/usr/share/pyshared/weboob/tools/parsers/elementtidyparser.py is in python-weboob-core 0.g-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 57 58 59 60 61 62 63 64 65 66 67 | # -*- coding: utf-8 -*-
# Copyright(C) 2010-2011 Romain Bignon
#
# This file is part of weboob.
#
# weboob is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# weboob 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 Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with weboob. If not, see <http://www.gnu.org/licenses/>.
# XXX Currently, elementtidy segfaults when there are no error, because of
# the behavior of libtidy.
# A patch has been sent to Debian:
# http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=576343
#
# As it is not integrated in Debian yet, and as this problem persists on other
# systems, using elementtidy is for now to avoid.
from elementtidy import TidyHTMLTreeBuilder
try:
from xml.etree import cElementTree as ElementTree
except ImportError:
from xml.etree import ElementTree
from .iparser import IParser
__all__ = ['ElementTidyParser']
class ElementTidyParser(IParser):
def parse(self, data, encoding=None):
TidyHTMLTreeBuilder.ElementTree = ElementTree
HTMLTreeBuilder = TidyHTMLTreeBuilder.TidyHTMLTreeBuilder
parser = HTMLTreeBuilder(encoding)
tree = ElementTree.parse(data, parser)
for elem in tree.getiterator():
if elem.tag.startswith('{'):
elem.tag = elem.tag[elem.tag.find('}')+1:]
return tree
def tostring(self, element):
e = ElementTree.Element('body')
e.text = element.text
e.tail = element.tail
for sub in element.getchildren():
e.append(sub)
s = ''
# XXX OK if it doesn't work with utf-8, the result will be fucking ugly.
for encoding in ('utf-8', 'ISO-8859-1'):
try:
s = ElementTree.tostring(e, encoding)
except UnicodeError:
continue
else:
break
return unicode(s)
|