كيفية سحب البيانات من CoinMarketCap: دليل كامل حول الـ Web Scraping

from playwright.sync_api import sync_playwright

def run():
    with sync_playwright() as p:
        # Launching a headed browser can sometimes help with debugging
        browser = p.chromium.launch(headless=True)
        context = browser.new_context(user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) Chrome/120.0.0.0')
        page = context.new_page()
        
        page.goto('https://coinmarketcap.com/')
        
        # Wait for the dynamic React table to render fully
        page.wait_for_selector('table.cmc-table')
        
        # Extracting the top 10 coin names using the specific class
        coins = page.query_selector_all('.coin-item-name')
        for coin in coins[:10]:
            print(coin.inner_text())
            
        browser.close()

run()

import scrapy

class CoinSpider(scrapy.Spider):
    name = 'coin_spider'
    start_urls = ['https://coinmarketcap.com/']
    
    def parse(self, response):
        # Scrapy selectors can handle CSS paths efficiently
        for row in response.css('table.cmc-table tbody tr'):
            yield {
                'name': row.css('p.coin-item-name::text').get(),
                'symbol': row.css('p.coin-item-symbol::text').get(),
                'price': row.css('div.sc-131cee3c-0 span::text').get()
            }
            
        # Basic pagination handling for subsequent pages
        next_page = response.css('li.next a::attr(href)').get()
        if next_page:
            yield response.follow(next_page, self.parse)

const puppeteer = require('puppeteer');

(async () => {
  const browser = await puppeteer.launch();
  const page = await browser.newPage();
  await page.setViewport({ width: 1280, height: 800 });
  
  // Using networkidle2 ensures most React components have finished loading
  await page.goto('https://coinmarketcap.com/', { waitUntil: 'networkidle2' });

  const data = await page.evaluate(() => {
    const results = [];
    const rows = document.querySelectorAll('table.cmc-table tbody tr');
    rows.forEach((row, index) => {
      if (index < 10) {
        results.push({
          name: row.querySelector('.coin-item-name')?.innerText,
          price: row.querySelector('.sc-131cee3c-0')?.innerText
        });
      }
    });
    return results;
  });

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