# Use Python 3.10+ base image
FROM python:3.11-slim

# Install system dependencies required for Playwright
RUN apt-get update && apt-get install -y \
    wget \
    gnupg \
    ca-certificates \
    fonts-liberation \
    libnss3 \
    libnspr4 \
    libatk1.0-0 \
    libatk-bridge2.0-0 \
    libcups2 \
    libdrm2 \
    libxkbcommon0 \
    libxcomposite1 \
    libxdamage1 \
    libxfixes3 \
    libxrandr2 \
    libgbm1 \
    libasound2 \
    libpango-1.0-0 \
    libcairo2 \
    && rm -rf /var/lib/apt/lists/*

# Set working directory
WORKDIR /app

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

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

# Install Playwright browsers
RUN playwright install chromium
RUN playwright install-deps chromium

# Copy the rest of the application
COPY . .

# Create output directory
RUN mkdir -p output

# Set Python path to include both project root and src directory
ENV PYTHONPATH=/app:/app/src

# Run the scraper
CMD ["python", "src/main.py"]