filter_enex.py

filter_enex.py

import re
import html
from lxml.etree import tostring
from ever2simple.converter import EverConverter


def my_unescape(s):
    s = s.replace(""", "PROTECTEDQUOT=====")
    s = html.unescape(s)
    s = s.replace("PROTECTEDQUOT=====", """)
    return s


conv = EverConverter("./notes.enex")
xml_tree = conv._load_xml(conv.enex_filename)
created = xml_tree.findall('//created')
updated = xml_tree.findall('//updated')
titles = xml_tree.findall('//title')
dates = []
for title in titles:
    m = re.match(r'Note - (?P<year>\d{4})-(?P<month>\d{2})-(?P<day>\d{2}) (?P<hour>\d{2}) (?P<min>\d{2}) (?P<sec>\d{2}) - (?P<title>.*)', title.text)
    if m:
        title.text = m.group('title')
        dates.append("%s%s%sT%s%s%sZ" % tuple([m.group(t) for t in ['year', 'month', 'day', 'hour', 'min', 'sec']]))
    else:
        raise ValueError("Invalid title: %s" % title.text)
for create_date, update_date, date in zip(created, updated, dates):
    create_date.text = date
    update_date.text = date
with open('./filtered.enex', 'w') as out_fh:
    out_fh.write(r'<?xml version="1.0" encoding="UTF-8"?>' + "\n")
    out_fh.write(
        my_unescape(tostring(xml_tree).decode('utf8'))
    )