Last active
March 9, 2019 22:40
-
-
Save iafisher/31979b1f912f023b047101be40ea3145 to your computer and use it in GitHub Desktop.
DEPRECATED (see my bookmarks_from_sql.py gist): A small Python utility to parse bookmarks exports from Firefox
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
""" | |
DEPRECATED: see my bookmarks_from_sql.py gist. | |
A short script to parse bookmark exports from Firefox so they can be | |
manipulated with Python. | |
Author: Ian Fisher ([email protected]) | |
Version: November 2018 | |
""" | |
from collections import namedtuple | |
from html.parser import HTMLParser | |
Bookmark = namedtuple( | |
'Bookmark', ['title', 'url', 'add_date', 'last_modified', 'section'] | |
) | |
class BookmarkParser(HTMLParser): | |
"""An incremental parser is less convenient to use than a DOM parser, but | |
the standard library doesn't offer a DOM parser for HTML, and unfortunately | |
Firefox's export format is not valid XML, so here we are. | |
""" | |
EXPECTING_NOTHING = 0 | |
EXPECTING_HEADER = 1 | |
EXPECTING_BOOKMARK = 2 | |
def __init__(self): | |
super().__init__() | |
self.current_section = None | |
self.mode = self.EXPECTING_NOTHING | |
self.bookmarks = [] | |
self.current_bookmark = None | |
def handle_starttag(self, tag, attrs): | |
if tag == 'a': | |
self.mode = self.EXPECTING_BOOKMARK | |
self.current_bookmark = Bookmark( | |
title='', | |
url=get_attr(attrs, 'href'), | |
last_modified=int(get_attr(attrs, 'last_modified')), | |
add_date=int(get_attr(attrs, 'add_date')), | |
section=self.current_section, | |
) | |
elif tag == 'h3': | |
self.mode = self.EXPECTING_HEADER | |
else: | |
self.mode = self.EXPECTING_NOTHING | |
def handle_data(self, data): | |
if self.mode == self.EXPECTING_HEADER: | |
self.current_section = data | |
elif self.mode == self.EXPECTING_BOOKMARK: | |
self.current_bookmark = self.current_bookmark._replace(title=data) | |
self.bookmarks.append(self.current_bookmark) | |
self.mode = self.EXPECTING_NOTHING | |
def get_attr(attrs, key): | |
for akey, aval in attrs: | |
if akey == key: | |
return aval | |
raise KeyError(key) | |
parser = BookmarkParser() | |
with open('bookmarks.html') as f: | |
parser.feed(f.read()) | |
# Bookmark objects are available as `parser.bookmarks` |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment