Source

python-clinic / Lib / urllib / request.py

   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
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
"""An extensible library for opening URLs using a variety of protocols

The simplest way to use this module is to call the urlopen function,
which accepts a string containing a URL or a Request object (described
below).  It opens the URL and returns the results as file-like
object; the returned object has some extra methods described below.

The OpenerDirector manages a collection of Handler objects that do
all the actual work.  Each Handler implements a particular protocol or
option.  The OpenerDirector is a composite object that invokes the
Handlers needed to open the requested URL.  For example, the
HTTPHandler performs HTTP GET and POST requests and deals with
non-error returns.  The HTTPRedirectHandler automatically deals with
HTTP 301, 302, 303 and 307 redirect errors, and the HTTPDigestAuthHandler
deals with digest authentication.

urlopen(url, data=None) -- Basic usage is the same as original
urllib.  pass the url and optionally data to post to an HTTP URL, and
get a file-like object back.  One difference is that you can also pass
a Request instance instead of URL.  Raises a URLError (subclass of
OSError); for HTTP errors, raises an HTTPError, which can also be
treated as a valid response.

build_opener -- Function that creates a new OpenerDirector instance.
Will install the default handlers.  Accepts one or more Handlers as
arguments, either instances or Handler classes that it will
instantiate.  If one of the argument is a subclass of the default
handler, the argument will be installed instead of the default.

install_opener -- Installs a new opener as the default opener.

objects of interest:

OpenerDirector -- Sets up the User Agent as the Python-urllib client and manages
the Handler classes, while dealing with requests and responses.

Request -- An object that encapsulates the state of a request.  The
state can be as simple as the URL.  It can also include extra HTTP
headers, e.g. a User-Agent.

BaseHandler --

internals:
BaseHandler and parent
_call_chain conventions

Example usage:

import urllib.request

# set up authentication info
authinfo = urllib.request.HTTPBasicAuthHandler()
authinfo.add_password(realm='PDQ Application',
                      uri='https://mahler:8092/site-updates.py',
                      user='klem',
                      passwd='geheim$parole')

proxy_support = urllib.request.ProxyHandler({"http" : "http://ahad-haam:3128"})

# build a new opener that adds authentication and caching FTP handlers
opener = urllib.request.build_opener(proxy_support, authinfo,
                                     urllib.request.CacheFTPHandler)

# install it
urllib.request.install_opener(opener)

f = urllib.request.urlopen('http://www.python.org/')
"""

# XXX issues:
# If an authentication error handler that tries to perform
# authentication for some reason but fails, how should the error be
# signalled?  The client needs to know the HTTP error code.  But if
# the handler knows that the problem was, e.g., that it didn't know
# that hash algo that requested in the challenge, it would be good to
# pass that information along to the client, too.
# ftp errors aren't handled cleanly
# check digest against correct (i.e. non-apache) implementation

# Possible extensions:
# complex proxies  XXX not sure what exactly was meant by this
# abstract factory for opener

import base64
import bisect
import email
import hashlib
import http.client
import io
import os
import posixpath
import re
import socket
import sys
import time
import collections
import tempfile
import contextlib
import warnings


from urllib.error import URLError, HTTPError, ContentTooShortError
from urllib.parse import (
    urlparse, urlsplit, urljoin, unwrap, quote, unquote,
    splittype, splithost, splitport, splituser, splitpasswd,
    splitattr, splitquery, splitvalue, splittag, to_bytes,
    unquote_to_bytes, urlunparse)
from urllib.response import addinfourl, addclosehook

# check for SSL
try:
    import ssl
except ImportError:
    _have_ssl = False
else:
    _have_ssl = True

__all__ = [
    # Classes
    'Request', 'OpenerDirector', 'BaseHandler', 'HTTPDefaultErrorHandler',
    'HTTPRedirectHandler', 'HTTPCookieProcessor', 'ProxyHandler',
    'HTTPPasswordMgr', 'HTTPPasswordMgrWithDefaultRealm',
    'AbstractBasicAuthHandler', 'HTTPBasicAuthHandler', 'ProxyBasicAuthHandler',
    'AbstractDigestAuthHandler', 'HTTPDigestAuthHandler', 'ProxyDigestAuthHandler',
    'HTTPHandler', 'FileHandler', 'FTPHandler', 'CacheFTPHandler', 'DataHandler',
    'UnknownHandler', 'HTTPErrorProcessor',
    # Functions
    'urlopen', 'install_opener', 'build_opener',
    'pathname2url', 'url2pathname', 'getproxies',
    # Legacy interface
    'urlretrieve', 'urlcleanup', 'URLopener', 'FancyURLopener',
]

# used in User-Agent header sent
__version__ = sys.version[:3]

_opener = None
def urlopen(url, data=None, timeout=socket._GLOBAL_DEFAULT_TIMEOUT,
            *, cafile=None, capath=None, cadefault=False):
    global _opener
    if cafile or capath or cadefault:
        if not _have_ssl:
            raise ValueError('SSL support not available')
        context = ssl.SSLContext(ssl.PROTOCOL_SSLv23)
        context.options |= ssl.OP_NO_SSLv2
        if cafile or capath or cadefault:
            context.verify_mode = ssl.CERT_REQUIRED
            if cafile or capath:
                context.load_verify_locations(cafile, capath)
            else:
                context.set_default_verify_paths()
            check_hostname = True
        else:
            check_hostname = False
        https_handler = HTTPSHandler(context=context, check_hostname=check_hostname)
        opener = build_opener(https_handler)
    elif _opener is None:
        _opener = opener = build_opener()
    else:
        opener = _opener
    return opener.open(url, data, timeout)

def install_opener(opener):
    global _opener
    _opener = opener

_url_tempfiles = []
def urlretrieve(url, filename=None, reporthook=None, data=None):
    """
    Retrieve a URL into a temporary location on disk.

    Requires a URL argument. If a filename is passed, it is used as
    the temporary file location. The reporthook argument should be
    a callable that accepts a block number, a read size, and the
    total file size of the URL target. The data argument should be
    valid URL encoded data.

    If a filename is passed and the URL points to a local resource,
    the result is a copy from local file to new file.

    Returns a tuple containing the path to the newly created
    data file as well as the resulting HTTPMessage object.
    """
    url_type, path = splittype(url)

    with contextlib.closing(urlopen(url, data)) as fp:
        headers = fp.info()

        # Just return the local path and the "headers" for file://
        # URLs. No sense in performing a copy unless requested.
        if url_type == "file" and not filename:
            return os.path.normpath(path), headers

        # Handle temporary file setup.
        if filename:
            tfp = open(filename, 'wb')
        else:
            tfp = tempfile.NamedTemporaryFile(delete=False)
            filename = tfp.name
            _url_tempfiles.append(filename)

        with tfp:
            result = filename, headers
            bs = 1024*8
            size = -1
            read = 0
            blocknum = 0
            if "content-length" in headers:
                size = int(headers["Content-Length"])

            if reporthook:
                reporthook(blocknum, bs, size)

            while True:
                block = fp.read(bs)
                if not block:
                    break
                read += len(block)
                tfp.write(block)
                blocknum += 1
                if reporthook:
                    reporthook(blocknum, bs, size)

    if size >= 0 and read < size:
        raise ContentTooShortError(
            "retrieval incomplete: got only %i out of %i bytes"
            % (read, size), result)

    return result

def urlcleanup():
    for temp_file in _url_tempfiles:
        try:
            os.unlink(temp_file)
        except OSError:
            pass

    del _url_tempfiles[:]
    global _opener
    if _opener:
        _opener = None

# copied from cookielib.py
_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.full_url
    host = urlparse(url)[1]
    if host == "":
        host = request.get_header("Host", "")

    # remove port, if present
    host = _cut_port_re.sub("", host, 1)
    return host.lower()

class Request:

    def __init__(self, url, data=None, headers={},
                 origin_req_host=None, unverifiable=False,
                 method=None):
        # unwrap('<URL:type://host/path>') --> 'type://host/path'
        self.full_url = unwrap(url)
        self.full_url, self.fragment = splittag(self.full_url)
        self.headers = {}
        self.unredirected_hdrs = {}
        self._data = None
        self.data = data
        self._tunnel_host = None
        for key, value in headers.items():
            self.add_header(key, value)
        if origin_req_host is None:
            origin_req_host = request_host(self)
        self.origin_req_host = origin_req_host
        self.unverifiable = unverifiable
        self.method = method
        self._parse()

    @property
    def data(self):
        return self._data

    @data.setter
    def data(self, data):
        if data != self._data:
            self._data = data
            # issue 16464
            # if we change data we need to remove content-length header
            # (cause it's most probably calculated for previous value)
            if self.has_header("Content-length"):
                self.remove_header("Content-length")

    @data.deleter
    def data(self):
        self._data = None

    def _parse(self):
        self.type, rest = splittype(self.full_url)
        if self.type is None:
            raise ValueError("unknown url type: %s" % self.full_url)
        self.host, self.selector = splithost(rest)
        if self.host:
            self.host = unquote(self.host)

    def get_method(self):
        """Return a string indicating the HTTP request method."""
        if self.method is not None:
            return self.method
        elif self.data is not None:
            return "POST"
        else:
            return "GET"

    def get_full_url(self):
        if self.fragment:
            return '%s#%s' % (self.full_url, self.fragment)
        else:
            return self.full_url

    # Begin deprecated methods

    def add_data(self, data):
        msg = "Request.add_data method is deprecated."
        warnings.warn(msg, DeprecationWarning, stacklevel=1)
        self.data = data

    def has_data(self):
        msg = "Request.has_data method is deprecated."
        warnings.warn(msg, DeprecationWarning, stacklevel=1)
        return self.data is not None

    def get_data(self):
        msg = "Request.get_data method is deprecated."
        warnings.warn(msg, DeprecationWarning, stacklevel=1)
        return self.data

    def get_type(self):
        msg = "Request.get_type method is deprecated."
        warnings.warn(msg, DeprecationWarning, stacklevel=1)
        return self.type

    def get_host(self):
        msg = "Request.get_host method is deprecated."
        warnings.warn(msg, DeprecationWarning, stacklevel=1)
        return self.host

    def get_selector(self):
        msg = "Request.get_selector method is deprecated."
        warnings.warn(msg, DeprecationWarning, stacklevel=1)
        return self.selector

    def is_unverifiable(self):
        msg = "Request.is_unverifiable method is deprecated."
        warnings.warn(msg, DeprecationWarning, stacklevel=1)
        return self.unverifiable

    def get_origin_req_host(self):
        msg = "Request.get_origin_req_host method is deprecated."
        warnings.warn(msg, DeprecationWarning, stacklevel=1)
        return self.origin_req_host

    # End deprecated methods

    def set_proxy(self, host, type):
        if self.type == 'https' and not self._tunnel_host:
            self._tunnel_host = self.host
        else:
            self.type= type
            self.selector = self.full_url
        self.host = host

    def has_proxy(self):
        return self.selector == self.full_url

    def add_header(self, key, val):
        # useful for something like authentication
        self.headers[key.capitalize()] = val

    def add_unredirected_header(self, key, val):
        # will not be added to a redirected request
        self.unredirected_hdrs[key.capitalize()] = val

    def has_header(self, header_name):
        return (header_name in self.headers or
                header_name in self.unredirected_hdrs)

    def get_header(self, header_name, default=None):
        return self.headers.get(
            header_name,
            self.unredirected_hdrs.get(header_name, default))

    def remove_header(self, header_name):
        self.headers.pop(header_name, None)
        self.unredirected_hdrs.pop(header_name, None)

    def header_items(self):
        hdrs = self.unredirected_hdrs.copy()
        hdrs.update(self.headers)
        return list(hdrs.items())

class OpenerDirector:
    def __init__(self):
        client_version = "Python-urllib/%s" % __version__
        self.addheaders = [('User-agent', client_version)]
        # self.handlers is retained only for backward compatibility
        self.handlers = []
        # manage the individual handlers
        self.handle_open = {}
        self.handle_error = {}
        self.process_response = {}
        self.process_request = {}

    def add_handler(self, handler):
        if not hasattr(handler, "add_parent"):
            raise TypeError("expected BaseHandler instance, got %r" %
                            type(handler))

        added = False
        for meth in dir(handler):
            if meth in ["redirect_request", "do_open", "proxy_open"]:
                # oops, coincidental match
                continue

            i = meth.find("_")
            protocol = meth[:i]
            condition = meth[i+1:]

            if condition.startswith("error"):
                j = condition.find("_") + i + 1
                kind = meth[j+1:]
                try:
                    kind = int(kind)
                except ValueError:
                    pass
                lookup = self.handle_error.get(protocol, {})
                self.handle_error[protocol] = lookup
            elif condition == "open":
                kind = protocol
                lookup = self.handle_open
            elif condition == "response":
                kind = protocol
                lookup = self.process_response
            elif condition == "request":
                kind = protocol
                lookup = self.process_request
            else:
                continue

            handlers = lookup.setdefault(kind, [])
            if handlers:
                bisect.insort(handlers, handler)
            else:
                handlers.append(handler)
            added = True

        if added:
            bisect.insort(self.handlers, handler)
            handler.add_parent(self)

    def close(self):
        # Only exists for backwards compatibility.
        pass

    def _call_chain(self, chain, kind, meth_name, *args):
        # Handlers raise an exception if no one else should try to handle
        # the request, or return None if they can't but another handler
        # could.  Otherwise, they return the response.
        handlers = chain.get(kind, ())
        for handler in handlers:
            func = getattr(handler, meth_name)
            result = func(*args)
            if result is not None:
                return result

    def open(self, fullurl, data=None, timeout=socket._GLOBAL_DEFAULT_TIMEOUT):
        # accept a URL or a Request object
        if isinstance(fullurl, str):
            req = Request(fullurl, data)
        else:
            req = fullurl
            if data is not None:
                req.data = data

        req.timeout = timeout
        protocol = req.type

        # pre-process request
        meth_name = protocol+"_request"
        for processor in self.process_request.get(protocol, []):
            meth = getattr(processor, meth_name)
            req = meth(req)

        response = self._open(req, data)

        # post-process response
        meth_name = protocol+"_response"
        for processor in self.process_response.get(protocol, []):
            meth = getattr(processor, meth_name)
            response = meth(req, response)

        return response

    def _open(self, req, data=None):
        result = self._call_chain(self.handle_open, 'default',
                                  'default_open', req)
        if result:
            return result

        protocol = req.type
        result = self._call_chain(self.handle_open, protocol, protocol +
                                  '_open', req)
        if result:
            return result

        return self._call_chain(self.handle_open, 'unknown',
                                'unknown_open', req)

    def error(self, proto, *args):
        if proto in ('http', 'https'):
            # XXX http[s] protocols are special-cased
            dict = self.handle_error['http'] # https is not different than http
            proto = args[2]  # YUCK!
            meth_name = 'http_error_%s' % proto
            http_err = 1
            orig_args = args
        else:
            dict = self.handle_error
            meth_name = proto + '_error'
            http_err = 0
        args = (dict, proto, meth_name) + args
        result = self._call_chain(*args)
        if result:
            return result

        if http_err:
            args = (dict, 'default', 'http_error_default') + orig_args
            return self._call_chain(*args)

# XXX probably also want an abstract factory that knows when it makes
# sense to skip a superclass in favor of a subclass and when it might
# make sense to include both

def build_opener(*handlers):
    """Create an opener object from a list of handlers.

    The opener will use several default handlers, including support
    for HTTP, FTP and when applicable HTTPS.

    If any of the handlers passed as arguments are subclasses of the
    default handlers, the default handlers will not be used.
    """
    def isclass(obj):
        return isinstance(obj, type) or hasattr(obj, "__bases__")

    opener = OpenerDirector()
    default_classes = [ProxyHandler, UnknownHandler, HTTPHandler,
                       HTTPDefaultErrorHandler, HTTPRedirectHandler,
                       FTPHandler, FileHandler, HTTPErrorProcessor,
                       DataHandler]
    if hasattr(http.client, "HTTPSConnection"):
        default_classes.append(HTTPSHandler)
    skip = set()
    for klass in default_classes:
        for check in handlers:
            if isclass(check):
                if issubclass(check, klass):
                    skip.add(klass)
            elif isinstance(check, klass):
                skip.add(klass)
    for klass in skip:
        default_classes.remove(klass)

    for klass in default_classes:
        opener.add_handler(klass())

    for h in handlers:
        if isclass(h):
            h = h()
        opener.add_handler(h)
    return opener

class BaseHandler:
    handler_order = 500

    def add_parent(self, parent):
        self.parent = parent

    def close(self):
        # Only exists for backwards compatibility
        pass

    def __lt__(self, other):
        if not hasattr(other, "handler_order"):
            # Try to preserve the old behavior of having custom classes
            # inserted after default ones (works only for custom user
            # classes which are not aware of handler_order).
            return True
        return self.handler_order < other.handler_order


class HTTPErrorProcessor(BaseHandler):
    """Process HTTP error responses."""
    handler_order = 1000  # after all other processing

    def http_response(self, request, response):
        code, msg, hdrs = response.code, response.msg, response.info()

        # According to RFC 2616, "2xx" code indicates that the client's
        # request was successfully received, understood, and accepted.
        if not (200 <= code < 300):
            response = self.parent.error(
                'http', request, response, code, msg, hdrs)

        return response

    https_response = http_response

class HTTPDefaultErrorHandler(BaseHandler):
    def http_error_default(self, req, fp, code, msg, hdrs):
        raise HTTPError(req.full_url, code, msg, hdrs, fp)

class HTTPRedirectHandler(BaseHandler):
    # maximum number of redirections to any single URL
    # this is needed because of the state that cookies introduce
    max_repeats = 4
    # maximum total number of redirections (regardless of URL) before
    # assuming we're in a loop
    max_redirections = 10

    def redirect_request(self, req, fp, code, msg, headers, newurl):
        """Return a Request or None in response to a redirect.

        This is called by the http_error_30x methods when a
        redirection response is received.  If a redirection should
        take place, return a new Request to allow http_error_30x to
        perform the redirect.  Otherwise, raise HTTPError if no-one
        else should try to handle this url.  Return None if you can't
        but another Handler might.
        """
        m = req.get_method()
        if (not (code in (301, 302, 303, 307) and m in ("GET", "HEAD")
            or code in (301, 302, 303) and m == "POST")):
            raise HTTPError(req.full_url, code, msg, headers, fp)

        # Strictly (according to RFC 2616), 301 or 302 in response to
        # a POST MUST NOT cause a redirection without confirmation
        # from the user (of urllib.request, in this case).  In practice,
        # essentially all clients do redirect in this case, so we do
        # the same.
        # be conciliant with URIs containing a space
        newurl = newurl.replace(' ', '%20')
        CONTENT_HEADERS = ("content-length", "content-type")
        newheaders = dict((k, v) for k, v in req.headers.items()
                          if k.lower() not in CONTENT_HEADERS)
        return Request(newurl,
                       headers=newheaders,
                       origin_req_host=req.origin_req_host,
                       unverifiable=True)

    # Implementation note: To avoid the server sending us into an
    # infinite loop, the request object needs to track what URLs we
    # have already seen.  Do this by adding a handler-specific
    # attribute to the Request object.
    def http_error_302(self, req, fp, code, msg, headers):
        # Some servers (incorrectly) return multiple Location headers
        # (so probably same goes for URI).  Use first header.
        if "location" in headers:
            newurl = headers["location"]
        elif "uri" in headers:
            newurl = headers["uri"]
        else:
            return

        # fix a possible malformed URL
        urlparts = urlparse(newurl)

        # For security reasons we don't allow redirection to anything other
        # than http, https or ftp.

        if urlparts.scheme not in ('http', 'https', 'ftp', ''):
            raise HTTPError(
                newurl, code,
                "%s - Redirection to url '%s' is not allowed" % (msg, newurl),
                headers, fp)

        if not urlparts.path:
            urlparts = list(urlparts)
            urlparts[2] = "/"
        newurl = urlunparse(urlparts)

        newurl = urljoin(req.full_url, newurl)

        # XXX Probably want to forget about the state of the current
        # request, although that might interact poorly with other
        # handlers that also use handler-specific request attributes
        new = self.redirect_request(req, fp, code, msg, headers, newurl)
        if new is None:
            return

        # loop detection
        # .redirect_dict has a key url if url was previously visited.
        if hasattr(req, 'redirect_dict'):
            visited = new.redirect_dict = req.redirect_dict
            if (visited.get(newurl, 0) >= self.max_repeats or
                len(visited) >= self.max_redirections):
                raise HTTPError(req.full_url, code,
                                self.inf_msg + msg, headers, fp)
        else:
            visited = new.redirect_dict = req.redirect_dict = {}
        visited[newurl] = visited.get(newurl, 0) + 1

        # Don't close the fp until we are sure that we won't use it
        # with HTTPError.
        fp.read()
        fp.close()

        return self.parent.open(new, timeout=req.timeout)

    http_error_301 = http_error_303 = http_error_307 = http_error_302

    inf_msg = "The HTTP server returned a redirect error that would " \
              "lead to an infinite loop.\n" \
              "The last 30x error message was:\n"


def _parse_proxy(proxy):
    """Return (scheme, user, password, host/port) given a URL or an authority.

    If a URL is supplied, it must have an authority (host:port) component.
    According to RFC 3986, having an authority component means the URL must
    have two slashes after the scheme:

    >>> _parse_proxy('file:/ftp.example.com/')
    Traceback (most recent call last):
    ValueError: proxy URL with no authority: 'file:/ftp.example.com/'

    The first three items of the returned tuple may be None.

    Examples of authority parsing:

    >>> _parse_proxy('proxy.example.com')
    (None, None, None, 'proxy.example.com')
    >>> _parse_proxy('proxy.example.com:3128')
    (None, None, None, 'proxy.example.com:3128')

    The authority component may optionally include userinfo (assumed to be
    username:password):

    >>> _parse_proxy('joe:password@proxy.example.com')
    (None, 'joe', 'password', 'proxy.example.com')
    >>> _parse_proxy('joe:password@proxy.example.com:3128')
    (None, 'joe', 'password', 'proxy.example.com:3128')

    Same examples, but with URLs instead:

    >>> _parse_proxy('http://proxy.example.com/')
    ('http', None, None, 'proxy.example.com')
    >>> _parse_proxy('http://proxy.example.com:3128/')
    ('http', None, None, 'proxy.example.com:3128')
    >>> _parse_proxy('http://joe:password@proxy.example.com/')
    ('http', 'joe', 'password', 'proxy.example.com')
    >>> _parse_proxy('http://joe:password@proxy.example.com:3128')
    ('http', 'joe', 'password', 'proxy.example.com:3128')

    Everything after the authority is ignored:

    >>> _parse_proxy('ftp://joe:password@proxy.example.com/rubbish:3128')
    ('ftp', 'joe', 'password', 'proxy.example.com')

    Test for no trailing '/' case:

    >>> _parse_proxy('http://joe:password@proxy.example.com')
    ('http', 'joe', 'password', 'proxy.example.com')

    """
    scheme, r_scheme = splittype(proxy)
    if not r_scheme.startswith("/"):
        # authority
        scheme = None
        authority = proxy
    else:
        # URL
        if not r_scheme.startswith("//"):
            raise ValueError("proxy URL with no authority: %r" % proxy)
        # We have an authority, so for RFC 3986-compliant URLs (by ss 3.
        # and 3.3.), path is empty or starts with '/'
        end = r_scheme.find("/", 2)
        if end == -1:
            end = None
        authority = r_scheme[2:end]
    userinfo, hostport = splituser(authority)
    if userinfo is not None:
        user, password = splitpasswd(userinfo)
    else:
        user = password = None
    return scheme, user, password, hostport

class ProxyHandler(BaseHandler):
    # Proxies must be in front
    handler_order = 100

    def __init__(self, proxies=None):
        if proxies is None:
            proxies = getproxies()
        assert hasattr(proxies, 'keys'), "proxies must be a mapping"
        self.proxies = proxies
        for type, url in proxies.items():
            setattr(self, '%s_open' % type,
                    lambda r, proxy=url, type=type, meth=self.proxy_open:
                        meth(r, proxy, type))

    def proxy_open(self, req, proxy, type):
        orig_type = req.type
        proxy_type, user, password, hostport = _parse_proxy(proxy)
        if proxy_type is None:
            proxy_type = orig_type

        if req.host and proxy_bypass(req.host):
            return None

        if user and password:
            user_pass = '%s:%s' % (unquote(user),
                                   unquote(password))
            creds = base64.b64encode(user_pass.encode()).decode("ascii")
            req.add_header('Proxy-authorization', 'Basic ' + creds)
        hostport = unquote(hostport)
        req.set_proxy(hostport, proxy_type)
        if orig_type == proxy_type or orig_type == 'https':
            # let other handlers take care of it
            return None
        else:
            # need to start over, because the other handlers don't
            # grok the proxy's URL type
            # e.g. if we have a constructor arg proxies like so:
            # {'http': 'ftp://proxy.example.com'}, we may end up turning
            # a request for http://acme.example.com/a into one for
            # ftp://proxy.example.com/a
            return self.parent.open(req, timeout=req.timeout)

