static void Main(string[] args) { // Create Bytescout.PDFExtractor.CSVExtractor instance CSVExtractor extractor = new CSVExtractor(); extractor.RegistrationName = "demo"; extractor.RegistrationKey = "demo"; // Load sample PDF document extractor.LoadDocumentFromFile("sample3.pdf"); //extractor.CSVSeparatorSymbol = ","; // you can change CSV separator symbol (if needed) from "," symbol to another if needed for non-US locales extractor.SaveCSVToFile("output.csv"); extractor.Dispose(); Console.WriteLine(); Console.WriteLine("Data has been extracted to 'output.csv' file."); Console.WriteLine(); Console.WriteLine("Press any key to continue and open CSV in default CSV viewer (or Excel)..."); Console.ReadKey(); Process.Start("output.csv"); }
static void Main(string[] args) { // Create Bytescout.PDFExtractor.CSVExtractor instance CSVExtractor extractor = new CSVExtractor(); extractor.RegistrationName = "demo"; extractor.RegistrationKey = "demo"; // Load sample PDF document extractor.LoadDocumentFromFile("sample3.pdf"); // you can change CSV separator symbol (if needed) from "," symbol to another if needed for non-US locales //extractor.CSVSeparatorSymbol = ","; // Save extracted CSV data extractor.SaveCSVToFile("output.csv"); // Cleanup extractor.Dispose(); Console.WriteLine(); Console.WriteLine("Data has been extracted to 'output.csv' file."); Console.WriteLine(); Console.WriteLine("Press any key to continue and open CSV in default CSV viewer (or Excel)..."); Console.ReadKey(); // Open result document in default associated application (for demo purpose) ProcessStartInfo processStartInfo = new ProcessStartInfo("output.csv"); processStartInfo.UseShellExecute = true; Process.Start(processStartInfo); }
static void Main(string[] args) { // Create Bytescout.PDFExtractor.CSVExtractor instance CSVExtractor extractor = new CSVExtractor(); extractor.RegistrationName = "demo"; extractor.RegistrationKey = "demo"; // Load sample PDF document extractor.LoadDocumentFromFile("borderless_table.pdf"); // Set extraction columns explicitly. // Coordinates in CustomExtractionColumns must match the left edges of the columns. // To get coordinates in PDF points you can use PDF Multitool application // installed with the SDK. It shows mouse cursor coodinates in PDF points in the toolbar. extractor.CustomExtractionColumns = new double[] { 0, 124.5, 185, 241 }; // Save extracted CSV data extractor.SaveCSVToFile("output.csv"); // Cleanup extractor.Dispose(); Console.WriteLine(); Console.WriteLine("Data has been extracted to 'output.csv' file."); Console.WriteLine(); Console.WriteLine("Press any key to continue and open CSV in default CSV viewer (or Excel)..."); Console.ReadKey(); // Open result document in default associated application (for demo purpose) ProcessStartInfo processStartInfo = new ProcessStartInfo("output.csv"); processStartInfo.UseShellExecute = true; Process.Start(processStartInfo); }
static void Main(string[] args) { // Create Bytescout.PDFExtractor.CSVExtractor instance CSVExtractor extractor = new CSVExtractor(); extractor.RegistrationName = "demo"; extractor.RegistrationKey = "demo"; // Load sample PDF document extractor.LoadDocumentFromFile(@".\SampleGroupDisabilityForm.pdf"); // Set extraction area extractor.SetExtractionArea(new System.Drawing.RectangleF(27F, 324.8F, 554.3F, 358.5F)); // Check whether rows can be grouped extractor.LineGroupingMode = LineGroupingMode.GroupByRows; // Extract results var outputFile = "result.csv"; extractor.SaveCSVToFile(outputFile); // Cleanup extractor.Dispose(); // Open with default associated program ProcessStartInfo processStartInfo = new ProcessStartInfo(outputFile); processStartInfo.UseShellExecute = true; Process.Start(processStartInfo); }
