Repository navigation
Expand file tree
/
Copy pathhttplib.py
More file actions
1470 lines (1250 loc) · 51.1 KB
/
Copy pathhttplib.py
File metadata and controls
1470 lines (1250 loc) · 51.1 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
r"""HTTP/1.1 client library
<intro stuff goes here>
<other stuff, too>
HTTPConnection goes through a number of "states", which define when a client
may legally make another request or fetch the response for a particular
request. This diagram details these state transitions:
(null)
|
| HTTPConnection()
v
Idle
|
| putrequest()
v
Request-started
|
| ( putheader() )* endheaders()
v
Request-sent
|
| response = getresponse()
v
Unread-response [Response-headers-read]
|\____________________
| |
| response.read() | putrequest()
v v
Idle Req-started-unread-response
______/|
/ |
response.read() | | ( putheader() )* endheaders()
v v
Request-started Req-sent-unread-response
|
| response.read()
v
Request-sent
This diagram presents the following rules:
-- a second request may not be started until {response-headers-read}
-- a response [object] cannot be retrieved until {request-sent}
-- there is no differentiation between an unread response body and a
partially read response body
Note: this enforcement is applied by the HTTPConnection class. The
HTTPResponse class does not enforce this state machine, which
implies sophisticated clients may accelerate the request/response
pipeline. Caution should be taken, though: accelerating the states
beyond the above pattern may imply knowledge of the server's
connection-close behavior for certain requests. For example, it
is impossible to tell whether the server will close the connection
UNTIL the response headers have been read; this means that further
requests cannot be placed into the pipeline until it is known that
the server will NOT be closing the connection.
Logical State __state __response
------------- ------- ----------
Idle _CS_IDLE None
Request-started _CS_REQ_STARTED None
Request-sent _CS_REQ_SENT None
Unread-response _CS_IDLE <response_class>
Req-started-unread-response _CS_REQ_STARTED <response_class>
Req-sent-unread-response _CS_REQ_SENT <response_class>
"""
from array import array
import os
import re
import socket
from sys import py3kwarning
from urlparse import urlsplit
import warnings
with warnings.catch_warnings():
if py3kwarning:
warnings.filterwarnings("ignore", ".*mimetools has been removed",
DeprecationWarning)
import mimetools
try:
from cStringIO import StringIO
except ImportError:
from StringIO import StringIO
__all__ = ["HTTP", "HTTPResponse", "HTTPConnection",
"HTTPException", "NotConnected", "UnknownProtocol",
"UnknownTransferEncoding", "UnimplementedFileMode",
"IncompleteRead", "InvalidURL", "ImproperConnectionState",
"CannotSendRequest", "CannotSendHeader", "ResponseNotReady",
"BadStatusLine", "error", "responses"]
HTTP_PORT = 80
HTTPS_PORT = 443
_UNKNOWN = 'UNKNOWN'
# connection states
_CS_IDLE = 'Idle'
_CS_REQ_STARTED = 'Request-started'
_CS_REQ_SENT = 'Request-sent'
# status codes
# informational
CONTINUE = 100
SWITCHING_PROTOCOLS = 101
PROCESSING = 102
# successful
OK = 200
CREATED = 201
ACCEPTED = 202
NON_AUTHORITATIVE_INFORMATION = 203
NO_CONTENT = 204
RESET_CONTENT = 205
PARTIAL_CONTENT = 206
MULTI_STATUS = 207
IM_USED = 226
# redirection
MULTIPLE_CHOICES = 300
MOVED_PERMANENTLY = 301
FOUND = 302
SEE_OTHER = 303
NOT_MODIFIED = 304
USE_PROXY = 305
TEMPORARY_REDIRECT = 307
# client error
BAD_REQUEST = 400
UNAUTHORIZED = 401
PAYMENT_REQUIRED = 402
FORBIDDEN = 403
NOT_FOUND = 404
METHOD_NOT_ALLOWED = 405
NOT_ACCEPTABLE = 406
