FROM python:3.14-slim

WORKDIR /app

# Install system deps
RUN apt-get update && apt-get install -y --no-install-recommends \
    curl ca-certificates && \
    rm -rf /var/lib/apt/lists/*

# Install Python packages
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy scraper code
COPY . .

# Create data directories
RUN mkdir -p /data/output /data/checkpoints /data/sources

ENV PYTHONUNBUFFERED=1
ENV S3_ENDPOINT=https://s3.siax.io
ENV OUTPUT_DIR=/data/output
ENV CHECKPOINT_DIR=/data/checkpoints

CMD ["python", "-m", "scrapers.run_pipeline"]