class HTTPPasswordMgr:

    def __init__(self):
        self.passwd = {}

    def add_password(self, realm, uri, user, passwd):
        # uri could be a single URI or a sequence
        if isinstance(uri, str):
            uri = [uri]
        if realm not in self.passwd:
            self.passwd[realm] = {}
        for default_port in True, False:
            reduced_uri = tuple(
                [self.reduce_uri(u, default_port) for u in uri])
            self.passwd[realm][reduced_uri] = (user, passwd)

    def find_user_password(self, realm, authuri):
        domains = self.passwd.get(realm, {})
        for default_port in True, False:
            reduced_authuri = self.reduce_uri(authuri, default_port)
            for uris, authinfo in domains.items():
                for uri in uris:
                    if self.is_suburi(uri, reduced_authuri):
                        return authinfo
        return None, None

    def reduce_uri(self, uri, default_port=True):
        """Accept authority or URI and extract only the authority and path."""
        # note HTTP URLs do not have a userinfo component
        parts = urlsplit(uri)
        if parts[1]:
            # URI
            scheme = parts[0]
            authority = parts[1]
            path = parts[2] or '/'
        else:
            # host or host:port
            scheme = None
            authority = uri
            path = '/'
        host, port = splitport(authority)
        if default_port and port is None and scheme is not None:
            dport = {"http": 80,
                     "https": 443,
                     }.get(scheme)
            if dport is not None:
                authority = "%s:%d" % (host, dport)
        return authority, path

    def is_suburi(self, base, test):
        """Check if test is below base in a URI tree

        Both args must be URIs in reduced form.
        """
        if base == test:
            return True
        if base[0] != test[0]:
            return False
        common = posixpath.commonprefix((base[1], test[1]))
        if len(common) == len(base[1]):
            return True
        return False


class HTTPPasswordMgrWithDefaultRealm(HTTPPasswordMgr):

    def find_user_password(self, realm, authuri):
        user, password = HTTPPasswordMgr.find_user_password(self, realm,
                                                            authuri)
        if user is not None:
            return user, password
        return HTTPPasswordMgr.find_user_password(self, None, authuri)


class AbstractBasicAuthHandler:

    # XXX this allows for multiple auth-schemes, but will stupidly pick
    # the last one with a realm specified.

    # allow for double- and single-quoted realm values
    # (single quotes are a violation of the RFC, but appear in the wild)
    rx = re.compile('(?:.*,)*[ \t]*([^ \t]+)[ \t]+'
                    'realm=(["\']?)([^"\']*)\\2', re.I)

    # XXX could pre-emptively send auth info already accepted (RFC 2617,
    # end of section 2, and section 1.2 immediately after "credentials"
    # production).

    def __init__(self, password_mgr=None):
        if password_mgr is None:
            password_mgr = HTTPPasswordMgr()
        self.passwd = password_mgr
        self.add_password = self.passwd.add_password
        self.retried = 0

    def reset_retry_count(self):
        self.retried = 0

    def http_error_auth_reqed(self, authreq, host, req, headers):
        # host may be an authority (without userinfo) or a URL with an
        # authority
        # XXX could be multiple headers
        authreq = headers.get(authreq, None)

        if self.retried > 5:
            # retry sending the username:password 5 times before failing.
            raise HTTPError(req.get_full_url(), 401, "basic auth failed",
                    headers, None)
        else:
            self.retried += 1

        if authreq:
            scheme = authreq.split()[0]
            if scheme.lower() != 'basic':
                raise ValueError("AbstractBasicAuthHandler does not"
                                 " support the following scheme: '%s'" %
                                 scheme)
            else:
                mo = AbstractBasicAuthHandler.rx.search(authreq)
                if mo:
                    scheme, quote, realm = mo.groups()
                    if quote not in ['"',"'"]:
                        warnings.warn("Basic Auth Realm was unquoted",
                                      UserWarning, 2)
                    if scheme.lower() == 'basic':
                        response = self.retry_http_basic_auth(host, req, realm)
                        if response and response.code != 401:
                            self.retried = 0
                        return response

    def retry_http_basic_auth(self, host, req, realm):
        user, pw = self.passwd.find_user_password(realm, host)
        if pw is not None:
            raw = "%s:%s" % (user, pw)
            auth = "Basic " + base64.b64encode(raw.encode()).decode("ascii")
            if req.headers.get(self.auth_header, None) == auth:
                return None
            req.add_unredirected_header(self.auth_header, auth)
            return self.parent.open(req, timeout=req.timeout)
        else:
            return None


class HTTPBasicAuthHandler(AbstractBasicAuthHandler, BaseHandler):

    auth_header = 'Authorization'

    def http_error_401(self, req, fp, code, msg, headers):
        url = req.full_url
        response = self.http_error_auth_reqed('www-authenticate',
                                          url, req, headers)
        self.reset_retry_count()
        return response


class ProxyBasicAuthHandler(AbstractBasicAuthHandler, BaseHandler):

    auth_header = 'Proxy-authorization'

    def http_error_407(self, req, fp, code, msg, headers):
        # http_error_auth_reqed requires that there is no userinfo component in
        # authority.  Assume there isn't one, since urllib.request does not (and
        # should not, RFC 3986 s. 3.2.1) support requests for URLs containing
        # userinfo.
        authority = req.host
        response = self.http_error_auth_reqed('proxy-authenticate',
                                          authority, req, headers)
        self.reset_retry_count()
        return response


# Return n random bytes.
_randombytes = os.urandom


class AbstractDigestAuthHandler:
    # Digest authentication is specified in RFC 2617.

