Terraform + CaptchaAI: Infraestrutura como código para trabalhadores CAPTCHA

O provisionamento manual de trabalhadores CAPTCHA não é escalonável. O Terraform permite que você defina toda a sua infraestrutura de resolução de CAPTCHA como código: crie versões, revise-as, replique-as em ambientes e desmonte-as quando terminar.

Arquitetura

terraform/
├── main.tf              # Provider config
├── variables.tf         # Input variables
├── outputs.tf           # Output values
├── modules/
│   └── captcha-worker/
│       ├── main.tf      # ECS/EC2 resources
│       ├── variables.tf # Module inputs
│       └── outputs.tf   # Module outputs
├── environments/
│   ├── dev.tfvars
│   ├── staging.tfvars
│   └── production.tfvars

Configuração principal do Terraform

Provedor e back-end

# main.tf
terraform {
  required_version = ">= 1.5"

  required_providers {
    aws = {
      source  = "hashicorp/aws"
      version = "~> 5.0"
    }
  }

  backend "s3" {
    bucket         = "my-terraform-state"
    key            = "captcha-workers/terraform.tfstate"
    region         = "us-east-1"
    dynamodb_table = "terraform-locks"
    encrypt        = true
  }
}

provider "aws" {
  region = var.aws_region
}

Variáveis

# variables.tf
variable "aws_region" {
  description = "AWS region for deployment"
  type        = string
  default     = "us-east-1"
}

variable "environment" {
  description = "Environment name (dev, staging, production)"
  type        = string
}

variable "worker_count" {
  description = "Number of CAPTCHA solving workers"
  type        = number
  default     = 3
}

variable "worker_cpu" {
  description = "CPU units for each worker (1024 = 1 vCPU)"
  type        = number
  default     = 512
}

variable "worker_memory" {
  description = "Memory in MB for each worker"
  type        = number
  default     = 1024
}

variable "max_workers" {
  description = "Maximum workers for auto-scaling"
  type        = number
  default     = 10
}

variable "captchaai_concurrency" {
  description = "Concurrent CAPTCHA tasks per worker"
  type        = number
  default     = 10
}

Gerenciamento de segredos

# secrets.tf — Store API key in AWS Secrets Manager
resource "aws_secretsmanager_secret" "captchaai_api_key" {
  name        = "${var.environment}/captchaai-api-key"
  description = "CaptchaAI API key for CAPTCHA solving workers"
}

# Reference secret in ECS task (never in plain text)
data "aws_secretsmanager_secret_version" "captchaai_api_key" {
  secret_id = aws_secretsmanager_secret.captchaai_api_key.id
}

Cluster de trabalhadores ECS

# ecs.tf — Fargate-based CAPTCHA workers
resource "aws_ecs_cluster" "captcha" {
  name = "captcha-workers-${var.environment}"

  setting {
    name  = "containerInsights"
    value = "enabled"
  }
}

resource "aws_ecs_task_definition" "captcha_worker" {
  family                   = "captcha-worker-${var.environment}"
  network_mode             = "awsvpc"
  requires_compatibilities = ["FARGATE"]
  cpu                      = var.worker_cpu
  memory                   = var.worker_memory
  execution_role_arn       = aws_iam_role.ecs_execution.arn
  task_role_arn            = aws_iam_role.ecs_task.arn

  container_definitions = jsonencode([
    {
      name  = "captcha-worker"
      image = "${aws_ecr_repository.captcha_worker.repository_url}:latest"

      environment = [
        { name = "CAPTCHAAI_CONCURRENCY", value = tostring(var.captchaai_concurrency) },
        { name = "CAPTCHAAI_POLL_INTERVAL", value = "5" },
        { name = "ENVIRONMENT", value = var.environment },
      ]

      secrets = [
        {
          name      = "CAPTCHAAI_API_KEY"
          valueFrom = aws_secretsmanager_secret.captchaai_api_key.arn
        }
      ]

      logConfiguration = {
        logDriver = "awslogs"
        options = {
          "awslogs-group"         = aws_cloudwatch_log_group.captcha.name
          "awslogs-region"        = var.aws_region
          "awslogs-stream-prefix" = "worker"
        }
      }
    }
  ])
}

resource "aws_ecs_service" "captcha_worker" {
  name            = "captcha-workers"
  cluster         = aws_ecs_cluster.captcha.id
  task_definition = aws_ecs_task_definition.captcha_worker.arn
  desired_count   = var.worker_count
  launch_type     = "FARGATE"

  network_configuration {
    subnets         = var.private_subnets
    security_groups = [aws_security_group.captcha_worker.id]
  }
}

Escalonamento automático

# autoscaling.tf
resource "aws_appautoscaling_target" "captcha" {
  max_capacity       = var.max_workers
  min_capacity       = var.worker_count
  resource_id        = "service/${aws_ecs_cluster.captcha.name}/${aws_ecs_service.captcha_worker.name}"
  scalable_dimension = "ecs:service:DesiredCount"
  service_namespace  = "ecs"
}