public void Convert(string filename) { // Create Bytescout.PDFExtractor.CSVExtractor instance // Load sample PDF document CsvExtractor.LoadDocumentFromFile(filename); //extractor.CSVSeparatorSymbol = ","; // you can change CSV separator symbol (if needed) from "," symbol to another if needed for non-US locales CsvExtractor.SaveCSVToFile(filename.Replace(".pdf", ".csv")); }
static void Main(string[] args) { //SautinSoft.PdfFocus f = new SautinSoft.PdfFocus(); //f.OpenPdf(@"C:\Users\i.upadhyay\Desktop\AV42104576.pdf"); //if (f.PageCount > 0) //{ // f.ToWord(@"C:\Users\i.upadhyay\Desktop\AV42104576.docx"); // Console.WriteLine("Finised"); // Console.ReadKey(); //} //string fileName = "myfile.ext"; //string path1 = @"mydir"; //string path2 = @"\mydir"; string fullPath; CSVExtractor extractor = new CSVExtractor(); extractor.RegistrationName = "demo"; extractor.RegistrationKey = "demo"; // Load sample PDF document extractor.LoadDocumentFromFile("AV42104576.pdf"); //extractor.CSVSeparatorSymbol = ","; // you can change CSV separator symbol (if needed) from "," symbol to another if needed for non-US locales extractor.SaveCSVToFile("output1.csv"); Console.WriteLine(); Console.WriteLine("Data has been extracted to 'output.csv' file."); Console.WriteLine(); Console.WriteLine("Press any key to continue and open CSV in default CSV viewer (or Excel)..."); Console.ReadKey(); Process.Start("output.csv"); //fullPath = System.IO.Path.GetFullPath(@"C:\Users\i.upadhyay\Desktop\AV42104576.pdf"); //Program n = new Program(); //n.ExportPDFToExcel(fullPath); }
static void Main(string[] args) { // Create Bytescout.PDFExtractor.CSVExtractor instance CSVExtractor extractor = new CSVExtractor(); extractor.RegistrationName = "demo"; extractor.RegistrationKey = "demo"; // Load sample PDF document extractor.LoadDocumentFromFile("sample_ocr.pdf"); // Enable Optical Character Recognition (OCR) // in .Auto mode (SDK automatically checks if needs to use OCR or not) extractor.OCRMode = OCRMode.Auto; // Set the location of OCR language data files extractor.OCRLanguageDataFolder = @"c:\Program Files\Bytescout PDF Extractor SDK\ocrdata_best\"; // Set OCR language extractor.OCRLanguage = "eng"; // "eng" for english, "deu" for German, "fra" for French, "spa" for Spanish etc - according to files in "ocrdata" folder // Find more language files at https://github.com/bytescout/ocrdata // Set PDF document rendering resolution extractor.OCRResolution = 300; // You can also apply various preprocessing filters // to improve the recognition on low-quality scans. // Automatically deskew skewed scans //extractor.OCRImagePreprocessingFilters.AddDeskew(); // Remove vertical or horizontal lines (sometimes helps to avoid OCR engine's page segmentation errors) //extractor.OCRImagePreprocessingFilters.AddVerticalLinesRemover(); //extractor.OCRImagePreprocessingFilters.AddHorizontalLinesRemover(); // Repair broken letters //extractor.OCRImagePreprocessingFilters.AddDilate(); // Remove noise //extractor.OCRImagePreprocessingFilters.AddMedian(); // Apply Gamma Correction //extractor.OCRImagePreprocessingFilters.AddGammaCorrection(); // Add Contrast //extractor.OCRImagePreprocessingFilters.AddContrast(20); // (!) You can use new OCRAnalyser class to find an optimal set of image preprocessing // filters for your specific document. // See "OCR Analyser" example. // Save extracted text to file extractor.SaveCSVToFile("output.csv"); // Cleanup extractor.Dispose(); // Open result document in default associated application (for demo purpose) ProcessStartInfo processStartInfo = new ProcessStartInfo("output.csv"); processStartInfo.UseShellExecute = true; Process.Start(processStartInfo); }