aboutsummaryrefslogtreecommitdiffstats
path: root/test/mitmproxy/test_contentview.py
blob: f113e2949e64e8154afdc289dddaa8ad08938210 (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
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
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
import mock
from mitmproxy.exceptions import ContentViewException
from netlib.http import Headers
from netlib.http import url
from mitmproxy.types import multidict

import mitmproxy.contentviews as cv
from . import tutils
import netlib.tutils

try:
    import pyamf
except ImportError:
    pyamf = None

try:
    import cssutils
except:
    cssutils = None


class TestContentView:

    def test_view_auto(self):
        v = cv.ViewAuto()
        f = v(
            b"foo",
            headers=Headers()
        )
        assert f[0] == "Raw"

        f = v(
            b"<html></html>",
            headers=Headers(content_type="text/html")
        )
        assert f[0] == "HTML"

        f = v(
            b"foo",
            headers=Headers(content_type="text/flibble")
        )
        assert f[0] == "Raw"

        f = v(
            b"<xml></xml>",
            headers=Headers(content_type="text/flibble")
        )
        assert f[0].startswith("XML")

        f = v(
            b"",
            headers=Headers()
        )
        assert f[0] == "No content"

        f = v(
            b"",
            headers=Headers(),
            query=multidict.MultiDict([("foo", "bar")]),
        )
        assert f[0] == "Query"

    def test_view_urlencoded(self):
        d = url.encode([("one", "two"), ("three", "four")]).encode()
        v = cv.ViewURLEncoded()
        assert v(d)
        d = url.encode([("adsfa", "")]).encode()
        v = cv.ViewURLEncoded()
        assert v(d)

    def test_view_html(self):
        v = cv.ViewHTML()
        s = b"<html><br><br></br><p>one</p></html>"
        assert v(s)

        s = b"gobbledygook"
        assert not v(s)

    def test_view_html_outline(self):
        v = cv.ViewHTMLOutline()
        s = b"<html><br><br></br><p>one</p></html>"
        assert v(s)
        assert v(b'\xfe')

    def test_view_json(self):
        cv.VIEW_CUTOFF = 100
        v = cv.ViewJSON()
        assert v(b"{}")
        assert not v(b"{")
        assert v(b"[1, 2, 3, 4, 5]")

    def test_view_xml(self):
        v = cv.ViewXML()
        assert v(b"<foo></foo>")
        assert not v(b"<foo>")
        s = b"""<?xml version="1.0" encoding="UTF-8"?>
            <?xml-stylesheet title="XSL_formatting"?>
            <rss
                xmlns:media="http://search.yahoo.com/mrss/"
                xmlns:atom="http://www.w3.org/2005/Atom"
                version="2.0">
            </rss>
        """
        assert v(s)

    def test_view_raw(self):
        v = cv.ViewRaw()
        assert v(b"foo")

    def test_view_javascript(self):
        v = cv.ViewJavaScript()
        assert v(b"[1, 2, 3]")
        assert v(b"[1, 2, 3")
        assert v(b"function(a){[1, 2, 3]}")
        assert v(b"\xfe")  # invalid utf-8

    def test_view_css(self):
        v = cv.ViewCSS()

        with open(tutils.test_data.path('data/1.css'), 'r') as fp:
            fixture_1 = fp.read()

        result = v('a')

        if cssutils:
            assert len(list(result[1])) == 0
        else:
            assert len(list(result[1])) == 1

        result = v(fixture_1)

        if cssutils:
            assert len(list(result[1])) > 1
        else:
            assert len(list(result[1])) == 1

    def test_view_hex(self):
        v = cv.ViewHex()
        assert v(b"foo")

    def test_view_image(self):
        v = cv.ViewImage()
        p = tutils.test_data.path("data/image.png")
        assert v(open(p, "rb").read())

        p = tutils.test_data.path("data/image.gif")
        assert v(open(p, "rb").read())

        p = tutils.test_data.path("data/image-err1.jpg")
        assert v(open(p, "rb").read())

        p = tutils.test_data.path("data/image.ico")
        assert v(open(p, "rb").read())

        assert not v(b"flibble")

    def test_view_multipart(self):
        view = cv.ViewMultipart()
        v = b"""
--AaB03x
Content-Disposition: form-data; name="submit-name"

