Sådan scraper du Moon.ly | Trin-for-trin guide til NFT-dataudtrækning

from playwright.sync_api import sync_playwright

def scrape_moonly(url):
    with sync_playwright() as p:
        # Start browser med en brugerdefineret user agent for at hjælpe med at omgå detektering
        browser = p.chromium.launch(headless=True)
        context = 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 = context.new_page()
        
        # Naviger og vent på, at siden indlæser JS-indhold fuldt ud
        page.goto(url, wait_until='networkidle')
        
        # Udtræk data ved hjælp af selektorer
        title = page.inner_text('h1')
        
        # Find floor price baseret på tekstlabels
        try:
            floor_price = page.locator("text=Floor price").locator(".. >> div").inner_text()
            print(f'Projekt: {title}, Floor: {floor_price}')
        except:
            print(f'Projekt: {title}, Floor price ikke fundet')
            
        browser.close()

scrape_moonly('https://moon.ly/nft/okay-bears')

import scrapy

class MoonlySpider(scrapy.Spider):
    name = 'moonly_spider'
    start_urls = ['https://moon.ly/solana']

    def parse(self, response):
        # Gennemgå projektkort på oversigtssiden
        for project in response.css('div.project-card'):
            yield {
                'name': project.css('h3::text').get(),
                'link': response.urljoin(project.css('a::attr(href)').get()),
                'floor': project.css('.floor-price::text').get(),
            }
        
        # Håndter paginering ved at finde linket til 'næste' knap
        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();
  
  // Brug af en brugerdefineret User-Agent er afgørende for Cloudflare-sider
  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');
  
  // Gå til mål-siden for NFT-kollektionen
  await page.goto('https://moon.ly/nft/okay-bears', { waitUntil: 'networkidle2' });

  const data = await page.evaluate(() => {
    return {
      title: document.querySelector('h1')?.innerText,
      description: document.querySelector('.project-description')?.innerText,
      mintDate: document.querySelector('.mint-date-selector')?.innerText
    };
  });

  console.log('Udtrukne data:', data);
  await browser.close();
})();