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
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
|
r"""HTTP cookie handling for web clients.
This module has (now fairly distant) origins in Gisle Aas' Perl module
HTTP::Cookies, from the libwww-perl library.
Docstrings, comments and debug strings in this code refer to the
attributes of the HTTP cookie system as cookie-attributes, to distinguish
them clearly from Python attributes.
Class diagram (note that BSDDBCookieJar and the MSIE* classes are not
distributed with the Python standard library, but are available from
http://wwwsearch.sf.net/):
CookieJar____
/ \ \
FileCookieJar \ \
/ | \ \ \
MozillaCookieJar | LWPCookieJar \ \
| | \
| ---MSIEBase | \
| / | | \
| / MSIEDBCookieJar BSDDBCookieJar
|/
MSIECookieJar
"""
__all__ = ['Cookie', 'CookieJar', 'CookiePolicy', 'DefaultCookiePolicy',
'FileCookieJar', 'LWPCookieJar', 'LoadError', 'MozillaCookieJar']
import os
import copy
import datetime
import re
import time
import urllib.parse, urllib.request
import threading as _threading
import http.client # only for the default HTTP port
from calendar import timegm
debug = False # set to True to enable debugging via the logging module
logger = None
def _debug(*args):
if not debug:
return
global logger
if not logger:
import logging
logger = logging.getLogger("http.cookiejar")
return logger.debug(*args)
HTTPONLY_ATTR = "HTTPOnly"
HTTPONLY_PREFIX = "#HttpOnly_"
DEFAULT_HTTP_PORT = str(http.client.HTTP_PORT)
NETSCAPE_MAGIC_RGX = re.compile("#( Netscape)? HTTP Cookie File")
MISSING_FILENAME_TEXT = ("a filename was not supplied (nor was the CookieJar "
"instance initialised with one)")
NETSCAPE_HEADER_TEXT = """\
# Netscape HTTP Cookie File
# http://curl.haxx.se/rfc/cookie_spec.html
# This is a generated file! Do not edit.
"""
def _warn_unhandled_exception():
# There are a few catch-all except: statements in this module, for
# catching input that's bad in unexpected ways. Warn if any
# exceptions are caught there.
import io, warnings, traceback
f = io.StringIO()
traceback.print_exc(None, f)
msg = f.getvalue()
warnings.warn("http.cookiejar bug!\n%s" % msg, stacklevel=2)
# Date/time conversion
# -----------------------------------------------------------------------------
EPOCH_YEAR = 1970
def _timegm(tt):
year, month, mday, hour, min, sec = tt[:6]
if ((year >= EPOCH_YEAR) and (1 <= month <= 12) and (1 <= mday <= 31) and
(0 <= hour <= 24) and (0 <= min <= 59) and (0 <= sec <= 61)):
return timegm(tt)
else:
return None
DAYS = ["Mon", "Tue", "Wed", "Thu", "Fri", "Sat", "Sun"]
MONTHS = ["Jan", "Feb", "Mar", "Apr", "May", "Jun",
"Jul", "Aug", "Sep", "Oct", "Nov", "Dec"]
MONTHS_LOWER = []
for month in MONTHS: MONTHS_LOWER.append(month.lower())
def time2isoz(t=None):
"""Return a string representing time in seconds since epoch, t.
If the function is called without an argument, it will use the current
time.
The format of the returned string is like "YYYY-MM-DD hh:mm:ssZ",
representing Universal Time (UTC, aka GMT). An example of this format is:
1994-11-24 08:49:37Z
"""
if t is None:
dt = datetime.datetime.utcnow()
else:
dt = datetime.datetime.utcfromtimestamp(t)
return "%04d-%02d-%02d %02d:%02d:%02dZ" % (
dt.year, dt.month, dt.day, dt.hour, dt.minute, dt.second)
def time2netscape(t=None):
"""Return a string representing time in seconds since epoch, t.
If the function is called without an argument, it will use the current
time.
The format of the returned string is like this:
Wed, DD-Mon-YYYY HH:MM:SS GMT
"""
if t is None:
dt = datetime.datetime.utcnow()
else:
dt = datetime.datetime.utcfromtimestamp(t)
return "%s, %02d-%s-%04d %02d:%02d:%02d GMT" % (
DAYS[dt.weekday()], dt.day, MONTHS[dt.month-1],
dt.year, dt.hour, dt.minute, dt.second)
UTC_ZONES = {"GMT": None, "UTC": None, "UT": None, "Z": None}
TIMEZONE_RE = re.compile(r"^([-+])?(\d\d?):?(\d\d)?$", re.ASCII)
def offset_from_tz_string(tz):
offset = None
if tz in UTC_ZONES:
offset = 0
else:
m = TIMEZONE_RE.search(tz)
if m:
offset = 3600 * int(m.group(2))
if m.group(3):
offset = offset + 60 * int(m.group(3))
if m.group(1) == '-':
offset = -offset
return offset
def _str2time(day, mon, yr, hr, min, sec, tz):
yr = int(yr)
if yr > datetime.MAXYEAR:
return None
# translate month name to number
# month numbers start with 1 (January)
try:
mon = MONTHS_LOWER.index(mon.lower())+1
except ValueError:
# maybe it's already a number
try:
imon = int(mon)
except ValueError:
return None
if 1 <= imon <= 12:
mon = imon
else:
return None
# make sure clock elements are defined
if hr is None: hr = 0
if min is None: min = 0
if sec is None: sec = 0
day = int(day)
hr = int(hr)
min = int(min)
sec = int(sec)
if yr < 1000:
# find "obvious" year
cur_yr = time.localtime(time.time())[0]
m = cur_yr % 100
tmp = yr
yr = yr + cur_yr - m
m = m - tmp
if abs(m) > 50:
if m > 0: yr = yr + 100
else: yr = yr - 100
# convert UTC time tuple to seconds since epoch (not timezone-adjusted)
t = _timegm((yr, mon, day, hr, min, sec, tz))
if t is not None:
# adjust time using timezone string, to get absolute time since epoch
if tz is None:
tz = "UTC"
tz = tz.upper()
offset = offset_from_tz_string(tz)
if offset is None:
return None
t = t - offset
return t
STRICT_DATE_RE = re.compile(
r"^[SMTWF][a-z][a-z], (\d\d) ([JFMASOND][a-z][a-z]) "
r"(\d\d\d\d) (\d\d):(\d\d):(\d\d) GMT$", re.ASCII)
WEEKDAY_RE = re.compile(
r"^(?:Sun|Mon|Tue|Wed|Thu|Fri|Sat)[a-z]*,?\s*", re.I | re.ASCII)
LOOSE_HTTP_DATE_RE = re.compile(
r"""^
(\d\d?) # day
(?:\s+|[-\/])
(\w+) # month
(?:\s+|[-\/])
(\d+) # year
(?:
(?:\s+|:) # separator before clock
(\d\d?):(\d\d) # hour:min
(?::(\d\d))? # optional seconds
)? # optional clock
\s*
(?:
([-+]?\d{2,4}|(?![APap][Mm]\b)[A-Za-z]+) # timezone
\s*
)?
(?:
\(\w+\) # ASCII representation of timezone in parens.
\s*
)?$""", re.X | re.ASCII)
def http2time(text):
"""Returns time in seconds since epoch of time represented by a string.
Return value is an integer.
None is returned if the format of str is unrecognized, the time is outside
the representable range, or the timezone string is not recognized. If the
string contains no timezone, UTC is assumed.
The timezone in the string may be numerical (like "-0800" or "+0100") or a
string timezone (like "UTC", "GMT", "BST" or "EST"). Currently, only the
timezone strings equivalent to UTC (zero offset) are known to the function.
