Update app.py

app.py

@@ -24,6 +24,15 @@ client = InferenceClient(model=HF_MODEL, token=HF_TOKEN)
 # State to manage datasets
 datasets_queue = []
 
+def extract_text_from_url(url):
+    try:
+        response = requests.get(url, timeout=10)
+        response.raise_for_status()
+        soup = BeautifulSoup(response.content, "lxml")  # Specify lxml here
+        return soup.get_text()
+    except Exception as e:
+        return f"Error scraping URL: {e}"
+
 # Helper Functions
 def extract_text_from_pdf(file_path):
     try: