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
61 lines
2.1 KiB
Python
61 lines
2.1 KiB
Python
"""Pry — AI Agent Plugin.
|
|
OpenAPI spec server, MCP server wrapper, and GPT Action helper."""
|
|
|
|
# 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.
|
|
|
|
import json
|
|
import logging
|
|
from pathlib import Path
|
|
from typing import Any, cast
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
OPENAPI_SPEC_PATH = Path(__file__).parent / "openapi.json"
|
|
|
|
|
|
def get_openapi_spec() -> dict[str, Any]:
|
|
"""Get the OpenAPI spec for AI agent integration."""
|
|
if OPENAPI_SPEC_PATH.exists():
|
|
try:
|
|
spec = cast(dict[str, Any], json.loads(OPENAPI_SPEC_PATH.read_text()))
|
|
return spec
|
|
except json.JSONDecodeError as e:
|
|
logger.error("openapi_spec_parse_failed", extra={"error": str(e)})
|
|
return {"error": "OpenAPI spec not found"}
|
|
|
|
|
|
def get_gpt_action_manifest() -> dict[str, Any]:
|
|
"""Get the GPT Action manifest for ChatGPT integration.
|
|
|
|
This manifest configures ChatGPT to use Pry as a custom GPT Action.
|
|
"""
|
|
return {
|
|
"schema_version": "v1",
|
|
"name_for_human": "Pry Web Scraper",
|
|
"name_for_model": "pry_scraper",
|
|
"description_for_human": "Scrape, crawl, and extract data from any website. Get clean markdown, structured JSON, and monitor changes.",
|
|
"description_for_model": "Plugin for scraping websites. Use it to extract content from URLs, crawl sites, extract structured data with CSS selectors, check legal compliance, monitor changes, and more.",
|
|
"auth": {"type": "none"},
|
|
"api": {"type": "openapi", "url": "/openapi.json"},
|
|
"contact_email": "support@pry.dev",
|
|
"legal_info_url": "https://pry.dev/terms",
|
|
}
|
|
|
|
|
|
def get_mcp_server_config() -> dict[str, Any]:
|
|
"""Get the MCP server config for Claude/Cursor integration.
|
|
|
|
This can be added to the AI tool's MCP configuration.
|
|
"""
|
|
return {
|
|
"pry_scraper": {
|
|
"type": "local",
|
|
"command": ["python3", "-m", "mcp_server"],
|
|
"description": "Scrape, crawl, and extract data from any website",
|
|
"enabled": True,
|
|
}
|
|
}
|