Update Dockerfile

Dockerfile

@@ -1,12 +1,15 @@
-# Use Python 3.10-slim as the base image.
-FROM python:3.10-slim
+# Use Python 3.9-slim as the base image.
+FROM python:3.9-slim
 
-# Disable .pyc file generation and force unbuffered stdout/stderr.
+# 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 /app
+WORKDIR /home/user/app
 
 # Install system dependencies.
 RUN apt-get update && apt-get install -y --no-install-recommends \
@@ -22,19 +25,32 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
  && git lfs install
 
 # Upgrade pip and install common packages.
-RUN pip install --upgrade pip
-
-# Copy requirements.txt into the container.
+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 .
 
-# Install the Python dependencies.
+# 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 . .
 
-# Expose the port (Streamlit defaults to 8501).
+# If your app listens on a specific port (e.g. for Streamlit), expose that port.
 EXPOSE 8501
 
-# Set the default command to run your Streamlit app.
-CMD ["streamlit", "run", "app.py", "--server.port=8501"]
+# Set the default command (adjust as needed).
+CMD ["python", "app.py"]