kys-school-scraper / Dockerfile
sharanyaswarup's picture
Fix Tesseract paths for Linux
8080b37
Raw
History Blame Contribute Delete
1.03 kB
FROM python:3.10-slim
# Install system dependencies including curl and the basics
RUN apt-get update && apt-get install -y curl gcc tesseract-ocr \
&& rm -rf /var/lib/apt/lists/*
# Install Playwright and run install-deps as root (requires sudo/root)
RUN pip install playwright && \
playwright install-deps chromium
# Set up a new user named "user" with user ID 1000
RUN useradd -m -u 1000 user
# Switch to the "user" user
USER user
# Set home to the user's home directory
ENV HOME=/home/user \
PATH=/home/user/.local/bin:$PATH \
PYTHONUNBUFFERED=1
WORKDIR $HOME/app
# Copy requirement files and install
COPY --chown=user requirements.txt $HOME/app/
RUN pip install --no-cache-dir --upgrade pip && \
pip install --no-cache-dir -r requirements.txt
# Install Playwright chromium browser locally for the user
RUN playwright install chromium
# Copy the rest of the application code
COPY --chown=user . $HOME/app
# Hugging Face exposes port 7860
EXPOSE 7860
# Run the application
CMD ["python", "app.py"]