# Scale up when queue is deep
resource "aws_appautoscaling_policy" "scale_up" {
  name               = "captcha-scale-up"
  policy_type        = "StepScaling"
  resource_id        = aws_appautoscaling_target.captcha.resource_id
  scalable_dimension = aws_appautoscaling_target.captcha.scalable_dimension
  service_namespace  = aws_appautoscaling_target.captcha.service_namespace

  step_scaling_policy_configuration {
    adjustment_type         = "ChangeInCapacity"
    cooldown                = 120

    step_adjustment {
      scaling_adjustment          = 2
      metric_interval_lower_bound = 0
    }
  }
}

# Scale down when idle
resource "aws_appautoscaling_policy" "scale_down" {
  name               = "captcha-scale-down"
  policy_type        = "StepScaling"
  resource_id        = aws_appautoscaling_target.captcha.resource_id
  scalable_dimension = aws_appautoscaling_target.captcha.scalable_dimension
  service_namespace  = aws_appautoscaling_target.captcha.service_namespace

  step_scaling_policy_configuration {
    adjustment_type         = "ChangeInCapacity"
    cooldown                = 300

    step_adjustment {
      scaling_adjustment          = -1
      metric_interval_upper_bound = 0
    }
  }
}

Variáveis por ambiente

# environments/dev.tfvars
environment           = "dev"
worker_count          = 1
max_workers           = 3
worker_cpu            = 256
worker_memory         = 512
captchaai_concurrency = 3

# environments/production.tfvars
environment           = "production"
worker_count          = 5
max_workers           = 20
worker_cpu            = 1024
worker_memory         = 2048
captchaai_concurrency = 20

Código de aplicação do trabalhador

"""captcha_worker.py — The container runs this."""
import os
import time
import signal
import requests

API_KEY = os.environ["CAPTCHAAI_API_KEY"]
CONCURRENCY = int(os.environ.get("CAPTCHAAI_CONCURRENCY", "10"))
POLL_INTERVAL = int(os.environ.get("CAPTCHAAI_POLL_INTERVAL", "5"))

running = True

def shutdown_handler(signum, frame):
    global running
    print("Graceful shutdown initiated")
    running = False

signal.signal(signal.SIGTERM, shutdown_handler)
signal.signal(signal.SIGINT, shutdown_handler)

session = requests.Session()

def solve_captcha(sitekey, pageurl):
    resp = session.post("https://ocr.captchaai.com/in.php", data={
        "key": API_KEY,
        "method": "userrecaptcha",
        "googlekey": sitekey,
        "pageurl": pageurl,
        "json": 1
    })
    data = resp.json()
    if data.get("status") != 1:
        return {"error": data.get("request")}

    captcha_id = data["request"]
    for _ in range(60):
        time.sleep(POLL_INTERVAL)
        result = session.get("https://ocr.captchaai.com/res.php", params={
            "key": API_KEY, "action": "get", "id": captcha_id, "json": 1
        }).json()
        if result.get("status") == 1:
            return {"solution": result["request"]}
        if result.get("request") != "CAPCHA_NOT_READY":
            return {"error": result.get("request")}

    return {"error": "TIMEOUT"}

# Main loop — pull tasks from SQS or Redis
print(f"Worker started: concurrency={CONCURRENCY}")
while running:
    # Pull tasks from your queue here
    time.sleep(1)

print("Worker shutdown complete")

Comandos de implantação

# Initialize
terraform init

# Plan for production
terraform plan -var-file=environments/production.tfvars

# Apply
terraform apply -var-file=environments/production.tfvars

# Destroy (dev cleanup)
terraform destroy -var-file=environments/dev.tfvars

Solução de problemas

Perguntas frequentes

Devo usar Fargate ou EC2 para trabalhadores CAPTCHA?

Fargate pela simplicidade e escalonamento automático. EC2 para otimização de custos em estado estacionário (instâncias reservadas). A maioria das equipes começa com o Fargate e transfere cargas de trabalho de alto volume para o EC2.

Como lidar com vários ambientes?

Use arquivos .tfvars por ambiente e arquivos de estado separados. Use espaços de trabalho ou back-ends de estado separados para isolar dev/staging/production.

Posso usar o Terraform com GCP ou Azure?

Sim. Substitua o provedor e os recursos da AWS por seus equivalentes do GCP (Cloud Run, GKE) ou do Azure (Container Instances, AKS). A estrutura do módulo permanece a mesma.

Próximas etapas

Codifique sua infraestrutura CAPTCHA —obtenha sua chave API CaptchaAIe implantar com Terraform.

Guias relacionados:

• Arquitetura multirregional
• Solução Docker Containerizada
• Trabalhadores de escalonamento automático