secure-web/backend/core/settings.py

"""
Django settings for Website Analyzer project.

This module contains all configuration settings for the Django application,
including database, caching, security, and third-party integrations.
"""

import os
from pathlib import Path

from dotenv import load_dotenv

# Load environment variables from .env file
load_dotenv()

# Build paths inside the project like this: BASE_DIR / 'subdir'.
BASE_DIR = Path(__file__).resolve().parent.parent

# SECURITY WARNING: keep the secret key used in production secret!
SECRET_KEY = os.getenv('SECRET_KEY', 'django-insecure-change-me-in-production')

# SECURITY WARNING: don't run with debug turned on in production!
DEBUG = os.getenv('DEBUG', 'False').lower() in ('true', '1', 'yes')

ALLOWED_HOSTS = os.getenv('ALLOWED_HOSTS', 'localhost,127.0.0.1').split(',')


# Application definition

INSTALLED_APPS = [
    'django.contrib.admin',
    'django.contrib.auth',
    'django.contrib.contenttypes',
    'django.contrib.sessions',
    'django.contrib.messages',
    'django.contrib.staticfiles',
    
    # Third-party apps
    'rest_framework',
    'corsheaders',
    
    # Local apps
    'websites',
    'scanner',
    'api',
]

MIDDLEWARE = [
    'django.middleware.security.SecurityMiddleware',
    'whitenoise.middleware.WhiteNoiseMiddleware',
    'corsheaders.middleware.CorsMiddleware',
    'django.contrib.sessions.middleware.SessionMiddleware',
    'django.middleware.common.CommonMiddleware',
    'django.middleware.csrf.CsrfViewMiddleware',
    'django.contrib.auth.middleware.AuthenticationMiddleware',
    'django.contrib.messages.middleware.MessageMiddleware',
    'django.middleware.clickjacking.XFrameOptionsMiddleware',
]

ROOT_URLCONF = 'core.urls'

TEMPLATES = [
    {
        'BACKEND': 'django.template.backends.django.DjangoTemplates',
        'DIRS': [BASE_DIR / 'templates'],
        'APP_DIRS': True,
        'OPTIONS': {
            'context_processors': [
                'django.template.context_processors.debug',
                'django.template.context_processors.request',
                'django.contrib.auth.context_processors.auth',
                'django.contrib.messages.context_processors.messages',
            ],
        },
    },
]

WSGI_APPLICATION = 'core.wsgi.application'


# Database
# Parse DATABASE_URL or use default PostgreSQL settings

DATABASE_URL = os.getenv('DATABASE_URL', 'postgres://analyzer:analyzer_password@localhost:5432/website_analyzer')

# Parse the DATABASE_URL
import re
db_pattern = r'postgres://(?P<user>[^:]+):(?P<password>[^@]+)@(?P<host>[^:]+):(?P<port>\d+)/(?P<name>.+)'
db_match = re.match(db_pattern, DATABASE_URL)

if db_match:
    DATABASES = {
        'default': {
            'ENGINE': 'django.db.backends.postgresql',
            'NAME': db_match.group('name'),
            'USER': db_match.group('user'),
            'PASSWORD': db_match.group('password'),
            'HOST': db_match.group('host'),
            'PORT': db_match.group('port'),
        }
    }
else:
    # Fallback for development
    DATABASES = {
        'default': {
            'ENGINE': 'django.db.backends.sqlite3',
            'NAME': BASE_DIR / 'db.sqlite3',
        }
    }


# Password validation
AUTH_PASSWORD_VALIDATORS = [
    {
        'NAME': 'django.contrib.auth.password_validation.UserAttributeSimilarityValidator',
    },
    {
        'NAME': 'django.contrib.auth.password_validation.MinimumLengthValidator',
    },
    {
        'NAME': 'django.contrib.auth.password_validation.CommonPasswordValidator',
    },
    {
        'NAME': 'django.contrib.auth.password_validation.NumericPasswordValidator',
    },
]


# Internationalization
LANGUAGE_CODE = 'en-us'
TIME_ZONE = 'UTC'
USE_I18N = True
USE_TZ = True


# Static files (CSS, JavaScript, Images)
STATIC_URL = 'static/'
STATIC_ROOT = BASE_DIR / 'staticfiles'
STATICFILES_DIRS = [BASE_DIR / 'static']
STATICFILES_STORAGE = 'whitenoise.storage.CompressedManifestStaticFilesStorage'

# Default primary key field type
DEFAULT_AUTO_FIELD = 'django.db.models.BigAutoField'


# =============================================================================
# REST Framework Configuration
# =============================================================================
REST_FRAMEWORK = {
    'DEFAULT_RENDERER_CLASSES': [
        'rest_framework.renderers.JSONRenderer',
        'rest_framework.renderers.BrowsableAPIRenderer',
    ],
    'DEFAULT_PAGINATION_CLASS': 'rest_framework.pagination.PageNumberPagination',
    'PAGE_SIZE': 20,
    'DEFAULT_THROTTLE_CLASSES': [
        'rest_framework.throttling.AnonRateThrottle',
        'rest_framework.throttling.UserRateThrottle'
    ],
    'DEFAULT_THROTTLE_RATES': {
        'anon': '100/hour',
        'user': '1000/hour',
        'scan': '10/hour',  # Specific rate for scan creation
    },
    'EXCEPTION_HANDLER': 'api.exceptions.custom_exception_handler',
}


