Cómo hacer scraping en CoinCatapult: La guía definitiva de datos cripto

from playwright.sync_api import sync_playwright

def scrape_coincatapult():
    with sync_playwright() as p:
        # Lanzar con un navegador real puede ayudar a evadir verificaciones básicas
        browser = p.chromium.launch(headless=True)
        page = browser.new_page()
        
        # Navegar al sitio
        page.goto('https://coincatapult.com/', wait_until='networkidle')
        
        # Esperar a que la tabla se renderice
        page.wait_for_selector('table')
        
        # Extraer datos usando evaluación de Javascript
        coins = page.evaluate("""() => {
            const rows = Array.from(document.querySelectorAll('table tbody tr'));
            return rows.map(row => {
                const tds = row.querySelectorAll('td');
                return {
                    name: tds[2]?.innerText.trim(),
                    chain: tds[3]?.querySelector('img')?.alt || 'Unknown',
                    votes: tds[5]?.innerText.trim()
                };
            });
        }""")
        
        for coin in coins:
            print(coin)
            
        browser.close()

if __name__ == '__main__':
    scrape_coincatapult()

import scrapy

class CoinSpider(scrapy.Spider):
    name = 'coincatapult_spider'
    start_urls = ['https://coincatapult.com/']
    
    def parse(self, response):
        # Iterar a través de las filas de la tabla usando selectores CSS
        for row in response.css('table tbody tr'):
            yield {
                'name': row.css('td:nth-child(3)::text').get(),
                'symbol': row.css('td:nth-child(5)::text').get(),
                'votes': row.css('td:nth-child(6)::text').get(),
                'launch_date': row.css('td:nth-child(7)::text').get()
            }
        
        # Manejo básico de paginación si existe un enlace 'Next'
        next_page = response.css('ul.pagination 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({ headless: true });
    const page = await browser.newPage();
    
    // Establecer un viewport realista
    await page.setViewport({ width: 1280, height: 800 });
    
    // Ir a CoinCatapult
    await page.goto('https://coincatapult.com/', { waitUntil: 'networkidle2' });
    
    const data = await page.evaluate(() => {
        const results = [];
        const rows = document.querySelectorAll('table tbody tr');
        rows.forEach(row => {
            const cells = row.querySelectorAll('td');
            if (cells.length >= 6) {
                results.push({
                    name: cells[2].innerText.trim(),
                    chain: cells[3].querySelector('img')?.alt || 'N/A',
                    votes: cells[5].innerText.trim()
                });
            }
        });
        return results;
    });
    
    console.log(data);
    await browser.close();
})();