Dockerfile

FROM python:3.9-slim

WORKDIR /app

# Install system dependencies required for Playwright
RUN apt-get update && apt-get install -y \
    chromium \
    fonts-ipafont-gothic \
    fonts-wqy-zenhei \
    fonts-thai-tlwg \
    fonts-kacst \
    fonts-freefont-ttf \
    libxss1 \
    && rm -rf /var/lib/apt/lists/*

# Set environment variable to use Chromium
ENV PLAYWRIGHT_BROWSERS_PATH=/ms-playwright
ENV PLAYWRIGHT_CHROMIUM_EXECUTABLE_PATH=/usr/bin/chromium

# Copy requirements first to leverage Docker cache
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Run Crawl4AI setup
RUN crawl4ai-setup

# Copy application code
COPY main.py .
COPY crawler.py .

# Create directory for crawl results
RUN mkdir -p /app/crawl_results

# Expose the port the app runs on
EXPOSE 8001

# Command to run the application
CMD ["python", "main.py"]