The function loosely parses the following formats:
Wed, 09 Feb 1994 22:23:32 GMT -- HTTP format
Tuesday, 08-Feb-94 14:15:29 GMT -- old rfc850 HTTP format
Tuesday, 08-Feb-1994 14:15:29 GMT -- broken rfc850 HTTP format
09 Feb 1994 22:23:32 GMT -- HTTP format (no weekday)
08-Feb-94 14:15:29 GMT -- rfc850 format (no weekday)
08-Feb-1994 14:15:29 GMT -- broken rfc850 format (no weekday)
The parser ignores leading and trailing whitespace. The time may be
absent.
If the year is given with only 2 digits, the function will select the
century that makes the year closest to the current date.
"""
# fast exit for strictly conforming string
m = STRICT_DATE_RE.search(text)
if m:
g = m.groups()
mon = MONTHS_LOWER.index(g[1].lower()) + 1
tt = (int(g[2]), mon, int(g[0]),
int(g[3]), int(g[4]), float(g[5]))
return _timegm(tt)
# No, we need some messy parsing...
# clean up
text = text.lstrip()
text = WEEKDAY_RE.sub("", text, 1) # Useless weekday
# tz is time zone specifier string
day, mon, yr, hr, min, sec, tz = [None]*7
# loose regexp parse
m = LOOSE_HTTP_DATE_RE.search(text)
if m is not None:
day, mon, yr, hr, min, sec, tz = m.groups()
else:
return None # bad format
return _str2time(day, mon, yr, hr, min, sec, tz)
ISO_DATE_RE = re.compile(
r"""^
(\d{4}) # year
[-\/]?
(\d\d?) # numerical month
[-\/]?
(\d\d?) # day
(?:
(?:\s+|[-:Tt]) # separator before clock
(\d\d?):?(\d\d) # hour:min
(?::?(\d\d(?:\.\d*)?))? # optional seconds (and fractional)
)? # optional clock
\s*
(?:
([-+]?\d\d?:?(:?\d\d)?
|Z|z) # timezone (Z is "zero meridian", i.e. GMT)
\s*
)?$""", re.X | re. ASCII)
def iso2time(text):
"""
As for http2time, but parses the ISO 8601 formats:
1994-02-03 14:15:29 -0100 -- ISO 8601 format
1994-02-03 14:15:29 -- zone is optional
1994-02-03 -- only date
1994-02-03T14:15:29 -- Use T as separator
19940203T141529Z -- ISO 8601 compact format
19940203 -- only date
"""
# clean up
text = text.lstrip()
# tz is time zone specifier string
day, mon, yr, hr, min, sec, tz = [None]*7
# loose regexp parse
m = ISO_DATE_RE.search(text)
if m is not None:
# XXX there's an extra bit of the timezone I'm ignoring here: is
# this the right thing to do?
yr, mon, day, hr, min, sec, tz, _ = m.groups()
else:
return None # bad format
return _str2time(day, mon, yr, hr, min, sec, tz)
# Header parsing
# -----------------------------------------------------------------------------
def unmatched(match):
"""Return unmatched part of re.Match object."""
start, end = match.span(0)
return match.string[:start]+match.string[end:]
HEADER_TOKEN_RE = re.compile(r"^\s*([^=\s;,]+)")
HEADER_QUOTED_VALUE_RE = re.compile(r"^\s*=\s*\"([^\"\\]*(?:\\.[^\"\\]*)*)\"")
HEADER_VALUE_RE = re.compile(r"^\s*=\s*([^\s;,]*)")
HEADER_ESCAPE_RE = re.compile(r"\\(.)")
def split_header_words(header_values):
r"""Parse header values into a list of lists containing key,value pairs.
The function knows how to deal with ",", ";" and "=" as well as quoted
values after "=". A list of space separated tokens are parsed as if they
were separated by ";".
If the header_values passed as argument contains multiple values, then they
are treated as if they were a single value separated by comma ",".
This means that this function is useful for parsing header fields that
follow this syntax (BNF as from the HTTP/1.1 specification, but we relax
the requirement for tokens).
headers = #header
header = (token | parameter) *( [";"] (token | parameter))
token = 1*<any CHAR except CTLs or separators>
separators = "(" | ")" | "<" | ">" | "@"
| "," | ";" | ":" | "\" | <">
| "/" | "[" | "]" | "?" | "="
| "{" | "}" | SP | HT
quoted-string = ( <"> *(qdtext | quoted-pair ) <"> )
qdtext = <any TEXT except <">>
quoted-pair = "\" CHAR
parameter = attribute "=" value
attribute = token
value = token | quoted-string
Each header is represented by a list of key/value pairs. The value for a
simple token (not part of a parameter) is None. Syntactically incorrect
headers will not necessarily be parsed as you would want.
This is easier to describe with some examples:
>>> split_header_words(['foo="bar"; port="80,81"; discard, bar=baz'])
[[('foo', 'bar'), ('port', '80,81'), ('discard', None)], [('bar', 'baz')]]
>>> split_header_words(['text/html; charset="iso-8859-1"'])
[[('text/html', None), ('charset', 'iso-8859-1')]]
>>> split_header_words([r'Basic realm="\"foo\bar\""'])
[[('Basic', None), ('realm', '"foobar"')]]
"""
assert not isinstance(header_values, str)
result = []
for text in header_values:
orig_text = text
pairs = []
while text:
m = HEADER_TOKEN_RE.search(text)
if m:
text = unmatched(m)
name = m.group(1)
m = HEADER_QUOTED_VALUE_RE.search(text)
if m: # quoted value
text = unmatched(m)
value = m.group(1)
value = HEADER_ESCAPE_RE.sub(r"\1", value)
else:
m = HEADER_VALUE_RE.search(text)
if m: # unquoted value
text = unmatched(m)
value = m.group(1)
value = value.rstrip()
else:
# no value, a lone token
value = None
pairs.append((name, value))
elif text.lstrip().startswith(","):
# concatenated headers, as per RFC 2616 section 4.2
text = text.lstrip()[1:]
if pairs: result.append(pairs)
pairs = []
else:
# skip junk
non_junk, nr_junk_chars = re.subn(r"^[=\s;]*", "", text)
assert nr_junk_chars > 0, (
"split_header_words bug: '%s', '%s', %s" %
(orig_text, text, pairs))
text = non_junk
if pairs: result.append(pairs)
return result
HEADER_JOIN_ESCAPE_RE = re.compile(r"([\"\\])")
def join_header_words(lists):
"""Do the inverse (almost) of the conversion done by split_header_words.
Takes a list of lists of (key, value) pairs and produces a single header
value. Attribute values are quoted if needed.
>>> join_header_words([[("text/plain", None), ("charset", "iso-8859-1")]])
'text/plain; charset="iso-8859-1"'
>>> join_header_words([[("text/plain", None)], [("charset", "iso-8859-1")]])
'text/plain, charset="iso-8859-1"'
"""
headers = []
for pairs in lists:
attr = []
for k, v in pairs:
if v is not None:
if not re.search(r"^\w+$", v):
v = HEADER_JOIN_ESCAPE_RE.sub(r"\\\1", v) # escape " and \
v = '"%s"' % v
k = "%s=%s" % (k, v)
attr.append(k)
if attr: headers.append("; ".join(attr))
return ", ".join(headers)
def strip_quotes(text):
if text.startswith('"'):
text = text[1:]
if text.endswith('"'):
text = text[:-1]
return text
def parse_ns_headers(ns_headers):
"""Ad-hoc parser for Netscape protocol cookie-attributes.
The old Netscape cookie format for Set-Cookie can for instance contain
an unquoted "," in the expires field, so we have to use this ad-hoc
parser instead of split_header_words.
XXX This may not make the best possible effort to parse all the crap
that Netscape Cookie headers contain. Ronald Tschalar's HTTPClient
parser is probably better, so could do worse than following that if
this ever gives any trouble.
Currently, this is also used for parsing RFC 2109 cookies.
