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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
|
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
|\_____________________________
| | getresponse() raises
| response = getresponse() | ConnectionError
v v
Unread-response Idle
[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>
"""
import email.parser
import email.message
import http
import io
import re
import socket
import collections.abc
from urllib.parse import urlsplit
# HTTPMessage, parse_headers(), and the HTTP status code constants are
# intentionally omitted for simplicity
__all__ = ["HTTPResponse", "HTTPConnection",
"HTTPException", "NotConnected", "UnknownProtocol",
"UnknownTransferEncoding", "UnimplementedFileMode",
"IncompleteRead", "InvalidURL", "ImproperConnectionState",
"CannotSendRequest", "CannotSendHeader", "ResponseNotReady",
"BadStatusLine", "LineTooLong", "RemoteDisconnected", "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'
# hack to maintain backwards compatibility
globals().update(http.HTTPStatus.__members__)
# another hack to maintain backwards compatibility
# Mapping status codes to official W3C names
responses = {v: v.phrase for v in http.HTTPStatus.__members__.values()}
# maximal amount of data to read at one time in _safe_read
MAXAMOUNT = 1048576
# maximal line length when calling readline().
_MAXLINE = 65536
_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(rb'[^:\s][^:\r\n]*').fullmatch
_is_illegal_header_value = re.compile(rb'\n(?![ \t])|\r(?![ \t\n])').search
# 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'}
def _encode(data, name='data'):
"""Call data.encode("latin-1") but show a better error message."""
try:
return data.encode("latin-1")
except UnicodeEncodeError as err:
raise UnicodeEncodeError(
err.encoding,
err.object,
err.start,
err.end,
"%s (%.20r) is not valid Latin-1. Use %s.encode('utf-8') "
"if you want to send it encoded in UTF-8." %
(name.title(), data[err.start:err.end], name)) from None
class HTTPMessage(email.message.Message):
# XXX The only usage of this method is in
# http.server.CGIHTTPRequestHandler. Maybe move the code there so
# that it doesn't need to be part of the public API. The API has
# never been defined so this could cause backwards compatibility
# issues.
def getallmatchingheaders(self, name):
"""Find all header lines matching a given header name.
Look through the list of headers and find all lines matching a given
header name (and their continuation lines). A list of the lines is
returned, without interpretation. If the header does not occur, an
empty list is returned. If the header occurs multiple times, all
occurrences are returned. Case is not important in the header name.
"""
name = name.lower() + ':'
n = len(name)
lst = []
hit = 0
for line in self.keys():
if line[:n].lower() == name:
hit = 1
elif not line[:1].isspace():
hit = 0
if hit:
lst.append(line)
return lst
def parse_headers(fp, _class=HTTPMessage):
"""Parses only RFC2822 headers from a file pointer.
email Parser wants to see strings rather than bytes.
But a TextIOWrapper around self.rfile would buffer too many bytes
from the stream, bytes which we later need to read as bytes.
So we read the correct bytes here, as bytes, for email Parser
to parse.
"""
headers = []
while True:
line = fp.readline(_MAXLINE + 1)
if len(line) > _MAXLINE:
raise LineTooLong("header line")
headers.append(line)
if len(headers) > _MAXHEADERS:
raise HTTPException("got more than %d headers" % _MAXHEADERS)
if line in (b'\r\n', b'\n', b''):
break
hstring = b''.join(headers).decode('iso-8859-1')
return email.parser.Parser(_class=_class).parsestr(hstring)
class HTTPResponse(io.BufferedIOBase):
