HtmlScrubber

namespace HtmlScrubber
{
    using System;
    using System.Collections.Generic;
    using System.IO;
    using System.Text;
    using System.Text.RegularExpressions;

    using Fizzler.Systems.HtmlAgilityPack;

    using HtmlAgilityPack;

    public class LinkObject
    {
        public string HeaderId { get; set; }

        public string Title { get; set; }
    }

    // install Fizzler.Systems.HtmlAgilityPack
    // install HtmlAgilityPack 1.4.9
    internal class Program
    {
        private static readonly Regex EverythingExceptWordCharactersRegex = new Regex("[^A-z0-9-]+");

        private static readonly Regex WhiteSpaceRegex = new Regex(@"\s+");

        public static string Base64Encode(string plainText)
        {
            var plainTextBytes = Encoding.UTF8.GetBytes(plainText);
            return Convert.ToBase64String(plainTextBytes);
        }

        private static string ConvertToValidId(string header)
        {
            string value = WhiteSpaceRegex.Replace(header, "-");

            value = EverythingExceptWordCharactersRegex.Replace(value, string.Empty);

            value = value.ToLower();

            return value;
        }

        private static void Main(string[] args)
        {
            string content = File.ReadAllText(@"C:\Users\hristo.kolev\Desktop\source.txt");

            var links = new List<LinkObject>();

            var document = new HtmlDocument();

            document.LoadHtml2(content);

            var root = document.DocumentNode;

            var headers = root.QuerySelectorAll("h1");

            foreach (var header in headers)
            {
                var link = new LinkObject
                {
                    Title = header.InnerText,
                    HeaderId = ConvertToValidId(header.InnerText)
                };

                links.Add(link);

                header.SetAttributeValue("id", link.HeaderId);
            }

            foreach (var link in links)
            {
                Console.WriteLine($"{link.Title}, {link.HeaderId}");
            }

            File.WriteAllText(@"C:\Users\hristo.kolev\Desktop\target.txt", root.InnerHtml);
        }
    }
}