blob: a193d9944ad6ca6b524cc6fe7f27a5369ed4633a (
plain)
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
|
import unittest
from lxml.tests.common_imports import make_doctest
import lxml.html
from lxml.html.clean import Cleaner, clean_html
class CleanerTest(unittest.TestCase):
def test_allow_tags(self):
html = """
<html>
<head>
</head>
<body>
<p>some text</p>
<table>
<tr>
<td>hello</td><td>world</td>
</tr>
<tr>
<td>hello</td><td>world</td>
</tr>
</table>
<img>
</body>
</html>
"""
html_root = lxml.html.document_fromstring(html)
cleaner = Cleaner(
remove_unknown_tags = False,
allow_tags = ['table', 'tr', 'td'])
result = cleaner.clean_html(html_root)
self.assertEqual(12-5+1, len(list(result.iter())))
def test_safe_attrs_included(self):
html = """<p><span style="color: #00ffff;">Cyan</span></p>"""
safe_attrs=set(lxml.html.defs.safe_attrs)
safe_attrs.add('style')
cleaner = Cleaner(
safe_attrs_only=True,
safe_attrs=safe_attrs)
result = cleaner.clean_html(html)
self.assertEqual(html, result)
def test_safe_attrs_excluded(self):
html = """<p><span style="color: #00ffff;">Cyan</span></p>"""
expected = """<p><span>Cyan</span></p>"""
safe_attrs=set()
cleaner = Cleaner(
safe_attrs_only=True,
safe_attrs=safe_attrs)
result = cleaner.clean_html(html)
self.assertEqual(expected, result)
def test_clean_invalid_root_tag(self):
# only testing that cleaning with invalid root tags works at all
s = lxml.html.fromstring('parent <invalid tag>child</another>')
self.assertEqual('parent child', clean_html(s).text_content())
s = lxml.html.fromstring('<invalid tag>child</another>')
self.assertEqual('child', clean_html(s).text_content())
def test_suite():
suite = unittest.TestSuite()
suite.addTests([make_doctest('test_clean.txt')])
suite.addTests([make_doctest('test_clean_embed.txt')])
suite.addTests(unittest.makeSuite(CleanerTest))
return suite
|
