Basic Text Extraction in .NET

text-extraction-pdfpig-dotnet.cs

using UglyToad.PdfPig;
using System;

class Program
{
    static void Main()
    {
        using var document = PdfDocument.Open("document.pdf");
        
        foreach (var page in document.GetPages())
        {
            Console.WriteLine($"Page {page.Number}:");
            Console.WriteLine(page.Text);
            
            // Get individual words with positions
            foreach (var word in page.GetWords())
            {
                Console.WriteLine($"Word: '{word.Text}' at {word.BoundingBox}");
            }
        }
    }
}