Repository navigation
Expand file tree
/
Copy pathtest_urllib.py
More file actions
1831 lines (1592 loc) · 76.6 KB
/
Copy pathtest_urllib.py
File metadata and controls
1831 lines (1592 loc) · 76.6 KB
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
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
"""Regression tests for what was in Python 2's "urllib" module"""
import urllib.parse
import urllib.request
import urllib.error
import http.client
import nturl2path
import email.message
import io
import unittest
from unittest.mock import patch
from test import support
from test.support import os_helper
from test.support import socket_helper
from test.support import warnings_helper
from test.support import control_characters_c0
from test.support.testcase import ExtraAssertions
import os
try:
import ssl
except ImportError:
ssl = None
import sys
import tempfile
from base64 import b64encode
import collections
if not socket_helper.has_gethostname:
raise unittest.SkipTest("test requires gethostname()")
def hexescape(char):
"""Escape char as RFC 2396 specifies"""
hex_repr = hex(ord(char))[2:].upper()
if len(hex_repr) == 1:
hex_repr = "0%s" % hex_repr
return "%" + hex_repr
# Shortcut for testing FancyURLopener
_urlopener = None
def urlopen(url, data=None, proxies=None):
"""urlopen(url [, data]) -> open file-like object"""
global _urlopener
if proxies is not None:
opener = urllib.request.FancyURLopener(proxies=proxies)
elif not _urlopener:
opener = FancyURLopener()
_urlopener = opener
else:
opener = _urlopener
if data is None:
return opener.open(url)
else:
return opener.open(url, data)
def FancyURLopener():
with warnings_helper.check_warnings(
('FancyURLopener style of invoking requests is deprecated.',
DeprecationWarning)):
return urllib.request.FancyURLopener()
def fakehttp(fakedata, mock_close=False):
class FakeSocket(io.BytesIO):
io_refs = 1
def sendall(self, data):
FakeHTTPConnection.buf = data
def makefile(self, *args, **kwds):
self.io_refs += 1
return self
def read(self, amt=None):
if self.closed:
return b""
return io.BytesIO.read(self, amt)
def readline(self, length=None):
if self.closed:
return b""
return io.BytesIO.readline(self, length)
def close(self):
self.io_refs -= 1
if self.io_refs == 0:
io.BytesIO.close(self)
class FakeHTTPConnection(http.client.HTTPConnection):
# buffer to store data for verification in urlopen tests.
buf = None
def connect(self):
self.sock = FakeSocket(self.fakedata)
type(self).fakesock = self.sock
if mock_close:
# bpo-36918: HTTPConnection destructor calls close() which calls
# flush(). Problem: flush() calls self.fp.flush() which raises
# "ValueError: I/O operation on closed file" which is logged as an
# "Exception ignored in". Override close() to silence this error.
def close(self):
pass
FakeHTTPConnection.fakedata = fakedata
return FakeHTTPConnection
class FakeHTTPMixin(object):
def fakehttp(self, fakedata, mock_close=False):
fake_http_class = fakehttp(fakedata, mock_close=mock_close)
self._connection_class = http.client.HTTPConnection
http.client.HTTPConnection = fake_http_class
def unfakehttp(self):
http.client.HTTPConnection = self._connection_class
class FakeFTPMixin(object):
def fakeftp(self):
class FakeFtpWrapper(object):
def __init__(self, user, passwd, host, port, dirs, timeout=None,
persistent=True):
pass
def retrfile(self, file, type):
return io.BytesIO(), 0
def close(self):
pass
self._ftpwrapper_class = urllib.request.ftpwrapper
urllib.request.ftpwrapper = FakeFtpWrapper
def unfakeftp(self):
urllib.request.ftpwrapper = self._ftpwrapper_class
class urlopen_FileTests(unittest.TestCase, ExtraAssertions):
"""Test urlopen() opening a temporary file.
Try to test as much functionality as possible so as to cut down on reliance
on connecting to the Net for testing.
