← back to articles

❯ cat itextsharp-parsepdf.md

Itextsharp ParsePdf

1 min readtr#C##iTextSharp#ParsePdf
public string ParsePdf(string fileName)
{
    string text = string.Empty;

    PdfReader reader = new PdfReader(fileName);
    byte[] streanBytes = reader.GetPageContent(1);
    PRTokeniser tokenizer = new PRTokeniser(streanBytes);

    while (tokenizer.NextToken())

        if (tokenizer.TokenType == PRTokeniser.TK_STRING)
        {
            text += tokenizer.StringValue;
        }
    return text;
}