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
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
|
from __future__ import absolute_import
#
# ElementTree
# $Id$
#
# 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) 1999-2007 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
from six import text_type
from . 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 = text_type(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])))
|
