A bash script that removes all Jupyter notebook outputs from a git repository's history

drop_outputs_in_git_history.sh

#!/bin/bash -e

echo 'Usage:
1. install git-filter-repo from https://github.com/newren/git-filter-repo
2. make a clean clone of your repository (keep a backup!)
3. cd to the repo and run this script
'

python -c 'input("Are you sure? Press Ctrl-C to cancel or Enter to continue.")'

git filter-repo --blob-callback '
import json
try:
    notebook = json.loads(blob.data)
    if "cells" in notebook:
        for cell in notebook["cells"]:
            if "outputs" in cell:
                cell["outputs"] = []
        blob.data = (json.dumps(notebook, ensure_ascii=False, indent=1,
                                sort_keys=True) + "\n").encode("utf-8")
except json.JSONDecodeError as ex:
    pass
except UnicodeDecodeError as ex:
    pass
'

M