import requests import re, json from datetime import datetime, timezone, timedelta import functions JST = timezone(timedelta(hours = 9)) class YahooAuctionsItem: def __init__(self, name: str, url: str): # note - incoming url is not validated in any way! self.name = name try: self.url = re.match(r"([^?]+)", url.rstrip("/")).group(1) # remove trailing slashes and query params except: # ??? raise self.id = re.match(r".+\/(.+?)$", self.url) # extract "x12345" from "https://buyee.jp/whatever/blah/x12345" self.last_checked = datetime.fromisoformat('1970-01-01') self.available = True self.update() def update(self): try: # the good news is, yahoo japan returns all the data we need in handy json format # the bad news is that the only way to get that json format is to download the whole auction page and grep it # r = requests.get("https://page.auctions.yahoo.co.jp/jp/auction/k487846283").text r = open("yahoo.html").read() j = json.loads(re.match(r'.*var pageData ?= ?(\{.*?\});', r, re.DOTALL).group(1)) except: raise j = j['items'] self.price = float(j['price']) self.bids = j['bids'] self.start_date = datetime.fromisoformat(j['starttime']).replace(tzinfo = JST) self.end_date = datetime.fromisoformat(j['endtime']).replace(tzinfo = JST) self.last_checked = datetime.now(JST) def price_jpy(self): return f"¥{self.price:.2f}" def price_aud(self, rate = 75.0): return f"${self.price / rate:.2f}"