mirror of
https://github.com/Hopiu/linkchecker.git
synced 2026-05-04 21:04:41 +00:00
support both HtmlPrint and HtmlPrettyPrinter
git-svn-id: https://linkchecker.svn.sourceforge.net/svnroot/linkchecker/trunk/linkchecker@2168 e7d03fd6-7b0d-0410-9947-9c21f3af8025
This commit is contained in:
parent
4b5629d9e9
commit
f6c1b61d08
1 changed files with 43 additions and 8 deletions
|
|
@ -1,13 +1,48 @@
|
|||
#!/usr/bin/env python
|
||||
#!/usr/bin/python2.3
|
||||
# Copyright (C) 2004-2005 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.
|
||||
# -*- coding: iso-8859-1 -*-
|
||||
import sys
|
||||
from linkcheck.parser.htmllib import HtmlPrinter
|
||||
|
||||
def _main (filename):
|
||||
data = file(filename).read()
|
||||
p = HtmlPrinter()
|
||||
p.feed(data)
|
||||
def _main (args):
|
||||
"""USAGE: test/run.sh test/parsefile.py test.html"""
|
||||
if len(args) < 1:
|
||||
print _main.__doc__
|
||||
sys.exit(1)
|
||||
from linkcheck.HtmlParser.htmllib import HtmlPrinter, HtmlPrettyPrinter
|
||||
if args[0] == "-p":
|
||||
klass = HtmlPrettyPrinter
|
||||
filename = args[1]
|
||||
else:
|
||||
klass = HtmlPrinter
|
||||
filename = args[0]
|
||||
if filename == '-':
|
||||
f = sys.stdin
|
||||
else:
|
||||
f = open(filename)
|
||||
from linkcheck.HtmlParser import htmlsax
|
||||
p = htmlsax.parser(klass())
|
||||
p.debug(1)
|
||||
size = 1024
|
||||
#size = 1
|
||||
data = f.read(size)
|
||||
while data:
|
||||
p.feed(data)
|
||||
data = f.read(size)
|
||||
p.flush()
|
||||
|
||||
if __name__=='__main__':
|
||||
_main(sys.argv[1])
|
||||
import sys
|
||||
_main(sys.argv[1:])
|
||||
|
|
|
|||
Loading…
Reference in a new issue