كيفية كشط بيانات Rocket Mortgage: دليل شامل

import asyncio
from playwright.async_api import async_playwright

async def scrape_rocket_rates():
    async with async_playwright() as p:
        # Launching with stealth-like configurations
        browser = p.chromium.launch(headless=True)
        context = await browser.new_context(user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36")
        page = await context.new_page()
        
        await page.goto("https://www.rocketmortgage.com/mortgage-rates", wait_until="networkidle")
        
        # Wait for dynamic React content to load
        await page.wait_for_selector(".rates-table")
        
        # Extract data from the DOM
        data = await page.evaluate("""() => {
            const items = Array.from(document.querySelectorAll('.rate-card-container'));
            return items.map(item => ({
                product: item.querySelector('.loan-title')?.innerText,
                rate: item.querySelector('.rate-percentage')?.innerText
            }));
        }""")
        
        print(data)
        await browser.close()

asyncio.run(scrape_rocket_rates())

import scrapy

class RocketSpider(scrapy.Spider):
    name = "rocket_spider"
    allowed_domains = ["rocketmortgage.com"]
    start_urls = ["https://www.rocketmortgage.com/mortgage-rates"]

    def parse(self, response):
        # لهذا الموقع، يوصى بشدة باستخدام Scrapy-Playwright للتعامل مع JS
        for rate_card in response.css(".rate-card"):
            yield {
                "product": rate_card.css(".product-name::text").get(),
                "interest_rate": rate_card.css(".rate-value::text").get(),
                "apr": rate_card.css(".apr-value::text").get()
            }

const puppeteer = require('puppeteer');

(async () => {
  const browser = await puppeteer.launch({ headless: true });
  const page = await browser.newPage();
  await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36');

  await page.goto('https://www.rocketmortgage.com/mortgage-rates', { waitUntil: 'networkidle2' });

  const rates = await page.evaluate(() => {
    const cards = Array.from(document.querySelectorAll('.rate-row'));
    return cards.map(c => c.innerText.trim());
  });

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