xxx

my_tools.py

@@ -267,50 +267,52 @@ def read_excel_data(file_path: str, sheet_name=0) -> str:
 
 def classify_botanical(items_list_str: str) -> str:
     """
-    Clasifica botánicamente una lista de alimentos (en inglés o español) en Verduras, Frutas u Otros.
+    Splits an input list of foods (English names) into botanical Vegetables,
+    Fruits, and Others, and returns the three groups as comma-separated lists.
+    Nothing that is a botanical fruit appears in the Vegetables list.
     """
-    mapping = {
-        "tomato": "tomate", "pepper": "pimiento", "bell pepper": "pimiento",
-        "green beans": "judía verde", "beans": "judía verde",
-        "zucchini": "calabacín", "eggplant": "berenjena", "cucumber": "pepino",
-        "broccoli": "brócoli", "celery": "apio", "lettuce": "lechuga",
-        "corn": "maíz", "peas": "guisante", "pea": "guisante",
-        "spinach": "espinaca", "kale": "col rizada",
-        "sweet potatoes": "batata", "sweet potato": "batata", "potato": "patata",
-        "onion": "cebolla", "garlic": "ajo", "carrot": "zanahoria",
-        "okra": "okra", "cabbage": "col", "cauliflower": "coliflor"
-    }
-    vegetables_es = {
-        "zanahoria","patata","batata","cebolla","ajo","puerro","apio",
-        "lechuga","espinaca","brócoli","calabacín","berenjena","pepino",
-        "judía verde","maíz","okra","col rizada","col","coliflor"
+
+    # --- botanical criteria -------------------------------------------------
+    botanical_fruits = {
+        "tomato", "bell pepper", "pepper", "green beans", "beans", "zucchini",
+        "cucumber", "eggplant", "corn", "peas", "pea", "pumpkin", "squash",
+        "avocado"
     }
-    fruits_es = {
-        "tomate","pepino","calabacín","berenjena","pimiento","aguacate",
-        "calabaza","guisante","judía verde","maíz"
+
+    botanical_vegetables = {
+        "broccoli", "celery", "lettuce", "kale", "spinach", "sweet potatoes",
+        "sweet potato", "potato", "onion", "garlic", "carrot", "okra",
+        "cabbage", "cauliflower", "beet", "turnip", "parsnip", "leek"
     }
 
-    items = []
-    for raw in items_list_str.split(','):
-        itm = raw.strip().lower()
-        itm_es = mapping.get(itm, itm)
-        items.append(itm_es)
+    # -----------------------------------------------------------------------
+    raw_items = [token.strip().lower() for token in items_list_str.split(",")]
+
+    vegetables = []
+    fruits = []
+    others = []
 
-    vegs = [i for i in items if i in vegetables_es and i not in fruits_es]
-    fruits_found = [i for i in items if i in fruits_es]
-    others = [i for i in items if i not in vegetables_es and i not in fruits_es]
+    for item in raw_items:
+        if item in botanical_vegetables and item not in botanical_fruits:
+            vegetables.append(item)
+        elif item in botanical_fruits:
+            fruits.append(item)
+        else:
+            others.append(item)
 
-    vegs_sorted = sorted(set(vegs))
-    fruits_sorted = sorted(set(fruits_found))
-    others_sorted = sorted(set(others))
+    # De-duplicate and alphabetise
+    vegetables = sorted(set(vegetables))
+    fruits     = sorted(set(fruits))
+    others     = sorted(set(others))
 
     return (
-    f"Vegetables: {', '.join(vegs_sorted)}\n"
-    f"Fruits: {', '.join(fruits_sorted)}\n"
-    f"Others: {', '.join(others_sorted)}"
-)
+        f"Vegetables: {', '.join(vegetables)}\n"
+        f"Fruits: {', '.join(fruits)}\n"
+        f"Others: {', '.join(others)}"
+    )
 
-def scrape_wikipedia_table(page_title: str, section: str, table_index: int = 0) -> str:
+
+def scrape_wikipedia_table_deprecated(page_title: str, section: str, table_index: int = 0) -> str:
     """
     Busca una sección en una página de Wikipedia y extrae la tabla indicada (por índice).
     Devuelve el CSV.
@@ -338,6 +340,34 @@ def scrape_wikipedia_table(page_title: str, section: str, table_index: int = 0)
     except Exception as e:
         return f"Error scrape_wiki_table: {e}"
 
+def scrape_wikipedia_table(page_title: str,
+                      section: str | None = None,
+                      table_index: int = 0) -> str:
+    """
+    Devuelve la tabla pedida en Markdown.  
+    Si `section` es None ⇒ busca en toda la página.
+    """
+    base_url = "https://en.wikipedia.org/wiki/"
+    url = base_url + page_title.replace(" ", "_")
+
+    html = requests.get(url, timeout=15).text
+    soup = BeautifulSoup(html, "html.parser")
+
+    # encontrar tablas
+    if section:
+        header = soup.find(id=section)
+        if not header:
+            raise ValueError(f"Section '{section}' not found.")
+        tables = header.find_all_next("table", class_="wikitable")
+    else:
+        tables = soup.find_all("table", class_="wikitable")
+
+    if not tables or table_index >= len(tables):
+        raise ValueError(f"Table index {table_index} out of range (found {len(tables)})")
+
+    df = pd.read_html(str(tables[table_index]), flavor="bs4")[0]
+    return df.to_markdown(index=False)
+
 # -------------------------------------------------------------------
 # 4) ENVUELTORES DE HERRAMIENTAS (FunctionTool)
 # -------------------------------------------------------------------