get auction id from url

listing.py

@@ -1,21 +1,27 @@
 import requests
 
 import re, json
-
 from datetime import datetime, timezone, timedelta
 
+import functions
+
 JST = timezone(timedelta(hours = 9))
 
 class YahooAuctionsItem:
-	def __init__(self, name, url):
-	 self.name = name
-	 self.url = url
-	 self.last_checked = datetime.fromisoformat('1970-01-01')
-	 self.available = True
-	 self.update()
+	def __init__(self, name: str, url: str):
+		# note - incoming url is not validated in any way!
+		self.name = name
+		self.url = re.match(url.rstrip("/"), r"([^?]+)") # remove trailing slashes and query params
+		self.id = re.match(self.url, r".+\/(.+?)$") # extract "x12345" from "https://buyee.jp/whatever/blah/x12345"
+		self.last_checked = datetime.fromisoformat('1970-01-01')
+		self.available = True
+		self.update()
 
 	def update(self):
 		try:
+			# the good news is, yahoo japan returns all the data we need in handy json format
+			# the bad news is that the only way to get that json format is to download the whole auction page and grep it
+
 			# r = requests.get("https://page.auctions.yahoo.co.jp/jp/auction/k487846283").text
 			r = open("yahoo.html").read()
 			j = json.loads(re.match(r'.*var pageData ?= ?(\{.*?\});', r, re.DOTALL).group(1))