From e44ef43531df00431c5d31ef4e0c6350e5364636 Mon Sep 17 00:00:00 2001
From: AnsahMohammad <mohdansah10@gmail.com>
Date: Wed, 5 Feb 2025 22:46:17 +0530
Subject: [PATCH] refactor: improved code optimization

---
 core/crawler.py   | 9 ++++-----
 core/extractor.py | 2 +-
 2 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/core/crawler.py b/core/crawler.py
index 19feb24..719a399 100644
--- a/core/crawler.py
+++ b/core/crawler.py
@@ -9,7 +9,7 @@ def handle_starttag(self, tag, attrs):
             for (key, value) in attrs:
                 if key == 'href':
                     newUrl = parse.urljoin(self.baseUrl, value)
-                    self.links = self.links + [newUrl]
+                    self.links.append(newUrl)
 
     def getLinks(self, url):
         self.links = []
@@ -28,10 +28,9 @@ def spider(url, maxPages):
     pagesToVisit = [url]
     numberVisited = 0
     foundWord = False
-    while numberVisited < maxPages and pagesToVisit != [] and not foundWord:
-        numberVisited = numberVisited +1
-        url = pagesToVisit[0]
-        pagesToVisit = pagesToVisit[1:]
+    while numberVisited < maxPages and pagesToVisit:
+        numberVisited += 1
+        url = pagesToVisit.pop()
         try:
             parser = LinkParser()
             data, links = parser.getLinks(url)
diff --git a/core/extractor.py b/core/extractor.py
index 02255d3..e8bd3ea 100644
--- a/core/extractor.py
+++ b/core/extractor.py
@@ -13,7 +13,7 @@ def param_extract(response, level, black_list, placeholder):
         
     for i in parsed:
         delim = i.find('=')
-        second_delim = i.find('=', i.find('=') + 1)
+        second_delim = i.find('=', delim + 1)
         if len(black_list) > 0:
             words_re = re.compile("|".join(black_list))
             if not words_re.search(i):