feat: add Django web app, CloudKit sync, dashboard, and game_datetime_utc export

Adds the full Django application layer on top of sportstime_parser:
- core: Sport, Team, Stadium, Game models with aliases and league structure
- scraper: orchestration engine, adapter, job management, Celery tasks
- cloudkit: CloudKit sync client, sync state tracking, sync jobs
- dashboard: staff dashboard for monitoring scrapers, sync, review queue
- notifications: email reports for scrape/sync results
- Docker setup for deployment (Dockerfile, docker-compose, entrypoint)

Game exports now use game_datetime_utc (ISO 8601 UTC) instead of
venue-local date+time strings, matching the canonical format used
by the iOS app.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Trey t
2026-02-19 14:04:27 -06:00
parent 4353d5943c
commit 63acf7accb
114 changed files with 13070 additions and 887 deletions

5
sportstime/__init__.py Normal file
View File

@@ -0,0 +1,5 @@
# This will make sure the app is always imported when
# Django starts so that shared_task will use this app.
from .celery import app as celery_app
__all__ = ('celery_app',)

22
sportstime/celery.py Normal file
View File

@@ -0,0 +1,22 @@
import os
from celery import Celery
# Set the default Django settings module for the 'celery' program.
os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'sportstime.settings')
app = Celery('sportstime')
# Using a string here means the worker doesn't have to serialize
# the configuration object to child processes.
# - namespace='CELERY' means all celery-related configuration keys
# should have a `CELERY_` prefix.
app.config_from_object('django.conf:settings', namespace='CELERY')
# Load task modules from all registered Django apps.
app.autodiscover_tasks()
@app.task(bind=True, ignore_result=True)
def debug_task(self):
print(f'Request: {self.request!r}')

236
sportstime/settings.py Normal file
View File

@@ -0,0 +1,236 @@
"""
Django settings for sportstime project.
"""
import os
from pathlib import Path
import dj_database_url
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.environ.get('SECRET_KEY', 'django-insecure-dev-key-change-in-production')
# SECURITY WARNING: don't run with debug turned on in production!
DEBUG = os.environ.get('DEBUG', 'False').lower() in ('true', '1', 'yes')
ALLOWED_HOSTS = [
host.strip()
for host in os.environ.get('ALLOWED_HOSTS', 'localhost,127.0.0.1').split(',')
if host.strip()
]
# Application definition
INSTALLED_APPS = [
'django.contrib.admin',
'django.contrib.auth',
'django.contrib.contenttypes',
'django.contrib.sessions',
'django.contrib.messages',
'django.contrib.staticfiles',
# Third party
'django_celery_beat',
'django_celery_results',
'simple_history',
'import_export',
# Local apps
'core',
'scraper',
'cloudkit',
'dashboard',
'notifications',
]
MIDDLEWARE = [
'django.middleware.security.SecurityMiddleware',
'whitenoise.middleware.WhiteNoiseMiddleware',
'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',
'simple_history.middleware.HistoryRequestMiddleware',
]
ROOT_URLCONF = 'sportstime.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 = 'sportstime.wsgi.application'
# Database
DATABASES = {
'default': dj_database_url.config(
default='postgresql://sportstime:changeme@localhost:5432/sportstime',
conn_max_age=600,
conn_health_checks=True,
)
}
# 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'] if (BASE_DIR / 'static').exists() else []
STATICFILES_STORAGE = 'whitenoise.storage.CompressedManifestStaticFilesStorage'
# Media files
MEDIA_URL = 'media/'
MEDIA_ROOT = BASE_DIR / 'media'
# Default primary key field type
DEFAULT_AUTO_FIELD = 'django.db.models.BigAutoField'
# Celery Configuration
CELERY_BROKER_URL = os.environ.get('REDIS_URL', 'redis://localhost:6379/0')
CELERY_RESULT_BACKEND = 'django-db'
CELERY_CACHE_BACKEND = 'django-cache'
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 = 30 * 60 # 30 minutes
CELERY_BEAT_SCHEDULER = 'django_celery_beat.schedulers:DatabaseScheduler'
# Email Configuration
EMAIL_BACKEND = 'django.core.mail.backends.smtp.EmailBackend'
EMAIL_HOST = os.environ.get('EMAIL_HOST', 'smtp.gmail.com')
EMAIL_PORT = int(os.environ.get('EMAIL_PORT', 587))
EMAIL_USE_TLS = os.environ.get('EMAIL_USE_TLS', 'True').lower() in ('true', '1', 'yes')
EMAIL_HOST_USER = os.environ.get('EMAIL_HOST_USER', '')
EMAIL_HOST_PASSWORD = os.environ.get('EMAIL_HOST_PASSWORD', '')
DEFAULT_FROM_EMAIL = os.environ.get('DEFAULT_FROM_EMAIL', 'SportsTime <noreply@example.com>')
ADMIN_EMAIL = os.environ.get('ADMIN_EMAIL', '')
# Security settings (for production behind proxy)
if not DEBUG:
SECURE_SSL_REDIRECT = os.environ.get('SECURE_SSL_REDIRECT', 'False').lower() in ('true', '1', 'yes')
SECURE_PROXY_SSL_HEADER = ('HTTP_X_FORWARDED_PROTO', 'https')
SESSION_COOKIE_SECURE = os.environ.get('SESSION_COOKIE_SECURE', 'True').lower() in ('true', '1', 'yes')
CSRF_COOKIE_SECURE = os.environ.get('CSRF_COOKIE_SECURE', 'True').lower() in ('true', '1', 'yes')
CSRF_TRUSTED_ORIGINS = [
origin.strip()
for origin in os.environ.get('CSRF_TRUSTED_ORIGINS', '').split(',')
if origin.strip()
]
# CloudKit Configuration
CLOUDKIT_CONTAINER = os.environ.get('CLOUDKIT_CONTAINER', 'iCloud.com.sportstime.app')
CLOUDKIT_ENVIRONMENT = os.environ.get('CLOUDKIT_ENVIRONMENT', 'development')
CLOUDKIT_KEY_ID = os.environ.get('CLOUDKIT_KEY_ID', '')
CLOUDKIT_PRIVATE_KEY_PATH = os.environ.get('CLOUDKIT_PRIVATE_KEY_PATH', '')
# Scraper Configuration
SCRAPER_REQUEST_DELAY = float(os.environ.get('SCRAPER_REQUEST_DELAY', 3.0))
SCRAPER_MAX_RETRIES = int(os.environ.get('SCRAPER_MAX_RETRIES', 3))
SCRAPER_FUZZY_THRESHOLD = int(os.environ.get('SCRAPER_FUZZY_THRESHOLD', 85))
SCRAPER_BACKOFF_FACTOR = 2.0
SCRAPER_INITIAL_BACKOFF = 5.0
# Expected game counts per sport (for validation)
EXPECTED_GAME_COUNTS = {
'nba': 1230,
'mlb': 2430,
'nfl': 272,
'nhl': 1312,
'mls': 544,
'wnba': 228,
'nwsl': 182,
}
# 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} {message}',
'style': '{',
},
},
'handlers': {
'console': {
'class': 'logging.StreamHandler',
'formatter': 'simple',
},
'file': {
'class': 'logging.handlers.RotatingFileHandler',
'filename': BASE_DIR / 'logs' / 'sportstime.log',
'maxBytes': 10 * 1024 * 1024, # 10 MB
'backupCount': 5,
'formatter': 'verbose',
},
},
'root': {
'handlers': ['console'],
'level': 'INFO',
},
'loggers': {
'django': {
'handlers': ['console'],
'level': os.environ.get('DJANGO_LOG_LEVEL', 'INFO'),
'propagate': False,
},
'scraper': {
'handlers': ['console', 'file'] if not DEBUG else ['console'],
'level': 'INFO',
'propagate': False,
},
'cloudkit': {
'handlers': ['console', 'file'] if not DEBUG else ['console'],
'level': '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)
# Admin site customization
ADMIN_SITE_HEADER = 'SportsTime Administration'
ADMIN_SITE_TITLE = 'SportsTime Admin'
ADMIN_INDEX_TITLE = 'Dashboard'

20
sportstime/urls.py Normal file
View File

@@ -0,0 +1,20 @@
"""
URL configuration for sportstime project.
"""
from django.contrib import admin
from django.urls import path, include
from django.conf import settings
from django.conf.urls.static import static
# Customize admin site
admin.site.site_header = 'SportsTime Admin'
admin.site.site_title = 'SportsTime'
admin.site.index_title = 'Sports Data Management'
urlpatterns = [
path('admin/', admin.site.urls),
path('dashboard/', include('dashboard.urls')),
]
if settings.DEBUG:
urlpatterns += static(settings.MEDIA_URL, document_root=settings.MEDIA_ROOT)

16
sportstime/wsgi.py Normal file
View File

@@ -0,0 +1,16 @@
"""
WSGI config for sportstime project.
It exposes the WSGI callable as a module-level variable named ``application``.
For more information on this file, see
https://docs.djangoproject.com/en/5.1/howto/deployment/wsgi/
"""
import os
from django.core.wsgi import get_wsgi_application
os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'sportstime.settings')
application = get_wsgi_application()