0

anybody help me extract the center-aligned lines from a PDF document using itext7 in .Net Core application.

I have written the following extraction code so far, but cannot get the lines that are center aligned. Is there any way, please help

private async Task Extruct()
 {
     _pdfFile = await UploadedFilesService.GetUploadedPdfById(entryId);
     MemoryStream stream = new MemoryStream(_pdfFile);

     using (PdfReader pdfReader = new PdfReader(stream))
     {
         using (PdfDocument pdfDocument = new PdfDocument(pdfReader))
         {
             for (int i = 1; i <= pdfDocument.GetNumberOfPages(); i++)
             {
                 PdfPage page = pdfDocument.GetPage(i);
                
                 string pageText = PdfTextExtractor.GetTextFromPage(page);

                 string[] lineTexts = pageText.Split('\n');
                 foreach (string lineText in lineTexts)
                 {
                     float lineWidth = lineText.Length;
                     float pageWidth = page.GetPageSize().GetWidth();
                     if ((pageWidth / 2 - lineWidth * 10) > 20)
                     {
                         persons.Add(lineText);
                     }
                 }
             }
             extracted = true;
         }
     }
     this.StateHasChanged();
}

0 Answers0