"""
known_attrs = ("expires", "domain", "path", "secure",
# RFC 2109 attrs (may turn up in Netscape cookies, too)
"version", "port", "max-age")
result = []
for ns_header in ns_headers:
pairs = []
version_set = False
# XXX: The following does not strictly adhere to RFCs in that empty
# names and values are legal (the former will only appear once and will
# be overwritten if multiple occurrences are present). This is
# mostly to deal with backwards compatibility.
for ii, param in enumerate(ns_header.split(';')):
param = param.strip()
key, sep, val = param.partition('=')
key = key.strip()
if not key:
if ii == 0:
break
else:
continue
# allow for a distinction between present and empty and missing
# altogether
val = val.strip() if sep else None
if ii != 0:
lc = key.lower()
if lc in known_attrs:
key = lc
if key == "version":
# This is an RFC 2109 cookie.
if val is not None:
val = strip_quotes(val)
version_set = True
elif key == "expires":
# convert expires date to seconds since epoch
if val is not None:
val = http2time(strip_quotes(val)) # None if invalid
pairs.append((key, val))
if pairs:
if not version_set:
pairs.append(("version", "0"))
result.append(pairs)
return result
IPV4_RE = re.compile(r"\.\d+$", re.ASCII)
def is_HDN(text):
"""Return True if text is a host domain name."""
# XXX
# This may well be wrong. Which RFC is HDN defined in, if any (for
# the purposes of RFC 2965)?
# For the current implementation, what about IPv6? Remember to look
# at other uses of IPV4_RE also, if change this.
if IPV4_RE.search(text):
return False
if text == "":
return False
if text[0] == "." or text[-1] == ".":
return False
return True
def domain_match(A, B):
"""Return True if domain A domain-matches domain B, according to RFC 2965.
A and B may be host domain names or IP addresses.
RFC 2965, section 1:
Host names can be specified either as an IP address or a HDN string.
Sometimes we compare one host name with another. (Such comparisons SHALL
be case-insensitive.) Host A's name domain-matches host B's if
* their host name strings string-compare equal; or
* A is a HDN string and has the form NB, where N is a non-empty
name string, B has the form .B', and B' is a HDN string. (So,
x.y.com domain-matches .Y.com but not Y.com.)
Note that domain-match is not a commutative operation: a.b.c.com
domain-matches .c.com, but not the reverse.
"""
# Note that, if A or B are IP addresses, the only relevant part of the
# definition of the domain-match algorithm is the direct string-compare.
A = A.lower()
B = B.lower()
if A == B:
return True
if not is_HDN(A):
return False
i = A.rfind(B)
if i == -1 or i == 0:
# A does not have form NB, or N is the empty string
return False
if not B.startswith("."):
return False
if not is_HDN(B[1:]):
return False
return True
def liberal_is_HDN(text):
"""Return True if text is a sort-of-like a host domain name.
For accepting/blocking domains.
"""
if IPV4_RE.search(text):
return False
return True
def user_domain_match(A, B):
"""For blocking/accepting domains.
A and B may be host domain names or IP addresses.
"""
A = A.lower()
B = B.lower()
if not (liberal_is_HDN(A) and liberal_is_HDN(B)):
if A == B:
# equal IP addresses
return True
return False
initial_dot = B.startswith(".")
if initial_dot and A.endswith(B):
return True
if not initial_dot and A == B:
return True
return False
cut_port_re = re.compile(r":\d+$", re.ASCII)
def request_host(request):
"""Return request-host, as defined by RFC 2965.
Variation from RFC: returned value is lowercased, for convenient
comparison.
"""
url = request.get_full_url()
host = urllib.parse.urlparse(url)[1]
if host == "":
host = request.get_header("Host", "")
# remove port, if present
host = cut_port_re.sub("", host, 1)
return host.lower()
def eff_request_host(request):
"""Return a tuple (request-host, effective request-host name).
As defined by RFC 2965, except both are lowercased.
"""
erhn = req_host = request_host(request)
if req_host.find(".") == -1 and not IPV4_RE.search(req_host):
erhn = req_host + ".local"
return req_host, erhn
def request_path(request):
"""Path component of request-URI, as defined by RFC 2965."""
url = request.get_full_url()
parts = urllib.parse.urlsplit(url)
path = escape_path(parts.path)
if not path.startswith("/"):
# fix bad RFC 2396 absoluteURI
path = "/" + path
return path
def request_port(request):
host = request.host
i = host.find(':')
if i >= 0:
port = host[i+1:]
try:
int(port)
except ValueError:
_debug("nonnumeric port: '%s'", port)
return None
else:
port = DEFAULT_HTTP_PORT
return port
# Characters in addition to A-Z, a-z, 0-9, '_', '.', and '-' that don't
# need to be escaped to form a valid HTTP URL (RFCs 2396 and 1738).
HTTP_PATH_SAFE = "%/;:@&=+$,!~*'()"
ESCAPED_CHAR_RE = re.compile(r"%([0-9a-fA-F][0-9a-fA-F])")
def uppercase_escaped_char(match):
return "%%%s" % match.group(1).upper()
def escape_path(path):
"""Escape any invalid characters in HTTP URL, and uppercase all escapes."""
# There's no knowing what character encoding was used to create URLs
# containing %-escapes, but since we have to pick one to escape invalid
# path characters, we pick UTF-8, as recommended in the HTML 4.0
# specification:
# http://www.w3.org/TR/REC-html40/appendix/notes.html#h-B.2.1
# And here, kind of: draft-fielding-uri-rfc2396bis-03
# (And in draft IRI specification: draft-duerst-iri-05)
# (And here, for new URI schemes: RFC 2718)
path = urllib.parse.quote(path, HTTP_PATH_SAFE)
path = ESCAPED_CHAR_RE.sub(uppercase_escaped_char, path)
return path
def reach(h):
"""Return reach of host h, as defined by RFC 2965, section 1.
The reach R of a host name H is defined as follows:
* If
- H is the host domain name of a host; and,
- H has the form A.B; and
- A has no embedded (that is, interior) dots; and
- B has at least one embedded dot, or B is the string "local".
then the reach of H is .B.
* Otherwise, the reach of H is H.
>>> reach("www.acme.com")
'.acme.com'
>>> reach("acme.com")
'acme.com'
>>> reach("acme.local")
'.local'
"""
i = h.find(".")
if i >= 0:
#a = h[:i] # this line is only here to show what a is
b = h[i+1:]
i = b.find(".")
if is_HDN(h) and (i >= 0 or b == "local"):
return "."+b
return h
def is_third_party(request):
"""
RFC 2965, section 3.3.6:
An unverifiable transaction is to a third-party host if its request-
host U does not domain-match the reach R of the request-host O in the
origin transaction.
"""
req_host = request_host(request)
if not domain_match(req_host, reach(request.origin_req_host)):
return True
else:
return False
class Cookie:
"""HTTP Cookie.
This class represents both Netscape and RFC 2965 cookies.
This is deliberately a very simple class. It just holds attributes. It's
possible to construct Cookie instances that don't comply with the cookie
standards. CookieJar.make_cookies is the factory function for Cookie
objects -- it deals with cookie parsing, supplying defaults, and
normalising to the representation used in this class. CookiePolicy is
responsible for checking them to see whether they should be accepted from
and returned to the server.
Note that the port may be present in the headers, but unspecified ("Port"
rather than"Port=80", for example); if this is the case, port is None.