"""
def setUp(self):
# Create a temp file to use for testing
self.text = bytes("test_urllib: %s\n" % self.__class__.__name__,
"ascii")
f = open(os_helper.TESTFN, 'wb')
try:
f.write(self.text)
finally:
f.close()
self.pathname = os_helper.TESTFN
self.quoted_pathname = urllib.parse.quote(os.fsencode(self.pathname))
self.returned_obj = urlopen("file:%s" % self.quoted_pathname)
def tearDown(self):
"""Shut down the open object"""
self.returned_obj.close()
os.remove(os_helper.TESTFN)
def test_interface(self):
# Make sure object returned by urlopen() has the specified methods
for attr in ("read", "readline", "readlines", "fileno",
"close", "info", "geturl", "getcode", "__iter__"):
self.assertHasAttr(self.returned_obj, attr)
def test_read(self):
self.assertEqual(self.text, self.returned_obj.read())
def test_readline(self):
self.assertEqual(self.text, self.returned_obj.readline())
self.assertEqual(b'', self.returned_obj.readline(),
"calling readline() after exhausting the file did not"
" return an empty string")
def test_readlines(self):
lines_list = self.returned_obj.readlines()
self.assertEqual(len(lines_list), 1,
"readlines() returned the wrong number of lines")
self.assertEqual(lines_list[0], self.text,
"readlines() returned improper text")
def test_fileno(self):
file_num = self.returned_obj.fileno()
self.assertIsInstance(file_num, int, "fileno() did not return an int")
self.assertEqual(os.read(file_num, len(self.text)), self.text,
"Reading on the file descriptor returned by fileno() "
"did not return the expected text")
def test_close(self):
# Test close() by calling it here and then having it be called again
# by the tearDown() method for the test
self.returned_obj.close()
def test_headers(self):
self.assertIsInstance(self.returned_obj.headers, email.message.Message)
def test_url(self):
self.assertEqual(self.returned_obj.url, self.quoted_pathname)
def test_status(self):
self.assertIsNone(self.returned_obj.status)
def test_info(self):
self.assertIsInstance(self.returned_obj.info(), email.message.Message)
def test_geturl(self):
self.assertEqual(self.returned_obj.geturl(), self.quoted_pathname)
def test_getcode(self):
self.assertIsNone(self.returned_obj.getcode())
def test_iter(self):
# Test iterator
# Don't need to count number of iterations since test would fail the
# instant it returned anything beyond the first line from the
# comparison.
# Use the iterator in the usual implicit way to test for ticket #4608.
for line in self.returned_obj:
self.assertEqual(line, self.text)
def test_relativelocalfile(self):
self.assertRaises(ValueError,urllib.request.urlopen,'./' + self.pathname)
class ProxyTests(unittest.TestCase):
def setUp(self):
# Records changes to env vars
self.env = self.enterContext(os_helper.EnvironmentVarGuard())
# Delete all proxy related env vars
for k in list(os.environ):
if 'proxy' in k.lower():
self.env.unset(k)
def test_getproxies_environment_keep_no_proxies(self):
self.env.set('NO_PROXY', 'localhost')
proxies = urllib.request.getproxies_environment()
# getproxies_environment use lowered case truncated (no '_proxy') keys
self.assertEqual('localhost', proxies['no'])
# List of no_proxies with space.
self.env.set('NO_PROXY', 'localhost, anotherdomain.com, newdomain.com:1234')
self.assertTrue(urllib.request.proxy_bypass_environment('anotherdomain.com'))
self.assertTrue(urllib.request.proxy_bypass_environment('anotherdomain.com:8888'))
self.assertTrue(urllib.request.proxy_bypass_environment('newdomain.com:1234'))
def test_proxy_cgi_ignore(self):
try:
self.env.set('HTTP_PROXY', 'http://somewhere:3128')
proxies = urllib.request.getproxies_environment()
self.assertEqual('http://somewhere:3128', proxies['http'])
self.env.set('REQUEST_METHOD', 'GET')
proxies = urllib.request.getproxies_environment()
self.assertNotIn('http', proxies)
finally:
self.env.unset('REQUEST_METHOD')
self.env.unset('HTTP_PROXY')
def test_proxy_bypass_environment_host_match(self):
bypass = urllib.request.proxy_bypass_environment
self.env.set('NO_PROXY',
'localhost, anotherdomain.com, newdomain.com:1234, .d.o.t')
self.assertTrue(bypass('localhost'))
self.assertTrue(bypass('LocalHost')) # MixedCase
self.assertTrue(bypass('LOCALHOST')) # UPPERCASE
self.assertTrue(bypass('.localhost'))
self.assertTrue(bypass('newdomain.com:1234'))
self.assertTrue(bypass('.newdomain.com:1234'))
self.assertTrue(bypass('foo.d.o.t')) # issue 29142
self.assertTrue(bypass('d.o.t'))
self.assertTrue(bypass('anotherdomain.com:8888'))
self.assertTrue(bypass('.anotherdomain.com:8888'))
self.assertTrue(bypass('www.newdomain.com:1234'))
self.assertFalse(bypass('prelocalhost'))
self.assertFalse(bypass('newdomain.com')) # no port
