Airbnb のリスティングと価格をスクレイピングする方法（2025年版ガイド）

import asyncio
from playwright.async_api import async_playwright

async def scrape_airbnb():
    async with async_playwright() as p:
        # ボット検出を回避するため、実際のユーザープロファイルでブラウザを起動
        browser = await p.chromium.launch(headless=True)
        page = await browser.new_page()
        await page.goto('https://www.airbnb.com/s/homes')
        
        # React 経由でリスティングがレンダリングされるのを待機
        await page.wait_for_selector('[data-testid="card-container"]')
        
        listings = await page.query_selector_all('[data-testid="card-container"]')
        for item in listings:
            title = await item.query_selector('[data-testid="listing-card-title"]')
            price = await item.query_selector('span._1y74zay')
            if title and price:
                print(f'{await title.inner_text()}: {await price.inner_text()}')
        
        await browser.close()

asyncio.run(scrape_airbnb())

import scrapy

class AirbnbSpider(scrapy.Spider):
    name = 'airbnb'
    start_urls = ['https://www.airbnb.com/s/homes']

    def parse(self, response):
        for listing in response.css('[data-testid="card-container"]'):
            yield {
                'title': listing.css('[data-testid="listing-card-title"]::text').get(),
                'price': listing.css('span._1y74zay::text').get(),
                'rating': listing.css('span[aria-label*="rating"]::text').get()
            }

        next_page = response.css('a[aria-label="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();
  await page.goto('https://www.airbnb.com/s/homes');

  // 動的な React コンテンツの読み込みを待機
  await page.waitForSelector('[data-testid="card-container"]');

  const results = await page.evaluate(() => {
    const items = Array.from(document.querySelectorAll('[data-testid="card-container"]'));
    return items.map(el => ({
      title: el.querySelector('[data-testid="listing-card-title"]')?.innerText,
      price: el.querySelector('span._1y74zay')?.innerText
    }));
  });

  console.log(results);
  await browser.close();
})();