Booking.com 스크래핑 방법: 종합 웹 스크래핑 가이드

import asyncio
from playwright.async_api import async_playwright

async def scrape_booking():
    async with async_playwright() as p:
        # 탐지를 피하기 위해 비헤드리스 브라우저 또는 스텔스 플러그인을 사용하세요
        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')
        
        # 속도 카드 데이터가 동적으로 로드될 때까지 대기
        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()
            }
        
        # 페이지네이션 처리
        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();
  
  // 실제 사용자와 같은 User-Agent 설정이 필수적입니다
  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();
})();