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

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

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

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

Learn PDF invoice parsing with PDF extractor SDK in C#

These source code samples are assembled by their programming language and functions they use. PDF invoice parsing with PDF extractor SDK in C# can be applied with ByteScout PDF Suite. ByteScout PDF Suite is the set that includes 6 SDK products to work with PDF from generating rich PDF reports to extracting data from PDF documents and converting them to HTML. This bundle includes PDF (Generator) SDK, PDF Renderer SDK, PDF Extractor SDK, PDF to HTML SDK, PDF Viewer SDK and PDF Generator SDK for Javascript.

If you want to quickly learn then these fast application programming interfaces of ByteScout PDF Suite for C# plus the guideline and the C# code below will help you quickly learn PDF invoice parsing with PDF extractor SDK. Follow the steps-by-step instructions from the scratch to work and copy and paste code for C# into your editor. Updated and detailed documentation and tutorials are available along with installed ByteScout PDF Suite if you’d like to learn more about the topic and the details of the API.

Trial version along with the source code samples for C# can be downloaded from 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();
		}
	}
}