app.py

# Use an official Python runtime as a parent image
FROM python:3.11-slim

# Set the working directory to /app
WORKDIR /app

# Install system dependencies for Playwright
RUN apt-get update && apt-get install -y --no-install-recommends \
    wget \
    unzip \
    libx11-xcb1 \
    libxcomposite1 \
    libxcursor1 \
    libxdamage1 \
    libxi6 \
    libxtst6 \
    libnss3 \
    libcups2 \
    libxss1 \
    libxrandr2 \
    libasound2 \
    libatk1.0-0 \
    libatk-bridge2.0-0 \
    libcairo2 \
    libgdk-pixbuf2.0-0 \
    libgtk-3-0 \
    libpango-1.0-0 \
    libpangocairo-1.0-0 \
    libx11-6 \
    && rm -rf /var/lib/apt/lists/*

# Copy the current directory contents into the container at /app
COPY . /app/

# Install any needed packages specified in requirements.txt
RUN pip install --no-cache-dir -r requirements.txt

# Install Playwright browsers *before* running the script, and use PLAYWRIGHT_BROWSERS_PATH
# This ensures the browsers are installed in a location Playwright can find them.
ENV PLAYWRIGHT_BROWSERS_PATH=/ms-playwright
RUN mkdir -p $PLAYWRIGHT_BROWSERS_PATH \
    && playwright install chromium --with-deps


# Make port available to the world outside this container (if you add a server later)
# EXPOSE 8000

# Define environment variables (replace with your actual username and password)
# Best practice: Use Docker secrets or environment variables during `docker run`
# ENV HUGGINGFACE_USERNAME=your_username
# ENV HUGGINGFACE_PASSWORD=your_password

# Run the app when the container launches.  Correct the filename here.
CMD ["python", "app.py"]