
public List<int> ReadPdfFile(string fileName, String searthText)
{
List<int> pages = new List<int>();
if (File.Exists(fileName))
{
PdfReader pdfReader = new PdfReader(fileName);
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string currentPageText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
if (currentPageText.Contains(searthText))
{
pages.Add(page);
}
}
pdfReader.Close();
}
return pages;
}