Java Requires Chilkat v11.7.0+

Extract PDF Text to a StringBuilder and Save to a File

See more PDF Text Extraction Examples

Demonstrates ExtractTextSb, which writes the extracted text to a StringBuilder instead of returning it as a JSON string. Use it for large documents. The JSON output still receives the quality report. 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 PDF used in this example is available at long_report.pdf

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

    System.out.println("Number of pages: " + pdf.get_NumPages());

    //  ExtractTextSb takes the same operation and options as ExtractText, but the text
    //  goes to a StringBuilder.  This avoids building a very large JSON string for
    //  documents with many pages.
    CkJsonObject json = new CkJsonObject();
    CkStringBuilder sbText = new CkStringBuilder();
    CkJsonObject jsonOut = new CkJsonObject();

    success = pdf.ExtractTextSb("text",json,sbText,jsonOut);
    if (success == false) {
        System.out.println(pdf.lastErrorText());
        return;
        }

    System.out.println("Extracted " + sbText.get_Length() + " characters.");

    //  Save the text to a file.
    success = sbText.WriteFile("qa_output/long_report.txt","utf-8",false);
    if (success == false) {
        System.out.println(sbText.lastErrorText());
        return;
        }

    //  The JSON output does not contain the text, but it still has the quality report.
    System.out.println("Quality: " + jsonOut.stringOf("quality.rating"));
    System.out.println("Pages with no text (need OCR): [" + jsonOut.stringOf("quality.pagesNeedingOcr") + "]");

    //  Sample output:

    //  Number of pages: 3
    //  Extracted 4522 characters.
    //  Quality: good
    //  Pages with no text (need OCR): []
  }
}