"""
def __init__(self, version, name, value,
port, port_specified,
domain, domain_specified, domain_initial_dot,
path, path_specified,
secure,
expires,
discard,
comment,
comment_url,
rest,
rfc2109=False,
):
if version is not None: version = int(version)
if expires is not None: expires = int(float(expires))
if port is None and port_specified is True:
raise ValueError("if port is None, port_specified must be false")
self.version = version
self.name = name
self.value = value
self.port = port
self.port_specified = port_specified
# normalise case, as per RFC 2965 section 3.3.3
self.domain = domain.lower()
self.domain_specified = domain_specified
# Sigh. We need to know whether the domain given in the
# cookie-attribute had an initial dot, in order to follow RFC 2965
# (as clarified in draft errata). Needed for the returned $Domain
# value.
self.domain_initial_dot = domain_initial_dot
self.path = path
self.path_specified = path_specified
self.secure = secure
self.expires = expires
self.discard = discard
self.comment = comment
self.comment_url = comment_url
self.rfc2109 = rfc2109
self._rest = copy.copy(rest)
def has_nonstandard_attr(self, name):
return name in self._rest
def get_nonstandard_attr(self, name, default=None):
return self._rest.get(name, default)
def set_nonstandard_attr(self, name, value):
self._rest[name] = value
def is_expired(self, now=None):
if now is None: now = time.time()
if (self.expires is not None) and (self.expires <= now):
return True
return False
def __str__(self):
if self.port is None: p = ""
else: p = ":"+self.port
limit = self.domain + p + self.path
if self.value is not None:
namevalue = "%s=%s" % (self.name, self.value)
else:
namevalue = self.name
return "<Cookie %s for %s>" % (namevalue, limit)
def __repr__(self):
args = []
for name in ("version", "name", "value",
"port", "port_specified",
"domain", "domain_specified", "domain_initial_dot",
"path", "path_specified",
"secure", "expires", "discard", "comment", "comment_url",
):
attr = getattr(self, name)
args.append("%s=%s" % (name, repr(attr)))
args.append("rest=%s" % repr(self._rest))
args.append("rfc2109=%s" % repr(self.rfc2109))
return "%s(%s)" % (self.__class__.__name__, ", ".join(args))
class CookiePolicy:
"""Defines which cookies get accepted from and returned to server.
May also modify cookies, though this is probably a bad idea.
The subclass DefaultCookiePolicy defines the standard rules for Netscape
and RFC 2965 cookies -- override that if you want a customized policy.
"""
def set_ok(self, cookie, request):
"""Return true if (and only if) cookie should be accepted from server.
Currently, pre-expired cookies never get this far -- the CookieJar
class deletes such cookies itself.
"""
raise NotImplementedError()
def return_ok(self, cookie, request):
"""Return true if (and only if) cookie should be returned to server."""
raise NotImplementedError()
def domain_return_ok(self, domain, request):
"""Return false if cookies should not be returned, given cookie domain.
"""
return True
def path_return_ok(self, path, request):
"""Return false if cookies should not be returned, given cookie path.
"""
return True
class DefaultCookiePolicy(CookiePolicy):
"""Implements the standard rules for accepting and returning cookies."""
DomainStrictNoDots = 1
DomainStrictNonDomain = 2
DomainRFC2965Match = 4
DomainLiberal = 0
DomainStrict = DomainStrictNoDots|DomainStrictNonDomain
def __init__(self,
blocked_domains=None, allowed_domains=None,
netscape=True, rfc2965=False,
rfc2109_as_netscape=None,
hide_cookie2=False,
strict_domain=False,
strict_rfc2965_unverifiable=True,
strict_ns_unverifiable=False,
strict_ns_domain=DomainLiberal,
strict_ns_set_initial_dollar=False,
strict_ns_set_path=False,
secure_protocols=("https", "wss")
):
"""Constructor arguments should be passed as keyword arguments only."""
self.netscape = netscape
self.rfc2965 = rfc2965
self.rfc2109_as_netscape = rfc2109_as_netscape
self.hide_cookie2 = hide_cookie2
self.strict_domain = strict_domain
self.strict_rfc2965_unverifiable = strict_rfc2965_unverifiable
self.strict_ns_unverifiable = strict_ns_unverifiable
self.strict_ns_domain = strict_ns_domain
self.strict_ns_set_initial_dollar = strict_ns_set_initial_dollar
self.strict_ns_set_path = strict_ns_set_path
self.secure_protocols = secure_protocols
if blocked_domains is not None:
self._blocked_domains = tuple(blocked_domains)
else:
self._blocked_domains = ()
if allowed_domains is not None:
allowed_domains = tuple(allowed_domains)
self._allowed_domains = allowed_domains
def blocked_domains(self):
"""Return the sequence of blocked domains (as a tuple)."""
return self._blocked_domains
def set_blocked_domains(self, blocked_domains):
"""Set the sequence of blocked domains."""
self._blocked_domains = tuple(blocked_domains)
def is_blocked(self, domain):
for blocked_domain in self._blocked_domains:
if user_domain_match(domain, blocked_domain):
return True
return False
def allowed_domains(self):
"""Return None, or the sequence of allowed domains (as a tuple)."""
return self._allowed_domains
def set_allowed_domains(self, allowed_domains):
"""Set the sequence of allowed domains, or None."""
if allowed_domains is not None:
allowed_domains = tuple(allowed_domains)
self._allowed_domains = allowed_domains
def is_not_allowed(self, domain):
if self._allowed_domains is None:
return False
for allowed_domain in self._allowed_domains:
if user_domain_match(domain, allowed_domain):
return False
return True
def set_ok(self, cookie, request):
"""
If you override .set_ok(), be sure to call this method. If it returns
false, so should your subclass (assuming your subclass wants to be more
strict about which cookies to accept).
"""
_debug(" - checking cookie %s=%s", cookie.name, cookie.value)
assert cookie.name is not None
for n in "version", "verifiability", "name", "path", "domain", "port":
fn_name = "set_ok_"+n
fn = getattr(self, fn_name)
if not fn(cookie, request):
return False
return True
def set_ok_version(self, cookie, request):
if cookie.version is None:
# Version is always set to 0 by parse_ns_headers if it's a Netscape
# cookie, so this must be an invalid RFC 2965 cookie.
_debug(" Set-Cookie2 without version attribute (%s=%s)",
cookie.name, cookie.value)
return False
if cookie.version > 0 and not self.rfc2965:
_debug(" RFC 2965 cookies are switched off")
return False
elif cookie.version == 0 and not self.netscape:
_debug(" Netscape cookies are switched off")
return False
return True
def set_ok_verifiability(self, cookie, request):
if request.unverifiable and is_third_party(request):
if cookie.version > 0 and self.strict_rfc2965_unverifiable:
_debug(" third-party RFC 2965 cookie during "
"unverifiable transaction")
return False
elif cookie.version == 0 and self.strict_ns_unverifiable:
_debug(" third-party Netscape cookie during "
"unverifiable transaction")
return False
return True
def set_ok_name(self, cookie, request):
# Try and stop servers setting V0 cookies designed to hack other
# servers that know both V0 and V1 protocols.
if (cookie.version == 0 and self.strict_ns_set_initial_dollar and
cookie.name.startswith("$")):
_debug(" illegal name (starts with '$'): '%s'", cookie.name)
return False
return True
def set_ok_path(self, cookie, request):
if cookie.path_specified:
req_path = request_path(request)
if ((cookie.version > 0 or
(cookie.version == 0 and self.strict_ns_set_path)) and
not self.path_return_ok(cookie.path, request)):
_debug(" path attribute %s is not a prefix of request "
"path %s", cookie.path, req_path)
return False
return True
def set_ok_domain(self, cookie, request):
if self.is_blocked(cookie.domain):
_debug(" domain %s is in user block-list", cookie.domain)
return False
if self.is_not_allowed(cookie.domain):
_debug(" domain %s is not in user allow-list", cookie.domain)
return False
if cookie.domain_specified:
req_host, erhn = eff_request_host(request)
domain = cookie.domain
if self.strict_domain and (domain.count(".") >= 2):
# XXX This should probably be compared with the Konqueror
# (kcookiejar.cpp) and Mozilla implementations, but it's a
# losing battle.
i = domain.rfind(".")
