How to Solve AWS Captcha / Challenge with Python

pip install capsolver requests beautifulsoup4

import capsolver
import requests
from bs4 import BeautifulSoup
import re
from urllib.parse import urlparse

# -------------------PLEASE MODIFY THESE VALUES-------------------
# Your proxy details in the format: http://username:password@ip:port
PROXY = "http://username:password@ip:port"
# The URL of the target website you want to solve AWS WAF for
PAGE_URL = "https://www.your-aws-protected-website.com"
# Your API key from the CapSolver Dashboard
CAPSOLVER_API_KEY = "Your_API_KEY"
# ----------------------------------------------------------------

def solve_aws_waf(is_captcha_challenge, **kwargs):
    """
    Solves an AWS WAF challenge or captcha using CapSolver.
    :param is_captcha_challenge: True for a captcha (405 status), False for a JS challenge (202 status).
    :param kwargs: Parameters required for the solving task.
    :return: The solution object, or None on failure.
    """
    task_type = "AntiAwsWafTask" if is_captcha_challenge else "AntiAwsWafTaskProxyLess"
    print(f"Creating '{task_type}' task...")
    
    task_payload = {
        "type": task_type,
        "websiteURL": PAGE_URL,
    }
    
    # Add specific parameters based on the challenge type
    if is_captcha_challenge:
        # For captcha challenges, awsKey, awsIv, awsContext are needed
        task_payload.update({
            "awsKey": kwargs.get("awsKey"),
            "awsIv": kwargs.get("awsIv"),
            "awsContext": kwargs.get("awsContext"),
            "awsChallengeJS": kwargs.get("awsChallengeJS"),
            "proxy": PROXY
        })
    else:
        # For JS challenges, only the awsChallengeJS URL is needed
        task_payload["awsChallengeJS"] = kwargs.get("awsChallengeJS")

    try:
        solution = capsolver.solve(task_payload)
        if solution and solution.get("errorId", 0) == 0:
            print("Solution retrieved successfully!")
            return solution
        else:
            error_desc = solution.get('errorDescription', 'Unknown error') if solution else 'Unknown error'
            print(f"Failed to solve task: {error_desc}")
            return None
    except Exception as e:
        print(f"An exception occurred while calling CapSolver: {e}")
        return None

def main():
    """Main function to execute the entire process."""
    capsolver.api_key = CAPSOLVER_API_KEY
    session = requests.Session()
    session.proxies = {"http": PROXY, "https": PROXY}
    
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.0.0 Safari/537.36",
        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8",
        "Accept-Language": "en-US,en;q=0.9",
    }

    print(f"Attempting to access: {PAGE_URL}")
    response = session.get(PAGE_URL, headers=headers)
    print(f"Received status code: {response.status_code}")

    solution = None
    
    # Scenario 1: Handle AWS JavaScript Challenge (Status Code 202)
    if response.status_code == 202:
        print("AWS JavaScript challenge detected.")
        soup = BeautifulSoup(response.content, 'html.parser')
        script_tag = soup.find('script', {'src': re.compile(r'token\.awswaf\.com')})
        if script_tag:
            challenge_js_url = script_tag['src']
            print(f"Found challenge JS URL: {challenge_js_url}")
            solution = solve_aws_waf(is_captcha_challenge=False, awsChallengeJS=challenge_js_url)
        else:
            print("Error: Could not find the AWS challenge script.")

    # Scenario 2: Handle AWS Captcha (Status Code 405)
    elif response.status_code == 405:
        print("AWS Captcha detected.")
        soup = BeautifulSoup(response.content, 'html.parser')
        script_tag = soup.find('script', {'src': re.compile(r'token\.awswaf\.com')})
        script_text_tag = soup.find('script', string=re.compile('.*key.*'))
        
        if script_tag and script_text_tag:
            challenge_js_url = script_tag['src']
            script_text = script_text_tag.string
            
            key = re.search(r'"key":"(.*?)"', script_text).group(1)
            iv = re.search(r'"iv":"(.*?)"', script_text).group(1)
            context = re.search(r'"context":"(.*?)"', script_text).group(1)
            
            print(f"Extracted parameters: Key={key[:5]}..., IV={iv[:5]}..., Context={context[:5]}...")
            solution = solve_aws_waf(
                is_captcha_challenge=True,
                awsKey=key,
                awsIv=iv,
                awsContext=context,
                awsChallengeJS=challenge_js_url
            )
        else:
            print("Error: Failed to extract all required captcha parameters from the page.")

    # If solved successfully, set the cookie and retry the request
    if solution and solution.get("cookie"):
        aws_token = solution["cookie"]
        print(f"Successfully obtained aws-waf-token: {aws_token[:30]}...")
        
        domain = f".{urlparse(PAGE_URL).netloc}"
        session.cookies.set("aws-waf-token", aws_token, domain=domain)
        
        print("Cookie set. Retrying request...")
        final_response = session.get(PAGE_URL, headers=headers)
        print(f"Final request status code: {final_response.status_code}")
        
        if final_response.status_code == 200:
            print("Successfully bypassed AWS WAF!")
            # print(final_response.text) # Uncomment to see the page content
        else:
            print("Request failed after setting cookie. Check the token or proxy.")
    else:
        print("Failed to solve AWS WAF. Exiting.")

if __name__ == "__main__":
    main()