add Dockerfile for containerized PDF-to-markdown conversion

Author: fraboniface

library/scraping/Dockerfile

@@ -0,0 +1,23 @@
+# to avoid OOM issues and give it a max amount of memory / CPUs, run this with
+# create image : docker build -t <image_name> -f scraping/Dockerfile .
+# run it docker run --memory="Ng" --memory-swap="Ng" --cpus="K" <image_name>
+
+FROM python:3.13-slim
+
+# Install wget for downloading files
+RUN apt-get update && apt-get install -y wget && rm -rf /var/lib/apt/lists/*
+
+# Install uv
+COPY --from=ghcr.io/astral-sh/uv:latest /uv /usr/local/bin/uv
+
+WORKDIR /app
+
+COPY pyproject.toml uv.lock* ./
+COPY .env ./
+
+RUN uv sync --frozen --no-dev --group pdfscraping
+
+COPY src/library ./library
+COPY scraping/extract_text_from_pdfs.py .
+
+CMD ["uv", "run", "extract_text_from_pdfs.py", "--md"]