j = domain.rfind(".", 0, i)
if j == 0: # domain like .foo.bar
tld = domain[i+1:]
sld = domain[j+1:i]
if sld.lower() in ("co", "ac", "com", "edu", "org", "net",
"gov", "mil", "int", "aero", "biz", "cat", "coop",
"info", "jobs", "mobi", "museum", "name", "pro",
"travel", "eu") and len(tld) == 2:
# domain like .co.uk
_debug(" country-code second level domain %s", domain)
return False
if domain.startswith("."):
undotted_domain = domain[1:]
else:
undotted_domain = domain
embedded_dots = (undotted_domain.find(".") >= 0)
if not embedded_dots and domain != ".local":
_debug(" non-local domain %s contains no embedded dot",
domain)
return False
if cookie.version == 0:
if (not erhn.endswith(domain) and
(not erhn.startswith(".") and
not ("."+erhn).endswith(domain))):
_debug(" effective request-host %s (even with added "
"initial dot) does not end with %s",
erhn, domain)
return False
if (cookie.version > 0 or
(self.strict_ns_domain & self.DomainRFC2965Match)):
if not domain_match(erhn, domain):
_debug(" effective request-host %s does not domain-match "
"%s", erhn, domain)
return False
if (cookie.version > 0 or
(self.strict_ns_domain & self.DomainStrictNoDots)):
host_prefix = req_host[:-len(domain)]
if (host_prefix.find(".") >= 0 and
not IPV4_RE.search(req_host)):
_debug(" host prefix %s for domain %s contains a dot",
host_prefix, domain)
return False
return True
def set_ok_port(self, cookie, request):
if cookie.port_specified:
req_port = request_port(request)
if req_port is None:
req_port = "80"
else:
req_port = str(req_port)
for p in cookie.port.split(","):
try:
int(p)
except ValueError:
_debug(" bad port %s (not numeric)", p)
return False
if p == req_port:
break
else:
_debug(" request port (%s) not found in %s",
req_port, cookie.port)
return False
return True
def return_ok(self, cookie, request):
"""
If you override .return_ok(), be sure to call this method. If it
returns false, so should your subclass (assuming your subclass wants to
be more strict about which cookies to return).
"""
# Path has already been checked by .path_return_ok(), and domain
# blocking done by .domain_return_ok().
_debug(" - checking cookie %s=%s", cookie.name, cookie.value)
for n in "version", "verifiability", "secure", "expires", "port", "domain":
fn_name = "return_ok_"+n
fn = getattr(self, fn_name)
if not fn(cookie, request):
return False
return True
def return_ok_version(self, cookie, request):
if cookie.version > 0 and not self.rfc2965:
_debug(" RFC 2965 cookies are switched off")
return False
elif cookie.version == 0 and not self.netscape:
_debug(" Netscape cookies are switched off")
return False
return True
def return_ok_verifiability(self, cookie, request):
if request.unverifiable and is_third_party(request):
if cookie.version > 0 and self.strict_rfc2965_unverifiable:
_debug(" third-party RFC 2965 cookie during unverifiable "
"transaction")
return False
elif cookie.version == 0 and self.strict_ns_unverifiable:
_debug(" third-party Netscape cookie during unverifiable "
"transaction")
return False
return True
def return_ok_secure(self, cookie, request):
if cookie.secure and request.type not in self.secure_protocols:
_debug(" secure cookie with non-secure request")
return False
return True
def return_ok_expires(self, cookie, request):
if cookie.is_expired(self._now):
_debug(" cookie expired")
return False
return True
def return_ok_port(self, cookie, request):
if cookie.port:
req_port = request_port(request)
if req_port is None:
req_port = "80"
for p in cookie.port.split(","):
if p == req_port:
break
else:
_debug(" request port %s does not match cookie port %s",
req_port, cookie.port)
return False
return True
def return_ok_domain(self, cookie, request):
req_host, erhn = eff_request_host(request)
domain = cookie.domain
if domain and not domain.startswith("."):
dotdomain = "." + domain
else:
dotdomain = domain
# strict check of non-domain cookies: Mozilla does this, MSIE5 doesn't
if (cookie.version == 0 and
(self.strict_ns_domain & self.DomainStrictNonDomain) and
not cookie.domain_specified and domain != erhn):
_debug(" cookie with unspecified domain does not string-compare "
"equal to request domain")
return False
if cookie.version > 0 and not domain_match(erhn, domain):
_debug(" effective request-host name %s does not domain-match "
"RFC 2965 cookie domain %s", erhn, domain)
return False
if cookie.version == 0 and not ("."+erhn).endswith(dotdomain):
_debug(" request-host %s does not match Netscape cookie domain "
"%s", req_host, domain)
return False
return True
def domain_return_ok(self, domain, request):
# Liberal check of. This is here as an optimization to avoid
# having to load lots of MSIE cookie files unless necessary.
req_host, erhn = eff_request_host(request)
if not req_host.startswith("."):
req_host = "."+req_host
if not erhn.startswith("."):
erhn = "."+erhn
if domain and not domain.startswith("."):
dotdomain = "." + domain
else:
dotdomain = domain
if not (req_host.endswith(dotdomain) or erhn.endswith(dotdomain)):
#_debug(" request domain %s does not match cookie domain %s",
# req_host, domain)
return False
if self.is_blocked(domain):
_debug(" domain %s is in user block-list", domain)
return False
if self.is_not_allowed(domain):
_debug(" domain %s is not in user allow-list", domain)
return False
return True
def path_return_ok(self, path, request):
_debug("- checking cookie path=%s", path)
req_path = request_path(request)
pathlen = len(path)
if req_path == path:
return True
elif (req_path.startswith(path) and
(path.endswith("/") or req_path[pathlen:pathlen+1] == "/")):
return True
_debug(" %s does not path-match %s", req_path, path)
return False
def vals_sorted_by_key(adict):
keys = sorted(adict.keys())
return map(adict.get, keys)
def deepvalues(mapping):
"""Iterates over nested mapping, depth-first, in sorted order by key."""
values = vals_sorted_by_key(mapping)
for obj in values:
mapping = False
try:
obj.items
except AttributeError:
pass
else:
mapping = True
yield from deepvalues(obj)
if not mapping:
yield obj
# Used as second parameter to dict.get() method, to distinguish absent
# dict key from one with a None value.
class Absent: pass
class CookieJar:
"""Collection of HTTP cookies.
You may not need to know about this class: try
urllib.request.build_opener(HTTPCookieProcessor).open(url).
"""
non_word_re = re.compile(r"\W")
quote_re = re.compile(r"([\"\\])")
strict_domain_re = re.compile(r"\.?[^.]*")
domain_re = re.compile(r"[^.]*")
dots_re = re.compile(r"^\.+")
magic_re = re.compile(r"^\#LWP-Cookies-(\d+\.\d+)", re.ASCII)
def __init__(self, policy=None):
if policy is None:
policy = DefaultCookiePolicy()
self._policy = policy
self._cookies_lock = _threading.RLock()
self._cookies = {}
def set_policy(self, policy):
self._policy = policy
def _cookies_for_domain(self, domain, request):
cookies = []
if not self._policy.domain_return_ok(domain, request):
return []
_debug("Checking %s for cookies to return", domain)
cookies_by_path = self._cookies[domain]
for path in cookies_by_path.keys():
if not self._policy.path_return_ok(path, request):
continue
cookies_by_name = cookies_by_path[path]
for cookie in cookies_by_name.values():
if not self._policy.return_ok(cookie, request):
_debug(" not returning cookie")
continue
_debug(" it's a match")
cookies.append(cookie)
return cookies
def _cookies_for_request(self, request):
"""Return a list of cookies to be returned to server."""
cookies = []
for domain in self._cookies.keys():
cookies.extend(self._cookies_for_domain(domain, request))
return cookies
def _cookie_attrs(self, cookies):
"""Return a list of cookie-attributes to be returned to server.
like ['foo="bar"; $Path="/"', ...]
