count-jupyter-nb-words.py

import io
import os
from nbformat import current

total_markdown = 0
total_heading = 0
total_code = 0

for root, dirs, files in os.walk("."):
    for file in files:
        if file.endswith(".ipynb") and not file.endswith("checkpoint.ipynb") :
            #print(os.path.join(root, file))
            with io.open(os.path.join(root, file), 'r', encoding='utf-8') as f:
                nb = current.read(f, 'json')

            word_count_markdown = 0
            word_count_heading = 0
            word_count_code = 0
            for cell in nb.worksheets[0].cells:
                if cell.cell_type == "markdown":
                    word_count_markdown += len(cell['source'].replace('#', '').lstrip().split(' '))
                elif cell.cell_type == "heading":
                    word_count_heading += len(cell['source'].replace('#', '').lstrip().split(' '))
                elif cell.cell_type == "code":
                    word_count_code += len(cell['input'].replace('#', '').lstrip().split(' '))
            total_markdown += word_count_markdown
            total_heading += word_count_heading
            total_code += word_count_code

print("{} Words in notebooks' markdown" .format(total_markdown))
print("{} Words in notebooks' heading" .format(total_heading))
print("{} Words in notebooks' code" .format(total_code))