Dockerfile

# Dockerfile for Phishing URL Detection FastAPI Application
# Base image: Python 3.10 slim for smaller image size
FROM python:3.10-slim

# Set environment variables
ENV PYTHONUNBUFFERED=1 \
    PYTHONDONTWRITEBYTECODE=1 \
    PIP_NO_CACHE_DIR=1 \
    PIP_DISABLE_PIP_VERSION_CHECK=1

# Install system dependencies required for ML libraries and Playwright
RUN apt-get update && apt-get install -y --no-install-recommends \
    libgomp1 \
    wget \
    # Playwright/Chromium dependencies
    libnss3 \
    libnspr4 \
    libatk1.0-0 \
    libatk-bridge2.0-0 \
    libcups2 \
    libdrm2 \
    libdbus-1-3 \
    libxkbcommon0 \
    libxcomposite1 \
    libxdamage1 \
    libxfixes3 \
    libxrandr2 \
    libgbm1 \
    libpango-1.0-0 \
    libcairo2 \
    libasound2 \
    libatspi2.0-0 \
    libxshmfence1 \
    && rm -rf /var/lib/apt/lists/*

# Create non-root user for security
RUN useradd -m -u 1000 user && \
    mkdir -p /app && \
    chown -R user:user /app

# Set working directory
WORKDIR /app

# Copy requirements first for better caching
COPY --chown=user:user requirements.txt .

# Switch to non-root user
USER user

# Add user's local bin to PATH
ENV PATH="/home/user/.local/bin:$PATH"

# Install Python dependencies
RUN pip install --user --no-cache-dir --upgrade pip && \
    pip install --user --no-cache-dir -r requirements.txt

# Install Playwright browsers (as user)
# System dependencies are already installed above, so we just need the browser binaries
RUN python -m playwright install chromium

# Copy application code and model
COPY --chown=user:user . .

# Expose ports (7860 is default, 8000 for compatibility)
EXPOSE 7860 8000

# Health check (uses port 7860 by default)
HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
    CMD python -c "import requests; requests.get('http://localhost:7860/health')" || exit 1

# Run the application
# Use app.py for HuggingFace Spaces compatibility, defaults to port 7860
CMD ["python", "app.py"]