Dart 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. Dart

import 'package:chilkat/chilkat.dart';

void main() {
  // 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

  final pdf = CkPdf();
  try {
    pdf.loadFile('qa_data/pdf/long_report.pdf');
  } on ChilkatException catch (e) {
    print(e.lastErrorText);
    return;
  }

  print('Number of pages: ${pdf.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.
  final json = CkJsonObject();
  final sbText = CkStringBuilder();
  final jsonOut = CkJsonObject();

  try {
    pdf.extractTextSb('text', json, sbText, jsonOut);
  } on ChilkatException catch (e) {
    print(e.lastErrorText);
    return;
  }

  print('Extracted ${sbText.length} characters.');

  // Save the text to a file.
  try {
    sbText.writeFile('qa_output/long_report.txt', 'utf-8', false);
  } on ChilkatException catch (e) {
    print(e.lastErrorText);
    return;
  }

  // The JSON output does not contain the text, but it still has the quality report.
  print('Quality: ${jsonOut.stringOf('quality.rating')}');
  print('Pages with no text (need OCR): [${jsonOut.stringOf('quality.pagesNeedingOcr')}]');

  // Sample output:

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