initial

mensa.py

@@ -0,0 +1,69 @@
+"""
+When there is an error there is no output but an error.
+All in german.
+"""
+
+import json
+import re
+import sys
+
+import requests
+from bs4 import BeautifulSoup
+
+DATE, MENSA = sys.argv[1:3]
+URL = f"https://www.studierendenwerk-goettingen.de/fileadmin/templates/php/mensaspeiseplan/cached/de/{DATE}/{MENSA}.html"
+
+r = requests.get(URL)
+if r.status_code == 404:
+    sys.exit(1)
+
+soup = BeautifulSoup(r.text, "html.parser")
+table = soup.select_one("table.sp_tab")
+
+if not table or "kein Angebot" in table.get_text():
+    sys.exit(1)
+
+dishes = []
+
+for row in table.select("tr")[1:]:
+    cells = row.select("td")
+    if len(cells) != 3:
+        continue
+
+    typ, bez, hin = cells
+    strong = bez.select_one("strong")
+    raw_title = strong.get_text(" ", strip=True) if strong else ""
+
+    title = re.sub(r"\s*\([^)]*\)", "", raw_title)
+
+    description = bez.get_text(" ", strip=True).removeprefix(raw_title).strip()
+    angebot = bez.select_one("i.smaller")
+    if angebot:
+        description = description.removesuffix(
+            angebot.get_text(" ", strip=True)
+        ).strip()
+
+    allergens = [
+        x.strip()
+        for group in re.findall(r"\(([^()]*)\)", raw_title + " " + description)
+        for x in group.split(",")
+    ]
+
+    category = [
+        str(img["src"]).rsplit("/", 1)[-1].rsplit(".", 1)[0]
+        for img in hin.select("img")
+    ]
+
+    dishes.append(
+        {
+            "date": DATE,
+            "mensa": MENSA,
+            "type": typ.get_text(strip=True),
+            "title": title,
+            "description": description,
+            "category": category,
+            "allergens": allergens,
+        }
+    )
+
+print(json.dumps(dishes, ensure_ascii=False))