葛飾区議会議員選挙ページをPythonでスクレイピングしてCSV出力してみた

sudo apt update
sudo apt install -y python3 python3-venv python3-pip

mkdir ~/katsushika-2025
cd ~/katsushika-2025
python3 -m venv venv
source venv/bin/activate

pip install beautifulsoup4 requests lxml

#!/usr/bin/env python3

import requests, csv, re, time, random
from bs4 import BeautifulSoup

URL = "https://go2senkyo.com/local/senkyo/25126"
HEADERS = {"User-Agent": "Mozilla/5.0 (compatible; ElectionScraper/1.0)"}

def fetch(url):
    for i in range(3):
        try:
            res = requests.get(url, headers=HEADERS, timeout=10)
            if res.status_code == 200:
                return res.text
        except Exception as e:
            print(f"retry {i+1}: {e}")
        time.sleep(random.uniform(2, 5))
    raise Exception("ページ取得失敗")

html = fetch(URL)
soup = BeautifulSoup(html, "lxml")

rows = soup.select("section.m_senkyo_result_data")
records = []

for row in rows:
    name_tag = row.select_one("h2 a")
    kana_tag = row.select_one("span.m_senkyo_result_data_kana")

    name = name_tag.contents[0].strip() if name_tag and name_tag.contents else ""
    kana = kana_tag.get_text(strip=True) if kana_tag else ""

    para = row.select_one(".m_senkyo_result_data_para")
    age, gender, jobtype = "", "", ""
    if para:
        text = para.get_text(" ", strip=True)
        m = re.search(r"(\d+)歳\s*\((男|女)\)\s*(現職|新人)?", text)
        if m:
            age, gender, jobtype = m.group(1), m.group(2), m.group(3) or ""

    party = row.select_one(".m_senkyo_result_data_circle")
    party = party.get_text(strip=True) if party else ""

    remark_tag = row.select_one(".m_senkyo_result_data_para.small")
    remark = remark_tag.get_text(strip=True) if remark_tag else ""

    records.append([name, kana, age, gender, jobtype, party, remark])

with open("senkyo_candidates_from_web.csv", "w", newline="", encoding="utf-8-sig") as f:
    writer = csv.writer(f)
    writer.writerow(["名前", "よみがな", "年齢", "性別", "職種区分", "所属政党", "備考"])
    writer.writerows(records)

print(f" {len(records)}件の候補者データを取得しました。")

python go2senkyo_extractor.py

# python go2senkyo_extractor.py
65件の候補者データを取得しました。

# ls *.csv
senkyo_candidates_from_web.csv