How can I convert my Jupyter Notebooks to Jekyll-ready blog posts in a single click? How do I streamline that process so that I can quickly fix typos, better explain topics, or add new ideas without the hassle of manually converting the notebooks to something more Jekyll-friendly? To answer this, I wrote a simple batch script that allows me to edit posts in Jupyter Notebooks and then post them as HTMLs. This is built for Windows and using Github Pages, which is what I use to host this blog.

EDIT: I no longer do this but I thought the post was worth keeping. I prefer to convert it to markdown using jupyter nbconvert --to markdown mynotebook.ipynb then make any final changes from there.

For anyone else interested in this method, the first thing you have to do is to make sure your Jupyter Notebook posts follow the file naming convention for Jekyll blogs posts. They have to start with a date code in the YYYY-MM-DD format, followed by the post name. For example, 2016-01-01-my-first-post.ipynb would work. The script we’ll use also allows for notebooks with a space in their name, so 2016-01-01-my first post.ipynb would work too.

The bulk of the work is done by nbconvert. Nbconvert is a great open source tool for converting Jupyter Notebooks to various formats, incluing HTML, LaTeX, Markdown, and even PDF. Jekyll uses kramdown to convert Markdown, so you could convert the post to either HTML or Markdown. I prefer HTML and that’s what we’ll do here.

The next step is to write a batch script that goes to the folder holding your posts and runs nbconvert. Then it initiates a Python script for the final touches. I wanted to include the beginning excerpt from each post on the main page. Jekyll does this well for Markdown files, but not for the HTMLs that are created by nbconvert. It prints the date code and the title at the beginning of the blog excerpt, which does not look good on the main page of the blog. That’s where the Python script comes in - it opens up every HTML file and removes the title section before saving it in the posts folder. Alright, now for the code. Here’s the batch script:

@echo off
title quick notebooks
cd C:\Users\HMISYS\Google Drive\JupyterNotebooks\Blog
REM This allows for files that have a space in their name
for /f "usebackq delims=|" %%f ^
in (`dir /b "C:\Users\HMISYS\Google Drive\JupyterNotebooks\Blog\*.ipynb"`) ^
do jupyter nbconvert --to html "%%f"
REM > "C:\Users\HMISYS\Documents\GitHub\\_posts"
REM now run the python script
C:\Users\HMISYS\Anaconda3\python.exe ^
C:\Users\HMISYS\Dropbox\jupyter_notebook_converter\ %*

And here’s the Python script that is called from the batch script:

# This function is to be run after the batch file
import os
import re

load_posts_path = 'C:/Users/HMISYS/Google Drive/JupyterNotebooks/Blog/'
save_posts_path = 'C:/Users/HMISYS/Documents/GitHub/'

items_in_path = os.listdir(load_posts_path)
# Use RegEx to find the title
regex_pattern = "<title>.*</title>"

for file in items_in_path:
    # If the file is HTML
    if file[-4:].lower() == 'html':
        with open(load_posts_path+file) as f:
                text = f.readlines()
                # Check to see if the file contains the regex pattern
                if, string=text[3]):
                    print("Removing file name from " + file)
                    # Remove the title from the text
                    text[3] = re.sub(regex_pattern, "", text[3]) # The title is in the third line
                    # Save the post
                    with open(save_posts_path+file, 'w') as w:
                        for line in text:
            except UnicodeDecodeError:
                print("File {} is having a problem".format(file))

The batch script can be run from the command line, but let’s take automation one step further and make a desktop icon to run this. Here’s how to do that:

  1. Open the start menu and type “cmd”
  2. Right-click on cmd.exe (the Command Prompt) and select Pin to Taskbar
  3. Hold Shift and right-click on the Command Prompt icon on the taskbar
  4. Select Properties
  5. In the Target field you should have %windir%\system32\cmd.exe, add the following to it: /c "C:\path\to\your\batch_file.bat"
  6. The Target field should look something like this: %windir%\system32\cmd.exe /c "C:\Users\HMISYS\Dropbox\jupyter_notebook_converter\jupyter_notebooks.bat"

Now, with a single click, your Jupyter Notebook will be ready to commit!