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
|
"""Tests to ensure that the html.parser tree builder generates good
trees."""
from pdb import set_trace
import pickle
import warnings
from bs4.testing import SoupTest, HTMLTreeBuilderSmokeTest
from bs4.builder import HTMLParserTreeBuilder
from bs4.builder._htmlparser import BeautifulSoupHTMLParser
class HTMLParserTreeBuilderSmokeTest(SoupTest, HTMLTreeBuilderSmokeTest):
default_builder = HTMLParserTreeBuilder
def test_namespaced_system_doctype(self):
# html.parser can't handle namespaced doctypes, so skip this one.
pass
def test_namespaced_public_doctype(self):
# html.parser can't handle namespaced doctypes, so skip this one.
pass
def test_builder_is_pickled(self):
"""Unlike most tree builders, HTMLParserTreeBuilder and will
be restored after pickling.
"""
tree = self.soup("<a><b>foo</a>")
dumped = pickle.dumps(tree, 2)
loaded = pickle.loads(dumped)
self.assertTrue(isinstance(loaded.builder, type(tree.builder)))
def test_redundant_empty_element_closing_tags(self):
self.assertSoupEquals('<br></br><br></br><br></br>', "<br/><br/><br/>")
self.assertSoupEquals('</br></br></br>', "")
def test_empty_element(self):
# This verifies that any buffered data present when the parser
# finishes working is handled.
self.assertSoupEquals("foo &# bar", "foo &# bar")
def test_tracking_line_numbers(self):
# The html.parser TreeBuilder keeps track of line number and
# position of each element.
markup = "\n <p>\n\n<sourceline>\n<b>text</b></sourceline><sourcepos></p>"
soup = self.soup(markup)
self.assertEqual(2, soup.p.sourceline)
self.assertEqual(3, soup.p.sourcepos)
self.assertEqual("sourceline", soup.p.find('sourceline').name)
# You can deactivate this behavior.
soup = self.soup(markup, store_line_numbers=False)
self.assertEqual("sourceline", soup.p.sourceline.name)
self.assertEqual("sourcepos", soup.p.sourcepos.name)
def test_on_duplicate_attribute(self):
# The html.parser tree builder has a variety of ways of
# handling a tag that contains the same attribute multiple times.
markup = '<a class="cls" href="url1" href="url2" href="url3" id="id">'
# If you don't provide any particular value for
# on_duplicate_attribute, later values replace earlier values.
soup = self.soup(markup)
self.assertEquals("url3", soup.a['href'])
self.assertEquals(["cls"], soup.a['class'])
self.assertEquals("id", soup.a['id'])
# You can also get this behavior explicitly.
def assert_attribute(on_duplicate_attribute, expected):
soup = self.soup(
markup, on_duplicate_attribute=on_duplicate_attribute
)
self.assertEquals(expected, soup.a['href'])
# Verify that non-duplicate attributes are treated normally.
self.assertEquals(["cls"], soup.a['class'])
self.assertEquals("id", soup.a['id'])
assert_attribute(None, "url3")
assert_attribute(BeautifulSoupHTMLParser.REPLACE, "url3")
# You can ignore subsequent values in favor of the first.
assert_attribute(BeautifulSoupHTMLParser.IGNORE, "url1")
# And you can pass in a callable that does whatever you want.
def accumulate(attrs, key, value):
if not isinstance(attrs[key], list):
attrs[key] = [attrs[key]]
attrs[key].append(value)
assert_attribute(accumulate, ["url1", "url2", "url3"])
def test_html5_attributes(self):
# The html.parser TreeBuilder can convert any entity named in
# the HTML5 spec to a sequence of Unicode characters, and
# convert those Unicode characters to a (potentially
# different) named entity on the way out.
for input_element, output_unicode, output_element in (
("⇄", u'\u21c4', b'⇄'),
('⊧', u'\u22a7', b'⊧'),
('𝔑', u'\U0001d511', b'𝔑'),
('≧̸', u'\u2267\u0338', b'≧̸'),
('¬', u'\xac', b'¬'),
('⫬', u'\u2aec', b'⫬'),
('"', u'"', b'"'),
('∴', u'\u2234', b'∴'),
('∴', u'\u2234', b'∴'),
('∴', u'\u2234', b'∴'),
("fj", u'fj', b'fj'),
("⊔", u'\u2294', b'⊔'),
("⊔︀", u'\u2294\ufe00', b'⊔︀'),
("'", u"'", b"'"),
("|", u"|", b"|"),
):
markup = u'<div>%s</div>' % input_element
div = self.soup(markup).div
without_element = div.encode()
expect = b"<div>%s</div>" % output_unicode.encode("utf8")
self.assertEquals(without_element, expect)
with_element = div.encode(formatter="html")
expect = b"<div>%s</div>" % output_element
self.assertEquals(with_element, expect)
class TestHTMLParserSubclass(SoupTest):
def test_error(self):
"""Verify that our HTMLParser subclass implements error() in a way
that doesn't cause a crash.
"""
parser = BeautifulSoupHTMLParser()
with warnings.catch_warnings(record=True) as warns:
parser.error("don't crash")
[warning] = warns
assert "don't crash" == str(warning.message)
|
