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
|
__all__ = [
'LXMLTreeBuilderForXML',
'LXMLTreeBuilder',
]
import collections
from lxml import etree
from bs4.element import Comment, Doctype
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]
@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 = []
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):
self.parser.feed(markup)
self.parser.close()
def close(self):
self.namespaces.clear()
def start(self, name, attrs, nsmap={}):
nsprefix = None
# Invert each namespace map as it comes in.
if len(nsmap) == 0:
self.nsmaps.append(None)
else:
inverted_nsmap = dict((value, key) for key, value in nsmap.items())
self.nsmaps.append(inverted_nsmap)
if "{" in name:
import pdb; pdb.set_trace()
namespace, name = self._getNsTag(name)
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_starttag(name, namespace, nsprefix, attrs)
def end(self, name):
self.soup.endData()
completed_tag = self.soup.tagStack[-1]
self.soup.handle_endtag(name)
self.nsmaps.pop()
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 test_fragment_to_document(self, fragment):
"""See `TreeBuilder`."""
return u'<html><body>%s</body></html>' % fragment
|
