ByteScout Premium Suite – C# – PDF Invoice Parsing with PDF Extractor SDK

Home
/
Articles
/
ByteScout Premium Suite – C# – PDF Invoice Parsing with PDF Extractor SDK

printable version:
ByteScout-Premium-Suite-C-sharp-PDF-Invoice-Parsing-with-PDF-Extractor-SDK.pdf

PDF invoice parsing with PDF extractor SDK in C# with ByteScout Premium Suite

Simple tutorial on how to do PDF invoice parsing with PDF extractor SDK in C#

Writing of the code to PDF invoice parsing with PDF extractor SDK in C# can be done by developers of any level using ByteScout Premium Suite. ByteScout Premium Suite was created to assist PDF invoice parsing with PDF extractor SDK in C#. ByteScout Premium Suite is the bundle that includes twelve SDK products from ByteScout including tools and components for PDF, barcodes, spreadsheets, screen video recording.

Save time on writing and testing code by using the code below and use it in your application. Just copy and paste this C# sample code to your C# application’s code editor, add a reference to ByteScout Premium Suite (if you haven’t added yet) and you are ready to go! Want to see how it works with your data then code testing will allow the function to be tested and work properly.

If you want to try other samples for C# then free trial version of ByteScout Premium Suite is available on our website.

On-demand (REST Web API) version:
Web API (on-demand version)

On-premise offline SDK for Windows:
60 Day Free Trial (on-premise)

Program.cs

      using System;
using System.Drawing;
using Bytescout.PDFExtractor;

namespace InvoiceParsing
{
	/// <summary>
	/// This example demonstrates parsing and data extraction from typical invoice.
	/// </summary>
	class Program
	{
		static void Main(string[] args)
		{
			// Create TextExtractor instance
			TextExtractor textExtractor = new TextExtractor("demo", "demo");
			textExtractor.WordMatchingMode = WordMatchingMode.ExactMatch; // Set exact search (default is SmartSearch that works like in Adobe Reader)

			// Create XMLExtractor instance
			XMLExtractor xmlExtractor = new XMLExtractor("demo", "demo");

			// Load document
			textExtractor.LoadDocumentFromFile("Invoice.pdf");
			xmlExtractor.LoadDocumentFromFile("Invoice.pdf");

			// Results
			string invoiceNo = string.Empty;
			string invoiceDate = string.Empty;
			string total = string.Empty;
			string tableData = string.Empty;

			// Iterate pages
			for (int i = 0; i < textExtractor.GetPageCount(); i++)
			{
				RectangleF pageRectangle = textExtractor.GetPageRectangle(i);
				RectangleF tableRect = new RectangleF(0, 0, pageRectangle.Width, 0);

				// Search for "Invoice No."
				if (textExtractor.Find(i, "Invoice No.", false))
				{
					// Get the found text rectangle
					RectangleF textRect = textExtractor.FoundText.Bounds;
					// Assume the text at right is the invoice number.
					// Shift the rectangle to the right:
					textRect.X = textRect.Right;
					textRect.Width = pageRectangle.Right - textRect.Left;
					// Set the extraction region and extract the text
					textExtractor.SetExtractionArea(textRect);
					invoiceNo = textExtractor.GetTextFromPage(i).Trim();
				}
				
				// Search for "Invoice Date" and extract text at right
				if (textExtractor.Find(i, "Invoice Date", false))
				{
					RectangleF textRect = textExtractor.FoundText.Bounds;
					textRect.X = textRect.Right;
					textRect.Width = pageRectangle.Right - textRect.Left;
					textExtractor.SetExtractionArea(textRect);
					invoiceDate = textExtractor.GetTextFromPage(i).Trim();
				}

				// Search for "Quantity" keyword to detect the top of the tabular data rectangle
				if (textExtractor.Find(i, "Quantity", false))
				{
					// Keep the top table coordinate
					tableRect.Y = textExtractor.FoundText.Bounds.Top; // use textRect.Bottom if you want to skip column headers
				}
				
				// Search for "TOTAL" (it will be also the bottom of tabular data rectangle)
				if (textExtractor.Find(i, "TOTAL", true /* case sensitive! */)) 
				{
					RectangleF textRect = textExtractor.FoundText.Bounds;
					textRect.X = textRect.Right;
					textRect.Width = pageRectangle.Right - textRect.Left;
					textExtractor.SetExtractionArea(textRect);
					total = textExtractor.GetTextFromPage(i).Trim();

					// Calculate the table height
					tableRect.Height = textRect.Top - tableRect.Top;
				}

				// Extract tabular data using XMLExtractor
				if (tableRect.Height > 0)
				{
					xmlExtractor.SetExtractionArea(tableRect);
					tableData = xmlExtractor.GetXMLFromPage(i);
				}
			}

			// Display extracted data
			Console.WriteLine("Invoice No.: " + invoiceNo);
			Console.WriteLine("Invoice Date: " + invoiceDate);
			Console.WriteLine("TOTAL: " + total);
			Console.WriteLine("Table Data: ");
			Console.WriteLine(tableData);

			// Cleanup
		    textExtractor.Dispose();
            xmlExtractor.Dispose();            
            
            Console.WriteLine();
			Console.WriteLine("Press any key...");
			Console.ReadKey();
		}
	}
}