Guide 03 · templates: playwright, playwright-headed

Browser automation & web scraping for AI agents

Agents that browse need Chromium, and Chromium needs a machine. The playwright template boots with the browser and drivers installed — write the script (or let the model write it), run it, download what it found.

from pilldrops import Sandbox
sb = Sandbox.create(template="playwright", vcpu=2, memory_mb=2048)

script = '''
from playwright.sync_api import sync_playwright
with sync_playwright() as p:
    page = p.chromium.launch().new_page()
    page.goto("https://news.ycombinator.com")
    titles = page.locator(".titleline a").all_inner_texts()
    open("/out/titles.txt","w").write("\\n".join(titles))
'''
sb.files.write("/work/scrape.py", script)

sb.run("mkdir -p /out && python /work/scrape.py", timeout=120).check()
sb.download("/out", "./scraped")
sb.kill()