summaryrefslogtreecommitdiffstats
path: root/Lib/test/test_urllibnet.py
blob: 6c2632c55a0fb7f176c8346952ab45214669c2c9 (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
#!/usr/bin/env python

import unittest
from test import support

import socket
import urllib
import sys
import os
import mimetools


def _open_with_retry(func, host, *args, **kwargs):
    # Connecting to remote hosts is flaky.  Make it more robust
    # by retrying the connection several times.
    last_exc = None
    for i in range(3):
        try:
            return func(host, *args, **kwargs)
        except IOError as err:
            last_exc = err
            continue
        except:
            raise
    raise last_exc


class URLTimeoutTest(unittest.TestCase):

    TIMEOUT = 10.0

    def setUp(self):
        socket.setdefaulttimeout(self.TIMEOUT)

    def tearDown(self):
        socket.setdefaulttimeout(None)

    def testURLread(self):
        f = _open_with_retry(urllib.urlopen, "http://www.python.org/")
        x = f.read()

class urlopenNetworkTests(unittest.TestCase):
    """Tests urllib.urlopen using the network.

    These tests are not exhaustive.  Assuming that testing using files does a
    good job overall of some of the basic interface features.  There are no
    tests exercising the optional 'data' and 'proxies' arguments.  No tests
    for transparent redirection have been written.

    setUp is not used for always constructing a connection to
    http://www.python.org/ since there a few tests that don't use that address
    and making a connection is expensive enough to warrant minimizing unneeded
    connections.

    """

    def urlopen(self, *args):
        return _open_with_retry(urllib.urlopen, *args)

    def test_basic(self):
        # Simple test expected to pass.
        open_url = self.urlopen("http://www.python.org/")
        for attr in ("read", "readline", "readlines", "fileno", "close",
                     "info", "geturl"):
            self.assert_(hasattr(open_url, attr), "object returned from "
                            "urlopen lacks the %s attribute" % attr)
        try:
            self.assert_(open_url.read(), "calling 'read' failed")
        finally:
            open_url.close()

    def test_readlines(self):
        # Test both readline and readlines.
        open_url = self.urlopen("http://www.python.org/")
        try:
            self.assert_(isinstance(open_url.readline(), bytes),
                         "readline did not return bytes")
            self.assert_(isinstance(open_url.readlines(), list),
                         "readlines did not return a list")
        finally:
            open_url.close()

    def test_info(self):
        # Test 'info'.
        open_url = self.urlopen("http://www.python.org/")
        try:
            info_obj = open_url.info()
        finally:
            open_url.close()
            self.assert_(isinstance(info_obj, mimetools.Message),
                         "object returned by 'info' is not an instance of "
                         "mimetools.Message")
            self.assertEqual(info_obj.getsubtype(), "html")

    def test_geturl(self):
        # Make sure same URL as opened is returned by geturl.
        URL = "http://www.python.org/"
        open_url = self.urlopen(URL)
        try:
            gotten_url = open_url.geturl()
        finally:
            open_url.close()
        self.assertEqual(gotten_url, URL)

    def test_getcode(self):
        # test getcode() with the fancy opener to get 404 error codes
        URL = "http://www.python.org/XXXinvalidXXX"
        open_url = urllib.FancyURLopener().open(URL)
        try:
            code = open_url.getcode()
        finally:
            open_url.close()
        self.assertEqual(code, 404)

    def test_fileno(self):
        if (sys.platform in ('win32',) or
                not hasattr(os, 'fdopen')):
            # On Windows, socket handles are not file descriptors; this
            # test can't pass on Windows.
            return
        # Make sure fd returned by fileno is valid.
        open_url = self.urlopen("http://www.python.org/")
        fd = open_url.fileno()
        # XXX(nnorwitz): There is currently no way to pass errors, encoding,
        # etc to fdopen. :-(
        FILE = os.fdopen(fd)
        FILE._errors = 'ignore'
        try:
            self.assert_(FILE.read(), "reading from file created using fd "
                                      "returned by fileno failed")
        finally:
            FILE.close()

    def test_bad_address(self):
        # Make sure proper exception is raised when connecting to a bogus
        # address.
        self.assertRaises(IOError,
                          # SF patch 809915:  In Sep 2003, VeriSign started
                          # highjacking invalid .com and .net addresses to
                          # boost traffic to their own site.  This test
                          # started failing then.  One hopes the .invalid
                          # domain will be spared to serve its defined
                          # purpose.
                          # urllib.urlopen, "http://www.sadflkjsasadf.com/")
                          urllib.urlopen, "http://www.python.invalid./")

class urlretrieveNetworkTests(unittest.TestCase):
    """Tests urllib.urlretrieve using the network."""

    def urlretrieve(self, *args):
        return _open_with_retry(urllib.urlretrieve, *args)

    def test_basic(self):
        # Test basic functionality.
        file_location,info = self.urlretrieve("http://www.python.org/")
        self.assert_(os.path.exists(file_location), "file location returned by"
                        " urlretrieve is not a valid path")
        FILE = open(file_location, errors='ignore')
        try:
            self.assert_(FILE.read(), "reading from the file location returned"
                         " by urlretrieve failed")
        finally:
            FILE.close()
            os.unlink(file_location)

    def test_specified_path(self):
        # Make sure that specifying the location of the file to write to works.
        file_location,info = self.urlretrieve("http://www.python.org/",
                                              support.TESTFN)
        self.assertEqual(file_location, support.TESTFN)
        self.assert_(os.path.exists(file_location))
        FILE = open(file_location, errors='ignore')
        try:
            self.assert_(FILE.read(), "reading from temporary file failed")
        finally:
            FILE.close()
            os.unlink(file_location)

    def test_header(self):
        # Make sure header returned as 2nd value from urlretrieve is good.
        file_location, header = self.urlretrieve("http://www.python.org/")
        os.unlink(file_location)
        self.assert_(isinstance(header, mimetools.Message),
                     "header is not an instance of mimetools.Message")



def test_main():
    support.requires('network')
    support.run_unittest(URLTimeoutTest,
                              urlopenNetworkTests,
                              urlretrieveNetworkTests)

if __name__ == "__main__":
    test_main()