Get properties from a PDF file


/ Published in: C#
Save to your folder(s)

Provide the PDF document content as a string and it will return the data content of properties like Title or Subject.


Copy this code and paste it in your HTML
  1. private static string GetPropertyValueEx(string pdfData, string propertyName)
  2. {
  3. var result = "";
  4.  
  5. var propertyNameLength = propertyName.Length + 3;
  6. var leadLength = 4;
  7.  
  8. var r2 = new Regex(string.Format("/{0} <[A-Za-z0-9]*>", propertyName));
  9. var m = r2.Match(pdfData);
  10. if (m.Success)
  11. {
  12. //System.Diagnostics.Debug.WriteLine(m.Index);
  13. var valueRaw = m.Value.Substring(propertyNameLength, m.Value.Length - propertyNameLength - 1);
  14. for (int i = leadLength; i < valueRaw.Length; i = i + 4)
  15. {
  16. var hexVal = valueRaw.Substring(i, 4);
  17. var num = (Convert.ToUInt32(hexVal, 16));
  18. result += (char)num;
  19. }
  20. }
  21.  
  22. return result;
  23. }

Report this snippet


Comments

RSS Icon Subscribe to comments

You need to login to post a comment.