Utility to convert the Standard Notes conversion of Evernote data from HTML to Markdown

standard-notes-html-to-md.py

#!/usr/bin/env python3
#
# This script augments the converter tool provided by standard notes to provide
# Markdown instead of HTML as the format for the export, which is useful in
# particular after a conversion from Evernote exports [1]. This allows them to
# be viewed with other editors within the standard notes platform.
#
# The pandoc command like tool must be installed locally in order for this
# script to work.
#
# [1] https://dashboard.standardnotes.org/tools

import argparse
import subprocess
import json


def main(args):
    with open(args.filename) as f:
        raw = f.read()
        data = json.loads(raw)
        for item in data['items']:
            if item['content_type'] != 'Note':
                continue
            html = item['content']['text']
            item['content']['text'] = subprocess.run(
                ['pandoc', '--from=html', '--to=markdown_strict'],
                input=html.encode('utf-8'), stdout=subprocess.PIPE,
            ).stdout.decode('utf-8')
        print(json.dumps(data, indent=2))


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('filename', default='evernote-to-sn.txt', nargs='?')
    args = parser.parse_args()
    main(args)