From cad99401df0aa0019fa706e38395ad7918a4a1ae Mon Sep 17 00:00:00 2001
From: Kuchen <daniel.schneeweis@a1.net>
Date: Fri, 28 Jun 2024 11:31:25 +0200
Subject: [PATCH] added support for even more websites that have html between
 them

---
 KC-Scraper.py | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/KC-Scraper.py b/KC-Scraper.py
index 354a424..21da591 100644
--- a/KC-Scraper.py
+++ b/KC-Scraper.py
@@ -111,6 +111,15 @@ class KCScraper:
                 self.goodSites.add(site)
         else:
             self.goodSites.add(site)
+
+            # Replace opening HTML tags with ':'
+            r = re.sub(r'<[^/][^>]*>', ':', r)
+            # Remove closing HTML tags
+            r = re.sub(r'</[^>]*>', '', r)
+
+            while r.count("::") > 0:
+                r = r.replace("::", ":")
+
             locProxies = re.findall(r"\b\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}" +
                                     self.proxyDelimiter +
                                     r"\d{1,5}\b", KCScraper.replaceAll(self, r))
@@ -328,4 +337,4 @@ class KCScraper:
 
 
 if __name__ == "__main__":
-    KCScraper().main()
+    KCScraper().main()
\ No newline at end of file