Merge pull request #252 from Friendly-Banana/master

fix dishes scraping path

scripts/download.sh

@@ -0,0 +1,9 @@
+# get from entities.py
+canteen_id='414'
+month='08'
+year='2024'
+
+# url needs two digits
+for day in {01..31}; do
+    wget "https://www.studierendenwerk-muenchen-oberbayern.de/mensa/speiseplan/speiseplan_${year}-${month}-${day}_${canteen_id}_-de.html" -O "${year}-${month}-${day}.html"
+done

src/entities.py

@@ -33,10 +33,10 @@ def __init__(
     def __repr__(self):
         if self.price_per_unit and self.unit:
             if isinstance(self.base_price, float):
-                return f"{self.base_price:.2f}€ + {self.price_per_unit:.2f} {self.unit}"
+                return f"{self.base_price: .2f}€ + {self.price_per_unit: .2f} {self.unit}"
             return f"{self.base_price} + {self.price_per_unit} {self.unit}"
         if isinstance(self.base_price, float):
-            return f"{self.base_price:.2f}€"
+            return f"{self.base_price: .2f}€"
         return f"{self.base_price}"
 
     def __eq__(self, other: Any) -> bool:

src/menu_parser.py

@@ -305,9 +305,7 @@ def __get_daily_menus_as_html(page):
     @staticmethod
     def __parse_dishes(menu_html: html.Element, canteen: Canteen) -> List[Dish]:
         # obtain the names of all dishes in a passed menu
-        dish_names: List[str] = [
-            dish.rstrip() for dish in menu_html.xpath("//p[@class='js-schedule-dish-description']/text()")
-        ]
+        dish_names: List[str] = [dish.rstrip() for dish in menu_html.xpath("//p[@class='c-menu-dish__title']/text()")]
         # make duplicates unique by adding (2), (3) etc. to the names
         dish_names = util.make_duplicates_unique(dish_names)
         # obtain the types of the dishes (e.g. 'Tagesgericht 1')
@@ -319,19 +317,20 @@ def __parse_dishes(menu_html: html.Element, canteen: Canteen) -> List[Dish]:
             dish_types += [current_type]
         # obtain all labels
         dish_markers_additional: List[str] = menu_html.xpath(
-            "//li[contains(@class, 'c-schedule__list-item  u-clearfix  clearfix  "
-            "js-menu__list-item')]/@data-essen-zusatz",
+            "//li[contains(@class, 'c-menu-dish-list__item  u-clearfix  "
+            "clearfix  js-menu__list-item')]/@data-essen-zusatz",
         )
         dish_markers_allergen: List[str] = menu_html.xpath(
-            "//li[contains(@class, 'c-schedule__list-item  u-clearfix  clearfix  "
-            "js-menu__list-item')]/@data-essen-allergene",
+            "//li[contains(@class, 'c-menu-dish-list__item  u-clearfix  "
+            "clearfix  js-menu__list-item')]/@data-essen-allergene",
         )
         dish_markers_type: List[str] = menu_html.xpath(
-            "//li[contains(@class, 'c-schedule__list-item  u-clearfix  clearfix  js-menu__list-item')]/@data-essen-typ",
+            "//li[contains(@class, 'c-menu-dish-list__item  u-clearfix  "
+            "clearfix  js-menu__list-item')]/@data-essen-typ",
         )
         dish_markers_meetless: List[str] = menu_html.xpath(
-            "//li[contains(@class, 'c-schedule__list-item  u-clearfix  clearfix  "
-            "js-menu__list-item')]/@data-essen-fleischlos",
+            "//li[contains(@class, 'c-menu-dish-list__item  u-clearfix  "
+            "clearfix  js-menu__list-item')]/@data-essen-fleischlos",
         )
 
         # create dictionary out of dish name and dish type
@@ -369,7 +368,7 @@ def __parse_dishes(menu_html: html.Element, canteen: Canteen) -> List[Dish]:
             labels |= StudentenwerkMenuParser._parse_label(dishes_dict[name][2])
             labels |= StudentenwerkMenuParser._parse_label(dishes_dict[name][3])
             StudentenwerkMenuParser.__add_diet(labels, dishes_dict[name][4])
-            # do not prices side dishes
+            # do not price side dishes
             prices: Prices
             if dishes_dict[name][0] == "Beilagen":
                 # set classic prices without any base price