Extract Table From PDF

extractDataFromPdf.js

function test() {
  const data = extractDataFromPdf('1jVppnsxpiK56RY7vVFMkTa1_GV8SCWxo');
  console.log(data);
}

function extractDataFromPdf(pdfId) {
  const PDF_LANGUAGE = 'th';
  const pdfFile = DriveApp.getFileById(pdfId);
  const { id } = Drive.Files.insert(
    {
      title: pdfFile.getName().replace(/\.pdf$/, ''),
      mimeType: pdfFile.getMimeType() || 'application/pdf',
    },
    pdfFile.getBlob(),
    {
      ocr: true,
      ocrLanguage: PDF_LANGUAGE,
      fields: 'id',
    }
  );
  const document = DocumentApp.openById(id);
  const data = [];
  const body = document.getBody();
  const table = body.getTables().pop();
  const numberOfRow = table.getNumRows();
  for (let i = 0; i < numberOfRow; i++) {
    const rowData = [];
    const row = table.getRow(i);
    const numberOfCell = row.getNumCells();

    for (let ii = 0; ii < numberOfCell; ii++) {
      const cell = row.getCell(ii);
      rowData.push(cell.getText());
    }

    data.push(rowData);
  }
  DriveApp.getFileById(id).setTrashed(true);
  return data;
}