summaryrefslogtreecommitdiff
path: root/scripts/importer.py
blob: 44453ea928b75597e350c24282868ad0e5251e76 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
#!/usr/bin/env python3
# vim: ft=python fileencoding=utf-8 sts=4 sw=4 et:

# Copyright 2014-2016 Claude (longneck) <longneck@scratchbook.ch>

# This file is part of qutebrowser.
#
# qutebrowser is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# qutebrowser is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with qutebrowser.  If not, see <http://www.gnu.org/licenses/>.


"""Tool to import data from other browsers.

Currently only importing bookmarks from Netscape Bookmark files is supported.
"""


import argparse


def main():
    args = get_args()
    if args.browser in ['chromium', 'firefox', 'ie']:
        import_netscape_bookmarks(args.bookmarks)


def get_args():
    """Get the argparse parser."""
    parser = argparse.ArgumentParser(
        epilog="To import bookmarks from Chromium, Firefox or IE, "
               "export them to HTML in your browsers bookmark manager.")
    parser.add_argument('browser', help="Which browser?",
                        choices=['chromium', 'firefox', 'ie'],
                        metavar='browser')
    parser.add_argument('bookmarks', help="Bookmarks file")
    args = parser.parse_args()
    return args


def import_netscape_bookmarks(bookmarks_file):
    """Import bookmarks from a NETSCAPE-Bookmark-file v1.

    Generated by Chromium, Firefox, IE and possibly more browsers
    """
    import bs4
    with open(bookmarks_file, encoding='utf-8') as f:
        soup = bs4.BeautifulSoup(f, 'html.parser')

    html_tags = soup.findAll('a')

    bookmarks = []
    for tag in html_tags:
        if tag['href'] not in bookmarks:
            bookmarks.append('{tag.string} {tag[href]}'.format(tag=tag))

    for bookmark in bookmarks:
        print(bookmark)


if __name__ == '__main__':
    main()