bb77eb5f35
Re-license Pry from full Proprietary to a dual-license model: - Core engine, extraction, templates (80+), MCP server, x402 payment rail, CLI, SDK, browser extension, WordPress plugin, Shopify app, and llm_providers: MIT (see LICENSE) - Anti-detection / stealth subset (15 files): BSL 1.1 with Change Date 2029-01-01 (see LICENSE-BSL-STEALTH) BSL files (anti-detection moat): ultimate_scraper.py, stealth_engine.py, stealth_scripts/*.js (6), camoufox_integration.py, tls_fingerprint.py, cookie_warmer.py, behavioral_biometrics.py, adaptive.py, browser_pool.py, network.py, captcha_solver.py, shadow_dom.py, lazy_load.py, signup_automator.py, auth_connector.py This enables community contributions to the core engine (templates, integrations, MCP tools) while protecting the anti-detection techniques that constitute the actual competitive moat. BSL Additional Use Grant permits free non-production use; production deployment requires a commercial license from enterprise@rugmunch.io. Changes: - Replace proprietary LICENSE with MIT LICENSE + new LICENSE-BSL-STEALTH - Add SPDX-License-Identifier headers to 300+ source files - Add docs/adr/0002-dual-licensing.md (ADR documenting the decision) - Update README.md: new License section with BSL Additional Use Grant - Update LICENSING_PRICING_STRATEGY.md: Section 3 (PryScraper) for dual license - Update AGENTS.md: license line in header + new rule 8 (PRs touching BSL rejected) - Update pyproject.toml: license = "MIT AND BSL-1.1" + classifiers + license-files - Update DECISIONS.md index with ADR-0002 - Update STATUS.md (2026-07-03) and PLAN.md sprint goals Refs: ADR-0002
82 lines
1.9 KiB
Python
82 lines
1.9 KiB
Python
"""PryScraper — global configuration.
|
|
|
|
Loads settings from environment variables (via Pydantic Settings).
|
|
All secrets come from gopass, never from .env files committed to git.
|
|
"""
|
|
|
|
# SPDX-License-Identifier: MIT
|
|
# Copyright (c) 2026 Rug Munch Media LLC
|
|
#
|
|
# Part of Pry — https://git.rugmunch.io/RugMunchMedia/pryscraper
|
|
# Licensed under MIT. See LICENSE.
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
from pathlib import Path
|
|
from typing import Literal
|
|
|
|
from pydantic import Field
|
|
from pydantic_settings import BaseSettings, SettingsConfigDict
|
|
|
|
|
|
class Settings(BaseSettings):
|
|
"""PryScraper application settings."""
|
|
|
|
model_config = SettingsConfigDict(
|
|
env_file=".env",
|
|
env_file_encoding="utf-8",
|
|
case_sensitive=False,
|
|
extra="ignore",
|
|
)
|
|
|
|
# Core
|
|
app_name: str = "PryScraper"
|
|
app_version: str = "3.0.0"
|
|
environment: Literal["dev", "staging", "prod"] = "dev"
|
|
log_level: str = "INFO"
|
|
port: int = 8002
|
|
|
|
# Database
|
|
database_url: str = "postgresql+asyncpg://pry:pry@localhost/pry"
|
|
|
|
# Cache
|
|
redis_url: str = "redis://localhost:6379/0"
|
|
|
|
# LLM Providers
|
|
openai_api_key: str = ""
|
|
anthropic_api_key: str = ""
|
|
cohere_api_key: str = ""
|
|
ollama_url: str = "http://localhost:11434"
|
|
|
|
# Stealth
|
|
stealth_enabled: bool = True
|
|
random_user_agent: bool = True
|
|
min_delay_ms: int = 500
|
|
max_delay_ms: int = 3000
|
|
|
|
# Rate limiting
|
|
rate_limit_per_domain: int = 10 # requests per second
|
|
rate_limit_per_ip: int = 60
|
|
|
|
# x402 Payment
|
|
x402_enabled: bool = False
|
|
x402_pay_to: str = ""
|
|
|
|
# MCP
|
|
mcp_enabled: bool = True
|
|
mcp_tools_count: int = 8
|
|
|
|
# Storage
|
|
screenshot_dir: Path = Path("/tmp/pry-screenshots")
|
|
cache_ttl_seconds: int = 3600
|
|
|
|
|
|
_settings: Settings | None = None
|
|
|
|
|
|
def get_settings() -> Settings:
|
|
"""Get cached settings instance."""
|
|
global _settings
|
|
if _settings is None:
|
|
_settings = Settings()
|
|
return _settings
|