Dockerfile

# Use Python 3.9-slim as the base image.
FROM python:3.9-slim

# Disable .pyc generation and enable unbuffered stdout.
ENV PYTHONDONTWRITEBYTECODE=1 \
    PYTHONUNBUFFERED=1

# Tell Scrapely to disable its C extensions (if supported).
ENV SCRAPELY_DISABLE_C_EXTENSIONS=1

# Set the working directory.
WORKDIR /home/user/app

# Install system dependencies.
RUN apt-get update && apt-get install -y --no-install-recommends \
    git \
    git-lfs \
    ffmpeg \
    libsm6 \
    libxext6 \
    cmake \
    rsync \
    libgl1-mesa-glx \
 && rm -rf /var/lib/apt/lists/* \
 && git lfs install

# Upgrade pip and install common packages.
RUN pip install --upgrade pip && \
    pip install --no-cache-dir \
      datasets \
      "huggingface-hub>=0.19" \
      "hf-transfer>=0.1.4" \
      "protobuf<4" \
      "click<8.1" \
      "pydantic~=1.0"

# Copy your requirements file.
COPY requirements.txt .

# IMPORTANT:
# Ensure your requirements.txt pins Scrapely to a compatible (or pure-Python) version.
# For example, include a line like:
#
#    scrapely==0.13.2
#
# Then install your Python dependencies.
RUN pip install --no-cache-dir -r requirements.txt

# Copy the rest of your application code.
COPY . .

# If your app listens on a specific port (e.g. for Streamlit), expose that port.
EXPOSE 8501

# Set the default command (adjust as needed).
CMD ["python", "app.py"]