Substitute Jupyter markdown cell content for text from file

substitute-md.py

"""
This script searches a Jupyter notebook for markdown cells that start with 
three colons (:::) and replaces their content with text from the file path 
that follows.

Example cell markup:
     ':::target_file.md'

Usage:
    python substitute-md.py my-report.ipynb
    python substitute-md.py my-report.ipynb --output my-report-final.ipynb

"""
import json

from argparse import ArgumentParser
from pathlib import Path


parser = ArgumentParser()
parser.add_argument("source")
parser.add_argument("--output")

args = parser.parse_args()

source = Path(args.source)
target = args.output or f"{source.stem}-new{source.suffix}"

nb = Path(source)
nb_json = json.loads(nb.read_text())

md_cells = [cell for cell in nb_json["cells"] if cell["cell_type"] == "markdown"]

for cell in md_cells:
    cell_source = cell["source"]
    if len(cell_source) == 1 and cell_source[0].startswith(":::"):
        target_file = cell_source[0].lstrip(":")
        cell["source"] = [Path(target_file).read_text()]
        print(f"Found target: {target_file}")

compiled_nb = json.dumps(nb_json)
Path(target).write_text(compiled_nb)

print(f"Output saved: {target}")