gendesign/tradein-mvp/backend/app/services/scrapers/browser_fetcher.py
bot-backend 6044a1fe3c fix(browser): local camoufox + HTTP wrapper, drop broken playwright WS server (#905)
The playwright WS-server path (camoufox.server.launch_server) is incompatible
with playwright >=1.45: camoufox 0.4.11's launchServer.js requires
playwright/driver/package/lib/browserServerImpl.js, which no longer exists in
any playwright 1.45-1.60 → tradein-browser crash-looped with MODULE_NOT_FOUND
('Server process terminated unexpectedly'). Verified by running the built image.

Pivot (no playwright protocol between containers):
- browser/server.py: aiohttp service holding a local AsyncCamoufox (headless,
  os/locale/geoip/humanize, proxy from SCRAPER_PROXY_URL). POST /fetch {url} →
  new_page/goto/content/close → {html}; GET /health. Page-recycle every N +
  crash-recovery (relaunch + 1 retry), serialized via asyncio.Lock.
- browser/Dockerfile: +aiohttp (camoufox fetch-as-root/#908 block untouched).
- backend BrowserFetcher: playwright.connect → httpx POST to the browser service
  (one retry on transport/HTTP error). All playwright imports dropped.
- config: browser_ws_endpoint → browser_http_endpoint (http://tradein-browser:3000).

Verified by a REAL local image build + run: image builds, container stays Up
(Restarts=0, no crash-loop), GET /health=200, POST /fetch launches camoufox and
drives Firefox (only NS_ERROR_UNKNOWN_HOST = no DNS egress in the local build env,
proving the full HTTP→camoufox→Firefox chain; real fetch validates on prod with
network+proxy). 7 unit tests + ruff clean.

Dormant: scraper_fetch_mode stays curl_cffi. Refs #905, #883, #884
2026-05-31 18:25:00 +03:00

104 lines
4.6 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

"""browser_fetcher.py — HTTP-клиент к tradein-browser сервису (#884/#905).
Тонкий клиент над tradein-browser контейнером, который запускает AsyncCamoufox
локально и экспонирует HTTP API (POST /fetch).
Публичный интерфейс не изменился:
async with BrowserFetcher() as fetcher:
html = await fetcher.fetch("https://example.com")
Внутреннее устройство: httpx.AsyncClient + POST к settings.browser_http_endpoint.
Recycle, crash-recovery и управление браузером живут на стороне сервера (server.py).
При HTTPError / ConnectError делает одну повторную попытку после короткой паузы,
затем пробрасывает исключение.
Архитектура выбрана потому, что playwright WS-сервер (launch_server) несовместим
с playwright >=1.45: ``browserServerImpl.js`` отсутствует → MODULE_NOT_FOUND.
Локальный AsyncCamoufox + HTTP — работающая альтернатива.
"""
from __future__ import annotations
import asyncio
import logging
import httpx
logger = logging.getLogger(__name__)
_RETRY_SLEEP_S: float = 1.0
_HTTP_TIMEOUT_S: float = 120.0 # навигация медленная → щедрый таймаут
class BrowserFetcher:
"""Async context manager: HTTP-клиент к tradein-browser HTTP-сервису.
Использование::
async with BrowserFetcher() as fetcher:
html = await fetcher.fetch("https://example.com")
"""
def __init__(self) -> None:
self._client: httpx.AsyncClient | None = None
self._endpoint: str | None = None
# ── lifecycle ──────────────────────────────────────────────────────────────
async def __aenter__(self) -> BrowserFetcher:
from app.core.config import settings
self._endpoint = settings.browser_http_endpoint
self._client = httpx.AsyncClient(timeout=_HTTP_TIMEOUT_S)
logger.info("BrowserFetcher: клиент создан, endpoint=%s", self._endpoint)
return self
async def __aexit__(self, *_: object) -> None:
if self._client is not None:
await self._client.aclose()
self._client = None
logger.debug("BrowserFetcher: клиент закрыт")
# ── public API ─────────────────────────────────────────────────────────────
async def fetch(self, url: str) -> str:
"""Запрашивает HTML страницы через tradein-browser HTTP-сервис.
При HTTPError или ConnectError делает одну повторную попытку после
короткой паузы. Остальные исключения всплывают к вызывающему коду.
Returns:
Полный HTML-контент страницы.
"""
assert self._client is not None, "BrowserFetcher: используй как async context manager"
assert self._endpoint is not None, "BrowserFetcher: endpoint не задан"
try:
return await self._post_fetch(url)
except (httpx.HTTPError, httpx.TransportError) as exc:
logger.warning(
"BrowserFetcher: ошибка запроса (%s), retry через %.1fs: %s",
type(exc).__name__,
_RETRY_SLEEP_S,
url,
)
await asyncio.sleep(_RETRY_SLEEP_S)
return await self._post_fetch(url)
# ── internal ───────────────────────────────────────────────────────────────
async def _post_fetch(self, url: str) -> str:
"""Один HTTP POST к /fetch эндпоинту сервиса."""
assert self._client is not None
assert self._endpoint is not None
resp = await self._client.post(
f"{self._endpoint}/fetch",
json={"url": url},
)
resp.raise_for_status()
data: dict[str, str] = resp.json()
html = data["html"]
logger.debug("BrowserFetcher: fetch OK url=%r html_len=%d", url, len(html))
return html