Merge pull request #10 from Erik-Hoffmann/dev

Dev

.gitignore

@@ -127,3 +127,6 @@ dmypy.json
 
 # Pyre type checker
 .pyre/
+
+# Custom
+deploy.sh

Dockerfile

@@ -1,11 +1,15 @@
-FROM python:3
+FROM python:3.9-slim-bullseye
+
+RUN python3 -m venv /opt/venv
 
 WORKDIR /usr/src/app
 
-COPY requirements.txt ./
-RUN pip install --no-cache-dir -r requirements.txt
+COPY requirements.txt .
+
+RUN . /opt/venv/bin/activate && pip install --no-cache-dir -r requirements.txt
 
 COPY . .
+
 COPY ./src .
 
-CMD [ "python", "./bot.py" ]
+CMD . /opt/venv/bin/activate && python ./bot.py

requirements.txt

@@ -1,4 +1,5 @@
-requests==2.22.0
 beautifulsoup4==4.8.2
 discord.py==1.7.3
-python-dotenv==0.20.0
+python-dotenv==0.20.0
+requests==2.25.1
+pyquery==2.0.0

src/bot.py

@@ -5,11 +5,10 @@
 import discord
 from discord.ext import commands
 from dotenv import load_dotenv
-from datetime import date
 
-from bs4 import BeautifulSoup
 import requests
-import re
+
+from speiseplan import Speiseplan_extractor
 
 load_dotenv()
 TOKEN = os.getenv('DISCORD_TOKEN')
@@ -18,28 +17,6 @@
 
 MENSA_HTWG = 'https://seezeit.com/essen/speiseplaene/mensa-htwg/'
 
-# Utility
-def validateIngr(sup):
-    return bool(re.match("\((\d\w?,?)+\)", sup))
-
-def attr_lookup(attribute):
-    lookup = {
-            "Veg": "Vegetarisch",
-            "Vegan": "Vegan",
-            "Sch": "Schwein",
-            "R": "Rind/Kalb",
-            "G": "Geflügel",
-            "L": "Lamm",
-            "W": "Wild",
-            "F": "Fisch/Meeresfrüchte"
-            }
-    result = []
-    if attribute:
-        for attr in attribute:
-            if attr in lookup:
-                result.append(lookup[attr])
-    return ", ".join(result) if result else ""
-
 # Commands
 @bot.event
 async def on_ready():
@@ -71,41 +48,27 @@ async def bug(ctx):
 
 @bot.command(name='mensa', help='Responds with the current menu')
 async def menu(ctx):
-    page_response = requests.get(MENSA_HTWG)
-    soup = BeautifulSoup(page_response.content, 'html.parser')
-    contents = soup.find('div', class_='tx-speiseplan')
-    date_tabs = contents.find_all('a', class_='tab')
-    current_tab = None
-    current_tab_class = None
-    attr_class='speiseplanTagKatIcon'
-    for tab in date_tabs:
-        current_tab = tab.text
-        if date.today().strftime("%d.%m.") in current_tab:
-        # if "16.05." in current_tab:
-            current_tab_class = tab.get('class')[1]
-            break
-
-
     response = discord.Embed(
-                title="In der Mensa gibt es:",
-                url=MENSA_HTWG
-            )
-    if not current_tab_class is None:
-
-        day = contents.find('div', {"id":current_tab_class})
-        menus = day.find_all('div', class_='speiseplanTagKat')
-
-
-        for menu in menus:
-            category=menu.find('div', class_='category')
-            food=menu.find('div', class_='title_preise_1').find('div', class_='title')
-            for sup in food.select('sup'):
-                if not validateIngr(sup.text): sup.unwrap()
-                else : sup.decompose()
-            attribute=menu.find('div', class_='title_preise_2').find('div', class_=attr_class)['class']
-            response.add_field(name=f"{category.text} : {attr_lookup(attribute)}", value=f"{food.text}", inline=True)
-    else:
-        response.add_field(name="Heute wohl nix", value="Zu oder so :(\nVielleicht heitert dich ein Quiz auf?\nhttps://www.mensa.de/about/membership/online-iq-test/")
+            title="In der Mensa gibt es:",
+            url=Speiseplan_extractor.address
+        )
+    try:
+        extractor = Speiseplan_extractor()
+        data = extractor.get_tab_json()
+        if not data:
+            response.add_field(name="Heute wohl nix", value="Zu oder so :(\nVielleicht heitert dich ein Quiz auf?\nhttps://www.mensa.de/about/membership/online-iq-test/")
+        else:
+            for menu in data:
+                response.add_field(name=f"{menu.get('category')} {': ' + str(menu.get('tags')) if menu.get('tags') else ''}", value=menu.get('food'), inline=True)
+
+    except requests.ConnectionError as e:
+        response.add_field(name="Fehler!", value=f"Seite nicht erreichbar!\n{e}")
+    except IndexError as e:
+        response.add_field(name="Fehler!", value=f"Tab ID nicht gefunden!\n{e}")
+    except ValueError as e:
+        response.add_field(name="Fehler!", value=e)
+    except Exception as e:
+        response.add_field(name="Fehler", value=f"Unhandled Exception:\n```{e}```")
 
