Bypassing Cloudflare Turnstile

from scrapling import StealthyFetcher

response = StealthyFetcher.fetch(
    'https://cloudflare-protected-site.com',
    solve_cloudflare=True
)

print(response.status)  # 200 - Challenge solved!
print(response.text)    # Actual page content

response = StealthyFetcher.fetch(
    'https://example.com',
    solve_cloudflare=True
)

# Scrapling waits for the challenge to disappear
while "<title>Just a moment...</title>" in page_content:
    page.wait_for_timeout(1000)
    page.wait_for_load_state()

response = StealthyFetcher.fetch(
    'https://example.com',
    solve_cloudflare=True,
    headless=True  # Works in headless mode!
)

response = StealthyFetcher.fetch(
    'https://example.com',
    solve_cloudflare=True
)

# Detects embedded turnstile from script tags
if selector.css('script[src*="challenges.cloudflare.com/turnstile/v"]'):
    challenge_type = "embedded"

def _detect_cloudflare(page_content: str) -> str | None:
    """Detect Cloudflare challenge type"""
    challenge_types = (
        "non-interactive",
        "managed",
        "interactive",
    )
    for ctype in challenge_types:
        if f"cType: '{ctype}'" in page_content:
            return ctype
    
    # Check for embedded turnstile
    if 'challenges.cloudflare.com/turnstile' in page_content:
        return "embedded"
    
    return None

# Find the challenge iframe
iframe = page.frame(url=re.compile(
    r"^https?://challenges\.cloudflare\.com/cdn-cgi/challenge-platform/.*"
))

# Get bounding box
outer_box = iframe.frame_element().bounding_box()

# Calculate click position with random offset (26-28, 25-27)
captcha_x = outer_box["x"] + randint(26, 28)
captcha_y = outer_box["y"] + randint(25, 27)

# Click with human-like delay
page.mouse.click(captcha_x, captcha_y, delay=randint(100, 200))

from scrapling import StealthyFetcher

response = StealthyFetcher.fetch(
    'https://cloudflare-site.com',
    solve_cloudflare=True,
    timeout=60000  # At least 60 seconds
)

from scrapling import StealthySession

with StealthySession(solve_cloudflare=True) as session:
    # First request solves challenge and gets cookies
    response1 = session.fetch('https://example.com/page1')
    
    # Subsequent requests use same cookies (no re-solving)
    response2 = session.fetch('https://example.com/page2')
    response3 = session.fetch('https://example.com/page3')

from scrapling import Spider, StealthySession

class CloudflareSpider(Spider):
    name = 'cf_spider'
    start_urls = ['https://cloudflare-protected.com']
    
    def configure_sessions(self, manager):
        manager.add('default', StealthySession(
            solve_cloudflare=True,
            timeout=60000,
            headless=True
        ))
    
    async def parse(self, response):
        # Challenge already solved!
        yield {'title': response.css('title::text').get()}
        
        # Follow links - cookies preserved
        for link in response.css('a::attr(href)').getall():
            yield response.follow(link, callback=self.parse_item)

from scrapling import AsyncStealthySession
import asyncio

async def scrape():
    async with AsyncStealthySession(solve_cloudflare=True) as session:
        response = await session.fetch('https://example.com')
        return response.text

result = asyncio.run(scrape())

response = StealthyFetcher.fetch(
    'https://example.com',
    solve_cloudflare=True,
    timeout=90000  # 90 seconds for slower challenges
)

from scrapling import StealthySession, ProxyRotator

rotator = ProxyRotator([
    'http://proxy1:8080',
    'http://proxy2:8080',
])

with StealthySession(
    solve_cloudflare=True,
    proxy_rotator=rotator
) as session:
    response = session.fetch('https://example.com')

def after_solve(page):
    # Cloudflare is already solved at this point
    page.click('button#load-more')
    page.wait_for_timeout(2000)

response = StealthyFetcher.fetch(
    'https://example.com',
    solve_cloudflare=True,
    page_action=after_solve
)

response = StealthyFetcher.fetch(
    'https://example.com',
    solve_cloudflare=True,
    wait_selector='div.content',
    wait_selector_state='visible'
)

# Recommended configuration
with StealthySession(
    solve_cloudflare=True,
    timeout=90000,
    hide_canvas=True,
    block_webrtc=True,
    google_search=True,
    disable_resources=True
) as session:
    for url in urls:
        response = session.fetch(url)
        # Process response
        await asyncio.sleep(2)  # Respect rate limits