Scrape current jpl matchweek every few hours

cogs/tasks.py

@@ -3,7 +3,9 @@ from data.remind import Reminders
 from discord.ext import commands, tasks
 from enums.numbers import Numbers
 from functions import timeFormatters
+from functions.config import config
 from functions.database import currency, poke, prison, birthdays, stats
+from functions.scraping import getMatchweek
 import json
 import random
 import requests
@@ -21,6 +23,7 @@ class Tasks(commands.Cog):
         self.checkBirthdays.start()
         self.updateMessageCounts.start()
         self.sendReminders.start()
+        self.updateMatchweek.start()
 
     @tasks.loop(hours=1.0)
     async def bankInterest(self):
@@ -218,9 +221,22 @@ class Tasks(commands.Cog):
     async def beforeSendReminders(self):
         await self.client.wait_until_ready()
 
-    # TODO
+    @tasks.loop(hours=2.0)
     async def updateMatchweek(self):
-        pass
+        """
+        Task that checks the current JPL matchweek & changes the dict value
+        """
+        matchweek = getMatchweek()
+
+        if matchweek is None:
+            return
+
+        # Change the setting in the config
+        config("jpl_day", int(matchweek))
+
+    @updateMatchweek.before_loop
+    async def beforeUpdateMatchweek(self):
+        await self.client.wait_until_ready()
 
     def getCurrentHour(self):
         return timeFormatters.dateTimeNow().hour

files/config.json

@@ -1 +1 @@
-{"semester": "1", "year": "2", "years": 2, "jpl": 161733, "jpl_day": 4}
+{"semester": "1", "year": "2", "years": 2, "jpl": 161733, "jpl_day": 21}

functions/scraping.py

@@ -1,3 +1,5 @@
+import re
+
 from requests import get
 from urllib.parse import urlencode
 from bs4 import BeautifulSoup
@@ -49,4 +51,28 @@ def getMatchweek():
     """
     Parses the current JPL matchweek out of Sporza's site
     """
-    pass
+    resp = get("https://sporza.be/nl/categorie/voetbal/jupiler-pro-league/")
+
+    if resp.status_code != 200:
+        return None
+
+    bs = BeautifulSoup(resp.text, "html.parser")
+    matchdays = bs.find_all("section", attrs={"class": "sc-matchdays"})
+
+    if len(matchdays) < 2:
+        return None
+
+    # Table header
+    header = matchdays[1]
+
+    # Regex to find current matchday
+    r = re.compile(r"speeldag\s*\d+", flags=re.I)
+
+    match = r.search(str(header))
+
+    # Something went wrong, just ignore
+    if match is None:
+        return None
+
+    # "Speeldag DD" -> split on space & take second
+    return match[0].split(" ")[1]