Web Scraper API vs DIY 网络爬虫

from playwright.sync_api import sync_playwright

def scrape_amazon_product(url: str, proxy: str) -> dict:
    with sync_playwright() as p:
        browser = p.chromium.launch(proxy={"server": proxy})
        page = browser.new_page()
        page.goto(url, wait_until="domcontentloaded")

        title = page.query_selector("#productTitle").inner_text().strip()
        price = page.query_selector(".a-price .a-offscreen").inner_text()
        rating = page.query_selector("#acrPopover span").inner_text()

        browser.close()
        return {"title": title, "price": price, "rating": rating}

curl "https://api.brightdata.com/datasets/v3/scrape?dataset_id=gd_l7q7dkf244hwjntr0&format=json" \
  -H "Authorization: Bearer API_KEY" \
  -H "Content-Type: application/json" \
  -d '[{"url": "https://www.amazon.com/dp/B0EXAMPLE"}]'

{
  "title": "Wireless Bluetooth Headphones",
  "price": 49.99,
  "currency": "USD",
  "rating": 4.5,
  "reviews_count": 12847,
  "seller": "TechBrand Official",
  "availability": "In Stock"
}