[Python] How can I avoid CAPTCHA with help of Playwright?

I am trying to login to familysearch.org with help of python and Playwright library.

Problem -- I see a CAPTCHA (attached image) when I am using my python script. Was trying playwright_stealth to overcome CAPTCH but it didn't help

My code

#!/usr/bin/env python3
"""
FamilySearch Login Script using Playwright Stealth
"""

import asyncio
import os
from playwright.async_api import async_playwright
from playwright_stealth import Stealth
import time


class FamilySearchLogin:
def __init__(self, headless: bool = False):
self.headless = headless
self.browser = None
self.page = None
self.playwright = None

async def start_browser(self):
"""Start the browser and create a new page with stealth mode"""
self.playwright = await async_playwright().start()

self.browser = await self.playwright.chromium.launch(
headless=self.headless,
args=[
'--no-sandbox',
'--disable-blink-features=AutomationControlled',
'--disable-dev-shm-usage',
'--disable-web-security',
'--disable-features=VizDisplayCompositor',
'--disable-background-timer-throttling',
'--disable-backgrounding-occluded-windows',
'--disable-renderer-backgrounding',
'--disable-field-trial-config',
'--disable-ipc-flooding-protection'
]
)

context = await self.browser.new_context(
viewport={'width': 1920, 'height': 1080},
user_agent='Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
locale='en-US',
timezone_id='America/New_York'
)

self.page = await context.new_page()

# Apply stealth mode
stealth = Stealth()
await stealth.apply_stealth_async(self.page)

# Additional stealth measures
await self.page.add_init_script("""
Object.defineProperty(navigator, 'webdriver', {
get: () => undefined,
});

// Override permissions
const originalQuery = window.navigator.permissions.query;
window.navigator.permissions.query = (parameters) => (
parameters.name === 'notifications' ?
Promise.resolve({ state: Notification.permission }) :
originalQuery(parameters)
);

// Override plugins
Object.defineProperty(navigator, 'plugins', {
get: () => [1, 2, 3, 4, 5],
});

// Override languages
Object.defineProperty(navigator, 'languages', {
get: () => ['en-US', 'en'],
});

// Override connection
Object.defineProperty(navigator, 'connection', {
get: () => ({
effectiveType: '4g',
rtt: 50,
downlink: 10,
saveData: false
}),
});
""")

async def navigate_to_login(self):
"""Navigate to the FamilySearch login page"""
login_url = "https://ident.familysearch.org/ru/identity/login/?state=https://www.familysearch.org/ru/"

print(f"Navigating to: {login_url}")

# Add random delays to appear more human-like
await asyncio.sleep(1 + (time.time() % 2))

await self.page.goto(login_url, wait_until='networkidle')

# Random wait time
await asyncio.sleep(2 + (time.time() % 3))
print("Successfully loaded FamilySearch login page")

async def handle_captcha_checkbox(self):
"""Handle the 'I'm not a robot' checkbox if present"""
try:
captcha_selectors = [
'iframe[title*="reCAPTCHA"]',
'iframe[src*="recaptcha"]',
'.recaptcha-checkbox',
'#recaptcha-anchor',
'iframe[title*="robot"]',
'iframe[title*="captcha"]'
]

for selector in captcha_selectors:
try:
captcha_frame = await self.page.query_selector(selector)
if captcha_frame:
print(f"Found captcha element: {selector}")

if 'iframe' in selector:
frame = await captcha_frame.content_frame()
if frame:
checkbox = await frame.query_selector('.recaptcha-checkbox-border')
if checkbox:
print("Clicking 'I'm not a robot' checkbox...")

# Human-like click with random delay
await asyncio.sleep(0.5 + (time.time() % 1))
await checkbox.click()
await asyncio.sleep(2 + (time.time() % 2))
return True
else:
print("Clicking 'I'm not a robot' checkbox...")
await asyncio.sleep(0.5 + (time.time() % 1))
await captcha_frame.click()
await asyncio.sleep(2 + (time.time() % 2))
return True

except Exception as e:
continue

print("No captcha checkbox found or already completed")
return False

except Exception as e:
print(f"Error handling captcha: {e}")
return False

async def fill_login_form(self, username: str, password: str):
"""Fill in the login form with credentials using human-like behavior"""
try:
print("Filling login form...")