self.assertFalse(bypass('newdomain.com:1235')) # wrong port
def test_proxy_bypass_environment_always_match(self):
bypass = urllib.request.proxy_bypass_environment
self.env.set('NO_PROXY', '*')
self.assertTrue(bypass('newdomain.com'))
self.assertTrue(bypass('newdomain.com:1234'))
self.env.set('NO_PROXY', '*, anotherdomain.com')
self.assertTrue(bypass('anotherdomain.com'))
self.assertFalse(bypass('newdomain.com'))
self.assertFalse(bypass('newdomain.com:1234'))
def test_proxy_bypass_environment_newline(self):
bypass = urllib.request.proxy_bypass_environment
self.env.set('NO_PROXY',
'localhost, anotherdomain.com, newdomain.com:1234')
self.assertFalse(bypass('localhost\n'))
self.assertFalse(bypass('anotherdomain.com:8888\n'))
self.assertFalse(bypass('newdomain.com:1234\n'))
class ProxyTests_withOrderedEnv(unittest.TestCase):
def setUp(self):
# We need to test conditions, where variable order _is_ significant
self._saved_env = os.environ
# Monkey patch os.environ, start with empty fake environment
os.environ = collections.OrderedDict()
def tearDown(self):
os.environ = self._saved_env
def test_getproxies_environment_prefer_lowercase(self):
# Test lowercase preference with removal
os.environ['no_proxy'] = ''
os.environ['No_Proxy'] = 'localhost'
self.assertFalse(urllib.request.proxy_bypass_environment('localhost'))
self.assertFalse(urllib.request.proxy_bypass_environment('arbitrary'))
os.environ['http_proxy'] = ''
os.environ['HTTP_PROXY'] = 'http://somewhere:3128'
proxies = urllib.request.getproxies_environment()
self.assertEqual({}, proxies)
# Test lowercase preference of proxy bypass and correct matching including ports
os.environ['no_proxy'] = 'localhost, noproxy.com, my.proxy:1234'
os.environ['No_Proxy'] = 'xyz.com'
self.assertTrue(urllib.request.proxy_bypass_environment('localhost'))
self.assertTrue(urllib.request.proxy_bypass_environment('noproxy.com:5678'))
self.assertTrue(urllib.request.proxy_bypass_environment('my.proxy:1234'))
self.assertFalse(urllib.request.proxy_bypass_environment('my.proxy'))
self.assertFalse(urllib.request.proxy_bypass_environment('arbitrary'))
# Test lowercase preference with replacement
os.environ['http_proxy'] = 'http://somewhere:3128'
os.environ['Http_Proxy'] = 'http://somewhereelse:3128'
proxies = urllib.request.getproxies_environment()
self.assertEqual('http://somewhere:3128', proxies['http'])
class urlopen_HttpTests(unittest.TestCase, FakeHTTPMixin, FakeFTPMixin):
"""Test urlopen() opening a fake http connection."""
def check_read(self, ver):
self.fakehttp(b"HTTP/" + ver + b" 200 OK\r\n\r\nHello!")
try:
fp = urlopen("http://python.org/")
self.assertEqual(fp.readline(), b"Hello!")
self.assertEqual(fp.readline(), b"")
self.assertEqual(fp.geturl(), 'http://python.org/')
self.assertEqual(fp.getcode(), 200)
finally:
self.unfakehttp()
def test_url_fragment(self):
# Issue #11703: geturl() omits fragments in the original URL.
url = 'http://docs.python.org/library/urllib.html#OK'
self.fakehttp(b"HTTP/1.1 200 OK\r\n\r\nHello!")
try:
fp = urllib.request.urlopen(url)
self.assertEqual(fp.geturl(), url)
finally:
self.unfakehttp()
def test_willclose(self):
self.fakehttp(b"HTTP/1.1 200 OK\r\n\r\nHello!")
try:
resp = urlopen("http://www.python.org")
self.assertTrue(resp.fp.will_close)
finally:
self.unfakehttp()
@unittest.skipUnless(ssl, "ssl module required")
def test_url_path_with_control_char_rejected(self):
for char_no in list(range(0, 0x21)) + [0x7f]:
char = chr(char_no)
schemeless_url = f"//localhost:7777/test{char}/"
self.fakehttp(b"HTTP/1.1 200 OK\r\n\r\nHello.")
try:
# We explicitly test urllib.request.urlopen() instead of the top
# level 'def urlopen()' function defined in this... (quite ugly)
# test suite. They use different url opening codepaths. Plain
# urlopen uses FancyURLOpener which goes via a codepath that
# calls urllib.parse.quote() on the URL which makes all of the
# above attempts at injection within the url _path_ safe.
escaped_char_repr = repr(char).replace('\\', r'\\')
InvalidURL = http.client.InvalidURL
with self.assertRaisesRegex(
InvalidURL, f"contain control.*{escaped_char_repr}"):
urllib.request.urlopen(f"http:{schemeless_url}")
with self.assertRaisesRegex(
InvalidURL, f"contain control.*{escaped_char_repr}"):
urllib.request.urlopen(f"https:{schemeless_url}")
# This code path quotes the URL so there is no injection.
resp = urlopen(f"http:{schemeless_url}")
self.assertNotIn(char, resp.geturl())
finally:
self.unfakehttp()
@unittest.skipUnless(ssl, "ssl module required")
def test_url_path_with_newline_header_injection_rejected(self):
self.fakehttp(b"HTTP/1.1 200 OK\r\n\r\nHello.")