PROXY_AUTHENTICATION_REQUIRED = 407
REQUEST_TIMEOUT = 408
CONFLICT = 409
GONE = 410
LENGTH_REQUIRED = 411
PRECONDITION_FAILED = 412
REQUEST_ENTITY_TOO_LARGE = 413
REQUEST_URI_TOO_LONG = 414
UNSUPPORTED_MEDIA_TYPE = 415
REQUESTED_RANGE_NOT_SATISFIABLE = 416
EXPECTATION_FAILED = 417
UNPROCESSABLE_ENTITY = 422
LOCKED = 423
FAILED_DEPENDENCY = 424
UPGRADE_REQUIRED = 426
# server error
INTERNAL_SERVER_ERROR = 500
NOT_IMPLEMENTED = 501
BAD_GATEWAY = 502
SERVICE_UNAVAILABLE = 503
GATEWAY_TIMEOUT = 504
HTTP_VERSION_NOT_SUPPORTED = 505
INSUFFICIENT_STORAGE = 507
NOT_EXTENDED = 510
# Mapping status codes to official W3C names
responses = {
100: 'Continue',
101: 'Switching Protocols',
200: 'OK',
201: 'Created',
202: 'Accepted',
203: 'Non-Authoritative Information',
204: 'No Content',
205: 'Reset Content',
206: 'Partial Content',
300: 'Multiple Choices',
301: 'Moved Permanently',
302: 'Found',
303: 'See Other',
304: 'Not Modified',
305: 'Use Proxy',
306: '(Unused)',
307: 'Temporary Redirect',
400: 'Bad Request',
401: 'Unauthorized',
402: 'Payment Required',
403: 'Forbidden',
404: 'Not Found',
405: 'Method Not Allowed',
406: 'Not Acceptable',
407: 'Proxy Authentication Required',
408: 'Request Timeout',
409: 'Conflict',
410: 'Gone',
411: 'Length Required',
412: 'Precondition Failed',
413: 'Request Entity Too Large',
414: 'Request-URI Too Long',
415: 'Unsupported Media Type',
416: 'Requested Range Not Satisfiable',
417: 'Expectation Failed',
500: 'Internal Server Error',
501: 'Not Implemented',
502: 'Bad Gateway',
503: 'Service Unavailable',
504: 'Gateway Timeout',
505: 'HTTP Version Not Supported',
}
# maximal amount of data to read at one time in _safe_read
MAXAMOUNT = 1048576
# maximal line length when calling readline().
_MAXLINE = 65536
# maximum amount of headers accepted
_MAXHEADERS = 100
# Header name/value ABNF (http://tools.ietf.org/html/rfc7230#section-3.2)
#
# VCHAR = %x21-7E
# obs-text = %x80-FF
# header-field = field-name ":" OWS field-value OWS
# field-name = token
# field-value = *( field-content / obs-fold )
# field-content = field-vchar [ 1*( SP / HTAB ) field-vchar ]
# field-vchar = VCHAR / obs-text
#
# obs-fold = CRLF 1*( SP / HTAB )
# ; obsolete line folding
# ; see Section 3.2.4
# token = 1*tchar
#
# tchar = "!" / "#" / "$" / "%" / "&" / "'" / "*"
# / "+" / "-" / "." / "^" / "_" / "`" / "|" / "~"
# / DIGIT / ALPHA
# ; any VCHAR, except delimiters
#
# VCHAR defined in http://tools.ietf.org/html/rfc5234#appendix-B.1
# the patterns for both name and value are more lenient than RFC
# definitions to allow for backwards compatibility
_is_legal_header_name = re.compile(r'\A[^:\s][^:\r\n]*\Z').match
_is_illegal_header_value = re.compile(r'\n(?![ \t])|\r(?![ \t\n])').search
# These characters are not allowed within HTTP URL paths.
# See https://tools.ietf.org/html/rfc3986#section-3.3 and the
# https://tools.ietf.org/html/rfc3986#appendix-A pchar definition.
# Prevents CVE-2019-9740. Includes control characters such as \r\n.
# Restrict non-ASCII characters above \x7f (0x80-0xff).
_contains_disallowed_url_pchar_re = re.compile('[\x00-\x20\x7f-\xff]')
# Arguably only these _should_ allowed:
# _is_allowed_url_pchars_re = re.compile(r"^[/!$&'()*+,;=:@%a-zA-Z0-9._~-]+$")
# We are more lenient for assumed real world compatibility purposes.
# We always set the Content-Length header for these methods because some
# servers will otherwise respond with a 411
_METHODS_EXPECTING_BODY = {'PATCH', 'POST', 'PUT'}
class HTTPMessage(mimetools.Message):
def addheader(self, key, value):
"""Add header for field key handling repeats."""
