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
102 lines
3.2 KiB
Python
102 lines
3.2 KiB
Python
"""Pry — shared Playwright browser pool.
|
|
Reuses browser instances across requests instead of launching per scrape."""
|
|
|
|
# SPDX-License-Identifier: BSL-1.1
|
|
# Copyright (c) 2026 Rug Munch Media LLC
|
|
#
|
|
# Part of Pry — Stealth / Anti-Detection Module
|
|
# Licensed under Business Source License 1.1 — see LICENSE-BSL-STEALTH.
|
|
# Change Date: 2029-01-01 (converts to MIT).
|
|
|
|
import asyncio
|
|
import logging
|
|
from typing import Any
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class BrowserPool:
|
|
"""Warm pool of Playwright browser instances.
|
|
|
|
Maximum `max_browsers` chromium instances. Each can create multiple
|
|
contexts/pages. Browsers are kept warm and reused across requests.
|
|
"""
|
|
|
|
def __init__(self, max_browsers: int = 2, headless: bool = True):
|
|
self.max_browsers = max_browsers
|
|
self.headless = headless
|
|
self._playwright: Any = None
|
|
self._browsers: list[Any] = []
|
|
self._lock = asyncio.Lock()
|
|
self._initialized = False
|
|
|
|
async def start(self) -> None:
|
|
"""Launch the Playwright manager and pre-warm browsers."""
|
|
from playwright.async_api import async_playwright
|
|
|
|
self._playwright = await async_playwright().start()
|
|
for _ in range(self.max_browsers):
|
|
browser = await self._launch_browser()
|
|
self._browsers.append(browser)
|
|
self._initialized = True
|
|
logger.info("browser_pool_started", extra={"browsers": self.max_browsers})
|
|
|
|
async def _launch_browser(self) -> Any:
|
|
"""Launch a single Chromium instance."""
|
|
assert self._playwright is not None
|
|
return await self._playwright.chromium.launch(
|
|
headless=self.headless,
|
|
args=[
|
|
"--no-sandbox",
|
|
"--disable-setuid-sandbox",
|
|
"--disable-dev-shm-usage",
|
|
"--disable-gpu",
|
|
],
|
|
)
|
|
|
|
async def get_browser(self) -> Any:
|
|
"""Get a browser from the pool (round-robin)."""
|
|
async with self._lock:
|
|
if not self._initialized:
|
|
await self.start()
|
|
if not self._browsers:
|
|
browser = await self._launch_browser()
|
|
self._browsers.append(browser)
|
|
# Simple round-robin: return first, rotate
|
|
browser = self._browsers.pop(0)
|
|
self._browsers.append(browser)
|
|
return browser
|
|
|
|
async def close(self) -> None:
|
|
"""Close all browsers and stop Playwright."""
|
|
for b in self._browsers:
|
|
try:
|
|
await b.close()
|
|
except Exception:
|
|
logger.exception("browser_close_failed")
|
|
self._browsers.clear()
|
|
if self._playwright:
|
|
await self._playwright.stop()
|
|
self._initialized = False
|
|
logger.info("browser_pool_stopped")
|
|
|
|
|
|
# Module-level singleton
|
|
_pool: BrowserPool | None = None
|
|
|
|
|
|
async def get_browser_pool() -> BrowserPool:
|
|
"""Get or create the global browser pool."""
|
|
global _pool
|
|
if _pool is None:
|
|
_pool = BrowserPool()
|
|
await _pool.start()
|
|
return _pool
|
|
|
|
|
|
async def close_browser_pool() -> None:
|
|
"""Close the global browser pool."""
|
|
global _pool
|
|
if _pool:
|
|
await _pool.close()
|
|
_pool = None
|