import pandas as pd import requests from bs4 import BeautifulSoup url = "https://www.pref.ehime.jp/h25300/4793/shokuchuudoku/hassei.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") data = [] for trs in soup.select("table.datatable > tbody > tr")[1:]: tmp = {} tds = [td for td in trs.select("td")] tmp["発生年月日"] = tds[0].get_text(strip=True) ps = tds[1].select("p") for p in ps[:-1]: t, c = p.get_text(strip=True).split(":", 1) tmp[t] = c tmp["プレスリリース"] = ps[-1].a.get("href") data.append(tmp) df = pd.DataFrame(data) df.to_csv("data.tsv", sep="\t")