prev = self.dict.get(key)
if prev is None:
self.dict[key] = value
else:
combined = ", ".join((prev, value))
self.dict[key] = combined
def addcontinue(self, key, more):
"""Add more field data from a continuation line."""
prev = self.dict[key]
self.dict[key] = prev + "\n " + more
def readheaders(self):
"""Read header lines.
Read header lines up to the entirely blank line that terminates them.
The (normally blank) line that ends the headers is skipped, but not
included in the returned list. If an invalid line is found in the
header section, it is skipped, and further lines are processed.
The variable self.status is set to the empty string if all went well,
otherwise it is an error message. The variable self.headers is a
completely uninterpreted list of lines contained in the header (so
printing them will reproduce the header exactly as it appears in the
file).
If multiple header fields with the same name occur, they are combined
according to the rules in RFC 2616 sec 4.2:
Appending each subsequent field-value to the first, each separated
by a comma. The order in which header fields with the same field-name
are received is significant to the interpretation of the combined
field value.
"""
# XXX The implementation overrides the readheaders() method of
# rfc822.Message. The base class design isn't amenable to
# customized behavior here so the method here is a copy of the
# base class code with a few small changes.
self.dict = {}
self.unixfrom = ''
self.headers = hlist = []
self.status = ''
headerseen = ""
firstline = 1
tell = None
if not hasattr(self.fp, 'unread') and self.seekable:
tell = self.fp.tell
while True:
if len(hlist) > _MAXHEADERS:
raise HTTPException("got more than %d headers" % _MAXHEADERS)
if tell:
try:
tell()
except IOError:
tell = None
self.seekable = 0
line = self.fp.readline(_MAXLINE + 1)
if len(line) > _MAXLINE:
raise LineTooLong("header line")
if not line:
self.status = 'EOF in headers'
break
# Skip unix From name time lines
if firstline and line.startswith('From '):
self.unixfrom = self.unixfrom + line
continue
firstline = 0
if headerseen and line[0] in ' \t':
# XXX Not sure if continuation lines are handled properly
# for http and/or for repeating headers
# It's a continuation line.
hlist.append(line)
self.addcontinue(headerseen, line.strip())
continue
elif self.iscomment(line):
# It's a comment. Ignore it.
continue
elif self.islast(line):
# Note! No pushback here! The delimiter line gets eaten.
break
headerseen = self.isheader(line)
if headerseen:
# It's a legal header line, save it.
hlist.append(line)
self.addheader(headerseen, line[len(headerseen)+1:].strip())
elif headerseen is not None:
# An empty header name. These aren't allowed in HTTP, but it's
# probably a benign mistake. Don't add the header, just keep
# going.
pass
else:
# It's not a header line; skip it and try the next line.
self.status = 'Non-header line where header expected'
class HTTPResponse:
# strict: If true, raise BadStatusLine if the status line can't be
# parsed as a valid HTTP/1.0 or 1.1 status line. By default it is
# false because it prevents clients from talking to HTTP/0.9
# servers. Note that a response with a sufficiently corrupted
# status line will look like an HTTP/0.9 response.
# See RFC 2616 sec 19.6 and RFC 1945 sec 6 for details.
def __init__(self, sock, debuglevel=0, strict=0, method=None, buffering=False):
if buffering:
# The caller won't be using any sock.recv() calls, so buffering
# is fine and recommended for performance.
self.fp = sock.makefile('rb')
else:
# The buffer size is specified as zero, because the headers of
# the response are read with readline(). If the reads were
# buffered the readline() calls could consume some of the
# response, which make be read via a recv() on the underlying
# socket.
self.fp = sock.makefile('rb', 0)
self.debuglevel = debuglevel
self.strict = strict
self._method = method
self.msg = None
# from the Status-Line of the response
self.version = _UNKNOWN # HTTP-Version
self.status = _UNKNOWN # Status-Code
self.reason = _UNKNOWN # Reason-Phrase
self.chunked = _UNKNOWN # is "chunked" being used?
