Clear the source and output cells in code blocks of jupyter/ipython sheets

nb_clear_codeblock.py

"""
Clear jupyter/ipython sheets by
	- removing the source cell and output cells in code blocks
	- removing highlight tag in markdown block by the highlighter extension

Usage: 
	python nb_clear_code_block.py notebook.ipynb <notebook2.ipynb ...>

Modified
    from https://github.com/flexxui/flexx-notebooks/blob/master/remove_output.py
    by Jun Nishii

Gist: https://gist.github.com/jnishii/555c87a2219d35fb3f082e1e3a13c51e
"""

import sys
import io
import os
import nbformat
import re

def clear_code_block(nb):
    for cell in nb.cells:
        if cell.cell_type == 'code':
            cell.source = []
            cell.outputs = []

def clear_highlight(nb):
    for cell in nb.cells:
        if cell.cell_type == 'markdown':
            cell.source = re.sub('<span class=\\"mark\\">(.*)</span>','\\1',cell.source)

if __name__ == '__main__':
    for fname in sys.argv[1:]:
        print(fname)
        with io.open(fname, 'r', encoding='utf-8') as f:
            nb = nbformat.read(f, as_version=4)

        clear_code_block(nb)
        clear_highlight(nb)

        base, ext = os.path.splitext(fname)
        new_ipynb = "%s_workbook%s" % (base, ext)        
        with io.open(new_ipynb, 'w', encoding='utf8') as f:
            nbformat.write(nb, f, version=4)
        print("wrote %s" % new_ipynb)