Idealistaをスクレイピングする方法：究極のテクニカルガイド (2025)

import asyncio
from playwright.async_api import async_playwright
from playwright_stealth import stealth

async def run():
    async with async_playwright() as p:
        browser = await p.chromium.launch(headless=True)
        context = await browser.new_context()
        page = await context.new_page()
        # 基本的なフィンガープリントを回避するためにステルスを適用
        await stealth(page)
        await page.goto('https://www.idealista.com/en/alquiler-viviendas/madrid-madrid/')
        await page.wait_for_selector('.item-info-container')
        
        items = await page.locator('.item-info-container').all()
        for item in items:
            title = await item.locator('.item-link').inner_text()
            price = await item.locator('.item-price').inner_text()
            print({'title': title.strip(), 'price': price.strip()})
        await browser.close()

asyncio.run(run())

import scrapy

class IdealistaSpider(scrapy.Spider):
    name = 'idealista'
    start_urls = ['https://www.idealista.com/en/venta-viviendas/madrid-madrid/']

    def parse(self, response):
        for listing in response.css('.item-info-container'):
            yield {
                'title': listing.css('.item-link::text').get().strip(),
                'price': listing.css('.item-price::text').get().strip(),
                'link': response.urljoin(listing.css('.item-link::attr(href)').get())
            }

        next_page = response.css('.next a::attr(href)').get()
        if next_page:
            yield response.follow(next_page, self.parse)

const puppeteer = require('puppeteer-extra');
const StealthPlugin = require('puppeteer-extra-plugin-stealth');
puppeteer.use(StealthPlugin());

(async () => {
  const browser = await puppeteer.launch({ headless: true });
  const page = await browser.newPage();
  await page.goto('https://www.idealista.com/en/venta-viviendas/madrid-madrid/');
  
  await page.waitForSelector('.item-info-container');
  const listings = await page.evaluate(() => {
    return Array.from(document.querySelectorAll('.item-info-container')).map(el => ({
      title: el.querySelector('.item-link')?.innerText.trim(),
      price: el.querySelector('.item-price')?.innerText.trim()
    }));
  });
  
  console.log(listings);
  await browser.close();
})();