# See RFC 2616 sec 19.6 and RFC 1945 sec 6 for details.
# The bytes from the socket object are iso-8859-1 strings.
# See RFC 2616 sec 2.2 which notes an exception for MIME-encoded
# text following RFC 2047. The basic status line parsing only
# accepts iso-8859-1.
def __init__(self, sock, debuglevel=0, method=None, url=None):
# If the response includes a content-length header, we need to
# make sure that the client doesn't read more than the
# specified number of bytes. If it does, it will block until
# the server times out and closes the connection. This will
# happen if a self.fp.read() is done (without a size) whether
# self.fp is buffered or not. So, no self.fp.read() by
# clients unless they know what they are doing.
self.fp = sock.makefile("rb")
self.debuglevel = debuglevel
self._method = method
# The HTTPResponse object is returned via urllib. The clients
# of http and urllib expect different attributes for the
# headers. headers is used here and supports urllib. msg is
# provided as a backwards compatibility layer for http
# clients.
self.headers = 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):
line = str(self.fp.readline(_MAXLINE + 1), "iso-8859-1")
if len(line) > _MAXLINE:
raise LineTooLong("status line")
if self.debuglevel > 0:
print("reply:", repr(line))
if not line:
# Presumably, the server closed the connection before
# sending a valid response.
raise RemoteDisconnected("Remote end closed connection without"
" response")
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.
version = ""
if not version.startswith("HTTP/"):
self._close_conn()
raise BadStatusLine(line)
# 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.headers 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.code = self.status = status
self.reason = reason.strip()
if version in ("HTTP/1.0", "HTTP/0.9"):
# Some servers might still return "0.9", treat it as 1.0 anyway
self.version = 10
elif version.startswith("HTTP/1."):
self.version = 11 # use HTTP/1.1 code for HTTP/1.x where x>=1
else:
raise UnknownProtocol(version)
self.headers = self.msg = parse_headers(self.fp)
if self.debuglevel > 0:
for hdr in self.headers:
print("header:", hdr + ":", self.headers.get(hdr))
# are we using the chunked-style of transfer encoding?
tr_enc = self.headers.get("transfer-encoding")
if tr_enc and tr_enc.lower() == "chunked":
self.chunked = True
self.chunk_left = None
else:
self.chunked = False
# 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"
self.length = None
length = self.headers.get("content-length")
# are we using the chunked-style of transfer encoding?
tr_enc = self.headers.get("transfer-encoding")
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 = True
def _check_close(self):
conn = self.headers.get("connection")
if self.version == 11:
# An HTTP/1.1 proxy is assumed to stay open unless
# explicitly closed.
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.headers.get("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.headers.get("proxy-connection")
if pconn and "keep-alive" in pconn.lower():
return False
# otherwise, assume it will close
return True
def _close_conn(self):
fp = self.fp
self.fp = None
fp.close()
def close(self):
try:
super().close() # set "closed" flag
finally:
if self.fp:
self._close_conn()
# These implementations are for the benefit of io.BufferedReader.
# XXX This class should probably be revised to act more like
# the "raw stream" that BufferedReader expects.
def flush(self):
super().flush()
if self.fp:
self.fp.flush()
def readable(self):
"""Always returns True"""
return True
# End of "raw stream" methods
def isclosed(self):
"""True if the connection is closed."""
# 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
def read(self, amt=None):
if self.fp is None:
return b""
if self._method == "HEAD":
self._close_conn()
return b""
if amt is not None:
# Amount is given, implement using readinto
b = bytearray(amt)
n = self.readinto(b)
return memoryview(b)[:n].tobytes()
else:
# Amount is not given (unbounded read) so we must check self.length
# and self.chunked
if self.chunked:
return self._readall_chunked()
if self.length is None:
s = self.fp.read()
else:
try:
s = self._safe_read(self.length)
except IncompleteRead:
self._close_conn()
raise
self.length = 0
self._close_conn() # we read everything
return s
def readinto(self, b):
"""Read up to len(b) bytes into bytearray b and return the number
of bytes read.
"""
if self.fp is None:
return 0
if self._method == "HEAD":
self._close_conn()
return 0
if self.chunked:
return self._readinto_chunked(b)
if self.length is not None:
if len(b) > self.length:
# clip the read to the "end of response"
b = memoryview(b)[0: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)
n = self.fp.readinto(b)
if not n and b:
# Ideally, we would raise IncompleteRead if the content-length
# wasn't satisfied, but it might break compatibility.
self._close_conn()
elif self.length is not None:
self.length -= n
if not self.length:
self._close_conn()
return n
def _read_next_chunk_size(self):
# Read the next chunk size from the file
line = self.fp.readline(_MAXLINE + 1)
if len(line) > _MAXLINE:
raise LineTooLong("chunk size")
i = line.find(b";")
if i >= 0:
line = line[:i] # strip chunk-extensions
try:
return int(line, 16)
except ValueError:
# close the connection as protocol synchronisation is
# probably lost
self._close_conn()
raise
def _read_and_discard_trailer(self):
# 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 in (b'\r\n', b'\n', b''):
break
def _get_chunk_left(self):
