Convert notes from Tomboy XML to Evernote XML

README.md

This is a quick script to convert notes from Tomboy to Evernote.

Usage

pip install -r requirements.txt
mkdir export/
python tomboy-export.py <tomboy-dir>

If you're on OS X, <tomboy-dir> would be /Users/{yourusername}/Library/Application\ Support/Tomboy/.

The .enex files will be created in the export/ dir.

Limitations

• the note content is converted to plain text

Resources

• https://blog.evernote.com/tech/2013/08/08/evernote-export-format-enex/
• https://wiki.gnome.org/Apps/Tomboy/NoteXmlFormat

requirements.txt

isodate==0.4.9
lxml==3.2.4

tomboy-export.py

from __future__ import print_function

import glob
import lxml.etree as ET
import os
import sys
import isodate
import datetime

TOMBOY_CAT_PREFIX = 'system:notebook:'

EV_EXPORT_XML = u"""<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE en-export SYSTEM "http://xml.evernote.com/pub/evernote-export3.dtd">
"""

EV_NOTE_XML = u"""<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<!DOCTYPE en-note SYSTEM "http://xml.evernote.com/pub/enml2.dtd">
"""

EV_DATE_FORMAT = '%Y%m%dT%H%M%SZ'

def el(name):
    return '{http://beatniksoftware.com/tomboy}' + name

def innertext(tag):
    """Convert Tomboy XML to Markdown"""

    text = (tag.text or '')

    if tag.tag == el('bold'):
        text = '**' + text.strip() + '**'
    elif tag.tag == el('list-item'):
        text = '- ' + text

    return text + ''.join(innertext(e) for e in tag) + (tag.tail or '')

def append_content(path, content):
    with open(path, 'r') as f:
        existingContent = f.read().decode('utf8')

    if -1 == existingContent.find(content):
        with open(path, 'a') as f:
            content = u'\n* *\n *\n\n' + content
            f.write(content.encode('utf8'))

def extract_data(path):
    root = ET.parse(path).getroot()

    tags = []
    category = None

    tagsEl = root.find(el('tags'))
    if tagsEl is not None:
        for tagEl in tagsEl:
            tag = tagEl.text

            if tag.startswith(TOMBOY_CAT_PREFIX):
                category = tag.replace(TOMBOY_CAT_PREFIX, '')
            else:
                tags.append(tag)

    if 'system:template' in tags:
        return None

    note = {}

    title = root.find(el('title')).text
    contentTag = root.find(el('text')).find(el('note-content'))
    content = innertext(contentTag)

    note['title'] = title
    note['content'] = content.replace(title, '').lstrip()

    for tag, key in [('create-date', 'created'), ('last-change-date', 'updated')]:
        dateTag = root.find(el(tag))
        note[key] = isodate.parse_datetime(dateTag.text)

    note['tags'] = tags
    note['category'] = category

    return note

def prepare_content(text_content):
    tree = ET.Element('en-note')

    for line in text_content.split('\n'):
        el = ET.SubElement(tree, 'div')

        line = line.strip()
        if line != '':
            el.text = line
        else:
            ET.SubElement(el, 'br')

    return EV_NOTE_XML + ET.tostring(tree, pretty_print=True)

def export_one(note, path, export_dt):
    tree = ET.Element('en-export', {
        'application': 'Tomboy Exporter',
        'version': '0.1',
        'export-date': export_dt.strftime(EV_DATE_FORMAT)
    })

    noteTag = ET.SubElement(tree, 'note')

    titleTag = ET.SubElement(noteTag, 'title')
    titleTag.text = note['title']

    contentTag = ET.SubElement(noteTag, 'content')
    contentTag.text = ET.CDATA(prepare_content(note['content']))

    for key in ['created', 'updated']:
        dateTag = ET.SubElement(noteTag, key)
        dateTag.text = note[key].strftime(EV_DATE_FORMAT)

    for tag in note['tags']:
        tagEl = ET.SubElement(noteTag, 'tag')
        tagEl.text = tag

    with open(path, 'w') as f:
        f.write(EV_EXPORT_XML)
        ET.ElementTree(tree).write(f)
        f.write('\n')

def main():
    if len(sys.argv) < 2:
        print('usage: python tomboy-export.py <tomboy-dir>', file=sys.stderr)
        sys.exit(1)

    export_dt = datetime.datetime.now()

    count = 0

    for path in glob.glob(sys.argv[1] + '/*.note'):
        note = extract_data(path)

        if not note:
            continue

        notePath = 'export/'
        if note['category']:
            notePath = os.path.join(notePath, note['category'])

        if not os.path.exists(notePath):
            os.makedirs(notePath)

        notePath = os.path.join(notePath, note['title'].replace('/', '|') + '.enex')

        export_one(note, notePath, export_dt)

        count += 1

    print('Exported %s notes.' % count)

main()

@scribu It doesn't respect bold or italic format. When I import it through api, all formattings are lost.