self.chunk_left = _UNKNOWN # bytes left to read in current chunk
self.length = _UNKNOWN # number of bytes left in response
self.will_close = _UNKNOWN # conn will close at end of response
def _read_status(self):
# Initialize with Simple-Response defaults
line = self.fp.readline(_MAXLINE + 1)
if len(line) > _MAXLINE:
raise LineTooLong("header line")
if self.debuglevel > 0:
print "reply:", repr(line)
if not line:
# Presumably, the server closed the connection before
# sending a valid response.
raise BadStatusLine("No status line received - the server has closed the connection")
try:
[version, status, reason] = line.split(None, 2)
except ValueError:
try:
[version, status] = line.split(None, 1)
reason = ""
except ValueError:
# empty version will cause next test to fail and status
# will be treated as 0.9 response.
version = ""
if not version.startswith('HTTP/'):
if self.strict:
self.close()
raise BadStatusLine(line)
else:
# assume it's a Simple-Response from an 0.9 server
self.fp = LineAndFileWrapper(line, self.fp)
return "HTTP/0.9", 200, ""
# The status code is a three-digit number
try:
status = int(status)
if status < 100 or status > 999:
raise BadStatusLine(line)
except ValueError:
raise BadStatusLine(line)
return version, status, reason
def begin(self):
if self.msg is not None:
# we've already started reading the response
return
# read until we get a non-100 response
while True:
version, status, reason = self._read_status()
if status != CONTINUE:
break
# skip the header from the 100 response
while True:
skip = self.fp.readline(_MAXLINE + 1)
if len(skip) > _MAXLINE:
raise LineTooLong("header line")
skip = skip.strip()
if not skip:
break
if self.debuglevel > 0:
print "header:", skip
self.status = status
self.reason = reason.strip()
if version == 'HTTP/1.0':
self.version = 10
elif version.startswith('HTTP/1.'):
self.version = 11 # use HTTP/1.1 code for HTTP/1.x where x>=1
elif version == 'HTTP/0.9':
self.version = 9
else:
raise UnknownProtocol(version)
if self.version == 9:
self.length = None
self.chunked = 0
self.will_close = 1
self.msg = HTTPMessage(StringIO())
return
self.msg = HTTPMessage(self.fp, 0)
if self.debuglevel > 0:
for hdr in self.msg.headers:
print "header:", hdr,
# don't let the msg keep an fp
self.msg.fp = None
# are we using the chunked-style of transfer encoding?
tr_enc = self.msg.getheader('transfer-encoding')
if tr_enc and tr_enc.lower() == "chunked":
self.chunked = 1
self.chunk_left = None
else:
self.chunked = 0
# will the connection close at the end of the response?
self.will_close = self._check_close()
# do we have a Content-Length?
# NOTE: RFC 2616, S4.4, #3 says we ignore this if tr_enc is "chunked"
length = self.msg.getheader('content-length')
if length and not self.chunked:
try:
self.length = int(length)
except ValueError:
self.length = None
else:
if self.length < 0: # ignore nonsensical negative lengths
self.length = None
else:
self.length = None
# does the body have a fixed length? (of zero)
if (status == NO_CONTENT or status == NOT_MODIFIED or
100 <= status < 200 or # 1xx codes
self._method == 'HEAD'):
self.length = 0
# if the connection remains open, and we aren't using chunked, and
# a content-length was not provided, then assume that the connection
# WILL close.
if not self.will_close and \
not self.chunked and \
self.length is None:
self.will_close = 1
def _check_close(self):
conn = self.msg.getheader('connection')
if self.version == 11:
# An HTTP/1.1 proxy is assumed to stay open unless
# explicitly closed.
conn = self.msg.getheader('connection')
if conn and "close" in conn.lower():
