Sådan scraper du LivePiazza: Philadelphia Real Estate Scraper

import asyncio
from playwright.async_api import async_playwright

async def scrape_live_piazza():
    async with async_playwright() as p:
        # Lancering med en specifik user agent for at efterligne en rigtig browser
        browser = await p.chromium.launch(headless=True)
        context = await browser.new_context(user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36')
        page = await context.new_page()
        
        await page.goto('https://www.livepiazza.com/alta/')
        
        # Vent på at den dynamiske enhedstabel indlæses
        await page.wait_for_selector('.unit-row', timeout=15000)
        
        units = await page.query_selector_all('.unit-row')
        for unit in units:
            unit_id = await (await unit.query_selector('.unit-id')).inner_text()
            rent = await (await unit.query_selector('.unit-rent')).inner_text()
            print(f'Unit: {unit_id.strip()} | Rent: {rent.strip()}')
        
        await browser.close()

asyncio.run(scrape_live_piazza())

import scrapy

class PiazzaSpider(scrapy.Spider):
    name = 'piazza_spider'
    start_urls = ['https://www.livepiazza.com/communities']

    def parse(self, response):
        # Scrapy kræver en JS-rendering middleware (som Scrapy-Playwright) til dette site
        for building in response.css('.building-section'):
            yield {
                'building_name': building.css('h3.name::text').get(),
                'link': building.css('a.explore-btn::attr(href)').get(),
                'starting_price': building.css('.starting-from::text').get()
            }
        
        # Eksempel på navigation til næste side
        next_page = response.css('a.next-page::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.livepiazza.com/montesino', { waitUntil: 'networkidle2' });

  // Vent på at residences-containeren bliver renderet
  await page.waitForSelector('.residences-container');

  const apartmentData = await page.evaluate(() => {
    const rows = Array.from(document.querySelectorAll('.apartment-listing'));
    return rows.map(row => ({
      type: row.querySelector('.plan-type').innerText,
      sqft: row.querySelector('.sqft').innerText,
      available: row.querySelector('.availability').innerText
    }));
  });

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