├── .gitignore
├── README.md
└── bm2evernote.py


/.gitignore:
--------------------------------------------------------------------------------
 1 | *.py[co]
 2 | 
 3 | # Packages
 4 | *.egg
 5 | *.egg-info
 6 | dist
 7 | build
 8 | eggs
 9 | parts
10 | bin
11 | var
12 | sdist
13 | develop-eggs
14 | .installed.cfg
15 | 
16 | # Installer logs
17 | pip-log.txt
18 | 
19 | # Unit test / coverage reports
20 | .coverage
21 | .tox
22 | 
23 | #Translations
24 | *.mo
25 | 
26 | #Mr Developer
27 | .mr.developer.cfg
28 | 
29 | venv
30 | *.enex
31 | *.html
32 | 
33 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | bookmarks2evernote
 2 | ==================
 3 | 
 4 | A simple command line tool to transform bookmarks exported from Google Chrome and Google Bookmarks into Evernote as _individual_ notes using EN's enex format.
 5 | If the html file you are using as input uses H3 as folder name, this are translated into Evernote tags.
 6 | For this to work correctly, you may have to ensure when exporting Google Chrome Bookmarks that all the folders are located at the end of your bookmark's list.
 7 | 
 8 | It also indentifies duplicated bookmarks in the same HTML file. Google Bookmarks export feature duplicates all bookmarks with more than one tag.
 9 | 
10 | Requisites:
11 | -----------
12 | 
13 | * Python
14 | * [Beautiful Soup](http://www.crummy.com/software/BeautifulSoup/). An excellent python library for html parsing and navigation. Follow their instructions for installation.
15 | 
16 | Usage:
17 | ------
18 | It takes a single parameter, the name of the input html file. 
19 | 
20 | E.g. `python bm2evernote.py YOUR_BOOKMARKS_EXPORT_FILE.html`
21 | 
22 | The output file will have the same name as the input but with an enex extension.
23 | 


--------------------------------------------------------------------------------
/bm2evernote.py:
--------------------------------------------------------------------------------
 1 | from bs4 import BeautifulSoup
 2 | import codecs
 3 | import argparse
 4 | import time
 5 | 
 6 | class Bookmark():
 7 |     """docstring for Bookmark"""
 8 |     def __init__(self, title, url, tag, date):
 9 |         self.title = title
10 |         self.url = url
11 |         self.tag = '<tag>' + tag + '</tag>'
12 |         self.date = time.strftime("%Y%m%dT%H%M%SZ", time.gmtime(float(date)))
13 |         self.content = '''<a href="%(url)s">%(title)s</a>''' % {'title': self.title, 'url': self.url}
14 | 
15 |     def printAsEnex(self):
16 |         output = """<note><title>%(title)s</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)s</en-note>]]></content><created>%(date)s</created><updated>%(date)s</updated>%(tag)s<note-attributes><source-url>%(url)s</source-url></note-attributes></note>""" % {'title': self.title, 'content': self.content, 'tag': self.tag, 'url': self.url, 'date': self.date,}
17 |         return output.replace('&', '&amp;')
18 | 
19 |     def __str__(self):
20 |         return unicode(self.title + " " + self.url + " " + self.tag)
21 | 
22 | def unique(bookmarks):
23 |     found = {}
24 |     res = []
25 | 
26 |     for bookmark in bookmarks:
27 |         if bookmark.url not in found:
28 |             found[bookmark.url] = bookmark
29 |         else:
30 |             found[bookmark.url].tag += bookmark.tag
31 | 
32 |     for key in found:
33 |         res.append(found[key])
34 | 
35 |     return res
36 | 
37 | def main():
38 |     
39 | 
40 |     try:
41 |         parser = argparse.ArgumentParser()
42 |         parser.add_argument("html_file", help="the file that contains the bookmarks in html format")
43 |         args = parser.parse_args()
44 |         soup = BeautifulSoup(codecs.open(args.html_file, encoding='utf-8'))
45 | 
46 |         html_tags = soup.findAll(['h3', 'a'])
47 | 
48 |         en_tag = ''
49 | 
50 |         bookmarks = []
51 | 
52 |         for tag in html_tags:
53 |             if tag.name == 'h3':
54 |                 en_tag = tag.string
55 |             if tag.name == 'a':
56 |                 new_bm = Bookmark(tag.string, tag['href'], en_tag, tag['add_date'])
57 |                 bookmarks.append(new_bm)
58 | 
59 |         print "Total Bookmarks: " + str(len(bookmarks))
60 | 
61 |         bookmarks = unique(bookmarks)
62 | 
63 |         print "Unique Bookmarks: " + str(len(bookmarks))
64 | 
65 |         output_file = args.html_file.split('.')[0] + ".enex"
66 |         out = codecs.open(output_file, 'w', encoding='utf-8')
67 | 
68 |         out.write("""<?xml version="1.0" encoding="UTF-8"?><!DOCTYPE en-export SYSTEM "http://xml.evernote.com/pub/evernote-export.dtd"><en-export application="Evernote/Windows" version="4.x">""")
69 |         for n in bookmarks:
70 |             out.write(n.printAsEnex())
71 | 
72 |         out.write("</en-export>")
73 |         out.close()
74 | 
75 |         print "Success! Output file name: " + output_file
76 |     except Exception as e:
77 |         print "Error!"
78 |         print type(e)
79 |         print e.args
80 | 
81 | 
82 | if __name__ == '__main__':
83 |     main()
84 | 


--------------------------------------------------------------------------------