using System.Collections.Generic;
using System.Text.RegularExpressions;
using System.Threading.Tasks;
static List<string> indexapo = new List<string>();
private Dictionary<string, string> dictionary = new Dictionary<string, string>()
private static List<string> patternList = new List<string>()
"<span class=\"\\w+\\s\\w+\\w+\"\\s\\w+-\\w+=\"\\w+.\\d+.\\d+\">",
"<span class=\"\\w+ \\w+ \\w+\" \\w+-\\w+=\"\\w+.\\w+.\\w+\\+\\w+.\\w+.\\w+\">",
public static void Main(string[] args)
List<string> BibleChapterFiles = GetFiles();
List<string> BibleHtmlCode = GetAllHtmlCodes();
foreach (string htmlcode in BibleHtmlCode)
Console.WriteLine(htmlcode);
static List<string> GetFiles()
List<string> BibleChapterFiles = new List<string>();
foreach (string BibleBookDirectory in Directory.GetDirectories(@"C: \Users\Argenis Pieternella\Documents\Bible"))
foreach (string BibleChapterFile in Directory.GetFiles(BibleBookDirectory))
BibleChapterFiles.Add(BibleChapterFile);
return BibleChapterFiles;
static List<string> GetAllHtmlCodes()
List<string> BibleChapterFiles = GetFiles();
List<string> BibleHtmlCode = new List<string>();
string pattern = @"&#\d+;";
foreach (string chapter in BibleChapterFiles)
content = File.ReadAllText(chapter);
foreach (Match m in Regex.Matches(content, pattern))
if (!BibleHtmlCode.Contains(m.Value))
BibleHtmlCode.Add(m.Value);
public static void Patterns(string content)
string replacement = "\n";
Regex rgx = new Regex(patternList[0]);
foreach (string pattern in patternList)
rgx = new Regex(pattern);
result = rgx.Replace(result, replacement);
Console.WriteLine(result.Trim());
public static string Diction(string content)
string pattern = @"&#\d+;";
Regex rgx = new Regex(pattern);
rgx = new Regex(pattern);
result = rgx.Replace(result, replacement);
Console.WriteLine(result);