Larry
--AaB03x
        """.strip()
        h = Headers(content_type="multipart/form-data; boundary=AaB03x")
        assert view(v, headers=h)

        h = Headers()
        assert not view(v, headers=h)

        h = Headers(content_type="multipart/form-data")
        assert not view(v, headers=h)

        h = Headers(content_type="unparseable")
        assert not view(v, headers=h)

    def test_view_query(self):
        d = ""
        v = cv.ViewQuery()
        f = v(d, query=multidict.MultiDict([("foo", "bar")]))
        assert f[0] == "Query"
        assert [x for x in f[1]] == [[("header", "foo: "), ("text", "bar")]]

    def test_add_cv(self):
        class TestContentView(cv.View):
            name = "test"
            prompt = ("t", "test")

        tcv = TestContentView()
        cv.add(tcv)

        # repeated addition causes exception
        tutils.raises(
            ContentViewException,
            cv.add,
            tcv
        )


def test_get_content_view():
    desc, lines, err = cv.get_content_view(
        cv.get("Raw"),
        b"[1, 2, 3]",
    )
    assert "Raw" in desc
    assert list(lines)
    assert not err

    desc, lines, err = cv.get_content_view(
        cv.get("Auto"),
        b"[1, 2, 3]",
        headers=Headers(content_type="application/json")
    )
    assert desc == "JSON"

    desc, lines, err = cv.get_content_view(
        cv.get("JSON"),
        b"[1, 2",
    )
    assert "Couldn't parse" in desc

    with mock.patch("mitmproxy.contentviews.ViewAuto.__call__") as view_auto:
        view_auto.side_effect = ValueError

        desc, lines, err = cv.get_content_view(
            cv.get("Auto"),
            b"[1, 2",
        )
        assert err
        assert "Couldn't parse" in desc


def test_get_message_content_view():
    r = netlib.tutils.treq()
    desc, lines, err = cv.get_message_content_view(cv.get("Raw"), r)
    assert desc == "Raw"

    r.encode("gzip")
    desc, lines, err = cv.get_message_content_view(cv.get("Raw"), r)
    assert desc == "[decoded gzip] Raw"

    r.headers["content-encoding"] = "deflate"
    desc, lines, err = cv.get_message_content_view(cv.get("Raw"), r)
    assert desc == "[cannot decode] Raw"

    r.content = None
    desc, lines, err = cv.get_message_content_view(cv.get("Raw"), r)
    assert list(lines) == [[("error", "content missing")]]


if pyamf:
    def test_view_amf_request():
        v = cv.ViewAMF()

        p = tutils.test_data.path("data/amf01")
        assert v(open(p, "rb").read())

        p = tutils.test_data.path("data/amf02")
        assert v(open(p, "rb").read())

    def test_view_amf_response():
        v = cv.ViewAMF()
        p = tutils.test_data.path("data/amf03")
        assert v(open(p, "rb").read())

if cv.ViewProtobuf.is_available():
    def test_view_protobuf_request():
        v = cv.ViewProtobuf()

        p = tutils.test_data.path("data/protobuf01")
        content_type, output = v(open(p, "rb").read())
        assert content_type == "Protobuf"
        assert output.next()[0][1] == '1: "3bbc333c-e61c-433b-819a-0b9a8cc103b8"'


def test_get_by_shortcut():
    assert cv.get_by_shortcut("h")


def test_pretty_json():
    assert cv.pretty_json(b'{"foo": 1}')
    assert not cv.pretty_json(b"moo")
    assert cv.pretty_json(b'{"foo" : "\xe4\xb8\x96\xe7\x95\x8c"}')  # utf8 with chinese characters
    assert not cv.pretty_json(b'{"foo" : "\xFF"}')