Java Requires Chilkat v11.7.0+

Get Every Occurrence of a Label in a PDF

See more PDF Text Extraction Examples

Demonstrates the "labelOccurrence" option. When the same label appears more than once (for example "Total:" on each of several receipts), "first" (the default) uses the first occurrence, "all" returns every occurrence with its page, and a number selects one occurrence. 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 PDF used in this example (three receipts, one per page) is available at three_receipts.pdf

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

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

        // Each of the three pages is a receipt with a "Total:" line.
        json.updateString("label", "Total");
        json.updateString("labelValue", "right");

        // By default only the first occurrence (in reading order) is used.
        try {
            pdf.extractText("text", json, jsonOut);
        } catch (ChilkatException e) {
            System.out.println(e.getLastErrorText());
            return;
        }

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

        // labelOccurrence "all" returns every occurrence.  The "text" member holds the values joined
        // by line breaks, and labelMatches has one entry per occurrence with its page.
        json.updateString("labelOccurrence", "all");
        try {
            pdf.extractText("text", json, jsonOut);
        } catch (ChilkatException e) {
            System.out.println(e.getLastErrorText());
            return;
        }

        int i = 0;
        int count_i = jsonOut.sizeOfArray("labelMatches");
        while (i < count_i) {
            jsonOut.setI(i);
            System.out.println("Page " + jsonOut.intOf("labelMatches[i].page") + " total: " + jsonOut.stringOf("labelMatches[i].text"));
            i = i + 1;
        }

        // A number selects one occurrence: 2 is the second.
        json.updateInt("labelOccurrence", 2);
        try {
            pdf.extractText("text", json, jsonOut);
        } catch (ChilkatException e) {
            System.out.println(e.getLastErrorText());
            return;
        }

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

        // The occurrences are counted over the selected pages, so combining "pages" with the label
        // is another way to pick one receipt:
        json.updateString("labelOccurrence", "first");
        json.updateString("pages", "3");
        json.updateString("label", "Receipt No.");
        try {
            pdf.extractText("text", json, jsonOut);
        } catch (ChilkatException e) {
            System.out.println(e.getLastErrorText());
            return;
        }

        System.out.println("Receipt number on page 3: " + jsonOut.stringOf("text"));

        // Sample output:

        // First total: $19.86
        // Page 1 total: $19.86
        // Page 2 total: $17.34
        // Page 3 total: $23.62
        // Second total: $17.34
        // Receipt number on page 3: 1003
    }
}