The $Version attribute is also added when appropriate (currently only
once per request).
"""
# add cookies in order of most specific (ie. longest) path first
cookies.sort(key=lambda a: len(a.path), reverse=True)
version_set = False
attrs = []
for cookie in cookies:
# set version of Cookie header
# XXX
# What should it be if multiple matching Set-Cookie headers have
# different versions themselves?
# Answer: there is no answer; was supposed to be settled by
# RFC 2965 errata, but that may never appear...
version = cookie.version
if not version_set:
version_set = True
if version > 0:
attrs.append("$Version=%s" % version)
# quote cookie value if necessary
# (not for Netscape protocol, which already has any quotes
# intact, due to the poorly-specified Netscape Cookie: syntax)
if ((cookie.value is not None) and
self.non_word_re.search(cookie.value) and version > 0):
value = self.quote_re.sub(r"\\\1", cookie.value)
else:
value = cookie.value
# add cookie-attributes to be returned in Cookie header
if cookie.value is None:
attrs.append(cookie.name)
else:
attrs.append("%s=%s" % (cookie.name, value))
if version > 0:
if cookie.path_specified:
attrs.append('$Path="%s"' % cookie.path)
if cookie.domain.startswith("."):
domain = cookie.domain
if (not cookie.domain_initial_dot and
domain.startswith(".")):
domain = domain[1:]
attrs.append('$Domain="%s"' % domain)
if cookie.port is not None:
p = "$Port"
if cookie.port_specified:
p = p + ('="%s"' % cookie.port)
attrs.append(p)
return attrs
def add_cookie_header(self, request):
"""Add correct Cookie: header to request (urllib.request.Request object).
The Cookie2 header is also added unless policy.hide_cookie2 is true.
"""
_debug("add_cookie_header")
self._cookies_lock.acquire()
try:
self._policy._now = self._now = int(time.time())
cookies = self._cookies_for_request(request)
attrs = self._cookie_attrs(cookies)
if attrs:
if not request.has_header("Cookie"):
request.add_unredirected_header(
"Cookie", "; ".join(attrs))
# if necessary, advertise that we know RFC 2965
if (self._policy.rfc2965 and not self._policy.hide_cookie2 and
not request.has_header("Cookie2")):
for cookie in cookies:
if cookie.version != 1:
request.add_unredirected_header("Cookie2", '$Version="1"')
break
finally:
self._cookies_lock.release()
self.clear_expired_cookies()
def _normalized_cookie_tuples(self, attrs_set):
"""Return list of tuples containing normalised cookie information.
attrs_set is the list of lists of key,value pairs extracted from
the Set-Cookie or Set-Cookie2 headers.
Tuples are name, value, standard, rest, where name and value are the
cookie name and value, standard is a dictionary containing the standard
cookie-attributes (discard, secure, version, expires or max-age,
domain, path and port) and rest is a dictionary containing the rest of
the cookie-attributes.
"""
cookie_tuples = []
boolean_attrs = "discard", "secure"
value_attrs = ("version",
"expires", "max-age",
"domain", "path", "port",
"comment", "commenturl")
for cookie_attrs in attrs_set:
name, value = cookie_attrs[0]
# Build dictionary of standard cookie-attributes (standard) and
# dictionary of other cookie-attributes (rest).
# Note: expiry time is normalised to seconds since epoch. V0
# cookies should have the Expires cookie-attribute, and V1 cookies
# should have Max-Age, but since V1 includes RFC 2109 cookies (and
# since V0 cookies may be a mish-mash of Netscape and RFC 2109), we
# accept either (but prefer Max-Age).
max_age_set = False
bad_cookie = False
standard = {}
rest = {}
for k, v in cookie_attrs[1:]:
lc = k.lower()
# don't lose case distinction for unknown fields
if lc in value_attrs or lc in boolean_attrs:
k = lc
if k in boolean_attrs and v is None:
# boolean cookie-attribute is present, but has no value
# (like "discard", rather than "port=80")
v = True
if k in standard:
# only first value is significant
continue
if k == "domain":
if v is None:
_debug(" missing value for domain attribute")
bad_cookie = True
break
# RFC 2965 section 3.3.3
v = v.lower()
if k == "expires":
if max_age_set:
# Prefer max-age to expires (like Mozilla)
continue
if v is None:
_debug(" missing or invalid value for expires "
"attribute: treating as session cookie")
continue
if k == "max-age":
max_age_set = True
try:
v = int(v)
except ValueError:
_debug(" missing or invalid (non-numeric) value for "
"max-age attribute")
bad_cookie = True
break
# convert RFC 2965 Max-Age to seconds since epoch
# XXX Strictly you're supposed to follow RFC 2616
# age-calculation rules. Remember that zero Max-Age
# is a request to discard (old and new) cookie, though.
k = "expires"
v = self._now + v
if (k in value_attrs) or (k in boolean_attrs):
if (v is None and
k not in ("port", "comment", "commenturl")):
_debug(" missing value for %s attribute" % k)
bad_cookie = True
break
standard[k] = v
else:
rest[k] = v
if bad_cookie:
continue
cookie_tuples.append((name, value, standard, rest))
return cookie_tuples
def _cookie_from_cookie_tuple(self, tup, request):
# standard is dict of standard cookie-attributes, rest is dict of the
# rest of them
name, value, standard, rest = tup
domain = standard.get("domain", Absent)
path = standard.get("path", Absent)
port = standard.get("port", Absent)
expires = standard.get("expires", Absent)
# set the easy defaults
version = standard.get("version", None)
if version is not None:
try:
version = int(version)
except ValueError:
return None # invalid version, ignore cookie
secure = standard.get("secure", False)
# (discard is also set if expires is Absent)
discard = standard.get("discard", False)
comment = standard.get("comment", None)
comment_url = standard.get("commenturl", None)
# set default path
if path is not Absent and path != "":
path_specified = True
path = escape_path(path)
else:
path_specified = False
path = request_path(request)
i = path.rfind("/")
if i != -1:
if version == 0:
# Netscape spec parts company from reality here
path = path[:i]
else:
path = path[:i+1]
if len(path) == 0: path = "/"
# set default domain
domain_specified = domain is not Absent
# but first we have to remember whether it starts with a dot
domain_initial_dot = False
if domain_specified:
domain_initial_dot = bool(domain.startswith("."))
if domain is Absent:
req_host, erhn = eff_request_host(request)
domain = erhn
elif not domain.startswith("."):
domain = "."+domain
# set default port
port_specified = False
if port is not Absent:
if port is None:
# Port attr present, but has no value: default to request port.
# Cookie should then only be sent back on that port.
port = request_port(request)
else:
port_specified = True
port = re.sub(r"\s+", "", port)
else:
# No port attr present. Cookie can be sent back on any port.
port = None
# set default expires and discard
if expires is Absent:
expires = None
discard = True
elif expires <= self._now:
# Expiry date in past is request to delete cookie. This can't be
# in DefaultCookiePolicy, because can't delete cookies there.
try:
self.clear(domain, path, name)
except KeyError:
pass
_debug("Expiring cookie, domain='%s', path='%s', name='%s'",
domain, path, name)
return None
return Cookie(version,
name, value,
port, port_specified,
domain, domain_specified, domain_initial_dot,
path, path_specified,
secure,
expires,
discard,
comment,
comment_url,
rest)
def _cookies_from_attrs_set(self, attrs_set, request):
cookie_tuples = self._normalized_cookie_tuples(attrs_set)
cookies = []
for tup in cookie_tuples:
cookie = self._cookie_from_cookie_tuple(tup, request)
if cookie: cookies.append(cookie)
return cookies
def _process_rfc2109_cookies(self, cookies):
rfc2109_as_ns = getattr(self._policy, 'rfc2109_as_netscape', None)
if rfc2109_as_ns is None:
rfc2109_as_ns = not self._policy.rfc2965
for cookie in cookies:
if cookie.version == 1:
cookie.rfc2109 = True
if rfc2109_as_ns:
# treat 2109 cookies as Netscape cookies rather than
# as RFC2965 cookies
cookie.version = 0
def make_cookies(self, response, request):
"""Return sequence of Cookie objects extracted from response object."""