    # XXX The client does not inspect the Authentication-Info header
    # in a successful response.

    # XXX It should be possible to test this implementation against
    # a mock server that just generates a static set of challenges.

    # XXX qop="auth-int" supports is shaky

    def __init__(self, passwd=None):
        if passwd is None:
            passwd = HTTPPasswordMgr()
        self.passwd = passwd
        self.add_password = self.passwd.add_password
        self.retried = 0
        self.nonce_count = 0
        self.last_nonce = None

    def reset_retry_count(self):
        self.retried = 0

    def http_error_auth_reqed(self, auth_header, host, req, headers):
        authreq = headers.get(auth_header, None)
        if self.retried > 5:
            # Don't fail endlessly - if we failed once, we'll probably
            # fail a second time. Hm. Unless the Password Manager is
            # prompting for the information. Crap. This isn't great
            # but it's better than the current 'repeat until recursion
            # depth exceeded' approach <wink>
            raise HTTPError(req.full_url, 401, "digest auth failed",
                            headers, None)
        else:
            self.retried += 1
        if authreq:
            scheme = authreq.split()[0]
            if scheme.lower() == 'digest':
                return self.retry_http_digest_auth(req, authreq)
            elif scheme.lower() != 'basic':
                raise ValueError("AbstractDigestAuthHandler does not support"
                                 " the following scheme: '%s'" % scheme)

    def retry_http_digest_auth(self, req, auth):
        token, challenge = auth.split(' ', 1)
        chal = parse_keqv_list(filter(None, parse_http_list(challenge)))
        auth = self.get_authorization(req, chal)
        if auth:
            auth_val = 'Digest %s' % auth
            if req.headers.get(self.auth_header, None) == auth_val:
                return None
            req.add_unredirected_header(self.auth_header, auth_val)
            resp = self.parent.open(req, timeout=req.timeout)
            return resp

    def get_cnonce(self, nonce):
        # The cnonce-value is an opaque
        # quoted string value provided by the client and used by both client
        # and server to avoid chosen plaintext attacks, to provide mutual
        # authentication, and to provide some message integrity protection.
        # This isn't a fabulous effort, but it's probably Good Enough.
        s = "%s:%s:%s:" % (self.nonce_count, nonce, time.ctime())
        b = s.encode("ascii") + _randombytes(8)
        dig = hashlib.sha1(b).hexdigest()
        return dig[:16]

    def get_authorization(self, req, chal):
        try:
            realm = chal['realm']
            nonce = chal['nonce']
            qop = chal.get('qop')
            algorithm = chal.get('algorithm', 'MD5')
            # mod_digest doesn't send an opaque, even though it isn't
            # supposed to be optional
            opaque = chal.get('opaque', None)
        except KeyError:
            return None

        H, KD = self.get_algorithm_impls(algorithm)
        if H is None:
            return None

        user, pw = self.passwd.find_user_password(realm, req.full_url)
        if user is None:
            return None

        # XXX not implemented yet
        if req.data is not None:
            entdig = self.get_entity_digest(req.data, chal)
        else:
            entdig = None

        A1 = "%s:%s:%s" % (user, realm, pw)
        A2 = "%s:%s" % (req.get_method(),
                        # XXX selector: what about proxies and full urls
                        req.selector)
        if qop == 'auth':
            if nonce == self.last_nonce:
                self.nonce_count += 1
            else:
                self.nonce_count = 1
                self.last_nonce = nonce
            ncvalue = '%08x' % self.nonce_count
            cnonce = self.get_cnonce(nonce)
            noncebit = "%s:%s:%s:%s:%s" % (nonce, ncvalue, cnonce, qop, H(A2))
            respdig = KD(H(A1), noncebit)
        elif qop is None:
            respdig = KD(H(A1), "%s:%s" % (nonce, H(A2)))
        else:
            # XXX handle auth-int.
            raise URLError("qop '%s' is not supported." % qop)

        # XXX should the partial digests be encoded too?

        base = 'username="%s", realm="%s", nonce="%s", uri="%s", ' \
               'response="%s"' % (user, realm, nonce, req.selector,
                                  respdig)
        if opaque:
            base += ', opaque="%s"' % opaque
        if entdig:
            base += ', digest="%s"' % entdig
        base += ', algorithm="%s"' % algorithm
        if qop:
            base += ', qop=auth, nc=%s, cnonce="%s"' % (ncvalue, cnonce)
        return base

    def get_algorithm_impls(self, algorithm):
        # lambdas assume digest modules are imported at the top level
        if algorithm == 'MD5':
            H = lambda x: hashlib.md5(x.encode("ascii")).hexdigest()
        elif algorithm == 'SHA':
            H = lambda x: hashlib.sha1(x.encode("ascii")).hexdigest()
        # XXX MD5-sess
        KD = lambda s, d: H("%s:%s" % (s, d))
        return H, KD

    def get_entity_digest(self, data, chal):
        # XXX not implemented yet
        return None


class HTTPDigestAuthHandler(BaseHandler, AbstractDigestAuthHandler):
    """An authentication protocol defined by RFC 2069

