web.pref.hyogo.lg.jp 重複除去 最新のファイルはスクレイピングで取得 import pathlib import re from urllib.parse import urljoin import pandas as pd import requests from bs4 import BeautifulSoup def fetch_soup(url, parser="html.parser"): r = requests.get(url) r.raise_for_status() soup = BeautifulSoup(r.content, parser) return soup def fetch_file(url, dir="."): p = pathlib.Path(dir, pathlib.PurePath(url).name) p.parent.mkdi