IDWR bulletin data scraping the number of reports per fixed point of influenza and by prefecture

• Data wrangling PDF about influenza outbreaks by the Ministry of Health, Labor and Welfare
• PDF data on influenza outbreaks from the Ministry of Health, Labor and Welfare (pdfplumber)

National Institute of Infectious Diseases has CSV of the same data, so scraping

from urllib.parse import urljoin

import requests
from bs4 import BeautifulSoup

url = "https://www.niid.go.jp/niid/ja/data.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.select_one(
    'div.leading-0 > table > tbody > tr > td > p.body1 > a[href$="-teiten.csv"]'
)

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

import pandas as pd

df = pd.read_csv(
    link,
    encoding="cp932",
    skiprows=3,
    index_col=0,
    header=0,
    usecols=[0, 1, 2],
    na_values="-",
)

df1 = df[df.index.notna()]