mirror of
https://github.com/Hopiu/linkchecker.git
synced 2026-03-22 08:50:24 +00:00
3eac1be9ab
Use Python 2.5 features and get rid of old compat code. Also some code cleanups have been made. git-svn-id: https://linkchecker.svn.sourceforge.net/svnroot/linkchecker/trunk/linkchecker@3737 e7d03fd6-7b0d-0410-9947-9c21f3af8025
53 lines
1.7 KiB
Python
53 lines
1.7 KiB
Python
# -*- coding: iso-8859-1 -*-
|
|
# Copyright (C) 2001-2008 Bastian Kleineidam
|
|
#
|
|
# 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., 675 Mass Ave, Cambridge, MA 02139, USA.
|
|
"""
|
|
Parse name of common link types.
|
|
"""
|
|
|
|
import re
|
|
from . import HtmlParser
|
|
from . import strformat
|
|
|
|
|
|
imgtag_re = re.compile(r"(?i)\s+alt\s*=\s*"+\
|
|
r"""(?P<name>("[^"\n]*"|'[^'\n]*'|[^\s>]+))""")
|
|
img_re = re.compile(r"""(?i)<\s*img\s+("[^"\n]*"|'[^'\n]*'|[^>])+>""")
|
|
endtag_re = re.compile(r"""(?i)</a\s*>""")
|
|
|
|
def _unquote (txt):
|
|
"""Resolve entities and markup from txt."""
|
|
return HtmlParser.resolve_entities(strformat.remove_markup(txt))
|
|
|
|
def image_name (txt):
|
|
"""Return the alt part of the first <img alt=""> tag in txt."""
|
|
mo = imgtag_re.search(txt)
|
|
if mo:
|
|
name = strformat.unquote(mo.group('name').strip())
|
|
return _unquote(name)
|
|
return u''
|
|
|
|
|
|
def href_name (txt):
|
|
"""Return the name part of the first <a href="">name</a> link in txt."""
|
|
name = u""
|
|
endtag = endtag_re.search(txt)
|
|
if not endtag:
|
|
return name
|
|
name = txt[:endtag.start()]
|
|
if img_re.search(name):
|
|
return image_name(name)
|
|
return _unquote(name)
|