Dockerfile

FROM python:3.10-slim

# Set working directory
WORKDIR /app

# Install system dependencies (for Playwright/Chromium)
RUN apt-get update && apt-get install -y \
    wget \
    gnupg \
    ca-certificates \
    fonts-liberation \
    libasound2 \
    libatk-bridge2.0-0 \
    libatk1.0-0 \
    libatspi2.0-0 \
    libcups2 \
    libdbus-1-3 \
    libdrm2 \
    libgbm1 \
    libgtk-3-0 \
    libnspr4 \
    libnss3 \
    libxcomposite1 \
    libxdamage1 \
    libxfixes3 \
    libxkbcommon0 \
    libxrandr2 \
    xdg-utils \
    && rm -rf /var/lib/apt/lists/*

# Copy requirements first for better caching
COPY requirements.txt ./requirements.txt

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

# Install Playwright browsers and dependencies
RUN python -m playwright install chromium

# Copy the app directory first to preserve structure
COPY app ./app

# Copy other necessary files (optional, for documentation)
COPY *.md LICENSE ./

# Verify app directory structure and Python can import it
RUN ls -la /app/app && python -c "import sys; sys.path.insert(0, '/app'); import app.main; print('✓ App module imported successfully')"

# Set environment variables
ENV PYTHONUNBUFFERED=1
ENV PLAYWRIGHT_BROWSERS_PATH=/ms-playwright
ENV PYTHONPATH=/app

# Expose port (use PORT env var, default to 7860 for HF Spaces)
EXPOSE 7860

# Health check (use PORT env var, default to 7860)
HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
    CMD python -c "import os; import requests; port = os.getenv('PORT', '7860'); requests.get(f'http://localhost:{port}/health')"

# Run the application (PORT env var will be used by main.py)
CMD PYTHONPATH=/app python -m uvicorn app.main:app --host 0.0.0.0 --port ${PORT:-7860}