Jarian Cottingham
724be90e7c
Carved out from the StockDocs monorepo. Collects financial news from 60+ outlets via RSS into a structured article corpus.
23 lines
609 B
Plaintext
23 lines
609 B
Plaintext
# Use an official Selenium Firefox standalone as a base image
|
|
FROM selenium/standalone-firefox:latest
|
|
|
|
USER root
|
|
# Set the working directory in the container
|
|
WORKDIR /app
|
|
|
|
# Install Python dependencies
|
|
COPY requirements.txt /app/
|
|
RUN pip install --break-system-packages --no-cache-dir -r requirements.txt && \
|
|
playwright install
|
|
|
|
# Copy the current directory contents into the container at /app
|
|
COPY . /app
|
|
RUN mkdir -p /app/articles && \
|
|
chown seluser:seluser /app/articles && \
|
|
chmod 755 /app/articles
|
|
|
|
USER seluser
|
|
# Run the Flask app
|
|
CMD ["python3", "scraper.py"]
|
|
|