host = "localhost:7777?a=1 HTTP/1.1\r\nX-injected: header\r\nTEST: 123"
schemeless_url = "//" + host + ":8080/test/?test=a"
try:
# We explicitly test urllib.request.urlopen() instead of the top
# level 'def urlopen()' function defined in this... (quite ugly)
# test suite. They use different url opening codepaths. Plain
# urlopen uses FancyURLOpener which goes via a codepath that
# calls urllib.parse.quote() on the URL which makes all of the
# above attempts at injection within the url _path_ safe.
InvalidURL = http.client.InvalidURL
with self.assertRaisesRegex(
InvalidURL, r"contain control.*\\r.*(found at least . .)"):
urllib.request.urlopen(f"http:{schemeless_url}")
with self.assertRaisesRegex(InvalidURL, r"contain control.*\\n"):
urllib.request.urlopen(f"https:{schemeless_url}")
# This code path quotes the URL so there is no injection.
resp = urlopen(f"http:{schemeless_url}")
self.assertNotIn(' ', resp.geturl())
self.assertNotIn('\r', resp.geturl())
self.assertNotIn('\n', resp.geturl())
finally:
self.unfakehttp()
@unittest.skipUnless(ssl, "ssl module required")
def test_url_host_with_control_char_rejected(self):
for char_no in list(range(0, 0x21)) + [0x7f]:
char = chr(char_no)
schemeless_url = f"//localhost{char}/test/"
self.fakehttp(b"HTTP/1.1 200 OK\r\n\r\nHello.")
try:
escaped_char_repr = repr(char).replace('\\', r'\\')
InvalidURL = http.client.InvalidURL
with self.assertRaisesRegex(
InvalidURL, f"contain control.*{escaped_char_repr}"):
urlopen(f"http:{schemeless_url}")
with self.assertRaisesRegex(InvalidURL, f"contain control.*{escaped_char_repr}"):
urlopen(f"https:{schemeless_url}")
finally:
self.unfakehttp()
@unittest.skipUnless(ssl, "ssl module required")
def test_url_host_with_newline_header_injection_rejected(self):
self.fakehttp(b"HTTP/1.1 200 OK\r\n\r\nHello.")
host = "localhost\r\nX-injected: header\r\n"
schemeless_url = "//" + host + ":8080/test/?test=a"
try:
InvalidURL = http.client.InvalidURL
with self.assertRaisesRegex(
InvalidURL, r"contain control.*\\r"):
urlopen(f"http:{schemeless_url}")
with self.assertRaisesRegex(InvalidURL, r"contain control.*\\n"):
urlopen(f"https:{schemeless_url}")
finally:
self.unfakehttp()
def test_read_0_9(self):
# "0.9" response accepted (but not "simple responses" without
# a status line)
self.check_read(b"0.9")
def test_read_1_0(self):
self.check_read(b"1.0")
def test_read_1_1(self):
self.check_read(b"1.1")
def test_read_bogus(self):
# urlopen() should raise OSError for many error codes.
self.fakehttp(b'''HTTP/1.1 401 Authentication Required
Date: Wed, 02 Jan 2008 03:03:54 GMT
Server: Apache/1.3.33 (Debian GNU/Linux) mod_ssl/2.8.22 OpenSSL/0.9.7e
Connection: close
Content-Type: text/html; charset=iso-8859-1
''', mock_close=True)
try:
with self.assertRaises(urllib.error.HTTPError) as cm:
urllib.request.urlopen("http://python.org/")
cm.exception.close()
finally:
self.unfakehttp()
def test_invalid_redirect(self):
# urlopen() should raise OSError for many error codes.
self.fakehttp(b'''HTTP/1.1 302 Found
Date: Wed, 02 Jan 2008 03:03:54 GMT
Server: Apache/1.3.33 (Debian GNU/Linux) mod_ssl/2.8.22 OpenSSL/0.9.7e
Location: file://guidocomputer.athome.com:/python/license
Connection: close
Content-Type: text/html; charset=iso-8859-1
''', mock_close=True)
try:
msg = "Redirection to url 'file:"
with self.assertRaisesRegex(urllib.error.HTTPError, msg) as cm:
urllib.request.urlopen("http://python.org/")
cm.exception.close()
finally:
self.unfakehttp()
def test_redirect_limit_independent(self):
