How to Integrate Helium with CapSolver for Seamless CAPTCHA Solving

# Install Helium
pip install helium

# Install requests library for CapSolver API
pip install requests

from helium import *

# Start browser and navigate
start_chrome("https://wikipedia.org")

# Type into search box
write("Python programming", into=S("input[name='search']"))

# Click search button
click(Button("Search"))

# Check if text exists
if Text("Python").exists():
    print("Found Python article!")

# Close browser
kill_browser()

pip install helium requests

import time
import requests
from helium import *

CAPSOLVER_API_KEY = "YOUR_API_KEY"
CAPSOLVER_API = "https://api.capsolver.com"


def create_task(task_payload: dict) -> str:
    """Create a CAPTCHA solving task and return the task ID."""
    response = requests.post(
        f"{CAPSOLVER_API}/createTask",
        json={
            "clientKey": CAPSOLVER_API_KEY,
            "task": task_payload
        }
    )
    result = response.json()
    if result.get("errorId") != 0:
        raise Exception(f"CapSolver error: {result.get('errorDescription')}")
    return result["taskId"]


def get_task_result(task_id: str, max_attempts: int = 120) -> dict:
    """Poll for task result until solved or timeout."""
    for _ in range(max_attempts):
        response = requests.post(
            f"{CAPSOLVER_API}/getTaskResult",
            json={
                "clientKey": CAPSOLVER_API_KEY,
                "taskId": task_id
            }
        )
        result = response.json()

        if result.get("status") == "ready":
            return result["solution"]
        elif result.get("status") == "failed":
            raise Exception(f"Task failed: {result.get('errorDescription')}")

        time.sleep(1)

    raise TimeoutError("CAPTCHA solving timed out")


def solve_captcha(task_payload: dict) -> dict:
    """Complete CAPTCHA solving workflow."""
    task_id = create_task(task_payload)
    return get_task_result(task_id)

// In the extension folder, edit: assets/config.js
var defined = {
    apiKey: "YOUR_CAPSOLVER_API_KEY",  // Replace with your actual API key
    enabledForBlacklistControl: false,
    blackUrlList: [],
    enabledForRecaptcha: true,
    enabledForRecaptchaV3: true,
    enabledForTurnstile: true,
    // ... other settings
}

from helium import *
from selenium.webdriver import ChromeOptions

options = ChromeOptions()
options.add_argument('--load-extension=/path/to/capsolver-extension')

start_chrome(options=options)
# The extension will automatically detect and solve CAPTCHAs

import time
import requests
from helium import *
from selenium.webdriver import ChromeOptions

CAPSOLVER_API_KEY = "YOUR_API_KEY"
CAPSOLVER_API = "https://api.capsolver.com"


def solve_recaptcha_v2(site_key: str, page_url: str) -> str:
    """Solve reCAPTCHA v2 and return the token."""
    # Create the task
    response = requests.post(
        f"{CAPSOLVER_API}/createTask",
        json={
            "clientKey": CAPSOLVER_API_KEY,
            "task": {
                "type": "ReCaptchaV2TaskProxyLess",
                "websiteURL": page_url,
                "websiteKey": site_key,
            }
        }
    )
    result = response.json()

    if result.get("errorId") != 0:
        raise Exception(f"Error: {result.get('errorDescription')}")

    task_id = result["taskId"]
    print(f"Task created: {task_id}")

    # Poll for result
    while True:
        result = requests.post(
            f"{CAPSOLVER_API}/getTaskResult",
            json={
                "clientKey": CAPSOLVER_API_KEY,
                "taskId": task_id
            }
        ).json()

        if result.get("status") == "ready":
            return result["solution"]["gRecaptchaResponse"]
        elif result.get("status") == "failed":
            raise Exception(f"Failed: {result.get('errorDescription')}")

        print("  Waiting for solution...")
        time.sleep(1)


def main():
    target_url = "https://www.google.com/recaptcha/api2/demo"

