public static void ExtractTextFromPDF()
{
// Read a local PDF file in the disk
PdfDocument document = PdfReader.Open("file1.pdf", PdfDocumentOpenMode.ReadOnly);
// Extract text from whole PDF document, contains every PDF pages
string allText = PdfTextExtractor.GetText(document);
Console.WriteLine(allText);
// Convert text from PDF to a txt file
File.WriteAllText("Output.txt", allText);
// Get total page count
int total = document.Pages.Count;
foreach (PdfPage page in document.Pages)
{
// Extract text from each page of PDF
string text = PdfTextExtractor.GetText(page);
Console.WriteLine(text);
}
}
static void Main(string[] args)
{
ITextParse.ExtractText("employe-1.pdf", "iparse.txt");
//using (PdfReader reader = new PdfReader("letter.pdf")) //Index was outside the bounds of the array.
//using (PdfReader reader = new PdfReader("employe-1.pdf")) //ok
//using (PdfReader reader = new PdfReader("feuille_de_paie.pdf")) //Rebuild failed: trailer not found.; Original message: PDF startxref not found.
using (iTextSharp.text.pdf.PdfReader reader = new iTextSharp.text.pdf.PdfReader("modele-bulletin-de-salaire.pdf")) //ok
{
StringBuilder text = new StringBuilder();
for (int page = 1; page <= reader.NumberOfPages; page++)
{
iTextSharp.text.pdf.parser.ITextExtractionStrategy strategy = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
//ITextExtractionStrategy strategy = new LocationTextExtractionStrategy();
string currentText = iTextSharp.text.pdf.parser.PdfTextExtractor.GetTextFromPage(reader, page, strategy);
currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
text.Append(currentText);
}
System.IO.StreamWriter file = new System.IO.StreamWriter("itextsharp.txt");
file.WriteLine(text);
file.Close();
//return text.ToString();
}
//PdfSharp
using (var _document = PdfReader.Open("letter.pdf", PdfDocumentOpenMode.ReadOnly)) //ok
//using (var _document = PdfReader.Open("employe-1.pdf", PdfDocumentOpenMode.ReadOnly)) //ok
//using (var _document = PdfReader.Open("feuille_de_paie.pdf", PdfDocumentOpenMode.ReadOnly)) //Non-negative number required.
//using (var _document = PdfReader.Open("modele-bulletin-de-salaire.pdf", PdfDocumentOpenMode.ReadOnly)) //ok
{
System.IO.StreamWriter file = new System.IO.StreamWriter("pdfsharp.txt");
foreach (PdfPage page in _document.Pages)
{
var text = ExtractText(page);
foreach (string s in text)
{
file.Write(s);
}
}
file.Close();
}
//iTextSharp too
PDFParser parser = new PDFParser();
//parser.ExtractText("letter.pdf", "pdfparser.txt"); //error
parser.ExtractText("employe-1.pdf", "pdfparser.txt"); //ok
//parser.ExtractText("feuille_de_paie.pdf", "pdfparser.txt"); //error
//parser.ExtractText("modele-bulletin-de-salaire.pdf", "pdfparser.txt"); //error
//PdfSharp
//string text2 = PdfTextExtractor.GetText("letter.pdf"); //ok
//string text2 = PdfTextExtractor.GetText("employe-1.pdf"); //ok
//string text2 = PdfTextExtractor.GetText("feuille_de_paie.pdf"); //Non-negative number required.
string text2 = PdfTextExtractor.GetText("modele-bulletin-de-salaire.pdf"); //ok
System.IO.StreamWriter file2 = new System.IO.StreamWriter("PdfTextExtractor.txt");
file2.Write(text2);
file2.Close();
}