mirror of
https://github.com/wasrusgen/zov-tech.git
synced 2026-06-03 22:04:48 +00:00
d5f290bd0a
DOCKERFILE: - + Chromium system deps (libnss3, libxkbcommon0, libgbm1, libgtk-3-0, etc.) - + RUN python -m playwright install chromium (~150MB) - + ENV PLAYWRIGHT_BROWSERS_PATH REQUIREMENTS: - + playwright >= 1.45 PARSERS: - new playwright_engine.py — singleton browser, isolated context per request, blocks images/fonts/CSS to save memory, waits for selector + JS hydration - yamarket.py — rewritten to use Playwright (Я.Маркет is React SPA) - ozon.py — Playwright fallback when composer-api returns challenge (403) - wb.py — exponential backoff on 429, still uses direct HTTP (JSON API, no JS needed) STRATEGY (Hybrid Path C): - Я.Маркет: Playwright (rendering JS) - OZON: composer-api first, Playwright fallback - WB: direct HTTP with backoff (JSON API, fast) - DNS: kept but lower priority (Qrator hard to crack) - No more proxy needed for primary path DEPLOY: removed PROXY_STATIC_LIST from .env, expect ~5min for first build (Chromium download)
42 lines
1.7 KiB
Docker
42 lines
1.7 KiB
Docker
FROM python:3.12-slim
|
|
|
|
# НУЦ Минцифры root CA — для GigaChat SSL.
|
|
# + системные пакеты для Playwright/Chromium (рендеринг JS-сайтов).
|
|
RUN apt-get update \
|
|
&& apt-get install -y --no-install-recommends \
|
|
ca-certificates curl \
|
|
# Chromium dependencies for Playwright
|
|
libnss3 libnspr4 libatk-bridge2.0-0 libatk1.0-0 libcups2 \
|
|
libxkbcommon0 libxcomposite1 libxdamage1 libxfixes3 libxrandr2 \
|
|
libgbm1 libgtk-3-0 libasound2 libpango-1.0-0 libcairo2 \
|
|
libdbus-1-3 libdrm2 libxshmfence1 \
|
|
fonts-liberation fonts-noto-color-emoji \
|
|
&& curl -fsSL -o /usr/local/share/ca-certificates/russian_trusted_root_ca.crt \
|
|
https://gu-st.ru/content/Other/doc/russian_trusted_root_ca.cer \
|
|
&& curl -fsSL -o /usr/local/share/ca-certificates/russian_trusted_sub_ca.crt \
|
|
https://gu-st.ru/content/Other/doc/russian_trusted_sub_ca.cer \
|
|
&& update-ca-certificates \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
WORKDIR /app
|
|
|
|
COPY requirements.txt .
|
|
RUN pip install --no-cache-dir -r requirements.txt
|
|
|
|
# Скачиваем только Chromium (без firefox/webkit) — ~150MB
|
|
RUN python -m playwright install chromium
|
|
|
|
COPY app /app/app
|
|
|
|
# httpx по умолчанию использует certifi → принудительно указываем системный bundle,
|
|
# куда мы добавили НУЦ Минцифры
|
|
ENV SSL_CERT_FILE=/etc/ssl/certs/ca-certificates.crt
|
|
ENV REQUESTS_CA_BUNDLE=/etc/ssl/certs/ca-certificates.crt
|
|
|
|
# Playwright кэш-каталог браузеров
|
|
ENV PLAYWRIGHT_BROWSERS_PATH=/root/.cache/ms-playwright
|
|
|
|
EXPOSE 8000
|
|
|
|
CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000", "--proxy-headers", "--forwarded-allow-ips=*"]
|