    # Configure browser with anti-detection
    options = ChromeOptions()
    options.add_experimental_option('excludeSwitches', ['enable-automation'])
    options.add_experimental_option('useAutomationExtension', False)
    options.add_argument('--disable-blink-features=AutomationControlled')

    print("Starting browser...")
    start_chrome(target_url, options=options)
    driver = get_driver()

    try:
        time.sleep(2)

        # Auto-detect site key from page
        recaptcha_element = driver.find_element("css selector", ".g-recaptcha")
        site_key = recaptcha_element.get_attribute("data-sitekey")
        print(f"Detected site key: {site_key}")

        # Solve the CAPTCHA
        print("\nSolving reCAPTCHA v2 with CapSolver...")
        token = solve_recaptcha_v2(site_key, target_url)
        print(f"Got token: {token[:50]}...")

        # Inject the token
        print("\nInjecting token...")
        driver.execute_script(f'''
            var responseField = document.getElementById('g-recaptcha-response');
            responseField.style.display = 'block';
            responseField.value = '{token}';
        ''')
        print("Token injected!")

        # Submit using Helium's simple syntax
        print("\nSubmitting form...")
        click("Submit")

        time.sleep(3)

        # Check for success
        if "Verification Success" in driver.page_source:
            print("\n=== SUCCESS! ===")
            print("reCAPTCHA was solved and form was submitted!")

    finally:
        kill_browser()


if __name__ == "__main__":
    main()

python demo_recaptcha_v2.py

import time
import requests
from helium import *
from selenium.webdriver import ChromeOptions

CAPSOLVER_API_KEY = "YOUR_API_KEY"
CAPSOLVER_API = "https://api.capsolver.com"


def solve_turnstile(site_key: str, page_url: str) -> str:
    """Solve Cloudflare Turnstile and return the token."""
    response = requests.post(
        f"{CAPSOLVER_API}/createTask",
        json={
            "clientKey": CAPSOLVER_API_KEY,
            "task": {
                "type": "AntiTurnstileTaskProxyLess",
                "websiteURL": page_url,
                "websiteKey": site_key,
            }
        }
    )
    result = response.json()

    if result.get("errorId") != 0:
        raise Exception(f"Error: {result.get('errorDescription')}")

    task_id = result["taskId"]

    while True:
        result = requests.post(
            f"{CAPSOLVER_API}/getTaskResult",
            json={
                "clientKey": CAPSOLVER_API_KEY,
                "taskId": task_id
            }
        ).json()

        if result.get("status") == "ready":
            return result["solution"]["token"]
        elif result.get("status") == "failed":
            raise Exception(f"Failed: {result.get('errorDescription')}")

        time.sleep(1)


def main():
    target_url = "https://your-target-site.com"
    turnstile_site_key = "0x4XXXXXXXXXXXXXXXXX"  # Find in page source

    # Configure browser
    options = ChromeOptions()
    options.add_argument('--disable-blink-features=AutomationControlled')

    start_chrome(target_url, options=options)
    driver = get_driver()

    try:
        # Wait for Turnstile to load
        time.sleep(3)

        # Solve the CAPTCHA
        print("Solving Turnstile...")
        token = solve_turnstile(turnstile_site_key, target_url)
        print(f"Got token: {token[:50]}...")

        # Inject the token
        driver.execute_script(f'''
            document.querySelector('input[name="cf-turnstile-response"]').value = "{token}";

            // Trigger callback if present
            const callback = document.querySelector('[data-callback]');
            if (callback) {{
                const callbackName = callback.getAttribute('data-callback');
                if (window[callbackName]) {{
                    window[callbackName]('{token}');
                }}
            }}
        ''')

        # Submit the form using Helium
        if Button("Submit").exists():
            click("Submit")

        print("Turnstile bypassed!")

    finally:
        kill_browser()


if __name__ == "__main__":
    main()

import time
import requests
from helium import *
from selenium.webdriver import ChromeOptions