await self.page.wait_for_load_state('networkidle')

# Find username field
username_selectors = [
'input[name="username"]',
'input[name="email"]',
'input[type="email"]',
'input[placeholder*="email"]',
'input[placeholder*="Email"]',
'input[id*="username"]',
'input[id*="email"]'
]

username_field = None
for selector in username_selectors:
try:
username_field = await self.page.query_selector(selector)
if username_field:
break
except:
continue

if not username_field:
print("Could not find username field")
return False

# Human-like typing for username
await username_field.click()
await asyncio.sleep(0.2)
await username_field.fill("")
await asyncio.sleep(0.1)

for char in username:
await username_field.type(char)
await asyncio.sleep(0.05 + (time.time() % 0.1))

print("Username filled")
await asyncio.sleep(0.5 + (time.time() % 1))

# Find password field
password_selectors = [
'input[name="password"]',
'input[type="password"]',
'input[placeholder*="password"]',
'input[placeholder*="Password"]',
'input[id*="password"]'
]

password_field = None
for selector in password_selectors:
try:
password_field = await self.page.query_selector(selector)
if password_field:
break
except:
continue

if not password_field:
print("Could not find password field")
return False

# Human-like typing for password
await password_field.click()
await asyncio.sleep(0.2)
await password_field.fill("")
await asyncio.sleep(0.1)

for char in password:
await password_field.type(char)
await asyncio.sleep(0.05 + (time.time() % 0.1))

print("Password filled")
await asyncio.sleep(0.5 + (time.time() % 1))

return True

except Exception as e:
print(f"Error filling login form: {e}")
return False

async def submit_login(self):
"""Submit the login form"""
try:
print("Submitting login form...")

submit_selectors = [
'button[type="submit"]',
'input[type="submit"]',
'button:has-text("Sign In")',
'button:has-text("Login")',
'button:has-text("Войти")',
'button:has-text("Вход")',
'button[class*="submit"]',
'button[class*="login"]'
]

submit_button = None
for selector in submit_selectors:
try:
submit_button = await self.page.query_selector(selector)
if submit_button:
break
except:
continue

if not submit_button:
print("Could not find submit button")
return False

# Human-like click with random delay
await asyncio.sleep(0.5 + (time.time() % 1))
await submit_button.click()
print("Login form submitted")

# Wait for navigation with random delay
await asyncio.sleep(3 + (time.time() % 3))

return True

except Exception as e:
print(f"Error submitting login form: {e}")
return False

async def check_login_success(self):
"""Check if login was successful"""
try:
await asyncio.sleep(2 + (time.time() % 2))
current_url = self.page.url
print(f"Current URL: {current_url}")

if "familysearch.org" in current_url and "login" not in current_url:
print("Login appears to be successful!")
return True
else:
print("Login may have failed - still on login page")
return False

except Exception as e:
print(f"Error checking login status: {e}")
return False

async def login(self, username: str, password: str):
"""Complete login process"""
try:
await self.start_browser()
await self.navigate_to_login()

await self.handle_captcha_checkbox()

if not await self.fill_login_form(username, password):
return False

if not await self.submit_login():
return False

success = await self.check_login_success()

if success:
print("Login completed successfully!")
return True
else:
print("Login failed or requires manual intervention")
return False

except Exception as e:
print(f"Error during login process: {e}")
return False

async def close(self):
"""Close browser and cleanup"""
if self.browser:
await self.browser.close()
if self.playwright:
await self.playwright.stop()


async def main():
"""Main function to run the login script"""
username = os.getenv('FAMILYSEARCH_USERNAME')
password = os.getenv('FAMILYSEARCH_PASSWORD')

if not username:
username = input("Enter FamilySearch username/email: ")
if not password:
password = input("Enter FamilySearch password: ")

login_handler = FamilySearchLogin(headless=False)

try:
success = await login_handler.login(username, password)

if success:
print("Login successful! You can now interact with the page.")
input("Press Enter to close the browser...")
else:
print("Login failed. Please check your credentials and try again.")

except Exception as e:
print(f"An error occurred: {e}")
finally:
await login_handler.close()


if __name__ == "__main__":
asyncio.run(main())

Continue reading...