# return self.chunk_left, reading a new chunk if necessary.
# chunk_left == 0: at the end of the current chunk, need to close it
# chunk_left == None: No current chunk, should read next.
# This function returns non-zero or None if the last chunk has
# been read.
chunk_left = self.chunk_left
if not chunk_left: # Can be 0 or None
if chunk_left is not None:
# We are at the end of chunk, discard chunk end
self._safe_read(2) # toss the CRLF at the end of the chunk
try:
chunk_left = self._read_next_chunk_size()
except ValueError:
raise IncompleteRead(b'')
if chunk_left == 0:
# last chunk: 1*("0") [ chunk-extension ] CRLF
self._read_and_discard_trailer()
# we read everything; close the "file"
self._close_conn()
chunk_left = None
self.chunk_left = chunk_left
return chunk_left
def _readall_chunked(self):
assert self.chunked != _UNKNOWN
value = []
try:
while True:
chunk_left = self._get_chunk_left()
if chunk_left is None:
break
value.append(self._safe_read(chunk_left))
self.chunk_left = 0
return b''.join(value)
except IncompleteRead:
raise IncompleteRead(b''.join(value))
def _readinto_chunked(self, b):
assert self.chunked != _UNKNOWN
total_bytes = 0
mvb = memoryview(b)
try:
while True:
chunk_left = self._get_chunk_left()
if chunk_left is None:
return total_bytes
if len(mvb) <= chunk_left:
n = self._safe_readinto(mvb)
self.chunk_left = chunk_left - n
return total_bytes + n
temp_mvb = mvb[:chunk_left]
n = self._safe_readinto(temp_mvb)
mvb = mvb[n:]
total_bytes += n
self.chunk_left = 0
except IncompleteRead:
raise IncompleteRead(bytes(b[0:total_bytes]))
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.
"""
s = []
while amt > 0:
chunk = self.fp.read(min(amt, MAXAMOUNT))
if not chunk:
raise IncompleteRead(b''.join(s), amt)
s.append(chunk)
amt -= len(chunk)
return b"".join(s)
def _safe_readinto(self, b):
"""Same as _safe_read, but for reading into a buffer."""
total_bytes = 0
mvb = memoryview(b)
while total_bytes < len(b):
if MAXAMOUNT < len(mvb):
temp_mvb = mvb[0:MAXAMOUNT]
n = self.fp.readinto(temp_mvb)
else:
n = self.fp.readinto(mvb)
if not n:
raise IncompleteRead(bytes(mvb[0:total_bytes]), len(b))
mvb = mvb[n:]
total_bytes += n
return total_bytes
def read1(self, n=-1):
"""Read with at most one underlying system call. If at least one
byte is buffered, return that instead.
"""
if self.fp is None or self._method == "HEAD":
return b""
if self.chunked:
return self._read1_chunked(n)
if self.length is not None and (n < 0 or n > self.length):
n = self.length
result = self.fp.read1(n)
if not result and n:
self._close_conn()
elif self.length is not None:
self.length -= len(result)
return result
def peek(self, n=-1):
# Having this enables IOBase.readline() to read more than one
# byte at a time
if self.fp is None or self._method == "HEAD":
return b""
if self.chunked:
return self._peek_chunked(n)
return self.fp.peek(n)
def readline(self, limit=-1):
if self.fp is None or self._method == "HEAD":
return b""
if self.chunked:
# Fallback to IOBase readline which uses peek() and read()
return super().readline(limit)
if self.length is not None and (limit < 0 or limit > self.length):
limit = self.length
result = self.fp.readline(limit)
if not result and limit:
self._close_conn()
elif self.length is not None:
self.length -= len(result)
return result
def _read1_chunked(self, n):