return True
return False
# Some HTTP/1.0 implementations have support for persistent
# connections, using rules different than HTTP/1.1.
# For older HTTP, Keep-Alive indicates persistent connection.
if self.msg.getheader('keep-alive'):
return False
# At least Akamai returns a "Connection: Keep-Alive" header,
# which was supposed to be sent by the client.
if conn and "keep-alive" in conn.lower():
return False
# Proxy-Connection is a netscape hack.
pconn = self.msg.getheader('proxy-connection')
if pconn and "keep-alive" in pconn.lower():
return False
# otherwise, assume it will close
return True
def close(self):
fp = self.fp
if fp:
self.fp = None
fp.close()
def isclosed(self):
# NOTE: it is possible that we will not ever call self.close(). This
# case occurs when will_close is TRUE, length is None, and we
# read up to the last byte, but NOT past it.
#
# IMPLIES: if will_close is FALSE, then self.close() will ALWAYS be
# called, meaning self.isclosed() is meaningful.
return self.fp is None
# XXX It would be nice to have readline and __iter__ for this, too.
def read(self, amt=None):
if self.fp is None:
return ''
if self._method == 'HEAD':
self.close()
return ''
if self.chunked:
return self._read_chunked(amt)
if amt is None:
# unbounded read
if self.length is None:
s = self.fp.read()
else:
try:
s = self._safe_read(self.length)
except IncompleteRead:
self.close()
raise
self.length = 0
self.close() # we read everything
return s
if self.length is not None:
if amt > self.length:
# clip the read to the "end of response"
amt = self.length
# we do not use _safe_read() here because this may be a .will_close
# connection, and the user is reading more bytes than will be provided
# (for example, reading in 1k chunks)
s = self.fp.read(amt)
if not s and amt:
# Ideally, we would raise IncompleteRead if the content-length
# wasn't satisfied, but it might break compatibility.
self.close()
if self.length is not None:
self.length -= len(s)
if not self.length:
self.close()
return s
def _read_chunked(self, amt):
assert self.chunked != _UNKNOWN
chunk_left = self.chunk_left
value = []
while True:
if chunk_left is None:
line = self.fp.readline(_MAXLINE + 1)
if len(line) > _MAXLINE:
raise LineTooLong("chunk size")
i = line.find(';')
if i >= 0:
line = line[:i] # strip chunk-extensions
try:
chunk_left = int(line, 16)
except ValueError:
# close the connection as protocol synchronisation is
# probably lost
self.close()
raise IncompleteRead(''.join(value))
if chunk_left == 0:
break
if amt is None:
value.append(self._safe_read(chunk_left))
elif amt < chunk_left:
value.append(self._safe_read(amt))
self.chunk_left = chunk_left - amt
return ''.join(value)
elif amt == chunk_left:
value.append(self._safe_read(amt))
self._safe_read(2) # toss the CRLF at the end of the chunk
self.chunk_left = None
return ''.join(value)
else:
value.append(self._safe_read(chunk_left))
amt -= chunk_left
# we read the whole chunk, get another
self._safe_read(2) # toss the CRLF at the end of the chunk
chunk_left = None
# read and discard trailer up to the CRLF terminator
### note: we shouldn't have any trailers!
while True:
line = self.fp.readline(_MAXLINE + 1)
if len(line) > _MAXLINE:
raise LineTooLong("trailer line")
if not line:
# a vanishingly small number of sites EOF without
# sending the trailer
break
if line == '\r\n':
break
# we read everything; close the "file"
self.close()
return ''.join(value)
def _safe_read(self, amt):
"""Read the number of bytes requested, compensating for partial reads.
Normally, we have a blocking socket, but a read() can be interrupted
by a signal (resulting in a partial read).
Note that we cannot distinguish between EOF and an interrupt when zero
bytes have been read. IncompleteRead() will be raised in this
situation.
This function should be used when <amt> bytes "should" be present for
reading. If the bytes are truly not available (due to EOF), then the
IncompleteRead exception can be used to detect the problem.