CAPSOLVER_API_KEY = "YOUR_API_KEY"
CAPSOLVER_API = "https://api.capsolver.com"


def solve_recaptcha_v3(
    site_key: str,
    page_url: str,
    action: str = "verify",
    min_score: float = 0.7
) -> str:
    """Solve reCAPTCHA v3 with specified action and minimum score."""
    response = requests.post(
        f"{CAPSOLVER_API}/createTask",
        json={
            "clientKey": CAPSOLVER_API_KEY,
            "task": {
                "type": "ReCaptchaV3TaskProxyLess",
                "websiteURL": page_url,
                "websiteKey": site_key,
                "pageAction": action,
                "minScore": min_score
            }
        }
    )
    result = response.json()

    if result.get("errorId") != 0:
        raise Exception(f"Error: {result.get('errorDescription')}")

    task_id = result["taskId"]

    while True:
        result = requests.post(
            f"{CAPSOLVER_API}/getTaskResult",
            json={
                "clientKey": CAPSOLVER_API_KEY,
                "taskId": task_id
            }
        ).json()

        if result.get("status") == "ready":
            return result["solution"]["gRecaptchaResponse"]
        elif result.get("status") == "failed":
            raise Exception(f"Failed: {result.get('errorDescription')}")

        time.sleep(1)


def main():
    target_url = "https://your-target-site.com"
    recaptcha_v3_key = "6LcXXXXXXXXXXXXXXXXXXXXXXXXX"

    # Setup headless browser for v3
    options = ChromeOptions()
    options.add_argument('--headless')

    start_chrome(target_url, options=options)
    driver = get_driver()

    try:
        # Solve reCAPTCHA v3 with "login" action
        print("Solving reCAPTCHA v3...")
        token = solve_recaptcha_v3(
            recaptcha_v3_key,
            target_url,
            action="login",
            min_score=0.9
        )

        # Inject the token
        driver.execute_script(f'''
            var responseField = document.querySelector('[name="g-recaptcha-response"]');
            if (responseField) {{
                responseField.value = '{token}';
            }}
            // Call callback if exists
            if (typeof onRecaptchaSuccess === 'function') {{
                onRecaptchaSuccess('{token}');
            }}
        ''')

        print("reCAPTCHA v3 bypassed!")

    finally:
        kill_browser()


if __name__ == "__main__":
    main()

from helium import *
from selenium.webdriver import ChromeOptions

options = ChromeOptions()
options.add_experimental_option('excludeSwitches', ['enable-automation'])
options.add_experimental_option('useAutomationExtension', False)
options.add_argument('--disable-blink-features=AutomationControlled')
options.add_argument('--window-size=1920,1080')

start_chrome(options=options)

from helium import *

start_chrome("https://target-site.com")

# Use Helium for simple interactions
write("username", into="Email")
write("password", into="Password")

# Access Selenium driver for complex operations
driver = get_driver()
driver.execute_script("window.scrollTo(0, document.body.scrollHeight)")

# Back to Helium
click("Login")

import random
import time

def human_delay(min_sec=1.0, max_sec=3.0):
    """Random delay to mimic human behavior."""
    time.sleep(random.uniform(min_sec, max_sec))

# Use between actions
click("Next")
human_delay()
write("data", into="Input")

def solve_with_retry(task_payload: dict, max_retries: int = 3) -> dict:
    """Solve CAPTCHA with retry logic."""
    for attempt in range(max_retries):
        try:
            return solve_captcha(task_payload)
        except TimeoutError:
            if attempt < max_retries - 1:
                print(f"Timeout, retrying... ({attempt + 1}/{max_retries})")
                time.sleep(5)
            else:
                raise
        except Exception as e:
            if "balance" in str(e).lower():
                raise  # Don't retry balance errors
            if attempt < max_retries - 1:
                time.sleep(2)
            else:
                raise

from helium import *
from selenium.webdriver import ChromeOptions

options = ChromeOptions()
options.add_argument('--headless')
options.add_argument('--disable-gpu')

start_chrome("https://target-site.com", options=options)