« back to all changes in this revision
Viewing changes to bookmarks.py
- browse files at revision 215
- compare with another revision
- download diff
- download tarball
- view history from revision 215
- Committer: Ulrik Sverdrup
- Date: 2009-02-18 00:41:20 UTC
- Revision ID: git-v1:4debb0ece5bd0731b612db62749b84ee97258e71
Move main application into kupfer/ package
- files added:
- kupfer
- files removed:
- bookmarks.py
- files modified:
- main.py
added
removed
bookmarks.py
1
#!/usr/bin/env python
2
# -*- coding: utf8 -*-
3
4
"""
5
Original file much thanks to
6
http://www.kylo.net/deli.py.txt
7
8
Modifications released under GPL v2 (or any later)
9
Ulrik Sverdrup <ulrik.sverdrup@gmail.com>
10
"""
11
12
from ConfigParser import RawConfigParser
13
from HTMLParser import HTMLParser
14
from os.path import join, expanduser, exists, basename
15
16
def get_firefox_home_file(needed_file):
17
firefox_dir = expanduser("~/.mozilla/firefox/")
18
config = RawConfigParser({"Default" : 0})
19
config.read(expanduser(join(firefox_dir, "profiles.ini")))
20
path = None
21
22
for section in config.sections():
23
if config.has_option(section, "Default") and config.get(section, "Default") == "1":
24
path = config.get (section, "Path")
25
break
26
elif path == None and config.has_option(section, "Path"):
27
path = config.get (section, "Path")
28
29
if path == None:
30
return ""
31
32
if path.startswith("/"):
33
return join(path, needed_file)
34
35
return join(firefox_dir, path, needed_file)
36
37
38
class BookmarksParser(HTMLParser):
39
40
def __init__(self):
41
# this is python: explicitly invoke base class constructor
42
HTMLParser.__init__(self)
43
self.inH3 = False
44
self.inA = False
45
self.tagCount = 0
46
self.tags = []
47
self.currentTag = ""
48
self.href = ""
49
self.description = ""
50
self.ignore = ""
51
52
self.debug = False
53
self.all_items = []
54
55
def setBaseTag(self, baseTag):
56
self.tags.append(baseTag)
57
58
def setIgnoreUrls(self, ignore):
59
self.ignore = ignore
60
61
# remove white space
62
# remove apostrophes, quote, double-quotes, colons, commas
63
def normalizeText(self, text):
64
text = text.replace('\'', '')
65
text = text.replace('"', '')
66
text = text.replace('`', '')
67
text = text.replace(':', '')
68
text = text.replace(',', '')
69
text = text.replace(' ', '')
70
text = text.replace(' ', '')
71
return text
72
73
def handle_starttag(self, tag, attrs):
74
if tag == "a":
75
self.inA = True
76
for attr in attrs:
77
if attr[0] == "href":
78
self.href = attr[1]
79
80
81
if tag == "h3":
82
self.inH3 = True
83
self.tagCount += 1
84
85
if tag == "dl":
86
pass
87
#print "Entering folder list; tags are", self.tags
88
89
def handle_endtag(self, tag):
90
if tag == "h3":
91
self.tags.append(self.currentTag)
92
self.currentTag = ""
93
self.inH3 = False
94
95
if tag == "a":
96
if self.debug == True:
97
print
98
print "href =", self.href
99
print "description =", self.description
100
print "tags =", self.tags
101
102
# validate href
103
validHref = True
104
if len(self.href) == 0:
105
validHref = False
106
if not self.href.split(":")[0] in ["http", "https", "news", "ftp"]:
107
validHref = False
108
if self.href in self.ignore:
109
validHref = False
110
111
# actually post here, make sure there's a url to post
112
if validHref:
113
bookmark = {
114
"href" : self.href,
115
"title": self.description,
116
"tags" : self.tags
117
}
118
self.all_items.append(bookmark)
119
120
self.href = ""
121
self.description = ""
122
self.inA = False
123
124
# exiting a dl means end of a bookmarks folder, pop the last tag off
125
if tag == "dl":
126
self.tags = self.tags[:-1]
127
128
# handle any data: note that this will miss the "escaped" stuff
129
# fix this by adding handle_charref, etc methods
130
def handle_data(self, data):
131
if self.inH3:
132
self.currentTag += self.normalizeText(data)
133
134
if self.inA:
135
self.description += data
136
137
def get_bookmarks(bookmarks_file):
138
"""
139
Return a list of bookmarks (dictionaries)
140
141
each bookmark has the keys:
142
href: URL
143
title: description
144
tags: list of tags/the folder
145
"""
146
# construct and configure the parser
147
parser = BookmarksParser()
148
149
# initiate the parse; this will submit requests to delicious
150
parser.feed(open(bookmarks_file).read())
151
152
# cleanup
153
parser.close()
154
155
return parser.all_items
156
157
def main():
158
# go forth
159
fileloc = get_firefox_home_file("bookmarks.html")
160
print fileloc
161
print get_bookmarks(fileloc)
162
163
if __name__ == "__main__":
164
main()
Loggerhead is a web-based interface for Breezy
Version: 2.0.1