Selenium 4でブログカードのタイトルとURLをCSVに保存する方法

import csv
from pathlib import Path
from urllib.parse import urljoin, urlparse
from bs4 import BeautifulSoup


def extract_cards(source, base_url):
    soup = BeautifulSoup(source, "html.parser")
    rows, seen = [], set()
    for card in soup.select("#main_content .p-postList__item"):
        title = card.select_one(".p-postList__title")
        link = card.select_one("a.p-postList__link[href]")
        if title is None or link is None:
            continue
        label = " ".join(title.get_text(" ", strip=True).split())
        target = urljoin(base_url, link["href"])
        parsed = urlparse(target)
        if not label or parsed.scheme not in ("http", "https") or not parsed.netloc:
            continue
        if target not in seen:
            rows.append((label, target))
            seen.add(target)
    return rows


def csv_text(value):
    value = str(value)
    # Avoid spreadsheet formula evaluation when a title begins with =,+,-,@.
    if value.lstrip().startswith(("=", "+", "-", "@")):
        return "'" + value
    return value


def write_csv(rows, output):
    if not rows:
        raise ValueError("No cards found; check the page and selector before writing.")
    with Path(output).open("x", encoding="utf-8-sig", newline="") as stream:
        writer = csv.writer(stream)
        writer.writerow(("ID", "TITLE", "URL"))
        for number, (title, target) in enumerate(rows, 1):
            writer.writerow((number, csv_text(title), csv_text(target)))

import argparse
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from card_extract import extract_cards, write_csv


def collect(url, output):
    driver = webdriver.Chrome()
    try:
        driver.set_page_load_timeout(30)
        driver.get(url)
        WebDriverWait(driver, 15).until(
            EC.presence_of_element_located(
                (By.CSS_SELECTOR, "#main_content .p-postList__item")
            )
        )
        rows = extract_cards(driver.page_source, driver.current_url)
        write_csv(rows, output)
        print(f"Saved {len(rows)} unique visible-page links: {output}")
    finally:
        driver.quit()


if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument("--url", default="https://cg-method.com/work-tools/")
    parser.add_argument("--output", default="cards.csv")
    args = parser.parse_args()
    collect(args.url, args.output)