PTT #1Z0PBY9H (Python)

# 文章網址 https://www.ptt.cc/bbs/Python/M.1661047522.A.251.html

import json
import re
import urllib.request as url_req

url = "https://tw.screener.finance.yahoo.net/future/"
query_args = "q?_=1661047090480&callback=jQuery111307735144102166103_1661047090479&mkt=01&perd=1m&sym=WTX%26&type=tick"

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.0.0 Safari/537.36",
    "Sec-CH-UA-Platform": "Windows",
}
req = url_req.Request(url + query_args, headers=headers)


def parsing_invalid_number(match):
    s = match.group()
    if not s.lstrip("0").isnumeric():
        return s
    s = s.lstrip("0")
    if "." in s:
        return "{:f}".format(float(s))
    return "{:d}".format(int(s))


def load_json(rawdata: str):
    match = re.match(r"(jQuery.+\()({.+})(\);)", rawdata)
    if not match:
        raise ValueError("Cannot find match in: {:s}".format(rawdata))
    json_text = match.groups()[1]
    json_text = re.sub(r"\d+\.?\d*", parsing_invalid_number, json_text)
    json_text = json_text.replace("sections", '"sections"')
    return json.loads(json_text)


with url_req.urlopen(req) as response:
    data = response.read().decode("utf-8")

data_json = load_json(data)

print(data_json)