[PYTHON] Get the address from the zip code

Used when you want to specify the address from the zip code

Use the post office area search https://www.post.japanpost.jp/zipcode/index.html

A function that parses the result of the above form and returns the return value as a dictionary

import requests
from bs4 import BeautifulSoup
import re


pref_key = {
    'Hokkaido': 1,
    'Aomori Prefecture': 2,
    'Iwate Prefecture': 3,
    'Miyagi Prefecture': 4,
    'Akita': 5,
    'Yamagata Prefecture': 6,
    'Fukushima Prefecture': 7,
    'Ibaraki Prefecture': 8,
    'Tochigi Prefecture': 9,
    'Gunma Prefecture': 10,
    'Saitama': 11,
    'Chiba': 12,
    'Tokyo': 13,
    'Kanagawa Prefecture': 14,
    'Niigata Prefecture': 15,
    'Toyama Prefecture': 16,
    'Ishikawa Prefecture': 17,
    'Fukui prefecture': 18,
    'Yamanashi Prefecture': 19,
    'Nagano Prefecture': 20,
    'Gifu Prefecture': 21,
    'Shizuoka Prefecture': 22,
    'Aichi prefecture': 23,
    'Mie Prefecture': 24,
    'Shiga Prefecture': 25,
    'Kyoto': 26,
    'Osaka': 27,
    'Hyogo prefecture': 28,
    'Nara Prefecture': 29,
    'Wakayama Prefecture': 30,
    'Tottori prefecture': 31,
    'Shimane Prefecture': 32,
    'Okayama Prefecture': 33,
    'Hiroshima Prefecture': 34,
    'Yamaguchi Prefecture': 35,
    'Tokushima Prefecture': 36,
    'Kagawa Prefecture': 37,
    'Ehime Prefecture': 38,
    'Kochi Prefecture': 39,
    'Fukuoka Prefecture': 40,
    'Saga Prefecture': 41,
    'Nagasaki Prefecture': 42,
    'Kumamoto Prefecture': 43,
    'Oita Prefecture': 44,
    'Miyazaki prefecture': 45,
    'Kagoshima prefecture': 46,
    'Okinawa Prefecture': 47
}


def get_html_text(url: str) -> str:
    try:
        req = requests.get(url)
    except requests.exceptions.ConnectionError:
        return False
    return req.content


def getAddress(postal_code: int) -> dict:
    url = f'https://www.post.japanpost.jp/smt-zipcode/zipcode.php?zip={postal_code}'
    content = get_html_text(url)
    if not content:
        return False
    soup = BeautifulSoup(content, 'html.parser')
    dds = [i.text.strip() for i in soup.body.findAll('dd')]
    if not dds:
        return False
    dds = dds[:4]
    info = {
        'postal': dds[0].replace('-', ''),
        'pref': dds[1],
        'city': dds[2],
        'address': re.sub(r'\(.*', '', dds[3])
    }
    info['pref_no'] = pref_key[info['pref']]
    return info


if __name__ == "__main__":
    data = getAddress(1000004)
    print(data)

"""
result
{
　　'postal': '1000004', 
　　'pref': 'Tokyo', 
　　'city': 'Chiyoda Ward', 
　　'address': 'Otemachi (excluding the following buildings, JA Building)', 
　　'pref_no': 13
}
"""