Start of year update

server/scraper/resto/allergens.py

@@ -28,12 +28,12 @@ def parse_section_item(section_item: str) -> Union[dict[str, list[str]], None]:
     """
     Parses strings of the form `food: allergen, allergen, allergen`
     """
-    
+
     if "soep van de dag" in section_item:
         item_name = "Soep van de dag"
         item_allergen_list = section_item
     else:
-        item_name, item_allergen_list = section_item.split(":")
+        item_name, item_allergen_list = section_item.split(":", maxsplit=1)
 
     # Sometimes a section will have extra info before the item list,
     # this should not be parsed
@@ -73,7 +73,8 @@ def make_sections(
         sections[section_header] = dict()
         for raw_section_item in raw_section_items:
             section_item = raw_section_item.get_text(strip=True)
-            assert section_item is not None
+            if not section_item:
+                continue
 
             section_item_map = parse_section_item(section_item)
             if section_item_map is None:

server/scraper/resto/menu.py

@@ -5,8 +5,9 @@
 import json
 import os
 import re
+import warnings
 
-from bs4 import BeautifulSoup
+from bs4 import BeautifulSoup, MarkupResemblesLocatorWarning
 import string
 import sys
 import traceback
@@ -15,6 +16,8 @@
 
 from pyquery import PyQuery as pq
 
+warnings.filterwarnings("ignore", category=MarkupResemblesLocatorWarning)
+
 # Bad python module system
 sys.path.append('..')
 
@@ -30,16 +33,11 @@
     "en": "https://www.ugent.be/en/facilities/restaurants/weekly-menu",
     "nl": "https://www.ugent.be/student/nl/meer-dan-studeren/resto/weekmenu",
     "nl-debrug-avond": "https://www.ugent.be/student/nl/meer-dan-studeren/resto/weekmenubrugavond",
-    "nl-coupure": "https://www.ugent.be/student/nl/meer-dan-studeren/resto/weekmenu",
-    "nl-dunant": "https://www.ugent.be/student/nl/meer-dan-studeren/resto/weekmenu",
-    "nl-merelbeke": "https://www.ugent.be/student/nl/meer-dan-studeren/resto/weekmenu",
 }
 
 NORMAL_WEEK = re.compile(r"week(\d+)$")
 INDIVIDUAL_DAY_URL_OVERRIDE = {
     "nl-coupure": r"week(\d+)coupure$",
-    "nl-dunant": r"week(\d+)(merelbekedunant|dunant)$",
-    "nl-merelbeke": r"week(\d+)(merelbekedunant|merelbeke)$",
     "nl-debrug": r"week(\d+)brugsterre|week(27)duurzaam|week(28)duurzaam",
     "nl-sterre": r"week(\d+)(brugsterre|sterre)|week(27)duurzaam",
     "nl-ardoyen": r"week(\d+)ardoyen"
@@ -50,12 +48,9 @@
 # which is very useful.
 COPIED_ENDPOINTS = {
     "nl-debrug": "nl",
-    "nl-heymans": "nl",
-    "nl-dunant": "nl",
     "nl-coupure": "nl",
     "nl-sterre": "nl",
     "nl-ardoyen": "nl",
-    "nl-merelbeke": "nl",
 }
 
 # Day names to day of the week.
@@ -346,8 +341,20 @@ def get_day_menu(which, url, allergens: Dict[str, str]):
 
         if HEADING_TO_TYPE[last_heading] == 'soup':
             name, price = split_price(meal)
+            if "€" in name:
+                name, price_large = split_price(name)
+            else:
+                price_large = None
             food_allergens = find_allergens_for_food(allergens, name)
-            soups.append(dict(price=price, name=name, type='side', allergens=food_allergens))
+            if price_large:
+                small = "klein" if "nl" in which else "small"
+                big = "groot" if "nl" in which else "big"
+                name_small = f"{name} {small}"
+                name_big = f"{name} {big}"
+                soups.append(dict(price=price, name=name_small, type='side', allergens=food_allergens))
+                soups.append(dict(price=price_large, name=name_big, type='side', allergens=food_allergens))
+            else:
+                soups.append(dict(price=price, name=name, type='side', allergens=food_allergens))
         elif HEADING_TO_TYPE[last_heading] == 'meal soup':
             name, price = split_price(meal)
             food_allergens = find_allergens_for_food(allergens, name)

server/scraper/resto/sandwiches.py

@@ -12,7 +12,7 @@
 import sys
 sys.path.append('..')
 
-from util import parse_money, write_json_to_file
+from util import parse_money, write_json_to_file, split_price
 
 SANDWICHES_URL = "https://www.ugent.be/student/nl/meer-dan-studeren/resto/broodjes/overzicht.htm"
 HTML_PARSER = 'lxml'
@@ -116,8 +116,7 @@ def weekly_sandwiches(output, soup):
                 'start': start,
                 'end': end,
                 'name': columns[1].text.strip(),
-                'ingredients': parse_ingredients(columns[2].text),
-                'vegan': 'x' in columns[3].text
+                'ingredients': parse_ingredients(columns[2].text)
             })
 
     today = datetime.date.today()
@@ -166,15 +165,17 @@ def salad_bowls(output, soup):
     """
     bowls = []
 
-    tables = soup.find_all('table', limit=3)
+    tables = soup.find_all('table', limit=4)
 
-    if len(tables) >= 3:
-        for row in soup.find_all('table', limit=3)[2].find_all("tr", class_=lambda x: x != 'tabelheader'):
+    if len(tables) >= 4:
+        header = soup.find('a', id="salad-bowls").parent
+        _, price = split_price(header.text) if header else (None, None)
+        for row in tables[3].find_all("tr", class_=lambda x: x != 'tabelheader'):
             columns = row.find_all("td")
             bowls.append({
                 'name': columns[0].text.strip(),
                 'description': columns[1].text.strip(),
-                'price': parse_money(columns[2].string) if columns[2].string else ""
+                'price': parse_money(price) if price else ""
             })
 
     output_file = os.path.join(output, SALADS)

server/scraper/util.py

@@ -49,9 +49,14 @@ def split_price(meal):
         name = '-'.join(meal.split('-')[:-1]).strip()
         name, price = move_junk_from_price_to_name(name, price)
         return name, price
+    elif "/" in meal and "€" in meal:
+        price = meal.split('/')[-1].strip()
+        name = '/'.join(meal.split('/')[:-1]).strip()
+        name, price = move_junk_from_price_to_name(name, price)
+        return name, price
     elif "€" in meal:
         meal, price = meal.split("€")
-        return meal.strip(), price
+        return meal.strip(), price.strip()
     else:
         return meal.strip(), ""