Carved out from the StockDocs monorepo. Collects financial news from 60+ outlets via RSS into a structured article corpus.
21 lines
672 B
Plaintext
21 lines
672 B
Plaintext
# --- Dockerfile.local ---
|
|
FROM python:3.13.5
|
|
|
|
# Firefox + GeckoDriver
|
|
RUN apt-get update && apt-get install -y --no-install-recommends \
|
|
firefox-esr wget ca-certificates gnupg2 \
|
|
&& GECKO=v0.36.0 && \
|
|
wget -qO- "https://github.com/mozilla/geckodriver/releases/download/${GECKO}/geckodriver-${GECKO}-linux64.tar.gz" \
|
|
| tar -xz -C /usr/local/bin geckodriver \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
WORKDIR /app
|
|
COPY requirements.txt .
|
|
RUN pip install --no-cache-dir -r requirements.txt
|
|
RUN playwright install
|
|
RUN playwright install-deps
|
|
RUN python3 -m nltk.downloader punkt_tab # Download NLTK data and bake into image
|
|
COPY . .
|
|
|
|
CMD ["python3", "scraper.py"]
|