Update app.py

app.py

@@ -236,7 +236,8 @@ def get_links_from_page(url, visited_urls, all_links):
         return
 
     visited_urls.add(url)
-    print(url)
+    print("Visitied" + visited_urls.lenght)
+    print("Getting next" + url)
     response = requests.get(url)
 
     if response.status_code == 200:
@@ -254,10 +255,40 @@ def get_links_from_page(url, visited_urls, all_links):
         print(f"Failed to retrieve content from {url}. Status code: {response.status_code}")
 
 
+def get_links_from_page(url, visited_urls, all_links, base_domain):
+    if url in visited_urls:
+        return
+
+    if len(visited_urls) > 25:
+        return
+
+    visited_urls.add(url)
+    print("Visitied" + visited_urls.lenght)
+    print("Getting next" + url)
+    response = requests.get(url)
+
+    if response.status_code == 200:
+        soup = BeautifulSoup(response.content, 'html.parser')
+        base_url = urlparse(url).scheme + '://' + urlparse(url).netloc
+        links = soup.find_all('a', href=True)
+
+        for link in links:
+            href = link.get('href')
+            absolute_url = urljoin(base_url, href)
+            parsed_url = urlparse(absolute_url)
+            
+            if parsed_url.netloc == base_domain:
+                all_links.add(absolute_url)
+                get_links_from_page(absolute_url, visited_urls, all_links, base_domain)
+
+    else:
+        print(f"Failed to retrieve content from {url}. Status code: {response.status_code}")
+
+
 def get_all_links_from_domain(domain_url):
     visited_urls = set()
     domain_links = set()
-    get_links_from_page(domain_url, visited_urls, domain_links)
+    get_links_from_page(domain_url, visited_urls, domain_links, domain_url)
     return domain_links