From 47c587926e96e5c6c13bfd2789800a4d312decbf Mon Sep 17 00:00:00 2001
From: Ross Healy <ross_healy@live.co.uk>
Date: Wed, 7 Feb 2024 19:26:59 +0000
Subject: [PATCH] URL Extractor from information source.

---
 lottery-co-uk-scraper/Program.cs              | 17 +++++++++--
 .../Utilities/URLExtractor.cs                 | 28 +++++++++++++++++++
 2 files changed, 43 insertions(+), 2 deletions(-)
 create mode 100644 lottery-co-uk-scraper/Utilities/URLExtractor.cs

diff --git a/lottery-co-uk-scraper/Program.cs b/lottery-co-uk-scraper/Program.cs
index d464722..7a94908 100644
--- a/lottery-co-uk-scraper/Program.cs
+++ b/lottery-co-uk-scraper/Program.cs
@@ -1,4 +1,5 @@
 using lottery_co_uk_scraper.NationalLottery;
+using lottery_co_uk_scraper.Utilities;
 
 namespace lottery_co_uk_scraper
 {
@@ -7,9 +8,21 @@ namespace lottery_co_uk_scraper
         static async Task Main()
         {
             using HttpClient client = new();
-            string url = "";
 
-            await Lotto.GetLottoNumbers(url, client);
+            List<string> urls =
+            [
+                "",
+                "",
+            ];
+
+            foreach (string url in urls)
+            {
+                List<string> extractedUrls = await URLExtractor.ExtractUrlsAsync(url);
+                foreach (string extractedUrl in extractedUrls)
+                {
+                    await Lotto.GetLottoNumbers(url, client);
+                }
+            }            
         }
     }
 }
\ No newline at end of file
diff --git a/lottery-co-uk-scraper/Utilities/URLExtractor.cs b/lottery-co-uk-scraper/Utilities/URLExtractor.cs
new file mode 100644
index 0000000..6f12585
--- /dev/null
+++ b/lottery-co-uk-scraper/Utilities/URLExtractor.cs
@@ -0,0 +1,28 @@
+using System.Text.RegularExpressions;
+
+namespace lottery_co_uk_scraper.Utilities
+{
+    internal partial class URLExtractor
+    {
+        public static async Task<List<string>> ExtractUrlsAsync(string url)
+        {
+            List<string> urls = [];
+
+            using (HttpClient client = new())
+            {
+                string content = await client.GetStringAsync(url);
+                MatchCollection matches = MyRegex().Matches(content);
+
+                foreach (Match match in matches.Cast<Match>())
+                {
+                    urls.Add(match.Value);
+                }
+            }
+
+            return urls;
+        }
+
+        [GeneratedRegex(@"(?<=<a href=""https:\/\/www\.lottery\.co\.uk\/lotto\/results-)[^\s""']+")]
+        private static partial Regex MyRegex();
+    }
+}
\ No newline at end of file