Dockerfile

# Use Python 3.9 slim image for smaller size
FROM python:3.9-slim

# Set working directory
WORKDIR /app

# Install system dependencies for Chrome/Selenium
RUN apt-get update && apt-get install -y \
    wget \
    gnupg \
    unzip \
    curl \
    && rm -rf /var/lib/apt/lists/*

# Install Chrome
RUN wget -q -O - https://dl.google.com/linux/linux_signing_key.pub | apt-key add - \
    && echo "deb [arch=amd64] http://dl.google.com/linux/chrome/deb/ stable main" >> /etc/apt/sources.list.d/chrome.list \
    && apt-get update \
    && apt-get install -y google-chrome-stable \
    && rm -rf /var/lib/apt/lists/*

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

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

# Copy the entire application
COPY . .

# Create outputs directory
RUN mkdir -p outputs

# Expose Streamlit port
EXPOSE 8501

# Set environment variables for Streamlit
ENV STREAMLIT_SERVER_HEADLESS=true
ENV STREAMLIT_SERVER_ENABLE_CORS=false
ENV STREAMLIT_SERVER_ENABLE_XSRF_PROTECTION=false

# Health check
HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health

# Run the app
CMD ["streamlit", "run", "web_app/app.py", "--server.address=0.0.0.0", "--server.port=8501"]