كيفية سحب البيانات من Crypto.com: دليل شامل لبيانات السوق

import asyncio
from playwright.async_api import async_playwright

async def scrape_crypto():
    async with async_playwright() as p:
        # Launching with a visible browser helps debug Cloudflare challenges
        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 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36'
        )
        page = await context.new_page()
        
        # Navigate to the price page
        await page.goto('https://crypto.com/price', wait_until='networkidle')
        
        # Wait for the table rows to render
        await page.wait_for_selector('tr')
        
        coins = await page.query_selector_all('tr')
        for coin in coins[:10]: # Scrape first 10 items
            name_el = await coin.query_selector('.css-1jj7z1p')
            price_el = await coin.query_selector('.css-16q9pr7')
            
            if name_el and price_el:
                name = await name_el.inner_text()
                price = await price_el.inner_text()
                print(f'Name: {name}, Price: {price}')
        
        await browser.close()

asyncio.run(scrape_crypto())

import scrapy

class CryptoSpider(scrapy.Spider):
    name = 'crypto_spider'
    allowed_domains = ['crypto.com']
    start_urls = ['https://crypto.com/price']

    def parse(self, response):
        # Scrapy requires a middleware like Scrapy-Playwright to handle Crypto.com JS
        for row in response.css('tr'):
            yield {
                'coin_name': row.css('.css-1jj7z1p::text').get(),
                'price': row.css('.css-16q9pr7::text').get(),
                'change_24h': row.css('.css-16ivz60::text').get(),
            }

        # Handle simple pagination if buttons are present
        next_page = response.css('a.pagination-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();
  
  // Set a realistic User Agent
  await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36');

  try {
    await page.goto('https://crypto.com/price', { waitUntil: 'networkidle2' });
    
    // Evaluate the page content
    const data = await page.evaluate(() => {
      const rows = Array.from(document.querySelectorAll('tr'));
      return rows.map(row => ({
        name: row.querySelector('.css-1jj7z1p')?.innerText.trim(),
        price: row.querySelector('.css-16q9pr7')?.innerText.trim()
      })).filter(item => item.name);
    });

    console.log(data);
  } catch (err) {
    console.error('Error during scraping:', err);
  } finally {
    await browser.close();
  }
})();