nbstripout

#!/usr/bin/env python
"""strip outputs from an IPython Notebook
Opens a notebook, strips its output, and writes the outputless version to the
original file. Useful mainly as a git filter or pre-commit hook for users who
don't want to track output in VCS. This does mostly the same thing as the
`Clear All Output` command in the notebook UI.
"""

import sys
from io import StringIO
import codecs

py2 = True

if (sys.version_info > (3, 0)):
    py2 = False

try:
    # Jupyter >= 4
    from nbformat import read, write, NO_CONVERT
except ImportError:
    # IPython 3
    try:
        from IPython.nbformat import read, write, NO_CONVERT
    except ImportError:
        # IPython < 3
        from IPython.nbformat import current
        
        def read(f, as_version):
            return current.read(f, 'json')

        def write(nb, f):
            return current.write(nb, f, 'json')


def _cells(nb):
    """Yield all cells in an nbformat-insensitive manner"""
    if nb.nbformat < 4:
        for ws in nb.worksheets:
            for cell in ws.cells:
                yield cell
    else:
        for cell in nb.cells:
            yield cell


def strip_output(nb):
    """strip the outputs from a notebook object"""
    nb.metadata.pop('signature', None)
    for cell in _cells(nb):
        if 'outputs' in cell:
            cell['outputs'] = []
        if 'prompt_number' in cell:
            cell['prompt_number'] = 0
        if 'execution_count' in cell:
            cell['execution_count'] = 0
        if 'metadata' in cell and 'ExecuteTime' in cell['metadata']:
            cell['metadata']['ExecuteTime'] = {}
    return nb


if __name__ == '__main__':
    nb = None
    if py2:
        UTF8Reader = codecs.getreader('utf8')
        sys.stdin = UTF8Reader(sys.stdin)
    nb = read(StringIO(sys.stdin.read()), as_version=NO_CONVERT)
    nb = strip_output(nb)
    write(nb, sys.stdout)