Automação de navegador

Quando o HTML estático não basta: sites com JavaScript, login, CAPTCHA leve e interações. Playwright é a escolha moderna; Selenium ainda é útil em legados.

O que você vai aprender

• Instalar e usar Playwright (recomendado) e Selenium
• Navegar, clicar, preencher formulários e esperar elementos
• Tirar screenshots e extrair dados de páginas dinâmicas
• Headless vs headed e debugging
• Boas práticas de estabilidade (waits explícitos)

1. Playwright — instalação

pip install playwright
playwright install chromium

2. Exemplo básico com Playwright

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://quotes.toscrape.com")
    page.wait_for_selector("div.quote")

    quotes = page.query_selector_all("div.quote")
    for q in quotes[:5]:
        texto = q.query_selector("span.text").inner_text()
        autor = q.query_selector("small.author").inner_text()
        print(f"{autor}: {texto[:60]}...")

    page.screenshot(path="quotes.png", full_page=True)
    browser.close()

3. Login e formulários

page.goto("https://exemplo.com/login")
page.fill("input[name=email]", "[email protected]")
page.fill("input[name=password]", "senha-secreta")
page.click("button[type=submit]")
page.wait_for_url("**/dashboard**")
print("Login OK:", page.url)

4. Selenium (alternativa legada)

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC

opts = Options()
opts.add_argument("--headless=new")
driver = webdriver.Chrome(options=opts)
driver.get("https://quotes.toscrape.com")
WebDriverWait(driver, 10).until(
    EC.presence_of_element_located((By.CSS_SELECTOR, "div.quote"))
)
print(driver.find_element(By.CSS_SELECTOR, "div.quote span.text").text)
driver.quit()

5. Script prático: monitorar preço

from playwright.sync_api import sync_playwright
import json
from pathlib import Path
from datetime import datetime

URL = "https://books.toscrape.com/catalogue/a-light-in-the-attic_1000/index.html"

def capturar_preco():
    with sync_playwright() as p:
        browser = p.chromium.launch(headless=True)
        page = browser.new_page()
        page.goto(URL)
        page.wait_for_selector("p.price_color")
        preco = page.query_selector("p.price_color").inner_text()
        titulo = page.query_selector("h1").inner_text()
        browser.close()
        return {"titulo": titulo, "preco": preco, "quando": datetime.utcnow().isoformat()}

dados = capturar_preco()
historico = Path("precos.json")
lista = json.loads(historico.read_text()) if historico.exists() else []
lista.append(dados)
historico.write_text(json.dumps(lista, ensure_ascii=False, indent=2))
print(dados)

Sumário do curso