Toptal 스크래핑 방법 | Toptal 웹 스크래퍼 가이드

import asyncio
from playwright.async_api import async_playwright

async def scrape_toptal():
    async with async_playwright() as p:
        # 스텔스 설정과 함께 헤드리스 또는 헤드형 브라우저 실행
        browser = await p.chromium.launch(headless=True)
        context = await browser.new_context(user_agent='Mozilla/5.0')
        page = await context.new_page()
        
        # 특정 인재 카테고리로 이동
        await page.goto('https://www.toptal.com/developers/python', wait_until='networkidle')
        
        # JavaScript를 통해 인재 카드가 렌더링될 때까지 대기
        await page.wait_for_selector('.talent-card')
        
        # 세부 정보 추출
        talents = await page.query_selector_all('.talent-card')
        for talent in talents:
            name_el = await talent.query_selector('.talent-name')
            name = await name_el.inner_text() if name_el else 'Unknown'
            print(f'Freelancer: {name}')
            
        await browser.close()

asyncio.run(scrape_toptal())

import scrapy

class ToptalSpider(scrapy.Spider):
    name = 'toptal_spider'
    start_urls = ['https://www.toptal.com/designers/all']
    
    # 추천: 사용자 에이전트(User Agent) 순환 및 Cloudflare 처리를 위한 미들웨어 사용
    custom_settings = {
        'USER_AGENT': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) Chrome/110.0.0.0 Safari/537.36',
        'CONCURRENT_REQUESTS': 1,
        'DOWNLOAD_DELAY': 3
    }

    def parse(self, response):
        # CSS 셀렉터를 사용하여 카드 루프 처리
        for talent in response.css('.talent-card'):
            yield {
                'name': talent.css('.talent-name::text').get().strip(),
                'title': talent.css('.talent-title::text').get().strip(),
                'skills': talent.css('.skill-tag::text').getall()
            }
            
        # 페이지네이션 처리 ('Load More' 링크가 보일 경우)
        next_page = response.css('a.next-page::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();
  
  // 실제 사용자처럼 위장
  await page.setUserAgent('Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36');
  
  await page.goto('https://www.toptal.com/product-managers', { waitUntil: 'networkidle2' });

  const data = await page.evaluate(() => {
    const cards = document.querySelectorAll('.talent-card');
    return Array.from(cards).map(card => ({
      name: card.querySelector('.talent-name')?.innerText,
      location: card.querySelector('.location')?.innerText
    }));
  });

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