# Strictly speaking, _get_chunk_left() may cause more than one read,
# but that is ok, since that is to satisfy the chunked protocol.
chunk_left = self._get_chunk_left()
if chunk_left is None or n == 0:
return b''
if not (0 <= n <= chunk_left):
n = chunk_left # if n is negative or larger than chunk_left
read = self.fp.read1(n)
self.chunk_left -= len(read)
if not read:
raise IncompleteRead(b"")
return read
def _peek_chunked(self, n):
# Strictly speaking, _get_chunk_left() may cause more than one read,
# but that is ok, since that is to satisfy the chunked protocol.
try:
chunk_left = self._get_chunk_left()
except IncompleteRead:
return b'' # peek doesn't worry about protocol
if chunk_left is None:
return b'' # eof
# peek is allowed to return more than requested. Just request the
# entire chunk, and truncate what we get.
return self.fp.peek(chunk_left)[:chunk_left]
def fileno(self):
return self.fp.fileno()
def getheader(self, name, default=None):
'''Returns the value of the header matching *name*.
If there are multiple matching headers, the values are
combined into a single string separated by commas and spaces.
If no matching header is found, returns *default* or None if
the *default* is not specified.
If the headers are unknown, raises http.client.ResponseNotReady.
'''
if self.headers is None:
raise ResponseNotReady()
headers = self.headers.get_all(name) or default
if isinstance(headers, str) or not hasattr(headers, '__iter__'):
return headers
else:
return ', '.join(headers)
def getheaders(self):
"""Return list of (header, value) tuples."""
if self.headers is None:
raise ResponseNotReady()
return list(self.headers.items())
# We override IOBase.__iter__ so that it doesn't check for closed-ness
def __iter__(self):
return self
# For compatibility with old-style urllib responses.
def info(self):
'''Returns an instance of the class mimetools.Message containing
meta-information associated with the URL.
When the method is HTTP, these headers are those returned by
the server at the head of the retrieved HTML page (including
Content-Length and Content-Type).
When the method is FTP, a Content-Length header will be
present if (as is now usual) the server passed back a file
length in response to the FTP retrieval request. A
Content-Type header will be present if the MIME type can be
guessed.
When the method is local-file, returned headers will include
a Date representing the file's last-modified time, a
Content-Length giving file size, and a Content-Type
containing a guess at the file's type. See also the
description of the mimetools module.
'''
return self.headers
def geturl(self):
'''Return the real URL of the page.
In some cases, the HTTP server redirects a client to another
URL. The urlopen() function handles this transparently, but in
some cases the caller needs to know which URL the client was
redirected to. The geturl() method can be used to get at this
redirected URL.
'''
return self.url
def getcode(self):
'''Return the HTTP status code that was sent with the response,
or None if the URL is not an HTTP URL.
'''
return self.status
class HTTPConnection:
_http_vsn = 11
_http_vsn_str = 'HTTP/1.1'
response_class = HTTPResponse
default_port = HTTP_PORT
auto_open = 1
debuglevel = 0
@staticmethod
def _is_textIO(stream):
"""Test whether a file-like object is a text or a binary stream.
"""
return isinstance(stream, io.TextIOBase)
@staticmethod
def _get_content_length(body, method):
"""Get the content-length based on the body.
If the body is None, we set Content-Length: 0 for methods that expect
a body (RFC 7230, Section 3.3.2). We also set the Content-Length for
any method if the body is a str or bytes-like object and not a file.
"""
if body is None:
# do an explicit check for not None here to distinguish
# between unset and set but empty
if method.upper() in _METHODS_EXPECTING_BODY:
return 0
else:
return None
if hasattr(body, 'read'):
# file-like object.
return None
try:
# does it implement the buffer protocol (bytes, bytearray, array)?
mv = memoryview(body)
return mv.nbytes
except TypeError:
pass
if isinstance(body, str):
return len(body)
return None
def __init__(self, host, port=None, timeout=socket._GLOBAL_DEFAULT_TIMEOUT,
source_address=None, blocksize=8192):
self.timeout = timeout
self.source_address = source_address
self.blocksize = blocksize
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 = {}
(self.host, self.port) = self._get_hostport(host, port)
# This is stored as an instance variable to allow unit
# tests to replace it with a suitable mockup
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 a proxy server that relays all communication to
the endpoint passed to `set_tunnel`. This done by sending an HTTP
CONNECT request to the proxy server when the connection is established.
