Update app.py

app.py

@@ -40,13 +40,17 @@ def get_healthy_cheat_meal(diet_type: str) -> List[Dict[str, Any]]:
 
             # Fetch recipe details
             details = visit_webpage(url)
-            if details:
-                recipes.append({
-                    "recipe_name": title,
-                    "url": url,
-                    "ingredients": details.get("ingredients", "Ingredients not found"),
-                    "instructions": details.get("instructions", "Instructions not found")
-                })
+
+            # Skip recipes with errors
+            if "error" in details:
+                continue
+
+            recipes.append({
+                "recipe_name": title,
+                "url": url,
+                "ingredients": details.get("ingredients", []),
+                "instructions": details.get("instructions", [])
+            })
 
         return recipes if recipes else [{"error": "No valid recipes found"}]
 
@@ -61,37 +65,43 @@ def visit_webpage(url: str) -> Dict[str, Any]:
         url: The recipe URL.
 
     Returns:
-        A dictionary containing 'ingredients' and 'instructions'.
+        A dictionary containing 'ingredients' and 'instructions', or an error message if the URL is invalid.
     """
     try:
+        # Validate URL format before making a request
+        if not url.startswith("http"):
+            return {"error": f"Invalid URL format: {url}"}
+
         response = requests.get(url, timeout=10, headers={
             'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
         })
-        response.raise_for_status()
+        response.raise_for_status()  # Raise an error for 404, 403, etc.
 
         soup = BeautifulSoup(response.content, 'html.parser')
 
-        # Extract ingredients and instructions using common patterns
-        ingredients = []
-        instructions = []
+        # Extract ingredients
+        ingredients = [tag.get_text(strip=True) for tag in soup.select('ul li, .ingredient')]
+        if not ingredients:
+            ingredients = [tag.get_text(strip=True) for tag in soup.find_all('li') if "ingredient" in tag.get_text(strip=True).lower()]
 
-        for ingredient_tag in soup.select('ul li, .ingredient'):
-            text = ingredient_tag.get_text(strip=True)
-            if text:
-                ingredients.append(text)
-
-        for instruction_tag in soup.select('ol li, .instruction, .step'):
-            text = instruction_tag.get_text(strip=True)
-            if text:
-                instructions.append(text)
+        # Extract instructions
+        instructions = [tag.get_text(strip=True) for tag in soup.select('ol li, .instruction, .step')]
+        if not instructions:
+            instructions = [tag.get_text(strip=True) for tag in soup.find_all('p') if "step" in tag.get_text(strip=True).lower()]
 
         return {
-            "ingredients": ingredients if ingredients else "Ingredients not found",
-            "instructions": instructions if instructions else "Instructions not found"
+            "ingredients": ingredients if ingredients else [],
+            "instructions": instructions if instructions else []
         }
 
+    except requests.exceptions.HTTPError as http_err:
+        return {"error": f"HTTP error {response.status_code}: {http_err}"}
+
+    except requests.exceptions.RequestException as req_err:
+        return {"error": f"Request failed: {req_err}"}
+
     except Exception as e:
-        return {"error": f"Failed to scrape {url}: {e}"}
+        return {"error": f"Failed to scrape {url}: {str(e)}"}
         
 # Initialize tools
 final_answer = FinalAnswerTool()