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
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
|
from pathlib import Path
from time import process_time
from urllib.parse import urlparse
import pytest
from scrapy.http import HtmlResponse, Response, TextResponse
from scrapy.utils.python import to_bytes
from scrapy.utils.response import (
_remove_html_comments,
get_base_url,
get_meta_refresh,
open_in_browser,
response_status_message,
)
class TestResponseUtils:
dummy_response = TextResponse(url="http://example.org/", body=b"dummy_response")
def test_open_in_browser(self):
url = "http:///www.example.com/some/page.html"
body = b"<html> <head> <title>test page</title> </head> <body>test body</body> </html>"
def browser_open(burl):
path = urlparse(burl).path
if not path or not Path(path).exists():
path = burl.replace("file://", "")
bbody = Path(path).read_bytes()
assert b'<base href="' + to_bytes(url) + b'">' in bbody
return True
response = HtmlResponse(url, body=body)
assert open_in_browser(response, _openfunc=browser_open), "Browser not called"
resp = Response(url, body=body)
with pytest.raises(TypeError):
open_in_browser(resp, debug=True) # pylint: disable=unexpected-keyword-arg
def test_get_meta_refresh(self):
r1 = HtmlResponse(
"http://www.example.com",
body=b"""
<html>
<head><title>Dummy</title><meta http-equiv="refresh" content="5;url=http://example.org/newpage" /></head>
<body>blahablsdfsal&</body>
</html>""",
)
r2 = HtmlResponse(
"http://www.example.com",
body=b"""
<html>
<head><title>Dummy</title><noScript>
<meta http-equiv="refresh" content="5;url=http://example.org/newpage" /></head>
</noSCRIPT>
<body>blahablsdfsal&</body>
</html>""",
)
r3 = HtmlResponse(
"http://www.example.com",
body=b"""
<noscript><meta http-equiv="REFRESH" content="0;url=http://www.example.com/newpage</noscript>
<script type="text/javascript">
if(!checkCookies()){
document.write('<meta http-equiv="REFRESH" content="0;url=http://www.example.com/newpage">');
}
</script>
""",
)
assert get_meta_refresh(r1) == (5.0, "http://example.org/newpage")
assert get_meta_refresh(r2) == (None, None)
assert get_meta_refresh(r3) == (None, None)
def test_get_base_url(self):
resp = HtmlResponse(
"http://www.example.com",
body=b"""
<html>
<head><base href="http://www.example.com/img/" target="_blank"></head>
<body>blahablsdfsal&</body>
</html>""",
)
assert get_base_url(resp) == "http://www.example.com/img/"
resp2 = HtmlResponse(
"http://www.example.com",
body=b"""
<html><body>blahablsdfsal&</body></html>""",
)
assert get_base_url(resp2) == "http://www.example.com"
def test_response_status_message(self):
assert response_status_message(200) == "200 OK"
assert response_status_message(404) == "404 Not Found"
assert response_status_message(573) == "573 Unknown Status"
def test_inject_base_url(self):
url = "http://www.example.com"
def check_base_url(burl):
path = urlparse(burl).path
if not path or not Path(path).exists():
path = burl.replace("file://", "")
bbody = Path(path).read_bytes()
assert bbody.count(b'<base href="' + to_bytes(url) + b'">') == 1
return True
r1 = HtmlResponse(
url,
body=b"""
<html>
<head><title>Dummy</title></head>
<body><p>Hello world.</p></body>
</html>""",
)
r2 = HtmlResponse(
url,
body=b"""
<html>
<head id="foo"><title>Dummy</title></head>
<body>Hello world.</body>
</html>""",
)
r3 = HtmlResponse(
url,
body=b"""
<html>
<head><title>Dummy</title></head>
<body>
<header>Hello header</header>
<p>Hello world.</p>
</body>
</html>""",
)
r4 = HtmlResponse(
url,
body=b"""
<html>
<!-- <head>Dummy comment</head> -->
<head><title>Dummy</title></head>
<body><p>Hello world.</p></body>
</html>""",
)
r5 = HtmlResponse(
url,
body=b"""
<html>
<!--[if IE]>
<head><title>IE head</title></head>
<![endif]-->
<!--[if !IE]>-->
<head><title>Standard head</title></head>
<!--<![endif]-->
<body><p>Hello world.</p></body>
</html>""",
)
assert open_in_browser(r1, _openfunc=check_base_url), "Inject base url"
assert open_in_browser(r2, _openfunc=check_base_url), (
"Inject base url with argumented head"
)
assert open_in_browser(r3, _openfunc=check_base_url), (
"Inject unique base url with misleading tag"
)
assert open_in_browser(r4, _openfunc=check_base_url), (
"Inject unique base url with misleading comment"
)
assert open_in_browser(r5, _openfunc=check_base_url), (
"Inject unique base url with conditional comment"
)
def test_open_in_browser_redos_comment(self):
MAX_CPU_TIME = 0.02
# Exploit input from
# https://makenowjust-labs.github.io/recheck/playground/
# for /<!--.*?-->/ (old pattern to remove comments).
body = b"-><!--\x00" * 25_000 + b"->\n<!---->"
response = HtmlResponse("https://example.com", body=body)
start_time = process_time()
open_in_browser(response, lambda url: True)
end_time = process_time()
assert end_time - start_time < MAX_CPU_TIME
def test_open_in_browser_redos_head(self):
MAX_CPU_TIME = 0.02
# Exploit input from
# https://makenowjust-labs.github.io/recheck/playground/
# for /(<head(?:>|\s.*?>))/ (old pattern to find the head element).
body = b"<head\t" * 8_000
response = HtmlResponse("https://example.com", body=body)
start_time = process_time()
open_in_browser(response, lambda url: True)
end_time = process_time()
assert end_time - start_time < MAX_CPU_TIME
@pytest.mark.parametrize(
("input_body", "output_body"),
[
(
b"a<!--",
b"a",
),
(
b"a<!---->b",
b"ab",
),
(
b"a<!--b-->c",
b"ac",
),
(
b"a<!--b-->c<!--",
b"ac",
),
(
b"a<!--b-->c<!--d",
b"ac",
),
(
b"a<!--b-->c<!---->d",
b"acd",
),
(
b"a<!--b--><!--c-->d",
b"ad",
),
],
)
def test_remove_html_comments(input_body, output_body):
assert _remove_html_comments(input_body) == output_body, (
f"{_remove_html_comments(input_body)=} == {output_body=}"
)
|
