Booking.comのスクレイピング方法：包括的なウェブスクレイピングガイド

import asyncio
from playwright.async_api import async_playwright

async def scrape_booking():
    async with async_playwright() as p:
        # 検出を避けるために非ヘッドレスブラウザやステルスプラグインを使用することを検討してください
        browser = await p.chromium.launch(headless=True)
        context = await browser.new_context(user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) ...')
        page = await context.new_page()
        
        await page.goto('https://www.booking.com/searchresults.html?ss=Paris', wait_until='networkidle')
        
        # プロパティカードが動的にロードされるのを待機
        await page.wait_for_selector('[data-testid="property-card"]')
        
        hotels = await page.query_selector_all('[data-testid="property-card"]')
        for hotel in hotels:
            title_el = await hotel.query_selector('[data-testid="title"]')
            title = await title_el.inner_text() if title_el else 'N/A'
            print(f'Name: {title}')
            
        await browser.close()

asyncio.run(scrape_booking())

import scrapy

class BookingSpider(scrapy.Spider):
    name = 'booking'
    allowed_domains = ['booking.com']
    start_urls = ['https://www.booking.com/searchresults.html?ss=New+York']

    custom_settings = {
        'USER_AGENT': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36',
        'DOWNLOAD_DELAY': 2
    }

    def parse(self, response):
        for hotel in response.css('[data-testid="property-card"]'):
            yield {
                'name': hotel.css('[data-testid="title"]::text').get(),
                'price': hotel.css('[data-testid="price-and-discounted-price"] span::text').get(),
                'score': hotel.css('[data-testid="review-score-badge"]::text').get()
            }
        
        # ページネーションの処理
        next_page = response.css('button[aria-label="Next page"]::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();
  
  // 現実的な User-Agent の設定は不可欠です
  await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36');
  
  await page.goto('https://www.booking.com/searchresults.html?ss=Berlin', { waitUntil: 'networkidle2' });
  
  await page.waitForSelector('[data-testid="property-card"]');
  
  const results = await page.evaluate(() => {
    const items = Array.from(document.querySelectorAll('[data-testid="property-card"]'));
    return items.map(item => ({
      name: item.querySelector('[data-testid="title"]')?.innerText,
      price: item.querySelector('[data-testid="price-and-discounted-price"]')?.innerText
    }));
  });
  
  console.log(results);
  await browser.close();
})();