Homes.comをスクレイピングする方法：不動産データ抽出ガイド

import asyncio; from playwright.async_api import async_playwright; async def scrape(): async with async_playwright() as p: browser = await p.chromium.launch(headless=True); context = await browser.new_context(user_agent='Mozilla/5.0'); page = await context.new_page(); await page.goto('https://www.homes.com/for-sale/chicago-il/', wait_until='networkidle'); listings = await page.query_selector_all('.placard-container'); for l in listings: p_el = await l.query_selector('.price-container'); print(await p_el.inner_text()); await browser.close(); asyncio.run(scrape())

import scrapy; class HomesSpider(scrapy.Spider): name = 'homes'; start_urls = ['https://www.homes.com/for-sale/houston-tx/']; def parse(self, response): for listing in response.css('li.placard-container'): yield {'price': listing.css('.price-container::text').get(), 'address': listing.css('.address-container::text').get()}; next_p = response.css('a.next-page::attr(href)').get(); if next_p: yield response.follow(next_p, self.parse)

const puppeteer = require('puppeteer'); (async () => { const browser = await puppeteer.launch(); const page = await browser.newPage(); await page.setUserAgent('Mozilla/5.0'); await page.goto('https://www.homes.com/for-sale/miami-fl/'); await page.waitForSelector('.placard-container'); const data = await page.evaluate(() => { return Array.from(document.querySelectorAll('.placard-container')).map(c => ({ price: c.querySelector('.price-container')?.innerText })); }); console.log(data); await browser.close(); })();