Update app.py

app.py

@@ -27,14 +27,16 @@ class StreamHandler(BaseCallbackHandler):
 
 
 @st.cache_data
+
 def get_page_urls(url):
     page = requests.get(url)
     soup = BeautifulSoup(page.content, 'html.parser')
-    links = [link['href'] for link in soup.find_all('a') if link['href'].startswith(url) and link['href'] not in [url]]
+    links = [link['href'] for link in soup.find_all('a') if 'href' in link.attrs and link['href'].startswith(url) and link['href'] not in [url]]
     links.append(url)
     return set(links)
 
 
+
 def get_url_content(url):
     response = requests.get(url)
     if url.endswith('.pdf'):