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
|
__all__ = [
'LXMLTreeBuilderForXML',
'LXMLTreeBuilder',
]
from StringIO import StringIO
import collections
from lxml import etree
from bs4.element import Comment, Doctype, NamespacedAttribute
from bs4.builder import (
FAST,
HTML,
HTMLTreeBuilder,
PERMISSIVE,
TreeBuilder,
XML)
from bs4.dammit import UnicodeDammit
LXML = 'lxml'
class LXMLTreeBuilderForXML(TreeBuilder):
DEFAULT_PARSER_CLASS = etree.XMLParser
is_xml = True
# Well, it's permissive by XML parser standards.
features = [LXML, XML, FAST, PERMISSIVE]
CHUNK_SIZE = 512
@property
def default_parser(self):
# This can either return a parser object or a class, which
# will be instantiated with default arguments.
return etree.XMLParser(target=self, strip_cdata=False, recover=True)
def __init__(self, parser=None, empty_element_tags=None):
if empty_element_tags is not None:
self.empty_element_tags = set(empty_element_tags)
if parser is None:
# Use the default parser.
parser = self.default_parser
if isinstance(parser, collections.Callable):
# Instantiate the parser with default arguments
parser = parser(target=self, strip_cdata=False)
self.parser = parser
self.soup = None
self.nsmaps = None
def _getNsTag(self, tag):
# Split the namespace URL out of a fully-qualified lxml tag
# name. Copied from lxml's src/lxml/sax.py.
if tag[0] == '{':
return tuple(tag[1:].split('}', 1))
else:
return (None, tag)
def prepare_markup(self, markup, user_specified_encoding=None,
document_declared_encoding=None):
"""
:return: A 3-tuple (markup, original encoding, encoding
declared within markup).
"""
if isinstance(markup, unicode):
return markup, None, None, False
try_encodings = [user_specified_encoding, document_declared_encoding]
dammit = UnicodeDammit(markup, try_encodings, is_html=True)
return (dammit.markup, dammit.original_encoding,
dammit.declared_html_encoding,
dammit.contains_replacement_characters)
def feed(self, markup):
if isinstance(markup, basestring):
markup = StringIO(markup)
# Call feed() at least once, even if the markup is empty,
# or the parser won't be initialized.
data = markup.read(self.CHUNK_SIZE)
self.parser.feed(data)
while data != '':
# Now call feed() on the rest of the data, chunk by chunk.
data = markup.read(self.CHUNK_SIZE)
if data != '':
self.parser.feed(data)
self.parser.close()
def close(self):
self.nsmaps = None
def start(self, name, attrs, nsmap={}):
# Make sure attrs is a mutable dict--lxml may send an immutable dictproxy.
attrs = dict(attrs)
nsprefix = None
# Invert each namespace map as it comes in.
if len(nsmap) == 0 and self.nsmaps != None:
# There are no new namespaces for this tag, but namespaces
# are in play, so we need a separate tag stack to know
# when they end.
self.nsmaps.append(None)
elif len(nsmap) > 0:
# A new namespace mapping has come into play.
if self.nsmaps is None:
self.nsmaps = []
inverted_nsmap = dict((value, key) for key, value in nsmap.items())
self.nsmaps.append(inverted_nsmap)
# Also treat the namespace mapping as a set of attributes on the
# tag, so we can recreate it later.
attrs = attrs.copy()
for prefix, namespace in nsmap.items():
attribute = NamespacedAttribute(
"xmlns", prefix, "http://www.w3.org/2000/xmlns/")
attrs[attribute] = namespace
if self.nsmaps is not None and len(self.nsmaps) > 0:
# Namespaces are in play. Find any attributes that came in
# from lxml with namespaces attached to their names, and
# turn then into NamespacedAttribute objects.
new_attrs = {}
for attr, value in attrs.items():
namespace, attr = self._getNsTag(attr)
if namespace is None:
new_attrs[attr] = value
else:
nsprefix = self._prefix_for_namespace(namespace)
attr = NamespacedAttribute(nsprefix, attr, namespace)
new_attrs[attr] = value
attrs = new_attrs
namespace, name = self._getNsTag(name)
nsprefix = self._prefix_for_namespace(namespace)
self.soup.handle_starttag(name, namespace, nsprefix, attrs)
def _prefix_for_namespace(self, namespace):
"""Find the currently active prefix for the given namespace."""
if namespace is None:
return None
for inverted_nsmap in reversed(self.nsmaps):
if inverted_nsmap is not None and namespace in inverted_nsmap:
return inverted_nsmap[namespace]
def end(self, name):
self.soup.endData()
completed_tag = self.soup.tagStack[-1]
namespace, name = self._getNsTag(name)
nsprefix = None
if namespace is not None:
for inverted_nsmap in reversed(self.nsmaps):
if inverted_nsmap is not None and namespace in inverted_nsmap:
nsprefix = inverted_nsmap[namespace]
break
self.soup.handle_endtag(name, nsprefix)
if self.nsmaps != None:
# This tag, or one of its parents, introduced a namespace
# mapping, so pop it off the stack.
self.nsmaps.pop()
if len(self.nsmaps) == 0:
# Namespaces are no longer in play, so don't bother keeping
# track of the namespace stack.
self.nsmaps = None
def pi(self, target, data):
pass
def data(self, content):
self.soup.handle_data(content)
def doctype(self, name, pubid, system):
self.soup.endData()
doctype = Doctype.for_name_and_ids(name, pubid, system)
self.soup.object_was_parsed(doctype)
def comment(self, content):
"Handle comments as Comment objects."
self.soup.endData()
self.soup.handle_data(content)
self.soup.endData(Comment)
def test_fragment_to_document(self, fragment):
"""See `TreeBuilder`."""
return u'<?xml version="1.0" encoding="utf-8"?>\n%s' % fragment
class LXMLTreeBuilder(HTMLTreeBuilder, LXMLTreeBuilderForXML):
features = [LXML, HTML, FAST, PERMISSIVE]
is_xml = False
@property
def default_parser(self):
return etree.HTMLParser
def feed(self, markup):
self.parser.feed(markup)
self.parser.close()
def test_fragment_to_document(self, fragment):
"""See `TreeBuilder`."""
return u'<html><body>%s</body></html>' % fragment
|
