cryptorugmunch
47ba268131
Adds missing standard artifacts: - README.md (if missing) - AGENTS.md (AI agent contract) - PLAN.md (current sprint) - STATUS.md (where we are) - DEVELOPMENT.md (dev workflow) - DEPLOYMENT.md (deploy procedure) - TESTING.md (test strategy) - DECISIONS.md (ADR index + templates) - .github/CODEOWNERS - .github/workflows/ci.yml Preserves all existing artifacts. Refs: RugMunchMedia/fleet-template
95 lines
2.9 KiB
Python
95 lines
2.9 KiB
Python
"""Pry — shared Playwright browser pool.
|
|
Reuses browser instances across requests instead of launching per scrape."""
|
|
|
|
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
|