# Ticket #12923: make sure independent requests each use their
# own retry limit.
for i in range(FancyURLopener().maxtries):
self.fakehttp(b'''HTTP/1.1 302 Found
Location: file://guidocomputer.athome.com:/python/license
Connection: close
''', mock_close=True)
try:
with self.assertRaises(urllib.error.HTTPError) as cm:
urllib.request.urlopen("http://something")
cm.exception.close()
finally:
self.unfakehttp()
def test_http_error_attribute_values(self):
hdrs = {
"Authorization": "Bearer foobar",
"Accept": "application/json"
}
err = urllib.error.HTTPError("http://something", 404, "foo", hdrs, None)
self.assertEqual(err.filename, "http://something")
self.assertEqual(err.code, 404)
self.assertEqual(err.msg, "foo")
self.assertEqual(err.reason, "foo")
self.assertEqual(err.hdrs, hdrs)
self.assertEqual(err.headers, hdrs)
err.close()
def test_http_error_default_fp(self):
err = urllib.error.HTTPError("http://something", 404, "foo", {}, None)
self.assertIsInstance(err.fp, io.BytesIO)
err.close()
def test_empty_socket(self):
# urlopen() raises OSError if the underlying socket does not send any
# data. (#1680230)
self.fakehttp(b'')
try:
self.assertRaises(OSError, urlopen, "http://something")
finally:
self.unfakehttp()
def test_missing_localfile(self):
# Test for #10836
with self.assertRaises(urllib.error.URLError) as e:
urlopen('file://localhost/a/file/which/doesnot/exists.py')
self.assertTrue(e.exception.filename)
self.assertTrue(e.exception.reason)
def test_file_notexists(self):
fd, tmp_file = tempfile.mkstemp()
tmp_fileurl = 'file://localhost/' + tmp_file.replace(os.path.sep, '/')
try:
self.assertTrue(os.path.exists(tmp_file))
with urlopen(tmp_fileurl) as fobj:
self.assertTrue(fobj)
finally:
os.close(fd)
os.unlink(tmp_file)
self.assertFalse(os.path.exists(tmp_file))
with self.assertRaises(urllib.error.URLError):
urlopen(tmp_fileurl)
def test_ftp_nohost(self):
test_ftp_url = 'ftp:///path'
with self.assertRaises(urllib.error.URLError) as e:
urlopen(test_ftp_url)
self.assertFalse(e.exception.filename)
self.assertTrue(e.exception.reason)
def test_ftp_nonexisting(self):
with self.assertRaises(urllib.error.URLError) as e:
urlopen('ftp://localhost/a/file/which/doesnot/exists.py')
self.assertFalse(e.exception.filename)
self.assertTrue(e.exception.reason)
@patch.object(urllib.request, 'MAXFTPCACHE', 0)
def test_ftp_cache_pruning(self):
self.fakeftp()
try:
urllib.request.ftpcache['test'] = urllib.request.ftpwrapper('user', 'pass', 'localhost', 21, [])
urlopen('ftp://localhost')
finally:
self.unfakeftp()
def test_url_error_stringified(self):
reason = 'sixseven'
err = urllib.error.URLError(reason)
self.assertEqual(str(err), f'<urlopen error {reason}>')
def test_userpass_inurl(self):
self.fakehttp(b"HTTP/1.0 200 OK\r\n\r\nHello!")
try:
fp = urlopen("http://user:pass@python.org/")
self.assertEqual(fp.readline(), b"Hello!")
self.assertEqual(fp.readline(), b"")
self.assertEqual(fp.geturl(), 'http://user:pass@python.org/')
self.assertEqual(fp.getcode(), 200)
finally:
self.unfakehttp()
def test_userpass_inurl_w_spaces(self):
self.fakehttp(b"HTTP/1.0 200 OK\r\n\r\nHello!")
try:
userpass = "a b:c d"
url = "http://{}@python.org/".format(userpass)
fakehttp_wrapper = http.client.HTTPConnection
authorization = ("Authorization: Basic %s\r\n" %
b64encode(userpass.encode("ASCII")).decode("ASCII"))
fp = urlopen(url)
# The authorization header must be in place
self.assertIn(authorization, fakehttp_wrapper.buf.decode("UTF-8"))
self.assertEqual(fp.readline(), b"Hello!")
self.assertEqual(fp.readline(), b"")
# the spaces are quoted in URL so no match
self.assertNotEqual(fp.geturl(), url)
self.assertEqual(fp.getcode(), 200)
finally:
self.unfakehttp()
def test_URLopener_deprecation(self):
with warnings_helper.check_warnings(('',DeprecationWarning)):
urllib.request.URLopener()
class urlopen_DataTests(unittest.TestCase, ExtraAssertions):
"""Test urlopen() opening a data URL."""
