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
|
#
# ElementTree
# $Id: ElementPath.py 1858 2004-06-17 21:31:41Z Fredrik $
#
# limited xpath support for element trees
#
# history:
# 2003-05-23 fl created
# 2003-05-28 fl added support for // etc
# 2003-08-27 fl fixed parsing of periods in element names
#
# Copyright (c) 2003-2004 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.
# --------------------------------------------------------------------
##
# Implementation module for XPath support. There's usually no reason
# to import this module directly; the <b>ElementTree</b> does this for
# you, if needed.
##
import re
xpath_tokenizer = re.compile(
"(::|\.\.|\(\)|[/.*:\[\]\(\)@=])|((?:\{[^}]+\})?[^/:\[\]\(\)@=\s]+)|\s+"
).findall
class xpath_descendant_or_self:
pass
##
# Wrapper for a compiled XPath.
class Path:
##
# Create an Path instance from an XPath expression.
def __init__(self, path):
tokens = xpath_tokenizer(path)
# the current version supports 'path/path'-style expressions only
self.path = []
self.tag = None
if tokens and tokens[0][0] == "/":
raise SyntaxError("cannot use absolute path on element")
while tokens:
op, tag = tokens.pop(0)
if tag or op == "*":
self.path.append(tag or op)
elif op == ".":
pass
elif op == "/":
self.path.append(xpath_descendant_or_self())
continue
else:
raise SyntaxError("unsupported path syntax (%s)" % op)
if tokens:
op, tag = tokens.pop(0)
if op != "/":
raise SyntaxError(
"expected path separator (%s)" % (op or tag)
)
if self.path and isinstance(self.path[-1], xpath_descendant_or_self):
raise SyntaxError("path cannot end with //")
if len(self.path) == 1 and isinstance(self.path[0], type("")):
self.tag = self.path[0]
##
# Find first matching object.
def find(self, element):
tag = self.tag
if tag is None:
nodeset = self.findall(element)
if not nodeset:
return None
return nodeset[0]
for elem in element:
if elem.tag == tag:
return elem
return None
##
# Find text for first matching object.
def findtext(self, element, default=None):
tag = self.tag
if tag is None:
nodeset = self.findall(element)
if not nodeset:
return default
return nodeset[0].text or ""
for elem in element:
if elem.tag == tag:
return elem.text or ""
return default
##
# Find all matching objects.
def findall(self, element):
nodeset = [element]
index = 0
while 1:
try:
path = self.path[index]
index = index + 1
except IndexError:
return nodeset
set = []
if isinstance(path, xpath_descendant_or_self):
try:
tag = self.path[index]
if not isinstance(tag, type("")):
tag = None
else:
index = index + 1
except IndexError:
tag = None # invalid path
for node in nodeset:
new = list(node.getiterator(tag))
if new and new[0] is node:
set.extend(new[1:])
else:
set.extend(new)
else:
for node in nodeset:
for node in node:
if path == "*" or node.tag == path:
set.append(node)
if not set:
return []
nodeset = set
_cache = {}
##
# (Internal) Compile path.
def _compile(path):
p = _cache.get(path)
if p is not None:
return p
p = Path(path)
if len(_cache) >= 100:
_cache.clear()
_cache[path] = p
return p
##
# Find first matching object.
def find(element, path):
return _compile(path).find(element)
##
# Find text for first matching object.
def findtext(element, path, default=None):
return _compile(path).findtext(element, default)
##
# Find all matching objects.
def findall(element, path):
return _compile(path).findall(element)
|
