Java Requires Chilkat v11.7.0+

Get the Text Block Below a PDF Caption

See more PDF Text Extraction Examples

Demonstrates the "label" option with labelValue "below", which captures the block of text directly under a caption such as "Ship To", ending at the next gap or heading. Combined with layout "lines", the lines of an address block are kept separate. Chilkat2 Java

import com.chilkatsoft.chilkat2.ChilkatException;
import com.chilkatsoft.chilkat2.JsonObject;
import com.chilkatsoft.chilkat2.Pdf;

public class ChilkatExample {

    public static void main(String[] args) {
        // This example requires the Chilkat API to have been previously unlocked.
        // See Global Unlock Sample for sample code.

        // The packing slip used in this example is available at packing_slip.pdf

        Pdf pdf = new Pdf();
        try {
            pdf.loadFile("qa_data/pdf/packing_slip.pdf");
        } catch (ChilkatException e) {
            System.out.println(e.getLastErrorText());
            return;
        }

        JsonObject json = new JsonObject();
        JsonObject jsonOut = new JsonObject();

        // The packing slip has the captions "Bill To" and "Ship To" side by side,
        // each with an address block below it.
        json.updateString("label", "Ship To");

        // "below" means the value is the block of text directly under the label.
        json.updateString("labelValue", "below");

        // With the default "flow" layout the lines of the block would be joined into one paragraph.
        // "lines" keeps each line of the address on its own line.
        json.updateString("layout", "lines");

        try {
            pdf.extractText("text", json, jsonOut);
        } catch (ChilkatException e) {
            System.out.println(e.getLastErrorText());
            return;
        }

        System.out.println("Ship To:");
        System.out.println(jsonOut.stringOf("text"));
        System.out.println("");

        json.updateString("label", "Bill To");
        try {
            pdf.extractText("text", json, jsonOut);
        } catch (ChilkatException e) {
            System.out.println(e.getLastErrorText());
            return;
        }

        System.out.println("Bill To:");
        System.out.println(jsonOut.stringOf("text"));
        System.out.println("");

        // A caption over a short paragraph works the same way.  Here the flow layout is better,
        // because the two lines are one piece of text.
        json.updateString("label", "Special Instructions");
        json.updateString("layout", "flow");
        try {
            pdf.extractText("text", json, jsonOut);
        } catch (ChilkatException e) {
            System.out.println(e.getLastErrorText());
            return;
        }

        System.out.println("Special Instructions:");
        System.out.println(jsonOut.stringOf("text"));

        // Sample output:

        // Ship To:
        // Frank Delgado
        // c/o Harbor Pet Boarding
        // 9 Ferry Lane
        // Portside, WA 98001
        //
        // Bill To:
        // Frank Delgado
        // Apartment 3B
        // 41 Mill Street
        // Portside, WA 98000
        //
        // Special Instructions:
        // Leave the carton with the boarding office if no one answers. Do not leave it outside; the cat tree is not packed for rain.
    }
}