def setUp(self):
# clear _opener global variable
self.addCleanup(urllib.request.urlcleanup)
# text containing URL special- and unicode-characters
self.text = "test data URLs :;,%=& \u00f6 \u00c4 "
# 2x1 pixel RGB PNG image with one black and one white pixel
self.image = (
b'\x89PNG\r\n\x1a\n\x00\x00\x00\rIHDR\x00\x00\x00\x02\x00\x00\x00'
b'\x01\x08\x02\x00\x00\x00{@\xe8\xdd\x00\x00\x00\x01sRGB\x00\xae'
b'\xce\x1c\xe9\x00\x00\x00\x0fIDAT\x08\xd7c```\xf8\xff\xff?\x00'
b'\x06\x01\x02\xfe\no/\x1e\x00\x00\x00\x00IEND\xaeB`\x82')
self.text_url = (
"data:text/plain;charset=UTF-8,test%20data%20URLs%20%3A%3B%2C%25%3"
"D%26%20%C3%B6%20%C3%84%20")
self.text_url_base64 = (
"data:text/plain;charset=ISO-8859-1;base64,dGVzdCBkYXRhIFVSTHMgOjs"
"sJT0mIPYgxCA%3D")
# base64 encoded data URL that contains ignorable spaces,
# such as "\n", " ", "%0A", and "%20".
self.image_url = (
"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAIAAAABCAIAAAB7\n"
"QOjdAAAAAXNSR0IArs4c6QAAAA9JREFUCNdj%0AYGBg%2BP//PwAGAQL%2BCm8 "
"vHgAAAABJRU5ErkJggg%3D%3D%0A%20")
self.text_url_resp = self.enterContext(
urllib.request.urlopen(self.text_url))
self.text_url_base64_resp = self.enterContext(
urllib.request.urlopen(self.text_url_base64))
self.image_url_resp = self.enterContext(urllib.request.urlopen(self.image_url))
def test_interface(self):
# Make sure object returned by urlopen() has the specified methods
for attr in ("read", "readline", "readlines",
"close", "info", "geturl", "getcode", "__iter__"):
self.assertHasAttr(self.text_url_resp, attr)
def test_info(self):
self.assertIsInstance(self.text_url_resp.info(), email.message.Message)
self.assertEqual(self.text_url_base64_resp.info().get_params(),
[('text/plain', ''), ('charset', 'ISO-8859-1')])
self.assertEqual(self.image_url_resp.info()['content-length'],
str(len(self.image)))
r = urllib.request.urlopen("data:,")
self.assertEqual(r.info().get_params(),
[('text/plain', ''), ('charset', 'US-ASCII')])
r.close()
def test_geturl(self):
self.assertEqual(self.text_url_resp.geturl(), self.text_url)
self.assertEqual(self.text_url_base64_resp.geturl(),
self.text_url_base64)
self.assertEqual(self.image_url_resp.geturl(), self.image_url)
def test_read_text(self):
self.assertEqual(self.text_url_resp.read().decode(
dict(self.text_url_resp.info().get_params())['charset']), self.text)
def test_read_text_base64(self):
self.assertEqual(self.text_url_base64_resp.read().decode(
dict(self.text_url_base64_resp.info().get_params())['charset']),
self.text)
def test_read_image(self):
self.assertEqual(self.image_url_resp.read(), self.image)
def test_missing_comma(self):
self.assertRaises(ValueError,urllib.request.urlopen,'data:text/plain')
def test_invalid_base64_data(self):
# missing padding character
self.assertRaises(ValueError,urllib.request.urlopen,'data:;base64,Cg=')
def test_invalid_mediatype(self):
for c0 in control_characters_c0():
self.assertRaises(ValueError,urllib.request.urlopen,
f'data:text/html;{c0},data')
for c0 in control_characters_c0():
self.assertRaises(ValueError,urllib.request.urlopen,
f'data:text/html{c0};base64,ZGF0YQ==')
class urlretrieve_FileTests(unittest.TestCase):
"""Test urllib.urlretrieve() on local files"""
def setUp(self):
# clear _opener global variable
self.addCleanup(urllib.request.urlcleanup)
# Create a list of temporary files. Each item in the list is a file
# name (absolute path or relative to the current working directory).
# All files in this list will be deleted in the tearDown method. Note,
# this only helps to makes sure temporary files get deleted, but it
# does nothing about trying to close files that may still be open. It
# is the responsibility of the developer to properly close files even
# when exceptional conditions occur.
self.tempFiles = []
# Create a temporary file.
self.registerFileForCleanUp(os_helper.TESTFN)
self.text = b'testing urllib.urlretrieve'
try:
FILE = open(os_helper.TESTFN, 'wb')
FILE.write(self.text)
FILE.close()
finally:
try: FILE.close()
except: pass
def tearDown(self):
# Delete the temporary files.
for each in self.tempFiles:
try: os.remove(each)
except: pass
def constructLocalFileUrl(self, filePath):
filePath = os.path.abspath(filePath)
return "file://%s" % urllib.request.pathname2url(filePath)
def createNewTempFile(self, data=b""):
"""Creates a new temporary file containing the specified data,
registers the file for deletion during the test fixture tear down, and
returns the absolute path of the file."""
