Automatización del navegador con Playwright

Playwright es el estándar

Install

# pip install playwright
playwright install   # downloads Chromium, Firefox, WebKit

Basic Usage

from playwright.sync_api import sync_playwright

with sync_playwright() as p:
    browser = p.chromium.launch(headless=True)
    page = browser.new_page()
    page.goto('https://example.com')
    print(page.title())
    browser.close()

Selectores

page.click('button.submit')                # CSS
page.click('text=Submit')                  # text
page.click('role=button[name="Submit"]')   # ARIA

Filling Forms

page.fill('input[name="email"]', 'alice@example.com')
page.fill('input[name="password"]', 'secret')
page.click('button[type="submit"]')
page.wait_for_url('https://example.com/dashboard')

Esperar a que aparezcan los elementos

page.click('button.export')
page.wait_for_selector('text=Download Ready')
page.click('text=Download Ready')

Reading Content

title = page.title()
body_text = page.inner_text('body')
href = page.get_attribute('a.download', 'href')

Screenshots

page.screenshot(path='page.png')
page.locator('.header').screenshot(path='header.png')

Full-Page Screenshot

page.screenshot(path='full.png', full_page=True)

Interceptación de red

def block_ads(route):
    if 'analytics' in route.request.url:
        route.abort()
    else:
        route.continue_()

page.route('**/*', block_ads)

Async API

from playwright.async_api import async_playwright
import asyncio

async def main():
    async with async_playwright() as p:
        browser = await p.chromium.launch()
        page = await browser.new_page()
        await page.goto('https://example.com')
        await browser.close()

asyncio.run(main())

Browser Context = una sesión

context = browser.new_context()
page = context.new_page()
# context.cookies, context.storage_state are isolated

Almacenamiento persistente

context.storage_state(path='state.json')
# Later:
context = browser.new_context(storage_state='state.json')

Tracing for Debugging

context.tracing.start(screenshots=True, snapshots=True)
# do stuff
context.tracing.stop(path='trace.zip')
# Open with: playwright show-trace trace.zip

¿Por qué Playwright?

Repaso