static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.XLSExtractor instance
XLSExtractor extractor = new XLSExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile("ProductsMonthWise.pdf");
// Uncomment this line if you need all pages converted into a single worksheet:
//extractor.PageToWorksheet = false;
// Set the output format to XLSX
extractor.OutputFormat = SpreadseetOutputFormat.XLSX;
// No of Pages
var pageCount = extractor.GetPageCount();
for (int i = 0; i < pageCount; i++)
{
string outputName = $"page_{i + 1}.xlsx";
// Save page to spreadsheet file
extractor.SavePageToXLSFile(i, outputName);
Console.WriteLine("'{0}' Created", outputName);
}
// Cleanup
extractor.Dispose();
Console.ReadLine();
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.XLSExtractor instance
XLSExtractor extractor = new XLSExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
File.Delete("output.xls");
// Load sample PDF document
extractor.LoadDocumentFromFile("sample3.pdf");
// Uncomment this line if you need all pages converted into a single worksheet:
//extractor.PageToWorksheet = false;
// Set the output format to XLS
extractor.OutputFormat = SpreadseetOutputFormat.XLS;
// Save the spreadsheet to file
extractor.SaveToXLSFile("output.xls");
// Cleanup
extractor.Dispose();
// Open result document in default associated application (for demo purpose)
ProcessStartInfo processStartInfo = new ProcessStartInfo("output.xls");
processStartInfo.UseShellExecute = true;
Process.Start(processStartInfo);
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.XLSExtractor instance
XLSExtractor extractor = new XLSExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
File.Delete("output.xls");
// Load sample PDF document
extractor.LoadDocumentFromFile("sample3.pdf");
// Uncomment this line if you need all pages converted into a single worksheet:
//extractor.PageToWorksheet = false;
// Splits all text into words
extractor.DetectNewColumnBySpacesRatio = 0.1f;
// Add the following params to get clean data with word nodes only:
extractor.PreserveFormattingOnTextExtraction = false; // Get rid of empty nodes
extractor.OutputFormat = SpreadseetOutputFormat.XLS; // Set the output format to XLS
// Save the spreadsheet to file
extractor.SaveToXLSFile("output.xls");
// Cleanup
extractor.Dispose();
// Open result document in default associated application (for demo purpose)
ProcessStartInfo processStartInfo = new ProcessStartInfo("output.xls");
processStartInfo.UseShellExecute = true;
Process.Start(processStartInfo);
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.XLSExtractor instance
XLSExtractor extractor = new XLSExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
File.Delete("output.xls");
// Load sample PDF document
extractor.LoadDocumentFromFile("sample3.pdf");
// Uncomment this line if you need all pages converted into a single worksheet:
//extractor.PageToWorksheet = false;
// Save the spreadsheet to file
extractor.SaveToXLSFile("output.xls");
// Cleanup
extractor.Dispose();
// Open the spreadsheet in default associated application
Process.Start("output.xls");
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.XLSExtractor instance
XLSExtractor extractor = new XLSExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
File.Delete("output.xls");
// Load sample PDF document
extractor.LoadDocumentFromFile("sample3.pdf");
// Save the spreadsheet to file
extractor.SaveToXLSFile("output.xls");
// Open the spreadsheet in default associated application
Process.Start("output.xls");
}
private void tsbExportToXLSX_Click(object sender, EventArgs e)
{
// Get selections from viewer
RectangleF[] selections = pdfViewerControl1.SelectionInPoints;
string outputFile = @".\result.xlsx";
using (XLSExtractor xlsExtractor = new XLSExtractor("demo", "demo"))
{
// Load document into extractor
xlsExtractor.LoadDocumentFromFile(pdfViewerControl1.InputFile);
xlsExtractor.OCRMode = OCRMode.Auto;
xlsExtractor.OCRResolution = 300;
xlsExtractor.OCRLanguage = "eng";
xlsExtractor.OCRLanguageDataFolder = @"c:\Program Files\Bytescout PDF Extractor SDK\ocrdata_best\";
xlsExtractor.OutputFormat = SpreadseetOutputFormat.XLSX;
xlsExtractor.RichTextFormatting = false;
// There are double spaces between some words in your document.
