兵庫県の圏域別受入可能病床数を取得

※JAVAのインストールが必要

!pip install tabula-py

import re
from urllib.parse import urljoin

import pandas as pd
import requests
from bs4 import BeautifulSoup

from tabula import read_pdf

url = "https://web.pref.hyogo.lg.jp/kk03/200129.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")

tag = soup.find("a", class_="icon_pdf", text=re.compile("医療提供体制の確保について"))

link = urljoin(url, tag.get("href"))

dfs = read_pdf(link, pages="1", lattice=True)

s = dfs[2].iloc[0]

# type(s)

d = s.to_dict()

d

total = d.pop("合計")

print(total)