Viewing file:  HTMLTreeBuilder.py (7.87 KB) -rw-r--r--
Select action/file-type:
 (+) |  (+) |  (+) | Code (+) | Session (+) |  (+) | SDB (+) |  (+) |  (+) |  (+) |  (+) |  (+) |
#
# ElementTree
# $Id: HTMLTreeBuilder.py 2325 2005-03-16 15:50:43Z fredrik $
#
# a simple tree builder, for HTML input
#
# history:
# 2002-04-06 fl created
# 2002-04-07 fl ignore IMG and HR end tags
# 2002-04-07 fl added support for 1.5.2 and later
# 2003-04-13 fl added HTMLTreeBuilder alias
# 2004-12-02 fl don't feed non-ASCII charrefs/entities as 8-bit strings
# 2004-12-05 fl don't feed non-ASCII CDATA as 8-bit strings
#
# Copyright (c) 1999-2004 by Fredrik Lundh. All rights reserved.
#
# fredrik@pythonware.com
# http://www.pythonware.com
#
# --------------------------------------------------------------------
# The ElementTree toolkit is
#
# Copyright (c) 1999-2004 by Fredrik Lundh
#
# By obtaining, using, and/or copying this software and/or its
# associated documentation, you agree that you have read, understood,
# and will comply with the following terms and conditions:
#
# Permission to use, copy, modify, and distribute this software and
# its associated documentation for any purpose and without fee is
# hereby granted, provided that the above copyright notice appears in
# all copies, and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of
# Secret Labs AB or the author not be used in advertising or publicity
# pertaining to distribution of the software without specific, written
# prior permission.
#
# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD
# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-
# ABILITY AND FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR
# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY
# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
# OF THIS SOFTWARE.
# --------------------------------------------------------------------
##
# Tools to build element trees from HTML files.
##
import htmlentitydefs
import re, string, sys
import mimetools, StringIO
import ElementTree
AUTOCLOSE = "p", "li", "tr", "th", "td", "head", "body"
IGNOREEND = "img", "hr", "meta", "link", "br"
if sys.version[:3] == "1.5":
is_not_ascii = re.compile(r"[\x80-\xff]").search # 1.5.2
else:
is_not_ascii = re.compile(eval(r'u"[\u0080-\uffff]"')).search
try:
from HTMLParser import HTMLParser
except ImportError:
from sgmllib import SGMLParser
# hack to use sgmllib's SGMLParser to emulate 2.2's HTMLParser
class HTMLParser(SGMLParser):
# the following only works as long as this class doesn't
# provide any do, start, or end handlers
def unknown_starttag(self, tag, attrs):
self.handle_starttag(tag, attrs)
def unknown_endtag(self, tag):
self.handle_endtag(tag)
##
# ElementTree builder for HTML source code. This builder converts an
# HTML document or fragment to an ElementTree.
# <p>
# The parser is relatively picky, and requires balanced tags for most
# elements. However, elements belonging to the following group are
# automatically closed: P, LI, TR, TH, and TD. In addition, the
# parser automatically inserts end tags immediately after the start
# tag, and ignores any end tags for the following group: IMG, HR,
# META, and LINK.
#
# @keyparam builder Optional builder object. If omitted, the parser
# uses the standard <b>elementtree</b> builder.
# @keyparam encoding Optional character encoding, if known. If omitted,
# the parser looks for META tags inside the document. If no tags
# are found, the parser defaults to ISO-8859-1. Note that if your
# document uses a non-ASCII compatible encoding, you must decode
# the document before parsing.
#
# @see elementtree.ElementTree
class HTMLTreeBuilder(HTMLParser):
# FIXME: shouldn't this class be named Parser, not Builder?
def __init__(self, builder=None, encoding=None):
self.__stack = []
if builder is None:
builder = ElementTree.TreeBuilder()
self.__builder = builder
self.encoding = encoding or "iso-8859-1"
HTMLParser.__init__(self)
##
# Flushes parser buffers, and return the root element.
#
# @return An Element instance.
def close(self):
HTMLParser.close(self)
return self.__builder.close()
##
# (Internal) Handles start tags.
def handle_starttag(self, tag, attrs):
if tag == "meta":
# look for encoding directives
http_equiv = content = None
for k, v in attrs:
if k == "http-equiv":
http_equiv = string.lower(v)
elif k == "content":
content = v
if http_equiv == "content-type" and content:
# use mimetools to parse the http header
header = mimetools.Message(
StringIO.StringIO("%s: %s\n\n" % (http_equiv, content))
)
encoding = header.getparam("charset")
if encoding:
self.encoding = encoding
if tag in AUTOCLOSE:
if self.__stack and self.__stack[-1] == tag:
self.handle_endtag(tag)
self.__stack.append(tag)
attrib = {}
if attrs:
for k, v in attrs:
attrib[string.lower(k)] = v
self.__builder.start(tag, attrib)
if tag in IGNOREEND:
self.__stack.pop()
self.__builder.end(tag)
##
# (Internal) Handles end tags.
def handle_endtag(self, tag):
if tag in IGNOREEND:
return
lasttag = self.__stack.pop()
if tag != lasttag and lasttag in AUTOCLOSE:
self.handle_endtag(lasttag)
self.__builder.end(tag)
##
# (Internal) Handles character references.
def handle_charref(self, char):
if char[:1] == "x":
char = int(char[1:], 16)
else:
char = int(char)
if 0 <= char < 128:
self.__builder.data(chr(char))
else:
self.__builder.data(unichr(char))
##
# (Internal) Handles entity references.
def handle_entityref(self, name):
entity = htmlentitydefs.entitydefs.get(name)
if entity:
if len(entity) == 1:
entity = ord(entity)
else:
entity = int(entity[2:-1])
if 0 <= entity < 128:
self.__builder.data(chr(entity))
else:
self.__builder.data(unichr(entity))
else:
self.unknown_entityref(name)
##
# (Internal) Handles character data.
def handle_data(self, data):
if isinstance(data, type('')) and is_not_ascii(data):
# convert to unicode, but only if necessary
data = unicode(data, self.encoding, "ignore")
self.__builder.data(data)
##
# (Hook) Handles unknown entity references. The default action
# is to ignore unknown entities.
def unknown_entityref(self, name):
pass # ignore by default; override if necessary
##
# An alias for the <b>HTMLTreeBuilder</b> class.
TreeBuilder = HTMLTreeBuilder
##
# Parse an HTML document or document fragment.
#
# @param source A filename or file object containing HTML data.
# @param encoding Optional character encoding, if known. If omitted,
# the parser looks for META tags inside the document. If no tags
# are found, the parser defaults to ISO-8859-1.
# @return An ElementTree instance
def parse(source, encoding=None):
return ElementTree.parse(source, HTMLTreeBuilder(encoding=encoding))
if __name__ == "__main__":
import sys
ElementTree.dump(parse(open(sys.argv[1])))
|