Files
crawle-snapp/Dockerfile
T

93 lines
3.3 KiB
Docker

# Usage:
# make build # Build all Docker images (admin + worker)
# docker compose up -d # Start all services
#
# - admin stage: python:3.11-slim (FastAPI only, no Chrome)
# - worker stage: Playwright Noble with Python + Chromium pre-installed
# from your local registry mirror.
# ── Build args ─────────────────────────────────────────────────────────────────
ARG BASE_IMAGE=python:3.11-slim
# ── Stage 1: dependency resolver ─────────────────────────────────────────────
FROM python:3.11-slim AS builder
RUN pip install --no-cache-dir uv==0.11.31
WORKDIR /app
ENV UV_INDEX_URL="http://pypi.reg.darano.ir/simple/"
COPY pyproject.toml uv.lock* ./
RUN uv sync --frozen --no-dev --no-install-project
# ── Stage 2a: admin runtime (python:3.11-slim, no Chrome needed) ──────────────
FROM ${BASE_IMAGE} AS admin
WORKDIR /app
ENV PATH="/app/.venv/bin:$PATH" \
PYTHONUNBUFFERED=1 \
PYTHONDONTWRITEBYTECODE=1 \
UV_INDEX_URL="http://pypi.reg.darano.ir/simple/"
COPY . .
COPY --from=builder /app/.venv /app/.venv
RUN mkdir -p data logs recordings \
&& useradd -m -u 1001 seed \
&& chown -R seed:seed /app
USER seed
EXPOSE 8000
CMD ["python", "main.py", "admin"]
# ── Stage 2b: worker runtime (Playwright Noble + Python installed) ─────────────
# Base: oci.reg.darano.ir/mcr.microsoft.com/playwright:v1.62.0-noble
# This image ships: Ubuntu 24.04 + Chromium + Firefox + WebKit + system libs.
# We add Python + uv ourselves.
FROM oci.reg.darano.ir/mcr.microsoft.com/playwright:v1.62.0-noble AS worker
# Install Python 3.12 + uv, then sync deps — all in one RUN so PATH is consistent.
# Use a mirror for apt since the VPS has network restrictions (Iran).
# curl is already installed (playwright system dep).
RUN printf 'Types: deb\nURIs: http://repo.iut.ac.ir/ubuntu/\nSuites: noble noble-updates noble-security\nComponents: main restricted universe multiverse\nSigned-By: /usr/share/keyrings/ubuntu-archive-keyring.gpg\n' \
> /etc/apt/sources.list.d/ubuntu.sources \
&& apt-get update && apt-get install -y --no-install-recommends \
python3 python3-venv \
&& rm -rf /var/lib/apt/lists/* \
&& curl -LsSf https://astral.sh/uv/install.sh | \
UV_INSTALL_DIR=/usr/local sh \
&& /usr/local/uv/bin/uv sync --frozen --no-dev --no-install-project
ENV PATH="/app/.venv/bin:$PATH" \
PYTHONUNBUFFERED=1 \
PYTHONDONTWRITEBYTECODE=1 \
UV_INDEX_URL="http://pypi.reg.darano.ir/simple/" \
# Chromium is pre-installed at /usr/bin/chromium
CHROME_BINARY=/usr/bin/chromium \
CHROMEDRIVER_PATH=/usr/bin/chromedriver \
HEADLESS=true
WORKDIR /app
# Copy manifests first (stable cache layer)
COPY pyproject.toml uv.lock* ./
# Copy app code
COPY . .
# mkdir for volumes, user for security
RUN mkdir -p data logs recordings \
&& useradd -m -u 1001 seed 2>/dev/null || true \
&& chown -R seed:seed /app 2>/dev/null || true
USER seed
# CMD overridden in docker-compose.yml to use RQ worker
CMD ["rq", "worker", "--url", "redis://redis:6379/0", "batch"]