Dockerfile

FROM python:3.11-slim

RUN apt-get update && apt-get install -y --no-install-recommends \
    curl \
    && apt-get clean && rm -rf /var/lib/apt/lists/*

WORKDIR /app

COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

ENV PLAYWRIGHT_BROWSERS_PATH=/ms-playwright
RUN playwright install --with-deps chromium

COPY . .
RUN pip install --no-cache-dir -e .

RUN mkdir -p output \
    && useradd -m -r scraper \
    && chown -R scraper:scraper /app \
    && chmod -R o+rx /ms-playwright

USER scraper
EXPOSE 8501

HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
    CMD curl -f http://localhost:8501/_stcore/health || exit 1

CMD ["streamlit", "run", "app.py", \
     "--server.port=8501", \
     "--server.address=0.0.0.0", \
     "--server.headless=true", \
     "--browser.gatherUsageStats=false"]