     await ctx.send(embed=response)
 

src/speiseplan.py

@@ -0,0 +1,89 @@
+from requests import ConnectionError
+from requests import get
+from pyquery import PyQuery as pq
+import re
+from pprint import pprint
+
+class Speiseplan_extractor:
+
+    address = "https://seezeit.com/essen/speiseplaene/mensa-htwg/"
+
+    def __init__(self):
+        self.speiseplan = self.get_menu()
+        self.tag_map = self.build_tag_map()
+
+    def get_menu(self):
+        req = get(self.address)
+        if not req.status_code == 200:
+            raise ConnectionError(req)
+        content = pq(req.content)
+        return content(".tx-speiseplan")
+
+    def get_aktiv_tab_id(self):
+        menu = self.speiseplan
+        return menu(".heute").attr("rel")
+
+    def get_tab_content(self, tab_idx):
+        menu = self.speiseplan
+        return menu(f"#tab{tab_idx}")
+
+    def get_tab_json(self, tab_idx=None):
+        menu = self.speiseplan
+        today_id = int(self.get_aktiv_tab_id())
+        if tab_idx is None:
+            idx = today_id
+        else:
+            idx = self.eval_index(today_id, tab_idx)
+            if not menu(f"#tab{idx}"):
+                raise IndexError("non existant tab id")
+        return self.extract_categories(self.get_tab_content(idx))
+
+    def eval_index(self, base_id: int, shift_id: str):
+        if re.match(r"^[+-]?\d$", shift_id):
+            try:
+                shift_val = int(shift_id[-1])
+            except Exception as err:
+                raise err
+            if shift_id.startswith('+'):
+                return base_id + shift_val
+            elif shift_id.startswith('-'):
+                return base_id - shift_val
+            else: return base_id + shift_val
+        raise ValueError(f"Invalid input: shift_id={shift_id}")
+
+    def extract_categories(self, tab):
+        return [self.elem_to_json(elem) for elem in tab(".speiseplanTagKat")]
+
+    def elem_to_json(self, elem):
+        cat_html = pq(elem)
+        cat_name = cat_html(".category").text()
+        cat_food = cat_html(".title").text()
+        tags_html = cat_html(".speiseplanTagKatIcon")
+        cat_tags = self.map_tags(tags_html)
+        return {"category": cat_name, "food": self.format_food(cat_food).rstrip(), "tags": cat_tags}
+
+    def format_food(self,food):
+        return re.sub(r"\(\d\d?\w?(,\d\d?\w?)*\)[ ]?",'', food)
+
+    def build_tag_map(self):
+        menu = self.speiseplan
+        tags = menu(".tabsIcons")(".tabIcon")
+        return {pq(elem).attr("class")[-1]: elem.text for elem in tags}
+
+    def map_tags(self, tags):
+        return list(
+                map(
+                    lambda x : self.tag_map.get(x, None),
+                    [pq(tag).attr("class")[-1] for tag in tags]
+                )
+            )
+
+
+
+
+if __name__ == '__main__':
+    extractor = Speiseplan_extractor()
+    pprint(
+        extractor.get_tab_json()
+    )
+