Daily Pawsをスクレイピングする方法：ステップバイステップのウェブスクレイパーガイド

from playwright.sync_api import sync_playwright

def scrape_daily_paws():
    with sync_playwright() as p:
        # 強力な Cloudflare 対策が必要な場合は headless モードをオフにする
        browser = p.chromium.launch(headless=True)
        page = browser.new_page()
        
        # 犬種一覧ページに移動
        page.goto('https://www.dailypaws.com/dogs-puppies/dog-breeds')
        
        # カードが読み込まれるのを待機
        page.wait_for_selector('.mntl-card-list-items')
        
        # 最初の5つの犬種のタイトルを抽出
        breeds = page.query_selector_all('.mntl-card-list-items span.card__title')
        for breed in breeds[:5]:
            print(breed.inner_text())
            
        browser.close()

scrape_daily_paws()

import scrapy

class DailyPawsSpider(scrapy.Spider):
    name = 'dailypaws'
    allowed_domains = ['dailypaws.com']
    start_urls = ['https://www.dailypaws.com/dogs-puppies/dog-breeds']

    def parse(self, response):
        # 犬種カードをループ処理
        for item in response.css('a.mntl-card-list-items'):
            yield {
                'name': item.css('span.card__title::text').get(),
                'link': item.attrib['href']
            }
        
        # ページネーションがある場合は追跡
        next_page = response.css('a.mntl-pagination__next::attr(href)').get()
        if next_page:
            yield response.follow(next_page, self.parse)

const puppeteer = require('puppeteer');

(async () => {
  const browser = await puppeteer.launch({ headless: true });
  const page = await browser.newPage();
  
  // 信頼できる User-Agent を設定
  await page.setUserAgent('Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36');
  
  await page.goto('https://www.dailypaws.com/dogs-puppies/dog-breeds');
  
  const data = await page.evaluate(() => {
    const titles = Array.from(document.querySelectorAll('.card__title'));
    return titles.map(t => t.innerText.trim());
  });

  console.log('Scraped Breeds:', data);
  await browser.close();
})();