Update app.py

app.py

@@ -31,6 +31,7 @@ import PyPDF2
 import io
 import requests
 from duckduckgo_search import DDGS
+import random
 
 # Load environment variables from a .env file
 load_dotenv()
@@ -54,6 +55,20 @@ client = InferenceClient(
 similarity_model = SentenceTransformer('all-MiniLM-L6-v2')
 
 
+# List of common user agents
+USER_AGENTS = [
+    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36",
+    "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:89.0) Gecko/20100101 Firefox/89.0",
+    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.1.1 Safari/605.1.15",
+    "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36",
+    "Mozilla/5.0 (iPhone; CPU iPhone OS 14_6 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/14.0 Mobile/15E148 Safari/604.1",
+    "Mozilla/5.0 (iPad; CPU OS 14_6 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) CriOS/91.0.4472.80 Mobile/15E148 Safari/604.1",
+    "Mozilla/5.0 (Android 11; Mobile; rv:68.0) Gecko/68.0 Firefox/88.0",
+]
+
+def get_random_user_agent():
+    return random.choice(USER_AGENTS)
+
 def duckduckgo_search(query, num_results=10, time_range="", language="", safesearch=2):
     try:
         ddgs = DDGS()
@@ -78,13 +93,18 @@ def duckduckgo_search(query, num_results=10, time_range="", language="", safesea
         else:
             safesearch_setting = "strict"
         
+        # Get a random user agent
+        user_agent = get_random_user_agent()
+        
+        # Set the user agent for the DDGS instance
+        ddgs.session.headers.update({'User-Agent': user_agent})
+        
         results = ddgs.text(
             query,
             region='wt-wt',
             safesearch=safesearch_setting,
             timelimit=timelimit,
-            max_results=num_results,
-            backend: str = "html"
+            max_results=num_results
         )
         
         return [{"url": result["href"], "title": result["title"]} for result in results]