Update app.py

app.py

@@ -1,6 +1,6 @@
 from fastapi import FastAPI
 from pydantic import BaseModel
-import requests
+import httpx  # Asynchronous HTTP client
 from bs4 import BeautifulSoup
 
 app = FastAPI()
@@ -14,44 +14,33 @@ url = 'https://www.durguniversity.ac.in/index.php/Home/Noticelist'
 
 @app.get("/notices", response_model=list[Notice])
 async def get_notices():
-    # Send a GET request to fetch the raw HTML content
-    response = requests.get(url)
-
-    # Check if the request was successful (status code 200)
+    async with httpx.AsyncClient() as client:
+        # Send an asynchronous GET request
+        response = await client.get(url)
+        
+    # Check if the request was successful
     if response.status_code != 200:
         return {"error": f"Failed to retrieve content. Status code: {response.status_code}"}
 
-    # Parse the HTML content using BeautifulSoup
-    soup = BeautifulSoup(response.text, 'html.parser')
+    # Parse the HTML content using a faster parser like 'lxml'
+    soup = BeautifulSoup(response.text, 'lxml')
 
     # Find all rows or columns containing notice information
-    rows = soup.find_all('td')
+    rows = soup.select('td a')  # Directly target <a> tags inside <td>
 
     # Initialize a list to hold notice name and links
     notice_list = []
-    seen_links = set()  # Set to track links we've already encountered
+    seen_links = set()  # Track unique links
 
-    # Iterate through all <td> tags and extract notice name and link
-    for row in rows:
-        # Find the anchor tag within the <td>
-        link_tag = row.find('a')
-        
-        # Check if there's a valid link
-        if link_tag:
-            # Extract the name (text) and link (href)
-            notice_name = link_tag.text.strip()
-            notice_link = link_tag.get('href')
-            
-            # Handle cases where the name is missing or the text is just a link
-            if not notice_name:
-                notice_name = f"Notice {len(notice_list) + 1}"  # Fallback if there's no text in the <a> tag
-
-            # Check if the link is already in the set of seen links (i.e., duplicate)
-            if notice_link not in seen_links:
-                # If not a duplicate, add the link to the seen set and add notice to the list
-                seen_links.add(notice_link)
-                notice_list.append({'name': notice_name, 'link': notice_link})
-
-    # Return the list of notices as JSON
-    return notice_list[:50]  # Return top 30 notices
+    # Extract and de-duplicate notice name and links
+    for link_tag in rows:
+        notice_link = link_tag.get('href', '').strip()
+        notice_name = link_tag.text.strip()
+
+        if notice_link and notice_link not in seen_links:
+            seen_links.add(notice_link)
+            notice_name = notice_name or f"Notice {len(notice_list) + 1}"  # Fallback for empty names
+            notice_list.append({'name': notice_name, 'link': notice_link})
 
+    # Return top 50 notices
+    return notice_list[:50]