From 92faf195494841fc44588cf0c6958eaf7c3f8761 Mon Sep 17 00:00:00 2001
From: Ross Healy <ross_healy@live.co.uk>
Date: Wed, 7 Feb 2024 19:54:34 +0000
Subject: [PATCH] Updated extractor, omitted urls.

---
 lottery-co-uk-scraper/Utilities/URLExtractor.cs | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/lottery-co-uk-scraper/Utilities/URLExtractor.cs b/lottery-co-uk-scraper/Utilities/URLExtractor.cs
index 6f12585..5a9a52b 100644
--- a/lottery-co-uk-scraper/Utilities/URLExtractor.cs
+++ b/lottery-co-uk-scraper/Utilities/URLExtractor.cs
@@ -6,23 +6,29 @@ namespace lottery_co_uk_scraper.Utilities
     {
         public static async Task<List<string>> ExtractUrlsAsync(string url)
         {
-            List<string> urls = [];
+            List<string> urls = new List<string>();
 
-            using (HttpClient client = new())
+            using (HttpClient client = new HttpClient())
             {
                 string content = await client.GetStringAsync(url);
                 MatchCollection matches = MyRegex().Matches(content);
 
-                foreach (Match match in matches.Cast<Match>())
+                foreach (Match match in matches)
                 {
-                    urls.Add(match.Value);
+                    string capturedUrl = match.Groups[1].Value;
+
+                    if (capturedUrl.StartsWith(""))
+                    {
+                        string modifiedUrl = "" + capturedUrl;
+                        urls.Add(modifiedUrl);
+                    }
                 }
             }
 
             return urls;
         }
 
-        [GeneratedRegex(@"(?<=<a href=""https:\/\/www\.lottery\.co\.uk\/lotto\/results-)[^\s""']+")]
+        [GeneratedRegex(@"<a\s+href=""([^""]+)""")]
         private static partial Regex MyRegex();
     }
 }
\ No newline at end of file