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
|
__all__ = [
'HTML5TreeBuilder',
]
from beautifulsoup.builder import HTMLTreeBuilder, SAXTreeBuilder
import html5lib
from html5lib.constants import DataLossWarning
import warnings
from beautifulsoup.element import (
Comment,
Doctype,
NavigableString,
Tag,
)
class HTML5TreeBuilder(HTMLTreeBuilder):
"""Use html5lib to build a tree."""
def prepare_markup(self, markup, user_specified_encoding):
# Store the user-specified encoding for use later on.
self.user_specified_encoding = user_specified_encoding
return markup, None, None
# These methods are defined by Beautiful Soup.
def feed(self, markup):
parser = html5lib.HTMLParser(tree=self.create_treebuilder)
doc = parser.parse(markup, encoding=self.user_specified_encoding)
# Set the character encoding detected by the tokenizer.
if isinstance(markup, unicode):
# We need to special-case this because html5lib sets
# charEncoding to UTF-8 if it gets Unicode input.
doc.original_encoding = None
else:
doc.original_encoding = parser.tokenizer.stream.charEncoding[0]
def create_treebuilder(self, namespaceHTMLElements):
self.underlying_builder = TreeBuilderForHtml5lib(
self.soup, namespaceHTMLElements)
return self.underlying_builder
def test_fragment_to_document(self, fragment):
"""See `TreeBuilder`."""
return u'<html><head></head><body>%s</body></html>' % fragment
class TreeBuilderForHtml5lib(html5lib.treebuilders._base.TreeBuilder):
def __init__(self, soup, namespaceHTMLElements):
self.soup = soup
if namespaceHTMLElements:
warnings.warn("namespaceHTMLElements not supported yet", DataLossWarning)
super(TreeBuilderForHtml5lib, self).__init__(namespaceHTMLElements)
def documentClass(self):
self.soup.reset()
return Element(self.soup, self.soup, None)
def insertDoctype(self, token):
name = token["name"]
publicId = token["publicId"]
systemId = token["systemId"]
doctype = Doctype.for_name_and_ids(name, publicId, systemId)
self.soup.object_was_parsed(doctype)
def elementClass(self, name, namespace):
if namespace is not None:
warnings.warn("BeautifulSoup cannot represent elements in any namespace", DataLossWarning)
return Element(Tag(self.soup, self.soup.builder, name), self.soup, namespace)
def commentClass(self, data):
return TextNode(Comment(data), self.soup)
def fragmentClass(self):
self.soup = BeautifulSoup("")
self.soup.name = "[document_fragment]"
return Element(self.soup, self.soup, None)
def appendChild(self, node):
self.soup.insert(len(self.soup.contents), node.element)
def testSerializer(self, element):
return testSerializer(element)
def getDocument(self):
return self.soup
def getFragment(self):
return html5lib.treebuilders._base.TreeBuilder.getFragment(self).element
class AttrList(object):
def __init__(self, element):
self.element = element
self.attrs = dict(self.element.attrs)
def __iter__(self):
return self.attrs.items().__iter__()
def __setitem__(self, name, value):
"set attr", name, value
self.element[name] = value
def items(self):
return self.attrs.items()
def keys(self):
return self.attrs.keys()
def __getitem__(self, name):
return self.attrs[name]
def __contains__(self, name):
return name in self.attrs.keys()
class Element(html5lib.treebuilders._base.Node):
def __init__(self, element, soup, namespace):
html5lib.treebuilders._base.Node.__init__(self, element.name)
self.element = element
self.soup = soup
self.namespace = namespace
def _nodeIndex(self, node, refNode):
# Finds a node by identity rather than equality
for index in range(len(self.element.contents)):
if id(self.element.contents[index]) == id(refNode.element):
return index
return None
def appendChild(self, node):
if (node.element.__class__ == NavigableString and self.element.contents
and self.element.contents[-1].__class__ == NavigableString):
# Concatenate new text onto old text node
# (TODO: This has O(n^2) performance, for input like "a</a>a</a>a</a>...")
newStr = NavigableString(self.element.contents[-1]+node.element)
# Remove the old text node
# (Can't simply use .extract() by itself, because it fails if
# an equal text node exists within the parent node)
oldElement = self.element.contents[-1]
del self.element.contents[-1]
oldElement.parent = None
oldElement.extract()
self.element.insert(len(self.element.contents), newStr)
else:
self.element.insert(len(self.element.contents), node.element)
node.parent = self
def getAttributes(self):
return AttrList(self.element)
def setAttributes(self, attributes):
if attributes is not None and attributes != {}:
for name, value in attributes.items():
self.element[name] = value
# The attributes may contain variables that need substitution.
# Call set_up_substitutions manually.
# The Tag constructor calls this method automatically,
# but html5lib creates a Tag object before setting up
# the attributes.
self.element.contains_substitutions = (
self.soup.builder.set_up_substitutions(
self.element))
attributes = property(getAttributes, setAttributes)
def insertText(self, data, insertBefore=None):
text = TextNode(NavigableString(data), self.soup)
if insertBefore:
self.insertBefore(text, insertBefore)
else:
self.appendChild(text)
def insertBefore(self, node, refNode):
index = self._nodeIndex(node, refNode)
if (node.element.__class__ == NavigableString and self.element.contents
and self.element.contents[index-1].__class__ == NavigableString):
# (See comments in appendChild)
newStr = NavigableString(self.element.contents[index-1]+node.element)
oldNode = self.element.contents[index-1]
del self.element.contents[index-1]
oldNode.parent = None
oldNode.extract()
self.element.insert(index-1, newStr)
else:
self.element.insert(index, node.element)
node.parent = self
def removeChild(self, node):
index = self._nodeIndex(node.parent, node)
del node.parent.element.contents[index]
node.element.parent = None
node.element.extract()
node.parent = None
def reparentChildren(self, newParent):
while self.element.contents:
child = self.element.contents[0]
child.extract()
if isinstance(child, Tag):
newParent.appendChild(Element(child, self.soup, namespaces["html"]))
else:
newParent.appendChild(TextNode(child, self.soup))
def cloneNode(self):
node = Element(Tag(self.soup, self.soup.builder, self.element.name), self.soup, self.namespace)
for key,value in self.attributes:
node.attributes[key] = value
return node
def hasContent(self):
return self.element.contents
def getNameTuple(self):
if self.namespace == None:
return namespaces["html"], self.name
else:
return self.namespace, self.name
nameTuple = property(getNameTuple)
class TextNode(Element):
def __init__(self, element, soup):
html5lib.treebuilders._base.Node.__init__(self, None)
self.element = element
self.soup = soup
def cloneNode(self):
raise NotImplementedError
|