newFd, newFilePath = tempfile.mkstemp()
try:
self.registerFileForCleanUp(newFilePath)
newFile = os.fdopen(newFd, "wb")
newFile.write(data)
newFile.close()
finally:
try: newFile.close()
except: pass
return newFilePath
def registerFileForCleanUp(self, fileName):
self.tempFiles.append(fileName)
def test_basic(self):
# Make sure that a local file just gets its own location returned and
# a headers value is returned.
result = urllib.request.urlretrieve("file:%s" % os_helper.TESTFN)
self.assertEqual(result[0], os_helper.TESTFN)
self.assertIsInstance(result[1], email.message.Message,
"did not get an email.message.Message instance "
"as second returned value")
def test_copy(self):
# Test that setting the filename argument works.
second_temp = "%s.2" % os_helper.TESTFN
self.registerFileForCleanUp(second_temp)
result = urllib.request.urlretrieve(self.constructLocalFileUrl(
os_helper.TESTFN), second_temp)
self.assertEqual(second_temp, result[0])
self.assertTrue(os.path.exists(second_temp), "copy of the file was not "
"made")
FILE = open(second_temp, 'rb')
try:
text = FILE.read()
FILE.close()
finally:
try: FILE.close()
except: pass
self.assertEqual(self.text, text)
def test_reporthook(self):
# Make sure that the reporthook works.
def hooktester(block_count, block_read_size, file_size, count_holder=[0]):
self.assertIsInstance(block_count, int)
self.assertIsInstance(block_read_size, int)
self.assertIsInstance(file_size, int)
self.assertEqual(block_count, count_holder[0])
count_holder[0] = count_holder[0] + 1
second_temp = "%s.2" % os_helper.TESTFN
self.registerFileForCleanUp(second_temp)
urllib.request.urlretrieve(
self.constructLocalFileUrl(os_helper.TESTFN),
second_temp, hooktester)
def test_reporthook_0_bytes(self):
# Test on zero length file. Should call reporthook only 1 time.
report = []
def hooktester(block_count, block_read_size, file_size, _report=report):
_report.append((block_count, block_read_size, file_size))
srcFileName = self.createNewTempFile()
urllib.request.urlretrieve(self.constructLocalFileUrl(srcFileName),
os_helper.TESTFN, hooktester)
self.assertEqual(len(report), 1)
self.assertEqual(report[0][2], 0)
def test_reporthook_5_bytes(self):
# Test on 5 byte file. Should call reporthook only 2 times (once when
# the "network connection" is established and once when the block is
# read).
report = []
def hooktester(block_count, block_read_size, file_size, _report=report):
_report.append((block_count, block_read_size, file_size))
srcFileName = self.createNewTempFile(b"x" * 5)
urllib.request.urlretrieve(self.constructLocalFileUrl(srcFileName),
os_helper.TESTFN, hooktester)
self.assertEqual(len(report), 2)
self.assertEqual(report[0][2], 5)
self.assertEqual(report[1][2], 5)
def test_reporthook_8193_bytes(self):
