Java Requires Chilkat v11.7.0+

Extract the Values of PDF Form Fields

See more PDF Text Extraction Examples

Demonstrates the "formFields" filter. The values of AcroForm fields (text fields, choices, check boxes) are not part of the page's text and are left out by default; "include" places each value at its field's position in the reading order, where a label capture can pick it up. Java

import com.chilkatsoft.*;

public class ChilkatExample {

  static {
    try {
        System.loadLibrary("chilkat");
    } catch (UnsatisfiedLinkError e) {
      System.err.println("Native code library failed to load.\n" + e);
      System.exit(1);
    }
  }

  public static void main(String argv[])
  {
    boolean success = false;

    //  This example requires the Chilkat API to have been previously unlocked.
    //  See Global Unlock Sample for sample code.

    //  The filled-in form used in this example is available at filled_form.pdf

    CkPdf pdf = new CkPdf();
    success = pdf.LoadFile("qa_data/pdf/filled_form.pdf");
    if (success == false) {
        System.out.println(pdf.lastErrorText());
        return;
        }

    CkJsonObject json = new CkJsonObject();
    CkJsonObject jsonOut = new CkJsonObject();

    //  By default only the page's own text is returned: the captions, without the values typed into the fields.
    json.UpdateString("layout","lines");
    success = pdf.ExtractText("text",json,jsonOut);
    if (success == false) {
        System.out.println(pdf.lastErrorText());
        return;
        }

    System.out.println("---- default ----");
    System.out.println(jsonOut.stringOf("text"));

    //  With formFields included, each field's value appears where the field is on the page.
    //  A checked check box appears as [x]; an unchecked one has no value.
    json.UpdateString("formFields","include");
    success = pdf.ExtractText("text",json,jsonOut);
    if (success == false) {
        System.out.println(pdf.lastErrorText());
        return;
        }

    System.out.println("---- formFields: include ----");
    System.out.println(jsonOut.stringOf("text"));

    //  A field value can be captured by the caption beside it, as for any other text.
    json.UpdateString("label","Email");
    success = pdf.ExtractText("text",json,jsonOut);
    if (success == false) {
        System.out.println(pdf.lastErrorText());
        return;
        }

    System.out.println("Email: " + jsonOut.stringOf("text"));

    //  Sample output:

    //  ---- default ----
    //  Membership Application
    //  Name:
    //  Email:
    //  Phone:
    //  Newsletter: Yes, send me the monthly newsletter
    //  Volunteer: I am willing to volunteer
    //  ---- formFields: include ----
    //  Membership Application
    //  Name: Dana Whitfield
    //  Email: dana.whitfield@example.com
    //  Phone: 555-0142
    //  Newsletter: [x] Yes, send me the monthly newsletter
    //  Volunteer: I am willing to volunteer
    //  Email: dana.whitfield@example.com
  }
}