Remove unused/obsolete parsers
lxmlsoup is currently used by one module.
This commit is contained in:
Laurent Bachelier
parent
f20f73a9cd
commit
afb3bc412f
4 changed files with 0 additions and 232 deletions
|
|
@ -43,21 +43,6 @@ def load_xml():
|
||||||
return LxmlXmlParser
|
return LxmlXmlParser
|
||||||
|
|
||||||
|
|
||||||
def load_html5lib():
|
|
||||||
from .html5libparser import Html5libParser
|
|
||||||
return Html5libParser
|
|
||||||
|
|
||||||
|
|
||||||
def load_elementtidy():
|
|
||||||
from .elementtidyparser import ElementTidyParser
|
|
||||||
return ElementTidyParser
|
|
||||||
|
|
||||||
|
|
||||||
def load_builtin():
|
|
||||||
from .htmlparser import HTMLParser
|
|
||||||
return HTMLParser
|
|
||||||
|
|
||||||
|
|
||||||
def load_json():
|
def load_json():
|
||||||
# This parser doesn't read HTML, don't include it in the
|
# This parser doesn't read HTML, don't include it in the
|
||||||
# preference_order default value below.
|
# preference_order default value below.
|
||||||
|
|
@ -82,7 +67,6 @@ def load_raw():
|
||||||
def get_parser(preference_order=('lxml', 'lxmlsoup')):
|
def get_parser(preference_order=('lxml', 'lxmlsoup')):
|
||||||
"""
|
"""
|
||||||
Get a parser from a preference order list.
|
Get a parser from a preference order list.
|
||||||
This allows Weboob to run on systems without lxml, which is the default parser.
|
|
||||||
Return a parser implementing IParser.
|
Return a parser implementing IParser.
|
||||||
"""
|
"""
|
||||||
if not isinstance(preference_order, (tuple, list)):
|
if not isinstance(preference_order, (tuple, list)):
|
||||||
|
|
|
||||||
|
|
@ -1,67 +0,0 @@
|
||||||
# -*- 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)
|
|
||||||
|
|
@ -1,53 +0,0 @@
|
||||||
# -*- coding: utf-8 -*-
|
|
||||||
|
|
||||||
# Copyright(C) 2010-2011 Romain Bignon, Christophe Benz
|
|
||||||
#
|
|
||||||
# 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/>.
|
|
||||||
|
|
||||||
|
|
||||||
from html5lib import treebuilders, HTMLParser
|
|
||||||
try:
|
|
||||||
from xml.etree import cElementTree as ElementTree
|
|
||||||
except ImportError:
|
|
||||||
from xml.etree import ElementTree
|
|
||||||
|
|
||||||
from .iparser import IParser
|
|
||||||
|
|
||||||
|
|
||||||
__all__ = ['Html5libParser']
|
|
||||||
|
|
||||||
|
|
||||||
class Html5libParser(HTMLParser, IParser):
|
|
||||||
"""
|
|
||||||
Parser using html5lib.
|
|
||||||
|
|
||||||
Note that it is not available on every systems.
|
|
||||||
"""
|
|
||||||
|
|
||||||
# Default implementation for each type of API.
|
|
||||||
defaults = {'etree': ElementTree}
|
|
||||||
|
|
||||||
def __init__(self, api='etree'):
|
|
||||||
# if no default implementation is defined for this api, set it to None
|
|
||||||
# to let getTreeBuilder() using the corresponding implementation.
|
|
||||||
implementation = self.defaults.get(api, None)
|
|
||||||
HTMLParser.__init__(self, tree=treebuilders.getTreeBuilder(api, implementation))
|
|
||||||
|
|
||||||
def parse(self, data, encoding):
|
|
||||||
return HTMLParser.parse(self, data, encoding=encoding)
|
|
||||||
|
|
||||||
def tostring(self, element):
|
|
||||||
return element.toxml()
|
|
||||||
|
|
@ -1,96 +0,0 @@
|
||||||
# -*- 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/>.
|
|
||||||
|
|
||||||
|
|
||||||
from HTMLParser import HTMLParser as _HTMLParser
|
|
||||||
import htmlentitydefs
|
|
||||||
try:
|
|
||||||
from xml.etree import cElementTree as ElementTree
|
|
||||||
except ImportError:
|
|
||||||
from xml.etree import ElementTree
|
|
||||||
|
|
||||||
from .iparser import IParser
|
|
||||||
|
|
||||||
|
|
||||||
__all__ = ['HTMLParser']
|
|
||||||
|
|
||||||
|
|
||||||
class HTMLTreeBuilder(_HTMLParser):
|
|
||||||
def __init__(self, encoding=None):
|
|
||||||
_HTMLParser.__init__(self)
|
|
||||||
self._target = ElementTree.TreeBuilder()
|
|
||||||
|
|
||||||
def doctype(self, name, pubid, system):
|
|
||||||
pass
|
|
||||||
|
|
||||||
def close(self):
|
|
||||||
tree = self._target.close()
|
|
||||||
return tree
|
|
||||||
|
|
||||||
def handle_starttag(self, tag, attrs):
|
|
||||||
self._target.start(tag, dict(attrs))
|
|
||||||
|
|
||||||
def handle_startendtag(self, tag, attrs):
|
|
||||||
self._target.start(tag, dict(attrs))
|
|
||||||
self._target.end(tag)
|
|
||||||
|
|
||||||
def handle_charref(self, name):
|
|
||||||
self._target.data(unichr(int(name)))
|
|
||||||
|
|
||||||
def handle_entityref(self, name):
|
|
||||||
try:
|
|
||||||
self._target.data(unichr(htmlentitydefs.name2codepoint[name]))
|
|
||||||
except KeyError:
|
|
||||||
self._target.data('&' + name)
|
|
||||||
|
|
||||||
def handle_data(self, data):
|
|
||||||
self._target.data(data)
|
|
||||||
|
|
||||||
def handle_endtag(self, tag):
|
|
||||||
try:
|
|
||||||
self._target.end(tag)
|
|
||||||
except:
|
|
||||||
pass
|
|
||||||
|
|
||||||
|
|
||||||
class HTMLParser(IParser):
|
|
||||||
def parse(self, data, encoding=None):
|
|
||||||
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)
|
|
||||||
Loading…
Add table
Add a link
Reference in a new issue