I am trying to read the contents from one of my PDF which is a multi language document . I tried with PDF Extractor as well as with TextAbsorber both but it’s giving an error “Index was outside the bounds of the array” at line “extractor.ExtractText(Encoding.ASCII)”. Please find the attached document and below code which i used to extract the pdf content :
private static string GetPdfFileContents(string fileName)
{
PdfExtractor extractor = new PdfExtractor();
//bind PDF file with the extractor object
extractor.BindPdf(fileName);
return GetPdfFileContents(extractor);
}
private static string GetPdfFileContents(PdfExtractor extractor)
{
string contents = string.Empty;
string tempPath = Path.GetDirectoryName(Assembly.GetExecutingAssembly().Location) + @"/Temp";
string outFilePath = tempPath + @"/temptOut.txt";
if (!Directory.Exists(tempPath))
{
Directory.CreateDirectory(tempPath);
}
//extract all text from the PDF
extractor.ExtractText(Encoding.ASCII);
//save extracted text in a text file
extractor.GetText(outFilePath);
contents = System.IO.File.ReadAllText(outFilePath);
System.IO.File.Delete(outFilePath);
return contents;
}