This method must be called before the HTML connection has been
established.
The headers argument should be a mapping of extra HTTP headers to send
with the CONNECT request.
"""
if self.sock:
raise RuntimeError("Can't set up 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):
connect_str = "CONNECT %s:%d HTTP/1.0\r\n" % (self._tunnel_host,
self._tunnel_port)
connect_bytes = connect_str.encode("ascii")
self.send(connect_bytes)
for header, value in self._tunnel_headers.items():
header_str = "%s: %s\r\n" % (header, value)
header_bytes = header_str.encode("latin-1")
self.send(header_bytes)
self.send(b'\r\n')
response = self.response_class(self.sock, method=self._method)
(version, code, message) = response._read_status()
if code != http.HTTPStatus.OK:
self.close()
raise OSError("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 a trailer
break
if line in (b'\r\n', b'\n', b''):
break
if self.debuglevel > 0:
print('header:', line.decode())
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)
self.sock.setsockopt(socket.IPPROTO_TCP, socket.TCP_NODELAY, 1)
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.
``data`` can be a string object, a bytes object, an array object, a
file-like object that supports a .read() method, or an iterable object.
"""
if self.sock is None:
if self.auto_open:
self.connect()
else:
raise NotConnected()
if self.debuglevel > 0:
print("send:", repr(data))
if hasattr(data, "read") :
if self.debuglevel > 0:
print("sendIng a read()able")
encode = self._is_textIO(data)
if encode and self.debuglevel > 0:
print("encoding file using iso-8859-1")
while 1:
datablock = data.read(self.blocksize)
if not datablock:
break
if encode:
datablock = datablock.encode("iso-8859-1")
self.sock.sendall(datablock)
return
try:
self.sock.sendall(data)
except TypeError:
if isinstance(data, collections.abc.Iterable):
for d in data:
self.sock.sendall(d)
else:
raise TypeError("data should be a bytes-like object "
"or an iterable, got %r" % type(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 _read_readable(self, readable):
if self.debuglevel > 0:
print("sendIng a read()able")
encode = self._is_textIO(readable)
if encode and self.debuglevel > 0:
print("encoding file using iso-8859-1")
while True:
datablock = readable.read(self.blocksize)
if not datablock:
break
if encode:
datablock = datablock.encode("iso-8859-1")
yield datablock
def _send_output(self, message_body=None, encode_chunked=False):
"""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((b"", b""))
msg = b"\r\n".join(self._buffer)
del self._buffer[:]
self.send(msg)
if message_body is not None:
# create a consistent interface to message_body
if hasattr(message_body, 'read'):
# Let file-like take precedence over byte-like. This
# is needed to allow the current position of mmap'ed
# files to be taken into account.
chunks = self._read_readable(message_body)
else:
try:
# this is solely to check to see if message_body
# implements the buffer API. it /would/ be easier
# to capture if PyObject_CheckBuffer was exposed
# to Python.
memoryview(message_body)
except TypeError:
try:
chunks = iter(message_body)
except TypeError:
raise TypeError("message_body should be a bytes-like "
"object or an iterable, got %r"
% type(message_body))
else:
# the object implements the buffer interface and
# can be passed directly into socket methods
chunks = (message_body,)
for chunk in chunks:
if not chunk:
if self.debuglevel > 0:
print('Zero length chunk ignored')
continue
if encode_chunked and self._http_vsn == 11:
# chunked encoding
chunk = f'{len(chunk):X}\r\n'.encode('ascii') + chunk \
+ b'\r\n'
self.send(chunk)
if encode_chunked and self._http_vsn == 11:
# end chunked transfer
self.send(b'0\r\n\r\n')
def putrequest(self, method, url, skip_host=False,
skip_accept_encoding=False):
"""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(self.__state)
# Save the method we use, we need it later in the response phase
self._method = method
if not url:
url = '/'
request = '%s %s %s' % (method, url, self._http_vsn_str)
# Non-ASCII characters should have been eliminated earlier
self._output(request.encode('ascii'))
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")
# As per RFC 273, IPv6 address should be wrapped with []
# when used as Host header
if host.find(':') >= 0:
host_enc = b'[' + host_enc + b']'
if port == self.default_port:
self.putheader('Host', host_enc)
else:
host_enc = host_enc.decode("ascii")
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).