# Test on 8193 byte file. Should call reporthook only 3 times (once
# when the "network connection" is established, once for the next 8192
# bytes, and once for the last byte).
report = []
def hooktester(block_count, block_read_size, file_size, _report=report):
_report.append((block_count, block_read_size, file_size))
srcFileName = self.createNewTempFile(b"x" * 8193)
urllib.request.urlretrieve(self.constructLocalFileUrl(srcFileName),
os_helper.TESTFN, hooktester)
self.assertEqual(len(report), 3)
self.assertEqual(report[0][2], 8193)
self.assertEqual(report[0][1], 8192)
self.assertEqual(report[1][1], 8192)
self.assertEqual(report[2][1], 8192)
class urlretrieve_HttpTests(unittest.TestCase, FakeHTTPMixin):
"""Test urllib.urlretrieve() using fake http connections"""
def test_short_content_raises_ContentTooShortError(self):
self.addCleanup(urllib.request.urlcleanup)
self.fakehttp(b'''HTTP/1.1 200 OK
Date: Wed, 02 Jan 2008 03:03:54 GMT
Server: Apache/1.3.33 (Debian GNU/Linux) mod_ssl/2.8.22 OpenSSL/0.9.7e
Connection: close
Content-Length: 100
Content-Type: text/html; charset=iso-8859-1
FF
''')
def _reporthook(par1, par2, par3):
pass
with self.assertRaises(urllib.error.ContentTooShortError):
try:
urllib.request.urlretrieve(support.TEST_HTTP_URL,
reporthook=_reporthook)
finally:
self.unfakehttp()
def test_short_content_raises_ContentTooShortError_without_reporthook(self):
self.addCleanup(urllib.request.urlcleanup)
self.fakehttp(b'''HTTP/1.1 200 OK
Date: Wed, 02 Jan 2008 03:03:54 GMT
Server: Apache/1.3.33 (Debian GNU/Linux) mod_ssl/2.8.22 OpenSSL/0.9.7e
Connection: close
Content-Length: 100
Content-Type: text/html; charset=iso-8859-1
FF
''')
with self.assertRaises(urllib.error.ContentTooShortError):
try:
urllib.request.urlretrieve(support.TEST_HTTP_URL)
finally:
self.unfakehttp()
class urlcleanup_Tests(unittest.TestCase, FakeHTTPMixin):
"""Test urllib.request.urlcleanup()"""
def setUp(self):
self.addCleanup(urllib.request.urlcleanup)
def urlretrieve(self):
self.fakehttp(b'HTTP/1.1 200 OK\r\n\r\ndata')
try:
filename, headers = urllib.request.urlretrieve(
support.TEST_HTTP_URL)
finally:
self.unfakehttp()
self.addCleanup(os_helper.unlink, filename)
return filename
def fake_urlopen(self, data):
self.fakehttp(b'HTTP/1.1 200 OK\r\n\r\n' + data)
try:
with urllib.request.urlopen(support.TEST_HTTP_URL) as fp:
return fp.read()
finally:
self.unfakehttp()
def test_temporary_files(self):
filename = self.urlretrieve()
self.assertTrue(os.path.exists(filename))
urllib.request.urlcleanup()
self.assertFalse(os.path.exists(filename))
# A file created after the cleanup is not deleted.
os_helper.create_empty_file(filename)
urllib.request.urlcleanup()
self.assertTrue(os.path.exists(filename))
def test_opener(self):
# The implicitly created opener supports http.
self.assertEqual(self.fake_urlopen(b'first'), b'first')
# An installed opener replaces it and supports only its handlers.
opener = urllib.request.OpenerDirector()
opener.add_handler(urllib.request.DataHandler())
opener.add_handler(urllib.request.UnknownHandler())
urllib.request.install_opener(opener)
with urllib.request.urlopen('data:,hello') as fp:
self.assertEqual(fp.read(), b'hello')
with self.assertRaises(urllib.error.URLError):
self.fake_urlopen(b'')
# urlcleanup() resets the opener.
urllib.request.urlcleanup()
self.assertEqual(self.fake_urlopen(b'second'), b'second')
class QuotingTests(unittest.TestCase):
r"""Tests for urllib.quote() and urllib.quote_plus()
According to RFC 3986 (Uniform Resource Identifiers), to escape a
character you write it as '%' + <2 character US-ASCII hex value>.
The Python code of ``'%' + hex(ord(<character>))[2:]`` escapes a
character properly. Case does not matter on the hex letters.
The various character sets specified are:
Reserved characters : ";/?:@&=+$,"
Have special meaning in URIs and must be escaped if not being used for
their special meaning
Data characters : letters, digits, and "-_.!~*'()"
Unreserved and do not need to be escaped; can be, though, if desired
Control characters : 0x00 - 0x1F, 0x7F
Have no use in URIs so must be escaped
space : 0x20
Must be escaped
Delimiters : '<>#%"'
Must be escaped
Unwise : "{}|\^[]`"
Must be escaped
"""
def test_never_quote(self):
# Make sure quote() does not quote letters, digits, and "_,.-"
do_not_quote = '' .join(["ABCDEFGHIJKLMNOPQRSTUVWXYZ",
"abcdefghijklmnopqrstuvwxyz",
"0123456789",
"_.-~"])
result = urllib.parse.quote(do_not_quote)
self.assertEqual(do_not_quote, result,
"using quote(): %r != %r" % (do_not_quote, result))
result = urllib.parse.quote_plus(do_not_quote)
self.assertEqual(do_not_quote, result,
"using quote_plus(): %r != %r" % (do_not_quote, result))
def test_default_safe(self):
# Test '/' is default value for 'safe' parameter
self.assertEqual(urllib.parse.quote.__defaults__[0], '/')
def test_safe(self):
# Test setting 'safe' parameter does what it should do
quote_by_default = "<>"
result = urllib.parse.quote(quote_by_default, safe=quote_by_default)
self.assertEqual(quote_by_default, result,