"""
# NOTE(gps): As of svn r74426 socket._fileobject.read(x) will never
# return less than x bytes unless EOF is encountered. It now handles
# signal interruptions (socket.error EINTR) internally. This code
# never caught that exception anyways. It seems largely pointless.
# self.fp.read(amt) will work fine.
s = []
while amt > 0:
chunk = self.fp.read(min(amt, MAXAMOUNT))
if not chunk:
raise IncompleteRead(''.join(s), amt)
s.append(chunk)
amt -= len(chunk)
return ''.join(s)
def fileno(self):
return self.fp.fileno()
def getheader(self, name, default=None):
if self.msg is None:
raise ResponseNotReady()
return self.msg.getheader(name, default)
def getheaders(self):
"""Return list of (header, value) tuples."""
if self.msg is None:
raise ResponseNotReady()
return self.msg.items()
class HTTPConnection:
_http_vsn = 11
_http_vsn_str = 'HTTP/1.1'
response_class = HTTPResponse
default_port = HTTP_PORT
auto_open = 1
debuglevel = 0
strict = 0
def __init__(self, host, port=None, strict=None,
timeout=socket._GLOBAL_DEFAULT_TIMEOUT, source_address=None):
self.timeout = timeout
self.source_address = source_address
self.sock = None
self._buffer = []
self.__response = None
self.__state = _CS_IDLE
self._method = None
self._tunnel_host = None
self._tunnel_port = None
self._tunnel_headers = {}
if strict is not None:
self.strict = strict
(self.host, self.port) = self._get_hostport(host, port)
self._validate_host(self.host)
# This is stored as an instance variable to allow unittests
# to replace with a suitable mock
self._create_connection = socket.create_connection
def set_tunnel(self, host, port=None, headers=None):
""" Set up host and port for HTTP CONNECT tunnelling.
In a connection that uses HTTP Connect tunneling, the host passed to the
constructor is used as proxy server that relays all communication to the
endpoint passed to set_tunnel. This is done by sending a HTTP CONNECT
request to the proxy server when the connection is established.
This method must be called before the HTTP connection has been
established.
The headers argument should be a mapping of extra HTTP headers
to send with the CONNECT request.
"""
# Verify if this is required.
if self.sock:
raise RuntimeError("Can't setup tunnel for established connection.")
self._tunnel_host, self._tunnel_port = self._get_hostport(host, port)
if headers:
self._tunnel_headers = headers
else:
self._tunnel_headers.clear()
def _get_hostport(self, host, port):
if port is None:
i = host.rfind(':')
j = host.rfind(']') # ipv6 addresses have [...]
if i > j:
try:
port = int(host[i+1:])
except ValueError:
if host[i+1:] == "": # http://foo.com:/ == http://foo.com/
port = self.default_port
else:
raise InvalidURL("nonnumeric port: '%s'" % host[i+1:])
host = host[:i]
else:
port = self.default_port
if host and host[0] == '[' and host[-1] == ']':
host = host[1:-1]
return (host, port)
def set_debuglevel(self, level):
self.debuglevel = level
def _tunnel(self):
self.send("CONNECT %s:%d HTTP/1.0\r\n" % (self._tunnel_host,
self._tunnel_port))
for header, value in self._tunnel_headers.iteritems():
self.send("%s: %s\r\n" % (header, value))
self.send("\r\n")
response = self.response_class(self.sock, strict = self.strict,
method = self._method)
(version, code, message) = response._read_status()
if version == "HTTP/0.9":
# HTTP/0.9 doesn't support the CONNECT verb, so if httplib has
# concluded HTTP/0.9 is being used something has gone wrong.
self.close()
raise socket.error("Invalid response from tunnel request")
if code != 200:
self.close()
raise socket.error("Tunnel connection failed: %d %s" % (code,
message.strip()))
while True:
line = response.fp.readline(_MAXLINE + 1)
if len(line) > _MAXLINE:
raise LineTooLong("header line")
if not line:
# for sites which EOF without sending trailer
break
if line == '\r\n':
break
def connect(self):
"""Connect to the host and port specified in __init__."""
self.sock = self._create_connection((self.host,self.port),
self.timeout, self.source_address)
if self._tunnel_host:
self._tunnel()
def close(self):
"""Close the connection to the HTTP server."""
self.__state = _CS_IDLE
try:
sock = self.sock
if sock:
self.sock = None
sock.close() # close it manually... there may be other refs
finally:
response = self.__response
if response:
self.__response = None
response.close()
def send(self, data):
"""Send `data' to the server."""
if self.sock is None:
if self.auto_open:
self.connect()
else:
raise NotConnected()
if self.debuglevel > 0:
print "send:", repr(data)
blocksize = 8192
if hasattr(data,'read') and not isinstance(data, array):
if self.debuglevel > 0: print "sendIng a read()able"
datablock = data.read(blocksize)
while datablock:
self.sock.sendall(datablock)
datablock = data.read(blocksize)
else:
self.sock.sendall(data)
def _output(self, s):
"""Add a line of output to the current request buffer.
