MakerWorld 크롤링 방법: 3D 모델 데이터 및 디자이너 통계

from playwright.sync_api import sync_playwright

def scrape_makerworld():
    with sync_playwright() as p:
        # stealth 스타일의 헤더로 실행
        browser = p.chromium.launch(headless=True)
        page = browser.new_page()
        page.goto('https://makerworld.com/en/models', wait_until='networkidle')
        
        # React를 통해 렌더링되는 모델 카드 대기
        page.wait_for_selector("div[data-testid='model-card']")
        
        models = page.query_selector_all("div[data-testid='model-card']")
        for model in models:
            # CSS 클래스보다 안정적인 표준 속성 사용
            title = model.query_selector('h3').inner_text()
            print(f'모델 발견: {title}')
            
        browser.close()

scrape_makerworld()

import scrapy
from scrapy_playwright.page import PageMethod

class MakerworldSpider(scrapy.Spider):
    name = 'makerworld'
    start_urls = ['https://makerworld.com/en/models']

    def start_requests(self):
        for url in self.start_urls:
            yield scrapy.Request(
                url,
                meta=dict(
                    playwright=True,
                    playwright_page_methods=[
                        PageMethod('wait_for_selector', "div[data-testid='model-card']"),
                    ],
                )
            )

    def parse(self, response):
        # Scrapy-playwright를 사용하여 JS로 렌더링된 HTML 파싱
        for model in response.css("div[data-testid='model-card']"):
            yield {
                'title': model.css('h3::text').get(),
                'downloads': model.css('span.stats-downloads::text').get(),
                'link': response.urljoin(model.css('a::attr(href)').get())
            }

const puppeteer = require('puppeteer');

(async () => {
  const browser = await puppeteer.launch({ headless: true });
  const page = await browser.newPage();
  
  // 실제 사용자와 유사한 User-Agent 설정
  await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) Chrome/119.0.0.0');
  
  await page.goto('https://makerworld.com/en/models', { waitUntil: 'networkidle2' });
  
  // React 컴포넌트가 마운트될 때까지 대기
  await page.waitForSelector("div[data-testid='model-card']");
  
  const models = await page.evaluate(() => {
    const cards = Array.from(document.querySelectorAll("div[data-testid='model-card']"));
    return cards.map(card => ({
      title: card.querySelector('h3')?.innerText,
      link: card.querySelector('a')?.href
    }));
  });
  
  console.log(models);
  await browser.close();
})();