Code: Alles auswählen
C:\keep>keep.py alt
Traceback (most recent call last):
File "C:\keep\keep.py", line 7, in <module>
from pathlib import path
ImportError: cannot import name 'path' from 'pathlib' (C:\Users\vierpunktzwo\AppData\Local\Programs\Python\Python38-32\lib\pathlib.py)
Code: Alles auswählen
C:\keep>keep.py alt
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE en-export SYSTEM "http://xml.evernote.com/pub/evernote-export3.dtd">
<en-export export-date="20180502T065115Z" application="Evernote" version="Evernote Mac 6.10 (454269)">
Traceback (most recent call last):
File "C:\keep\keep.py", line 92, in <module>
mungefile(path)
File "C:\keep\keep.py", line 16, in mungefile
with open(path, 'r') as file :
PermissionError: [Errno 13] Permission denied: 'alt'
Code: Alles auswählen
#!/usr/bin/env python3
# originally created and posted by user dgc on
# https://discussion.evernote.com/topic/97201-how-to-transfer-all-the-notes-from-google-keep-to-evernote/
# until now, Google Takeout for Keep does NOT export:
# - correct order of lists notes (non-checked first, checked last)
# - list items indentation
import sys
import re
import parsedatetime as pdt
import time
cal = pdt.Calendar()
r1 = re.compile(
'<li class="listitem checked"><span class="bullet">☑</span>.*?<span class="text">(.*?)</span>.*?</li>')
r2 = re.compile('<li class="listitem"><span class="bullet">☐</span>.*?<span class="text">(.*?)</span>.*?</li>')
r3 = re.compile('<span class="chip label"><span class="label-name">([^<]*)</span>[^<]*</span>')
f = open("export.enex", "w+")
def readlineUntil(file, str):
currLine = ""
while not str in currLine:
currLine = file.readline()
return currLine
def mungefile(fn):
fp = open(fn, 'r')
# title = fp.readline().strip()
title = readlineUntil(fp, "<title>").strip()
title = title.replace('<title>', '').replace('</title>', '')
readlineUntil(fp, "<body>")
t = fp.readline()
tags = ''
if '"archived"' in t:
tags = '<tag>archived</tag>'
fp.readline() # </div> alone
date = fp.readline().strip().replace('</div>', '')
dt, flat = cal.parse(date)
iso = time.strftime('%Y%m%dT%H%M%SZ', time.gmtime(time.mktime(dt)))
fp.readline() # extra title
# I still couldn't import a note with an image attachment
# MAYBE I could turn this replace into a standard div
# and remove the div removal below... just an idea.
# For the moment, I'll just import the offending note by hand,
# but if you have lots of notes with attached images, this code
# still doesn't handle it
content = fp.readline().replace('<div class="content">', '')
content = content.replace('<ul class="list">', '')
for line in fp:
line = line.strip()
if line == '</div></body></html>' or line.startswith('<div class="chips">'):
break
content += line + '\n'
content = content.replace('<br>', '<br/>')
content = content.replace('\n', '\0')
while True:
m = r1.search(content)
if not m:
break
content = content[:m.start()] + '<en-todo checked="true"/>' + m.group(1) + '<br/>' + content[m.end():]
while True:
m = r2.search(content)
if not m:
break
content = content[:m.start()] + '<en-todo checked="false"/>' + m.group(1) + '<br/>' + content[m.end():]
content = content.replace('\0', '\n')
# remove final div close
content = content.strip()
if content.endswith('</div>'):
content = content[:-6]
# remove list close (if it was a list)
if content.endswith('</ul>'):
content = content[:-5]
# line might still has chips
if line.startswith('<div class="chips">'):
content += line + '\n'
for line in fp:
line = line.strip()
if line == '</div></body></html>':
break
content += line + '\n'
m = r3.search(content)
if m:
content = content[:m.start()] + content[m.end():]
tags = '<tag>' + m.group(1) + '</tag>'
content = re.sub(
r'class="[^"]*"',
'',
content
)
fp.close()
f.write('''
<note>
<title>{title}</title>
<content><![CDATA[<?xml version="1.0" encoding="UTF-8"?><!DOCTYPE en-note SYSTEM "http://xml.evernote.com/pub/enml2.dtd"><en-note style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;">{content}</en-note>]]></content>
<created>{iso}</created>
<updated>{iso}</updated>
{tags}
<note-attributes>
<latitude>0</latitude>
<longitude>0</longitude>
<source>google-keep</source>
<reminder-order>0</reminder-order>
</note-attributes>
</note>
'''.format(**locals()))
f.write('''<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE en-export SYSTEM "http://xml.evernote.com/pub/evernote-export3.dtd">
<en-export export-date="20180502T065115Z" application="Evernote/Windows" version="6.x">''')
for arg in sys.argv[1:]:
mungefile(arg)
f.write('''</en-export>''')
f.close()Code: Alles auswählen
C:\keep>keep1.py alt/*.html /*.enex
Traceback (most recent call last):
File "C:\keep\keep1.py", line 135, in <module>
mungefile(arg)
File "C:\keep\keep1.py", line 33, in mungefile
fp = open(fn, 'r')
OSError: [Errno 22] Invalid argument: 'alt/*.html'Code: Alles auswählen
#!/usr/bin/env python3
import sys
import bs4
import dateutil.parser
from pathlib import Path
from xml.etree import ElementTree as et
def convert_note(filename):
with open(filename) as content:
html = bs4.BeautifulSoup(content)
archived = bool(html.find('span', class_='archived'))
title = html.find('div', class_='title').text
date = html.find('div', class_='heading').text.strip()
date = dateutil.parser.parse(date, dayfirst=True)
en_note = et.Element('en-note', style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;")
items = html.find('div', class_='content').find_all('li', class_='listitem')
for item in items:
checked="true" if 'checked' in item.attrs['class'] else "false"
et.SubElement(en_note, 'en-todo', checked=checked).tail = item.find('span', class_='text').text
chips = html.find('div', class_='chips')
if chips:
tags = chips.find_all('span', class_='chip')
tags = [tag.find('span', class_='label-name').text for tag in tags]
else:
tags = []
note = et.Element('note')
et.SubElement(note, 'title').text = title
et.SubElement(note, 'content').text = et.tostring(en_note, encoding='unicode')
et.SubElement(note, 'created').text = '{:%Y%m%dT%H%M%SZ}'.format(date)
et.SubElement(note, 'updated').text = '{:%Y%m%dT%H%M%SZ}'.format(date)
tags_element = et.SubElement(note, 'tags')
for tag in tags:
et.SubElement(tags_element, 'tag').text = tag
attr = et.SubElement(note, 'note-attributes')
et.SubElement(attr, 'latitude').text = '0'
et.SubElement(attr, 'longitude').text = '0'
et.SubElement(attr, 'source').text = 'google-keep'
et.SubElement(attr, 'reminder-order').text = '0'
return note
def main(argv):
export = et.Element("en-export", {
"export-date": "20180502T065115Z",
"application": "Evernote/Windows",
"version": "6.x"
})
for pattern in argv:
pattern = Path(pattern)
anchor = Path(pattern.anchor)
for filename in anchor.glob(str(pattern.relative_to(anchor)):
export.append(convert_note(filename))
with open("export.enex", "w", encoding="utf8") as output:
output.write('<?xml version="1.0" encoding="UTF-8"?>\n'
'<!DOCTYPE en-export SYSTEM "http://xml.evernote.com/pub/evernote-export3.dtd">\n')
et.ElementTree(export).write(output, encoding='unicode')
if __name__ == '__main__':
main(sys.argv[1:])