# =============================================================================
# CORS Configuration
# =============================================================================
CORS_ALLOWED_ORIGINS = os.getenv(
    'CORS_ALLOWED_ORIGINS', 
    'http://localhost:3000,http://localhost:8000'
).split(',')
CORS_ALLOW_CREDENTIALS = True


# =============================================================================
# Celery Configuration
# =============================================================================
CELERY_BROKER_URL = os.getenv('CELERY_BROKER_URL', 'redis://localhost:6379/0')
CELERY_RESULT_BACKEND = os.getenv('CELERY_RESULT_BACKEND', 'redis://localhost:6379/1')
CELERY_ACCEPT_CONTENT = ['json']
CELERY_TASK_SERIALIZER = 'json'
CELERY_RESULT_SERIALIZER = 'json'
CELERY_TIMEZONE = TIME_ZONE
CELERY_TASK_TRACK_STARTED = True
CELERY_TASK_TIME_LIMIT = int(os.getenv('MAX_SCAN_TIME_SECONDS', '300'))
CELERY_TASK_SOFT_TIME_LIMIT = CELERY_TASK_TIME_LIMIT - 30


# =============================================================================
# Redis Cache Configuration
# =============================================================================
REDIS_URL = os.getenv('REDIS_URL', 'redis://localhost:6379/0')
CACHES = {
    'default': {
        'BACKEND': 'django.core.cache.backends.redis.RedisCache',
        'LOCATION': REDIS_URL,
    }
}


# =============================================================================
# Scanner Configuration
# =============================================================================
SCANNER_CONFIG = {
    # OWASP ZAP settings
    'ZAP_API_KEY': os.getenv('ZAP_API_KEY', ''),
    'ZAP_HOST': os.getenv('ZAP_HOST', 'http://localhost:8080'),
    'ZAP_TIMEOUT': 120,
    
    # Lighthouse settings
    'LIGHTHOUSE_CHROME_FLAGS': os.getenv(
        'LIGHTHOUSE_CHROME_FLAGS', 
        '--headless --no-sandbox --disable-gpu'
    ),
    'LIGHTHOUSE_TIMEOUT': 60,
    
    # Playwright settings
    'PLAYWRIGHT_TIMEOUT': 30000,  # milliseconds
    'PLAYWRIGHT_VIEWPORT': {'width': 1920, 'height': 1080},
    
    # General scan settings
    'MAX_SCAN_TIME_SECONDS': int(os.getenv('MAX_SCAN_TIME_SECONDS', '300')),
    'SCAN_RATE_LIMIT_MINUTES': int(os.getenv('SCAN_RATE_LIMIT_MINUTES', '5')),
    'MAX_CONCURRENT_SCANS': int(os.getenv('MAX_CONCURRENT_SCANS', '3')),
    
    # Safety settings - blocked IP ranges (RFC1918 private ranges + localhost)
    'BLOCKED_IP_RANGES': [
        '10.0.0.0/8',
        '172.16.0.0/12',
        '192.168.0.0/16',
        '127.0.0.0/8',
        '169.254.0.0/16',  # Link-local
        '::1/128',  # IPv6 localhost
        'fc00::/7',  # IPv6 private
        'fe80::/10',  # IPv6 link-local
    ],
    'BLOCKED_HOSTS': ['localhost', 'localhost.localdomain'],
    
    # Large file thresholds
    'LARGE_IMAGE_THRESHOLD_BYTES': 1024 * 1024,  # 1 MB
    'LARGE_JS_BUNDLE_THRESHOLD_BYTES': 500 * 1024,  # 500 KB
}


# =============================================================================
# Logging Configuration
# =============================================================================
LOGGING = {
    'version': 1,
    'disable_existing_loggers': False,
    'formatters': {
        'verbose': {
            'format': '{levelname} {asctime} {module} {process:d} {thread:d} {message}',
            'style': '{',
        },
        'simple': {
            'format': '{levelname} {asctime} {module} {message}',
            'style': '{',
        },
    },
    'handlers': {
        'console': {
            'class': 'logging.StreamHandler',
            'formatter': 'simple',
        },
        'file': {
            'class': 'logging.FileHandler',
            'filename': BASE_DIR / 'logs' / 'django.log',
            'formatter': 'verbose',
        },
    },
    'root': {
        'handlers': ['console'],
        'level': 'INFO',
    },
    'loggers': {
        'django': {
            'handlers': ['console'],
            'level': os.getenv('DJANGO_LOG_LEVEL', 'INFO'),
            'propagate': False,
        },
        'scanner': {
            'handlers': ['console'],
            'level': 'DEBUG' if DEBUG else 'INFO',
            'propagate': False,
        },
        'celery': {
            'handlers': ['console'],
            'level': 'INFO',
            'propagate': False,
        },
    },
}

# Create logs directory if it doesn't exist
(BASE_DIR / 'logs').mkdir(exist_ok=True)