Java Requires Chilkat v11.7.0+

Search for Text in a PDF

See more PDF Text Extraction Examples

Demonstrates the "search" operation, which finds every occurrence of a string in a PDF and returns each match with its page number and the text around it. Matching ignores case unless caseSensitive is true. 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 three-page PDF used in this example is available at search_context.pdf

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

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

        // The string to find.
        json.updateString("query", "chilkat");

        // The number of characters returned before and after each match.  The default is 40.
        json.updateInt("context", 30);

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

        // "count" is the number of matches.  Each match has the page, the matched text as it appears
        // in the PDF, and the text before and after it.
        System.out.println("Matches: " + jsonOut.intOf("count"));

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

        // The search ignores case by default.  Set caseSensitive to find only the exact spelling.
        json.updateBool("caseSensitive", true);
        json.updateString("query", "Chilkat");
        try {
            pdf.extractText("search", json, jsonOut);
        } catch (ChilkatException e) {
            System.out.println(e.getLastErrorText());
            return;
        }

        System.out.println("Case-sensitive matches for Chilkat: " + jsonOut.intOf("count"));

        // Sample output:

        // Matches: 5
        // page 1: ...[Chilkat] River Field Notes The Chilkat...
        // page 1: ...Chilkat River Field Notes The [Chilkat] River runs for about fifty mi...
        // page 2: ...DAY ONE: UPPER [CHILKAT] FLATS Clear and cold, minus e...
        // page 2: ...he river is sometimes spelled [chilkat] in older records, and the val...
        // page 3: ...y because the fish run on the [Chilkat] was thinning. Two tagged bird...
        // Case-sensitive matches for Chilkat: 3
    }
}