# we only want a Content-Encoding of "identity" since we don't
# support encodings such as x-gzip or x-deflate.
if not skip_accept_encoding:
self.putheader('Accept-Encoding', 'identity')
# we can accept "chunked" Transfer-Encodings, but no others
# NOTE: no TE header implies *only* "chunked"
#self.putheader('TE', 'chunked')
# if TE is supplied in the header, then it must appear in a
# Connection header.
#self.putheader('Connection', 'TE')
else:
# For HTTP/1.0, the server will assume "not chunked"
pass
def putheader(self, header, *values):
"""Send a request header line to the server.
For example: h.putheader('Accept', 'text/html')
"""
if self.__state != _CS_REQ_STARTED:
raise CannotSendHeader()
if hasattr(header, 'encode'):
header = header.encode('ascii')
if not _is_legal_header_name(header):
raise ValueError('Invalid header name %r' % (header,))
values = list(values)
for i, one_value in enumerate(values):
if hasattr(one_value, 'encode'):
values[i] = one_value.encode('latin-1')
elif isinstance(one_value, int):
values[i] = str(one_value).encode('ascii')
if _is_illegal_header_value(values[i]):
raise ValueError('Invalid header value %r' % (values[i],))
value = b'\r\n\t'.join(values)
header = header + b': ' + value
self._output(header)
def endheaders(self, message_body=None, *, encode_chunked=False):
"""Indicate that the last header line has been sent to the server.
This method sends the request to the server. The optional message_body
argument can be used to pass a message body associated with the
request.
"""
if self.__state == _CS_REQ_STARTED:
self.__state = _CS_REQ_SENT
else:
raise CannotSendHeader()
self._send_output(message_body, encode_chunked=encode_chunked)
def request(self, method, url, body=None, headers={}, *,
encode_chunked=False):
"""Send a complete request to the server."""
self._send_request(method, url, body, headers, encode_chunked)
def _send_request(self, method, url, body, headers, encode_chunked):
# Honor explicitly requested Host: and Accept-Encoding: headers.
header_names = frozenset(k.lower() for k in headers)
skips = {}
if 'host' in header_names:
skips['skip_host'] = 1
if 'accept-encoding' in header_names:
skips['skip_accept_encoding'] = 1
self.putrequest(method, url, **skips)
# chunked encoding will happen if HTTP/1.1 is used and either
# the caller passes encode_chunked=True or the following
# conditions hold:
# 1. content-length has not been explicitly set
# 2. the body is a file or iterable, but not a str or bytes-like
# 3. Transfer-Encoding has NOT been explicitly set by the caller
if 'content-length' not in header_names:
# only chunk body if not explicitly set for backwards
# compatibility, assuming the client code is already handling the
# chunking
if 'transfer-encoding' not in header_names:
# if content-length cannot be automatically determined, fall
# back to chunked encoding
encode_chunked = False
content_length = self._get_content_length(body, method)
if content_length is None:
if body is not None:
if self.debuglevel > 0:
print('Unable to determine size of %r' % body)
encode_chunked = True
self.putheader('Transfer-Encoding', 'chunked')
else:
self.putheader('Content-Length', str(content_length))
else:
encode_chunked = False
for hdr, value in headers.items():
self.putheader(hdr, value)
if isinstance(body, str):
# RFC 2616 Section 3.7.1 says that text default has a
# default charset of iso-8859-1.
body = _encode(body, 'body')
self.endheaders(body, encode_chunked=encode_chunked)
def getresponse(self):
"""Get the response from the server.
If the HTTPConnection is in the correct state, returns an
instance of HTTPResponse or of whatever object is returned by
the response_class variable.
If a request has not been sent or if a previous response has
not be handled, ResponseNotReady is raised. If the HTTP
response indicates that the connection should be closed, then
it will be closed before the response is returned. When the
connection is closed, the underlying socket is closed.