Assumes that the line does *not* end with \\r\\n.
"""
self._buffer.append(s)
def _send_output(self, message_body=None):
"""Send the currently buffered request and clear the buffer.
Appends an extra \\r\\n to the buffer.
A message_body may be specified, to be appended to the request.
"""
self._buffer.extend(("", ""))
msg = "\r\n".join(self._buffer)
del self._buffer[:]
# If msg and message_body are sent in a single send() call,
# it will avoid performance problems caused by the interaction
# between delayed ack and the Nagle algorithm.
if isinstance(message_body, str):
msg += message_body
message_body = None
self.send(msg)
if message_body is not None:
#message_body was not a string (i.e. it is a file) and
#we must run the risk of Nagle
self.send(message_body)
def putrequest(self, method, url, skip_host=0, skip_accept_encoding=0):
"""Send a request to the server.
`method' specifies an HTTP request method, e.g. 'GET'.
`url' specifies the object being requested, e.g. '/index.html'.
`skip_host' if True does not add automatically a 'Host:' header
`skip_accept_encoding' if True does not add automatically an
'Accept-Encoding:' header
"""
# if a prior response has been completed, then forget about it.
if self.__response and self.__response.isclosed():
self.__response = None
# in certain cases, we cannot issue another request on this connection.
# this occurs when:
# 1) we are in the process of sending a request. (_CS_REQ_STARTED)
# 2) a response to a previous request has signalled that it is going
# to close the connection upon completion.
# 3) the headers for the previous response have not been read, thus
# we cannot determine whether point (2) is true. (_CS_REQ_SENT)
#
# if there is no prior response, then we can request at will.
#
# if point (2) is true, then we will have passed the socket to the
# response (effectively meaning, "there is no prior response"), and
# will open a new one when a new request is made.
#
# Note: if a prior response exists, then we *can* start a new request.
# We are not allowed to begin fetching the response to this new
# request, however, until that prior response is complete.
#
if self.__state == _CS_IDLE:
self.__state = _CS_REQ_STARTED
else:
raise CannotSendRequest()
# Save the method for use later in the response phase
self._method = method
url = url or '/'
self._validate_path(url)
request = '%s %s %s' % (method, url, self._http_vsn_str)
self._output(self._encode_request(request))
if self._http_vsn == 11:
# Issue some standard headers for better HTTP/1.1 compliance
if not skip_host:
# this header is issued *only* for HTTP/1.1
# connections. more specifically, this means it is
# only issued when the client uses the new
# HTTPConnection() class. backwards-compat clients
# will be using HTTP/1.0 and those clients may be
# issuing this header themselves. we should NOT issue
# it twice; some web servers (such as Apache) barf
# when they see two Host: headers
# If we need a non-standard port,include it in the
# header. If the request is going through a proxy,
# but the host of the actual URL, not the host of the
# proxy.
netloc = ''
if url.startswith('http'):
nil, netloc, nil, nil, nil = urlsplit(url)
if netloc:
try:
netloc_enc = netloc.encode("ascii")
except UnicodeEncodeError:
netloc_enc = netloc.encode("idna")
self.putheader('Host', netloc_enc)
else:
if self._tunnel_host:
host = self._tunnel_host
port = self._tunnel_port
else:
host = self.host
port = self.port
try:
host_enc = host.encode("ascii")
except UnicodeEncodeError:
host_enc = host.encode("idna")
# Wrap the IPv6 Host Header with [] (RFC 2732)
if host_enc.find(':') >= 0:
host_enc = "[" + host_enc + "]"
if port == self.default_port:
self.putheader('Host', host_enc)
else:
self.putheader('Host', "%s:%s" % (host_enc, port))
# note: we are assuming that clients will not attempt to set these
# headers since *this* library must deal with the
# consequences. this also means that when the supporting
# libraries are updated to recognize other forms, then this
# code should be changed (removed or updated).