// To avoid such words break column structure increase the space ratio to 2.
xlsExtractor.DetectNewColumnBySpacesRatio = 2;
// FYI, removing horizontal lines may increase the text recognition quality in some cases
//xlsExtractor.OCRImagePreprocessingFilters.AddHorizontalLinesRemover();
// Another filter able to improve the recognition
//xlsExtractor.OCRImagePreprocessingFilters.AddGammaCorrection();
// If selection exists set the extraction area.
// Overwise it will extract the whole page.
if (selections.Length > 0)
{
xlsExtractor.SetExtractionArea(selections[0]);
}
// Save extraction results to XLSX files
xlsExtractor.SavePageToXLSFile(pdfViewerControl1.CurrentPageIndex, outputFile);
}
Process.Start(outputFile);
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.XLSExtractor instance
XLSExtractor extractor = new XLSExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
File.Delete("output.xls");
// Document Password Can be set in two ways
// 1. Using Property
// 2. Using Events
// 1. Handle document password using Property
// extractor.Password = "******"
// 2. Handle document password using Event
extractor.PasswordRequired += new System.EventHandler(extractor_PasswordRequired);
// Load sample PDF document
extractor.LoadDocumentFromFile(@".\encrypted (password is 'password').pdf");
// Set the output format to XLS
extractor.OutputFormat = SpreadseetOutputFormat.XLS;
// Save the spreadsheet to file
extractor.SaveToXLSFile("output.xls");
// Cleanup
extractor.Dispose();
// Open result document in default associated application (for demo purpose)
ProcessStartInfo processStartInfo = new ProcessStartInfo("output.xls");
processStartInfo.UseShellExecute = true;
Process.Start(processStartInfo);
}
public void Extract()
{
string xlsFile = string.Empty;
string _pdfFile = string.Empty;
var rootFolder = FileLocation.CreateBaseFolderIsfNotExists();
var files = Directory.GetFiles(rootFolder + ConfigurationManager.AppSettings["PdfFileLocation"]).Where(x => x.EndsWith(".pdf")).ToArray();
if (files.Length == 0)
{
Logger.Info("No Pdf File Found");
return;
}
var extractor = new XLSExtractor();
FileInfo info = null;
extractor.RegistrationName = "NOT - FOR - RESALE - SINGLE - ENDUSER - ONLY - NO - PRIVATE - SUPPORT - [email protected]";
extractor.RegistrationKey = "10C9-AC43-B36E-997C-CCCF-BDEB-C9D";
_pdfFile = files[0];
Logger.Info("Total file Loaded: " + files.Length);
Logger.Info("Pdf file loaded: " + _pdfFile);
extractor.PageDataCaching = PageDataCaching.None;
Logger.Info("Xsl file loaded: " + xlsFile);
extractor.AutoAlignColumnsToHeader = true;
Logger.Info("Pdf file extraction started");
Logger.Info("Loaded file:" + files[0]);
info = new FileInfo(_pdfFile);
xlsFile = FileLocation.GetFilePath(FileLocationEnum.Xls);
xlsFile += info.Name.Split('.')[0] + ".xls";
try
{
extractor.LoadDocumentFromFile(files[0]);
extractor.SaveToXLSFile(xlsFile);
extractor.Reset();
}
catch (PDFExtractorException ex)
{
Logger.Info("PDFExtractorException: " + ex.Message);
}
if (extractor.IsDocumentLoaded)
{
extractor.Dispose();
}
XlsReaderService.ReadXls(xlsFile);
try
{
var destination = FileLocation.GetFilePath(FileLocationEnum.ProcessedPdf);
var fileName = info.Name.Split('.')[0];
info.MoveTo(destination + fileName + ".pdf");
}
catch (IOException ex)
{
Logger.Info("Delete Error: " + ex.Message);
}
}