# get cookie-attributes for RFC 2965 and Netscape protocols
headers = response.info()
rfc2965_hdrs = headers.get_all("Set-Cookie2", [])
ns_hdrs = headers.get_all("Set-Cookie", [])
self._policy._now = self._now = int(time.time())
rfc2965 = self._policy.rfc2965
netscape = self._policy.netscape
if ((not rfc2965_hdrs and not ns_hdrs) or
(not ns_hdrs and not rfc2965) or
(not rfc2965_hdrs and not netscape) or
(not netscape and not rfc2965)):
return [] # no relevant cookie headers: quick exit
try:
cookies = self._cookies_from_attrs_set(
split_header_words(rfc2965_hdrs), request)
except Exception:
_warn_unhandled_exception()
cookies = []
if ns_hdrs and netscape:
try:
# RFC 2109 and Netscape cookies
ns_cookies = self._cookies_from_attrs_set(
parse_ns_headers(ns_hdrs), request)
except Exception:
_warn_unhandled_exception()
ns_cookies = []
self._process_rfc2109_cookies(ns_cookies)
# Look for Netscape cookies (from Set-Cookie headers) that match
# corresponding RFC 2965 cookies (from Set-Cookie2 headers).
# For each match, keep the RFC 2965 cookie and ignore the Netscape
# cookie (RFC 2965 section 9.1). Actually, RFC 2109 cookies are
# bundled in with the Netscape cookies for this purpose, which is
# reasonable behaviour.
if rfc2965:
lookup = {}
for cookie in cookies:
lookup[(cookie.domain, cookie.path, cookie.name)] = None
def no_matching_rfc2965(ns_cookie, lookup=lookup):
key = ns_cookie.domain, ns_cookie.path, ns_cookie.name
return key not in lookup
ns_cookies = filter(no_matching_rfc2965, ns_cookies)
if ns_cookies:
cookies.extend(ns_cookies)
return cookies
def set_cookie_if_ok(self, cookie, request):
"""Set a cookie if policy says it's OK to do so."""
self._cookies_lock.acquire()
try:
self._policy._now = self._now = int(time.time())
if self._policy.set_ok(cookie, request):
self.set_cookie(cookie)
finally:
self._cookies_lock.release()
def set_cookie(self, cookie):
"""Set a cookie, without checking whether or not it should be set."""
c = self._cookies
self._cookies_lock.acquire()
try:
if cookie.domain not in c: c[cookie.domain] = {}
c2 = c[cookie.domain]
if cookie.path not in c2: c2[cookie.path] = {}
c3 = c2[cookie.path]
c3[cookie.name] = cookie
finally:
self._cookies_lock.release()
def extract_cookies(self, response, request):
"""Extract cookies from response, where allowable given the request."""
_debug("extract_cookies: %s", response.info())
self._cookies_lock.acquire()
try:
for cookie in self.make_cookies(response, request):
if self._policy.set_ok(cookie, request):
_debug(" setting cookie: %s", cookie)
self.set_cookie(cookie)
finally:
self._cookies_lock.release()
def clear(self, domain=None, path=None, name=None):
"""Clear some cookies.
Invoking this method without arguments will clear all cookies. If
given a single argument, only cookies belonging to that domain will be
removed. If given two arguments, cookies belonging to the specified
path within that domain are removed. If given three arguments, then
the cookie with the specified name, path and domain is removed.
Raises KeyError if no matching cookie exists.
"""
if name is not None:
if (domain is None) or (path is None):
raise ValueError(
"domain and path must be given to remove a cookie by name")
del self._cookies[domain][path][name]
elif path is not None:
if domain is None:
raise ValueError(
"domain must be given to remove cookies by path")
del self._cookies[domain][path]
elif domain is not None:
del self._cookies[domain]
else:
self._cookies = {}
def clear_session_cookies(self):
"""Discard all session cookies.
Note that the .save() method won't save session cookies anyway, unless
you ask otherwise by passing a true ignore_discard argument.
"""
self._cookies_lock.acquire()
try:
for cookie in self:
if cookie.discard:
self.clear(cookie.domain, cookie.path, cookie.name)
finally:
self._cookies_lock.release()
def clear_expired_cookies(self):
"""Discard all expired cookies.
You probably don't need to call this method: expired cookies are never
sent back to the server (provided you're using DefaultCookiePolicy),
this method is called by CookieJar itself every so often, and the
.save() method won't save expired cookies anyway (unless you ask
otherwise by passing a true ignore_expires argument).
"""
self._cookies_lock.acquire()
try:
now = time.time()
for cookie in self:
if cookie.is_expired(now):
self.clear(cookie.domain, cookie.path, cookie.name)
finally:
self._cookies_lock.release()
def __iter__(self):
return deepvalues(self._cookies)
def __len__(self):
"""Return number of contained cookies."""
i = 0
for cookie in self: i = i + 1
return i
def __repr__(self):
r = []
for cookie in self: r.append(repr(cookie))
return "<%s[%s]>" % (self.__class__.__name__, ", ".join(r))
def __str__(self):
r = []
for cookie in self: r.append(str(cookie))
return "<%s[%s]>" % (self.__class__.__name__, ", ".join(r))
# derives from OSError for backwards-compatibility with Python 2.4.0
class LoadError(OSError): pass
class FileCookieJar(CookieJar):
"""CookieJar that can be loaded from and saved to a file."""
def __init__(self, filename=None, delayload=False, policy=None):
"""
Cookies are NOT loaded from the named file until either the .load() or
.revert() method is called.
"""
CookieJar.__init__(self, policy)
if filename is not None:
filename = os.fspath(filename)
self.filename = filename
self.delayload = bool(delayload)
def save(self, filename=None, ignore_discard=False, ignore_expires=False):
"""Save cookies to a file."""
raise NotImplementedError()
def load(self, filename=None, ignore_discard=False, ignore_expires=False):
"""Load cookies from a file."""
if filename is None:
if self.filename is not None: filename = self.filename
else: raise ValueError(MISSING_FILENAME_TEXT)
with open(filename) as f:
self._really_load(f, filename, ignore_discard, ignore_expires)
def revert(self, filename=None,
ignore_discard=False, ignore_expires=False):
"""Clear all cookies and reload cookies from a saved file.
Raises LoadError (or OSError) if reversion is not successful; the
object's state will not be altered if this happens.
"""
if filename is None:
if self.filename is not None: filename = self.filename
else: raise ValueError(MISSING_FILENAME_TEXT)
self._cookies_lock.acquire()
try:
old_state = copy.deepcopy(self._cookies)
self._cookies = {}
try:
self.load(filename, ignore_discard, ignore_expires)
except OSError:
self._cookies = old_state
raise
finally:
self._cookies_lock.release()
def lwp_cookie_str(cookie):
"""Return string representation of Cookie in the LWP cookie file format.
Actually, the format is extended a bit -- see module docstring.
