Link Search Menu Expand Document

Extraction From Complex Borderless Tables - C#

PDF Extractor SDK sample in C# demonstrating ‘Extraction From Complex Borderless Tables’

Program.cs
using Bytescout.PDFExtractor;
using System;
using System.Diagnostics;

namespace ConsoleApplication1
{
    class Program
    {
        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);
        }
    }
}

Download Source Code (.zip)

Return to the previous page Explore PDF Extractor SDK


Copyright © 2016 - 2021 ByteScout