www.mhlw.go.jp
import requests
from bs4 import BeautifulSoup
from urllib.parse import urljoin
import camelot
import pandas as pd
url = "https://www.mhlw.go.jp/stf/seisakunitsuite/bunya/kenkou_iryou/iryou/rinsyo/index_00014.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, "html5lib")
for i in soup.select("ul.m-listLink--hCol2 > li > a"):
link = urljoin(url, i.get("href"))
print(i.get_text(), link)
tables = camelot.read_pdf(link, pages="all")
df = pd.concat([table.df for table in tables])
df.to_csv(f"{i.get_text()}.csv", index=None, header=None)
