Update app.py

app.py

@@ -134,7 +134,11 @@ def extract_background_from_url(url: str):
 @app.get("/extract-page-text/")
 def extract_page_content(url: str, max_char: int = 5000):
     try:
-        response = requests.get(url, timeout=20, verify=False)
+        headers = {
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36",
+            "Accept": "application/pdf"
+        }
+        response = requests.get(url, headers=headers, timeout=20, verify=False)
         response.raise_for_status()
         
         soup = BeautifulSoup(response.text, 'html.parser')