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
|
# css.py - parser functions for css content
#
# Copyright (C) 2005, 2006, 2009, 2011 Arthur de Jong
#
# This program 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 2 of the License, or
# (at your option) any later version.
#
# This program 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 this program; if not, write to the Free Software
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
#
# The files produced as output from the software do not automatically fall
# under the copyright of the software, unless explicitly stated otherwise.
"""This modules attempts to parse CSS files.
It currently looks for url() links in stylesheet contents and also
looks for @import processing directives."""
mimetypes = ('text/css',)
import re
import urlparse
# pattern for matching /* ... */ comments in css
_commentpattern = re.compile('/\*.*?\*/', re.IGNORECASE | re.DOTALL)
# pattern for matching @import "url" statments in css
_importpattern = re.compile('@import\s+["\']([^"\']*)["\']',
re.IGNORECASE | re.DOTALL)
# pattern for matching url(...) in css
_urlpattern = re.compile('url\(["\']?(.*?)["\']?\)')
def parse(content, link, base=None):
"""Parse the specified content and extract information for crawling the
site further."""
# if no base is specified, get it from the link
base = base or link.url
# strip out comments from the content
content = _commentpattern.sub('', content)
# handle @imports
for embed in _importpattern.findall(content):
link.add_embed(urlparse.urljoin(base, embed))
# handle url()s
for embed in _urlpattern.findall(content):
link.add_embed(urlparse.urljoin(base, embed))
|