martinholovsky/claude-skills-generator/browser-automation

# tests/test_browser_automation.py
import pytest
from playwright.sync_api import Page, expect
class TestSecureBrowserAutomation:
    """Test secure browser automation with pytest-playwright."""
    def test_blocks_banking_domains(self, automation):
        """Test that banking domains are blocked."""
        with pytest.raises(SecurityError, match="URL blocked"):
            automation.navigate("https://chase.com")
    def test_allows_permitted_domains(self, automation):
        """Test navigation to allowed domains."""
        automation.navigate("https://example.com")
        assert "Example" in automation.page.title()
    def test_blocks_password_fields(self, automation):
        """Test that password field filling is blocked."""
        automation.navigate("https://example.com/form")
        with pytest.raises(SecurityError, match="password"):
            automation.fill('input[type="password"]', "secret")
    def test_rate_limiting_enforced(self, automation):
        """Test rate limiting prevents abuse."""
        for _ in range(60):
            automation.check_request()
        with pytest.raises(RateLimitError):
            automation.check_request()
@pytest.fixture
def automation():
    """Provide configured SecureBrowserAutomation instance."""
    auto = SecureBrowserAutomation(
        domain_allowlist=['example.com'],
        permission_tier='standard'
    )
    auto.start_session()
    yield auto
    auto.close()

# Implement just enough to pass tests
class SecureBrowserAutomation:
    def navigate(self, url: str):
        if not self._validate_url(url):
            raise SecurityError(f"URL blocked: {url}")
        self.page.goto(url)

# Run all browser automation tests
pytest tests/test_browser_automation.py -v --headed
 
# Run with coverage
pytest tests/test_browser_automation.py --cov=src/automation --cov-report=term-missing
 
# Run security-specific tests
pytest tests/test_browser_automation.py -k "security" -v

# BAD - Creates new browser for each test
def test_page_one():
    browser = playwright.chromium.launch()
    page = browser.new_page()
    page.goto("https://example.com/one")
    browser.close()
def test_page_two():
    browser = playwright.chromium.launch()  # Slow startup again
    page = browser.new_page()
    page.goto("https://example.com/two")
    browser.close()
# GOOD - Reuse browser context
@pytest.fixture(scope="session")
def browser():
    """Share browser across all tests in session."""
    pw = sync_playwright().start()
    browser = pw.chromium.launch()
    yield browser
    browser.close()
    pw.stop()
@pytest.fixture
def page(browser):
    """Create fresh context per test for isolation."""
    context = browser.new_context()
    page = context.new_page()
    yield page
    context.close()

# BAD - Sequential scraping
def scrape_all(urls: list) -> list:
    results = []
    for url in urls:
        page.goto(url)
        results.append(page.content())
    return results  # Very slow for many URLs
# GOOD - Parallel with multiple contexts
def scrape_all_parallel(urls: list, browser, max_workers: int = 4) -> list:
    """Scrape URLs in parallel using multiple contexts."""
    from concurrent.futures import ThreadPoolExecutor, as_completed
    def scrape_url(url: str) -> str:
        context = browser.new_context()
        page = context.new_page()
        try:
            page.goto(url, wait_until='domcontentloaded')
            return page.content()
        finally:
            context.close()
    with ThreadPoolExecutor(max_workers=max_workers) as executor:
        futures = {executor.submit(scrape_url, url): url for url in urls}
        return [future.result() for future in as_completed(futures)]

# BAD - Load all resources
page.goto("https://example.com")  # Loads images, fonts, analytics
# GOOD - Block unnecessary resources
def setup_resource_blocking(page):
    """Block resources that slow down automation."""
    page.route("**/*", lambda route: (
        route.abort() if route.request.resource_type in [
            "image", "media", "font", "stylesheet"
        ] else route.continue_()
    ))
# Usage
setup_resource_blocking(page)
page.goto("https://example.com")  # 2-3x faster

# BAD - Allow all tracking requests
page.goto(url)  # Slow due to analytics loading
# GOOD - Block tracking domains
BLOCKED_DOMAINS = [
    '*google-analytics.com*',
    '*googletagmanager.com*',
    '*facebook.com/tr*',
    '*doubleclick.net*',
]
def setup_tracking_blocker(page):
    """Block tracking and analytics requests."""
    for pattern in BLOCKED_DOMAINS:
        page.route(pattern, lambda route: route.abort())
# Apply before navigation
setup_tracking_blocker(page)
page.goto(url)  # Faster, no tracking overhead

# BAD - Slow selectors
page.locator("//div[@class='container']//span[contains(text(), 'Submit')]").click()
page.wait_for_selector(".dynamic-content", timeout=30000)
# GOOD - Fast, specific selectors
page.locator("[data-testid='submit-button']").click()  # Direct attribute
page.locator("#unique-id").click()  # ID is fastest
# GOOD - Use role selectors for accessibility
page.get_by_role("button", name="Submit").click()
page.get_by_label("Email").fill("test@example.com")
# GOOD - Combine selectors for specificity without XPath
page.locator("form.login >> button[type='submit']").click()

from playwright.sync_api import sync_playwright
import logging
import re
from urllib.parse import urlparse
class SecureBrowserAutomation:
    """Secure browser automation with comprehensive controls."""
    BLOCKED_DOMAINS = {
        'chase.com', 'bankofamerica.com', 'wellsfargo.com',
        'accounts.google.com', 'login.microsoft.com',
        'paypal.com', 'venmo.com', 'stripe.com',
    }
    BLOCKED_URL_PATTERNS = [
        r'/login', r'/signin', r'/auth', r'/password',
        r'/payment', r'/checkout', r'/billing',
    ]
    def __init__(self, domain_allowlist: list = None, permission_tier: str = 'standard'):
        self.domain_allowlist = domain_allowlist
        self.permission_tier = permission_tier
        self.logger = logging.getLogger('browser.security')
        self.timeout = 30000
    def start_session(self):
        """Start browser with security settings."""
        self.playwright = sync_playwright().start()
        self.browser = self.playwright.chromium.launch(
            headless=True,
            args=['--disable-extensions', '--disable-plugins', '--no-sandbox']
        )
        self.context = self.browser.new_context(ignore_https_errors=False)
        self.context.set_default_timeout(self.timeout)
        self.page = self.context.new_page()
    def navigate(self, url: str):
        """Navigate with URL validation."""
        if not self._validate_url(url):
            raise SecurityError(f"URL blocked: {url}")
        self._audit_log('navigate', url)
        self.page.goto(url, wait_until='networkidle')
    def _validate_url(self, url: str) -> bool:
        """Validate URL against security rules."""
        parsed = urlparse(url)
        domain = parsed.netloc.lower().removeprefix('www.')
        if any(domain == d or domain.endswith('.' + d) for d in self.BLOCKED_DOMAINS):
            return False
        if self.domain_allowlist:
            if not any(domain == d or domain.endswith('.' + d) for d in self.domain_allowlist):
                return False
        return not any(re.search(p, url, re.I) for p in self.BLOCKED_URL_PATTERNS)
    def close(self):
        """Clean up browser session."""
        if hasattr(self, 'context'):
            self.context.clear_cookies()
            self.context.close()
        if hasattr(self, 'browser'):
            self.browser.close()
        if hasattr(self, 'playwright'):
            self.playwright.stop()

import time
class BrowserRateLimiter:
    """Rate limit browser operations."""
    def __init__(self, requests_per_minute: int = 60):
        self.requests_per_minute = requests_per_minute
        self.request_times = []
    def check_request(self):
        """Check if request is allowed."""
        cutoff = time.time() - 60
        self.request_times = [t for t in self.request_times if t > cutoff]
        if len(self.request_times) >= self.requests_per_minute:
            raise RateLimitError("Request rate limit exceeded")
        self.request_times.append(time.time())