厚生労働省の各都道府県の検査陽性者の状況のPDFをスクレイピング

apt install python3-tk ghostscript
pip install camelot-py[cv]
pip install requests
pip install beautifulsoup4

import re
from urllib.parse import urljoin

import camelot
import pandas as pd

import requests
from bs4 import BeautifulSoup

def get_link(url, text):

    r = requests.get(url)
    r.raise_for_status()

    soup = BeautifulSoup(r.content, "html.parser")

    tag = soup.find("a", text=re.compile(text))

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

    return link

def set_col(df, n = 1):

    if n > 1:
        columns = ["".join(i) for i in zip(*(df.head(n).values))]

    else:
        columns = df.iloc[0]

    return df.iloc[n:].set_axis(columns, axis=1).reset_index(drop=True)

url = get_link(
    "https://www.mhlw.go.jp/stf/seisakunitsuite/bunya/0000121431_00086.html",
    "^新型コロナウイルス感染症の現在の状況と厚生労働省の対応について",
)

link = get_link(url, "別紙１")

tables = camelot.read_pdf(link, pages="all", split_text=True, strip_text=" 　,\n")

df1 = set_col(tables[0].df, 2)
df2 = set_col(tables[1].df)

df = pd.concat([df1, df2], axis=1)

df.columns = df.columns.str.replace("※\d", "")

df["都道府県名"] = df["都道府県名"].str.replace("※\d", "")

df.mask(df == "-", inplace=True)

df.to_csv("corona.csv", encoding="utf_8_sig")