風邪気味なので2024年末のインフルエンザの状況を確認してみた

import requests
from bs4 import BeautifulSoup
import re
from datetime import datetime
import os

# URL to scrape
url = "https://www.mhlw.go.jp/stf/seisakunitsuite/bunya/kenkou_iryou/kenkou/kekkaku-kansenshou01/houdou_00018.html"

# Send a GET request to the URL
response = requests.get(url)
response.raise_for_status()

# Parse the HTML content
soup = BeautifulSoup(response.content, "html.parser")

# Find all links containing the specified text
links = soup.find_all("a", string=re.compile("インフルエンザの発生状況について"))

# Extract the dates and links
date_link_pairs = []
for link in links:
    href = link.get("href")
    text = link.get_text()
    # Extract date from the link text
    date_match = re.search(r"\d{4}年\s?[０-９\d]{1,2}月\s*[０-９\d]{1,2}日", text)
    if date_match:
        date_str = date_match.group().replace(" ", "").replace('\xa0', '').translate(str.maketrans("０１２３４５６７８９", "0123456789"))
        date_obj = datetime.strptime(date_str, "%Y年%m月%d日")
        date_link_pairs.append((date_obj, href))

# Create the "pdfs" directory if it doesn't exist
os.makedirs("pdfs", exist_ok=True)

# Download all PDFs and save them with filenames based on the date
for date_obj, href in date_link_pairs:
    # Complete the URL if it's relative
    if not href.startswith("http"):
        href = "https://www.mhlw.go.jp" + href

    # Send a GET request to download the PDF
    pdf_response = requests.get(href)
    pdf_response.raise_for_status()

    # Format the filename
    filename = date_obj.strftime("%Y%m%d") + "_flu.pdf"
    filepath = os.path.join("pdfs", filename)

    # Save the PDF to a file
    with open(filepath, "wb") as pdf_file:
        pdf_file.write(pdf_response.content)

import tabula
import pandas as pd
import os


# Load all PDF under "pdfs" folder
pdf_files = [f for f in os.listdir("pdfs") if f.endswith(".pdf")]
dfs = []
for pdf_file in pdf_files:
    print(f'pdf_file: {pdf_file}')
    if pdf_file == '20241108_flu.pdf':
        pages = "3"
    else:
        pages = "2"

    tables = tabula.read_pdf(os.path.join("pdfs", pdf_file), pages=pages, multiple_tables=False)
    if len(tables) == 0:
      continue

    df = tables[0].drop(index=[0, 48, 49])

    df.columns = ['pref', 'reported', 'ratio']
    df['date'] = pd.to_datetime(pdf_file.split("_")[0])
    df['reported'] = pd.to_numeric(df['reported'].str.replace(',', ''), errors='coerce')
    print(f"Loaded {len(df)} tables from {pdf_file}")
    dfs.append(df)

# Integrate dfs to one dataframe
df = pd.concat(dfs, ignore_index=True)

print(df)

import plotly.express as px


fig = px.bar(
    df,
    x='date',
    y='reported',
    color='pref',
    title="都道府県別 インフルエンザ報告数 都道府県積み上げ",
    labels={'reported': '報告数', 'pref': '都道府県'}
)

fig.show()

fig = px.bar(
    df,
    x='pref',         # X軸: 都道府県
    y='reported',     # Y軸: 報告数
    color='date',
    title='都道府県別 インフルエンザ報告数 週次積み上げ',
    labels={'reported': '報告数', 'pref': '都道府県'},
    category_orders={'date': sorted(df['date'].unique(), reverse=False)}
)

fig.show()