Convert data from PDF invoice to Excel CSV file in C# using PDF Extractor SDK

The sample code below shows how to extract data from PDF to CSV Excel file in C# using Bytescout PDF Extractor SDK.

In these screenshots you can see input PDF invoice and Excel CSV file with data extracted from the invoice.

	Input PDF file
↓
	Output CSV file for Excel

C#

using System;
using System.IO;
using System.Text;
using Bytescout.PDFExtractor;

namespace Example
{
	class Program
	{
		static void Main(string[] args)
		{
			// Create Bytescout.PDFExtractor.TextExtractor instance
			TextExtractor extractor = new TextExtractor();
			extractor.RegistrationName = "demo";
			extractor.RegistrationKey = "demo";

			// Load sample PDF document
			extractor.LoadDocumentFromFile("sample3.pdf");

			// Table dimensions (in points)
			const int tableX = 207;
			const int tableY = 110;
			const int rowHeight = 24;
			const int col1width = 177;
			const int col2width = 76;
			const int col3width = 76;

			StringBuilder stringBuilder = new StringBuilder();
			
			// Parse text from table cells
			for (int row = 0; row < 5; row++)
			{
				string cell1 = extractor.GetTextFromPage(0, tableX, tableY + row * rowHeight, col1width, rowHeight).Trim();
				string cell2 = extractor.GetTextFromPage(0, tableX + col1width, tableY + row * rowHeight, col2width, rowHeight).Trim();
				string cell3 = extractor.GetTextFromPage(0, tableX + col1width + col2width, tableY + row * rowHeight, col3width, rowHeight).Trim();

				Console.WriteLine("Line #{0}: {1}, {2}, {3}", row, cell1, cell2, cell3);
				stringBuilder.AppendFormat("{0},{1},{2}rn", cell1, cell2, cell3);
			}

			// Save text to file
			File.WriteAllText("output.csv", stringBuilder.ToString());

			Console.WriteLine();
			Console.WriteLine("Data has been extracted to 'output.csv' file.");
			Console.WriteLine();
			Console.WriteLine("Press any key to continue...");
			Console.ReadKey();
		}
	}
}