import datetime
import re
from urllib.parse import urljoin

import requests
from bs4 import BeautifulSoup

url = "https://biz.goto.jata-net.or.jp/couponlist.html"

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko"
}

r = requests.get(url, headers=headers)
r.raise_for_status()

soup = BeautifulSoup(r.content, "html.parser")

area = {}

for a in soup.select("section.download_couponlist div.button_area > a"):

    s = a.get("aria-label")
    m = re.search("地域共通クーポン取扱店舗一覧_(.+)（(\d{4})年(\d{1,2})月(\d{1,2})日時点）", s)

    year, month, day = map(int, m.group(2, 3, 4))

    area[m.group(1)] = {
        "link": urljoin(url, a.get("href")),
        "date": datetime.date(year, month, day),
    }

area

import pandas as pd

# area.keys()
# dict_keys(['北海道', '東北地方', '関東地方', '中部地方', '近畿地方', '中国地方', '四国地方', '九州・沖縄地方', '全国'])

df0 = pd.read_excel(area["全国"]["link"])

df0["紙クーポン"] = df0["クーポン種別"].str.contains("紙", na=False).astype(int)
df0["電子クーポン"] = df0["クーポン種別"].str.contains("電子", na=False).astype(int)

industries = df0["業種"].str.split(".", expand=True).rename(columns={0: "業種コード", 1:"業種名"})

industries["業種コード"] = industries["業種コード"].astype(int)

df1 = pd.concat([df0, industries], axis=1)

pd.crosstab(df1["業種名"], df1["都道府県"])