"""
h = [(cookie.name, cookie.value),
("path", cookie.path),
("domain", cookie.domain)]
if cookie.port is not None: h.append(("port", cookie.port))
if cookie.path_specified: h.append(("path_spec", None))
if cookie.port_specified: h.append(("port_spec", None))
if cookie.domain_initial_dot: h.append(("domain_dot", None))
if cookie.secure: h.append(("secure", None))
if cookie.expires: h.append(("expires",
time2isoz(float(cookie.expires))))
if cookie.discard: h.append(("discard", None))
if cookie.comment: h.append(("comment", cookie.comment))
if cookie.comment_url: h.append(("commenturl", cookie.comment_url))
keys = sorted(cookie._rest.keys())
for k in keys:
h.append((k, str(cookie._rest[k])))
h.append(("version", str(cookie.version)))
return join_header_words([h])
class LWPCookieJar(FileCookieJar):
"""
The LWPCookieJar saves a sequence of "Set-Cookie3" lines.
"Set-Cookie3" is the format used by the libwww-perl library, not known
to be compatible with any browser, but which is easy to read and
doesn't lose information about RFC 2965 cookies.
Additional methods
as_lwp_str(ignore_discard=True, ignore_expired=True)
"""
def as_lwp_str(self, ignore_discard=True, ignore_expires=True):
"""Return cookies as a string of "\\n"-separated "Set-Cookie3" headers.
ignore_discard and ignore_expires: see docstring for FileCookieJar.save
"""
now = time.time()
r = []
for cookie in self:
if not ignore_discard and cookie.discard:
continue
if not ignore_expires and cookie.is_expired(now):
continue
r.append("Set-Cookie3: %s" % lwp_cookie_str(cookie))
return "\n".join(r+[""])
def save(self, filename=None, ignore_discard=False, ignore_expires=False):
if filename is None:
if self.filename is not None: filename = self.filename
else: raise ValueError(MISSING_FILENAME_TEXT)
with open(filename, "w") as f:
# There really isn't an LWP Cookies 2.0 format, but this indicates
# that there is extra information in here (domain_dot and
# port_spec) while still being compatible with libwww-perl, I hope.
f.write("#LWP-Cookies-2.0\n")
f.write(self.as_lwp_str(ignore_discard, ignore_expires))
def _really_load(self, f, filename, ignore_discard, ignore_expires):
magic = f.readline()
if not self.magic_re.search(magic):
msg = ("%r does not look like a Set-Cookie3 (LWP) format "
"file" % filename)
raise LoadError(msg)
now = time.time()
header = "Set-Cookie3:"
boolean_attrs = ("port_spec", "path_spec", "domain_dot",
"secure", "discard")
value_attrs = ("version",
"port", "path", "domain",
"expires",
"comment", "commenturl")
try:
while 1:
line = f.readline()
if line == "": break
if not line.startswith(header):
continue
line = line[len(header):].strip()
for data in split_header_words([line]):
name, value = data[0]
standard = {}
rest = {}
for k in boolean_attrs:
standard[k] = False
for k, v in data[1:]:
if k is not None:
lc = k.lower()
else:
lc = None
# don't lose case distinction for unknown fields
if (lc in value_attrs) or (lc in boolean_attrs):
k = lc
if k in boolean_attrs:
if v is None: v = True
standard[k] = v
elif k in value_attrs:
standard[k] = v
else:
rest[k] = v
h = standard.get
expires = h("expires")
discard = h("discard")
if expires is not None:
expires = iso2time(expires)
if expires is None:
discard = True
domain = h("domain")
domain_specified = domain.startswith(".")
c = Cookie(h("version"), name, value,
h("port"), h("port_spec"),
domain, domain_specified, h("domain_dot"),
h("path"), h("path_spec"),
h("secure"),
expires,
discard,
h("comment"),
h("commenturl"),
rest)
if not ignore_discard and c.discard:
continue
if not ignore_expires and c.is_expired(now):
continue
self.set_cookie(c)
except OSError:
raise
except Exception:
_warn_unhandled_exception()
raise LoadError("invalid Set-Cookie3 format file %r: %r" %
(filename, line))
class MozillaCookieJar(FileCookieJar):
"""
WARNING: you may want to backup your browser's cookies file if you use
this class to save cookies. I *think* it works, but there have been
bugs in the past!
This class differs from CookieJar only in the format it uses to save and
load cookies to and from a file. This class uses the Mozilla/Netscape
`cookies.txt' format. lynx uses this file format, too.
Don't expect cookies saved while the browser is running to be noticed by
the browser (in fact, Mozilla on unix will overwrite your saved cookies if
you change them on disk while it's running; on Windows, you probably can't
save at all while the browser is running).
Note that the Mozilla/Netscape format will downgrade RFC2965 cookies to
Netscape cookies on saving.
In particular, the cookie version and port number information is lost,
together with information about whether or not Path, Port and Discard were
specified by the Set-Cookie2 (or Set-Cookie) header, and whether or not the
domain as set in the HTTP header started with a dot (yes, I'm aware some
domains in Netscape files start with a dot and some don't -- trust me, you
really don't want to know any more about this).
Note that though Mozilla and Netscape use the same format, they use
slightly different headers. The class saves cookies using the Netscape
header by default (Mozilla can cope with that).
"""
def _really_load(self, f, filename, ignore_discard, ignore_expires):
now = time.time()
if not NETSCAPE_MAGIC_RGX.match(f.readline()):
raise LoadError(
"%r does not look like a Netscape format cookies file" %
filename)
try:
while 1:
line = f.readline()
rest = {}
if line == "": break
# httponly is a cookie flag as defined in rfc6265
# when encoded in a netscape cookie file,
# the line is prepended with "#HttpOnly_"
if line.startswith(HTTPONLY_PREFIX):
rest[HTTPONLY_ATTR] = ""
line = line[len(HTTPONLY_PREFIX):]
# last field may be absent, so keep any trailing tab
if line.endswith("\n"): line = line[:-1]
# skip comments and blank lines XXX what is $ for?
if (line.strip().startswith(("#", "$")) or
line.strip() == ""):
continue
domain, domain_specified, path, secure, expires, name, value = \
line.split("\t")
secure = (secure == "TRUE")
domain_specified = (domain_specified == "TRUE")
if name == "":
# cookies.txt regards 'Set-Cookie: foo' as a cookie
# with no name, whereas http.cookiejar regards it as a
# cookie with no value.
name = value
value = None
initial_dot = domain.startswith(".")
assert domain_specified == initial_dot
discard = False
if expires == "":
expires = None
discard = True
# assume path_specified is false
c = Cookie(0, name, value,
None, False,
domain, domain_specified, initial_dot,
path, False,
secure,
expires,
discard,
None,
None,
rest)
if not ignore_discard and c.discard:
continue
if not ignore_expires and c.is_expired(now):
continue
self.set_cookie(c)
except OSError:
raise
except Exception:
_warn_unhandled_exception()
raise LoadError("invalid Netscape format cookies file %r: %r" %
(filename, line))
def save(self, filename=None, ignore_discard=False, ignore_expires=False):
if filename is None:
if self.filename is not None: filename = self.filename
else: raise ValueError(MISSING_FILENAME_TEXT)
with open(filename, "w") as f:
f.write(NETSCAPE_HEADER_TEXT)
now = time.time()
for cookie in self:
domain = cookie.domain
if not ignore_discard and cookie.discard:
continue
if not ignore_expires and cookie.is_expired(now):
continue
if cookie.secure: secure = "TRUE"
else: secure = "FALSE"
if domain.startswith("."): initial_dot = "TRUE"
else: initial_dot = "FALSE"
if cookie.expires is not None:
expires = str(cookie.expires)
else:
expires = ""
if cookie.value is None:
# cookies.txt regards 'Set-Cookie: foo' as a cookie
# with no name, whereas http.cookiejar regards it as a
# cookie with no value.
name = ""
value = cookie.name
else:
name = cookie.name
value = cookie.value
if cookie.has_nonstandard_attr(HTTPONLY_ATTR):
domain = HTTPONLY_PREFIX + domain
f.write(
"\t".join([domain, initial_dot, cookie.path,
secure, expires, name, value])+
"\n")
|