"""
# if a prior response has been completed, then forget about it.
if self.__response and self.__response.isclosed():
self.__response = None
# if a prior response exists, then it must be completed (otherwise, we
# cannot read this response's header to determine the connection-close
# behavior)
#
# note: if a prior response existed, but was connection-close, then the
# socket and response were made independent of this HTTPConnection
# object since a new request requires that we open a whole new
# connection
#
# this means the prior response had one of two states:
# 1) will_close: this connection was reset and the prior socket and
# response operate independently
# 2) persistent: the response was retained and we await its
# isclosed() status to become true.
#
if self.__state != _CS_REQ_SENT or self.__response:
raise ResponseNotReady(self.__state)
if self.debuglevel > 0:
response = self.response_class(self.sock, self.debuglevel,
method=self._method)
else:
response = self.response_class(self.sock, method=self._method)
try:
try:
response.begin()
except ConnectionError:
self.close()
raise
assert response.will_close != _UNKNOWN
self.__state = _CS_IDLE
if response.will_close:
# this effectively passes the connection to the response
self.close()
else:
# remember this, so we can tell when it is complete
self.__response = response
return response
except:
response.close()
raise
try:
import ssl
except ImportError:
pass
else:
class HTTPSConnection(HTTPConnection):
"This class allows communication via SSL."
default_port = HTTPS_PORT
# XXX Should key_file and cert_file be deprecated in favour of context?
def __init__(self, host, port=None, key_file=None, cert_file=None,
timeout=socket._GLOBAL_DEFAULT_TIMEOUT,
source_address=None, *, context=None,
check_hostname=None, blocksize=8192):
super(HTTPSConnection, self).__init__(host, port, timeout,
source_address,
blocksize=blocksize)
if (key_file is not None or cert_file is not None or
check_hostname is not None):
import warnings
warnings.warn("key_file, cert_file and check_hostname are "
"deprecated, use a custom context instead.",
DeprecationWarning, 2)
self.key_file = key_file
self.cert_file = cert_file
if context is None:
context = ssl._create_default_https_context()
will_verify = context.verify_mode != ssl.CERT_NONE
if check_hostname is None:
check_hostname = context.check_hostname
if check_hostname and not will_verify:
raise ValueError("check_hostname needs a SSL context with "
"either CERT_OPTIONAL or CERT_REQUIRED")
if key_file or cert_file:
context.load_cert_chain(cert_file, key_file)
self._context = context
if check_hostname is not None:
self._context.check_hostname = check_hostname
def connect(self):
"Connect to a host on a given (SSL) port."
super().connect()
if self._tunnel_host:
server_hostname = self._tunnel_host
else:
server_hostname = self.host
self.sock = self._context.wrap_socket(self.sock,
server_hostname=server_hostname)
__all__.append("HTTPSConnection")
class HTTPException(Exception):
# Subclasses that define an __init__ must call Exception.__init__
# or define self.args. Otherwise, str() will fail.
pass
class NotConnected(HTTPException):
pass
class InvalidURL(HTTPException):
pass
class UnknownProtocol(HTTPException):
def __init__(self, version):
self.args = version,
self.version = version
class UnknownTransferEncoding(HTTPException):
pass
class UnimplementedFileMode(HTTPException):
pass
class IncompleteRead(HTTPException):
def __init__(self, partial, expected=None):
self.args = partial,
self.partial = partial
self.expected = expected
def __repr__(self):
if self.expected is not None:
e = ', %i more expected' % self.expected
else:
e = ''
return '%s(%i bytes read%s)' % (self.__class__.__name__,
len(self.partial), e)
def __str__(self):
return repr(self)
class ImproperConnectionState(HTTPException):
pass
class CannotSendRequest(ImproperConnectionState):
pass
class CannotSendHeader(ImproperConnectionState):
pass
class ResponseNotReady(ImproperConnectionState):
pass
class BadStatusLine(HTTPException):
def __init__(self, line):
if not line:
line = repr(line)
self.args = line,
self.line = line
class LineTooLong(HTTPException):
def __init__(self, line_type):
HTTPException.__init__(self, "got more than %d bytes when reading %s"
% (_MAXLINE, line_type))
class RemoteDisconnected(ConnectionResetError, BadStatusLine):
def __init__(self, *pos, **kw):
BadStatusLine.__init__(self, "")
ConnectionResetError.__init__(self, *pos, **kw)
# for backwards compatibility
error = HTTPException
|