jprs_domain_resaler.py

#!/usr/bin/env python

import os
import sys
import requests
import csv
from bs4 import BeautifulSoup

URL = "https://jprs.jp/registration/list/meibo/meibo_list_{0}.html"

PAGES  = [ "a", "ka", "sa", "ta", "na", "ha", "ma", "ya", "ra", "wa" ]
HEADER = ["指定事業者", "汎用", "都道府県型", "日本語", "AC", "AD", "CO", "ED", "GO", "GR", "NE", "OR", "地域型", "ドメイン名登録のみ", "ホスティングサービス", "IPv6ホスト情報登録", "IPv6接続", "DNSSEC署名鍵", "DNSSEC権威DNS", "DNSSECキャッシュDNS" ]

writer = csv.writer(sys.stdout)
writer.writerow(HEADER)
for page in PAGES:

    url     = URL.format(page)
    res     = requests.get(url)
    content = res.content

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

    tables = soup.find_all("table", class_="tb-sml")
    for table in tables:
        rows = table.find_all("tr")

        for row in rows:
            cols = row.find_all("td")
            writer.writerow( [ col.text.strip() for col in cols ] )