トップ > toyama

toyama 

import requests
from bs4 import BeautifulSoup

from urllib.parse import urljoin

import pathlib
import re

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko"
}


def fetch_soup(url, parser="html.parser"):

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

    soup = BeautifulSoup(r.content, parser)

    return soup


def fetch_file(url, dir="."):

    p = pathlib.Path(dir, pathlib.PurePath(url).name)
    p.parent.mkdir(parents=True, exist_ok=True)

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

    with p.open(mode="wb") as fw:
        fw.write(r.content)
    return p


url = "https://www.pref.toyama.jp/120507/kurashi/kenkou/kenkou/covid-19/kj00022038.html"

soup = fetch_soup(url)

href = soup.find("a", text=re.compile("^強化・緩和の判断指標")).get("href")

link = urljoin(url, href)

p = fetch_file(link)

import pandas as pd

df0 = (
    pd.read_excel(p, index_col=None, header=None)
    .iloc[2:9, 3:]
    .T.reset_index(drop=True)
    .set_axis(["date", "入院者数", "重症病床稼働率", "新規陽性者数", "感染経路不明者数", "陽性率", "先週対比"], axis=1)
)

df_date = df0["date"].str.extract("(\d{1,2}/\d{1,2})").rename({0: "date"}, axis=1)

df_date["year"] = 2020 + (df_date["date"] == "1/1").cumsum()

df_date[["month", "day"]] = (
    df_date["date"].str.extract("(\d{1,2})/(\d{1,2})", expand=True).astype(int)
)

df_date.drop("date", axis=1, inplace=True)

df0["date"] = pd.to_datetime(df_date, errors="coerce")

df0.set_index("date", inplace=True)

df0.mask(df0 == "-", inplace=True)

df1 = df0.astype(float)

df1["日付"] = df1.index.strftime("%Y-%m-%d")

df1.iloc[-1].to_dict()

import requests
from bs4 import BeautifulSoup

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko"
}


def fetch_soup(url, parser="html.parser"):

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

    soup = BeautifulSoup(r.content, parser)

    return soup


url = "https://www.pref.toyama.jp/120507/kurashi/kenkou/kenkou/covid-19/kj00021798.html"

soup = fetch_soup(url)

summary = soup.find("div", id="tmp_contents").get_text(strip=True)

import unicodedata

text = unicodedata.normalize("NFKC", summary)

print(text)

import re

data = {}

for i in re.finditer(
    "(新規感染者数|累計|入院者数|重症者|宿泊療養施設入所者数|自宅療養者数|死亡者数|退院及び療養解除者数|アルファ株|デルタ株|オミクロン株) *?([0-9,]+)人?",
    text,
):
    data[i.group(1)] = int(i.group(2).replace(",", ""))

data

import pathlib
import re
from urllib.parse import urljoin

import pandas as pd
import requests
from bs4 import BeautifulSoup

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko"
}


def fetch_soup(url, parser="html.parser"):

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

    soup = BeautifulSoup(r.content, parser)

    return soup


def fetch_file(url, dir="."):

    p = pathlib.Path(dir, pathlib.PurePath(url).name)
    p.parent.mkdir(parents=True, exist_ok=True)

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

    with p.open(mode="wb") as fw:
        fw.write(r.content)
    return p


url = "https://www.pref.toyama.jp/120507/kurashi/kenkou/kenkou/covid-19/kj00021798.html"

soup = fetch_soup(url)

href = soup.find(
    "a", text=re.compile("^富山県内における新型コロナウイルス感染症の発生状況一覧"), href=re.compile("\.xlsx?$")
).get("href")

link = urljoin(url, href)

p = fetch_file(link)


df0 = pd.read_excel(p, skiprows=2)

df0.rename(columns={"県番号": "No", "検査結果判明日": "日付"}, inplace=True)

df1 = df0[df0["市番号"] != "患者発生届取り下げ"].copy()

flg_is_serial = df1["日付"].astype("str").str.isdigit()

fromSerial = pd.to_datetime(
    df1.loc[flg_is_serial, "日付"].astype(float),
    unit="D",
    origin=pd.Timestamp("1899/12/30"),
)

fromString = pd.to_datetime(df1.loc[~flg_is_serial, "日付"])

df1["日付"] = pd.concat([fromString, fromSerial])

df1

df1["性別"] = df1["性別"].replace({"男": "男性", "女": "女性"})

df1["性別"].unique()

df1["年代"] = df1["年代"].str.replace("\s", "", regex=True)

df1["年代"] = df1["年代"].replace(["90代", "90代以上"], "90歳以上")

df1["年代"] = df1["年代"].replace(["1歳未満", "10歳未満代"], "10歳未満")

df1["年代"].unique()

df1["居住地"] = df1["居住地"].str.replace("\s", "", regex=True)

df1["居住地"] = df1["居住地"].replace("冨山市", "富山市")

df1["居住地"].unique()

df1

data = (
    df1["居住地"]
    .value_counts()
    .reset_index()
    .rename(columns={"index": "label", "居住地": "count"})
    .to_dict(orient="records")
)

data