    Digest authentication improves on basic authentication because it
    does not transmit passwords in the clear.
    """

    auth_header = 'Authorization'
    handler_order = 490  # before Basic auth

    def http_error_401(self, req, fp, code, msg, headers):
        host = urlparse(req.full_url)[1]
        retry = self.http_error_auth_reqed('www-authenticate',
                                           host, req, headers)
        self.reset_retry_count()
        return retry


class ProxyDigestAuthHandler(BaseHandler, AbstractDigestAuthHandler):

    auth_header = 'Proxy-Authorization'
    handler_order = 490  # before Basic auth

    def http_error_407(self, req, fp, code, msg, headers):
        host = req.host
        retry = self.http_error_auth_reqed('proxy-authenticate',
                                           host, req, headers)
        self.reset_retry_count()
        return retry

class AbstractHTTPHandler(BaseHandler):

    def __init__(self, debuglevel=0):
        self._debuglevel = debuglevel

    def set_http_debuglevel(self, level):
        self._debuglevel = level

    def do_request_(self, request):
        host = request.host
        if not host:
            raise URLError('no host given')

        if request.data is not None:  # POST
            data = request.data
            if isinstance(data, str):
                msg = "POST data should be bytes or an iterable of bytes. " \
                      "It cannot be of type str."
                raise TypeError(msg)
            if not request.has_header('Content-type'):
                request.add_unredirected_header(
                    'Content-type',
                    'application/x-www-form-urlencoded')
            if not request.has_header('Content-length'):
                try:
                    mv = memoryview(data)
                except TypeError:
                    if isinstance(data, collections.Iterable):
                        raise ValueError("Content-Length should be specified "
                                "for iterable data of type %r %r" % (type(data),
                                data))
                else:
                    request.add_unredirected_header(
                            'Content-length', '%d' % (len(mv) * mv.itemsize))

        sel_host = host
        if request.has_proxy():
            scheme, sel = splittype(request.selector)
            sel_host, sel_path = splithost(sel)
        if not request.has_header('Host'):
            request.add_unredirected_header('Host', sel_host)
        for name, value in self.parent.addheaders:
            name = name.capitalize()
            if not request.has_header(name):
                request.add_unredirected_header(name, value)

        return request

    def do_open(self, http_class, req, **http_conn_args):
        """Return an HTTPResponse object for the request, using http_class.

        http_class must implement the HTTPConnection API from http.client.
        """
        host = req.host
        if not host:
            raise URLError('no host given')

        # will parse host:port
        h = http_class(host, timeout=req.timeout, **http_conn_args)

        headers = dict(req.unredirected_hdrs)
        headers.update(dict((k, v) for k, v in req.headers.items()
                            if k not in headers))

        # TODO(jhylton): Should this be redesigned to handle
        # persistent connections?

        # We want to make an HTTP/1.1 request, but the addinfourl
        # class isn't prepared to deal with a persistent connection.
        # It will try to read all remaining data from the socket,
        # which will block while the server waits for the next request.
        # So make sure the connection gets closed after the (only)
        # request.
        headers["Connection"] = "close"
        headers = dict((name.title(), val) for name, val in headers.items())

        if req._tunnel_host:
            tunnel_headers = {}
            proxy_auth_hdr = "Proxy-Authorization"
            if proxy_auth_hdr in headers:
                tunnel_headers[proxy_auth_hdr] = headers[proxy_auth_hdr]
                # Proxy-Authorization should not be sent to origin
                # server.
                del headers[proxy_auth_hdr]
            h.set_tunnel(req._tunnel_host, headers=tunnel_headers)

        try:
            h.request(req.get_method(), req.selector, req.data, headers)
        except OSError as err: # timeout error
            h.close()
            raise URLError(err)
        else:
            r = h.getresponse()
            # If the server does not send us a 'Connection: close' header,
            # HTTPConnection assumes the socket should be left open. Manually
            # mark the socket to be closed when this response object goes away.
            if h.sock:
                h.sock.close()
                h.sock = None

        r.url = req.get_full_url()
        # This line replaces the .msg attribute of the HTTPResponse
        # with .headers, because urllib clients expect the response to
        # have the reason in .msg.  It would be good to mark this
        # attribute is deprecated and get then to use info() or
        # .headers.
        r.msg = r.reason
        return r


class HTTPHandler(AbstractHTTPHandler):

    def http_open(self, req):
        return self.do_open(http.client.HTTPConnection, req)

    http_request = AbstractHTTPHandler.do_request_

if hasattr(http.client, 'HTTPSConnection'):

    class HTTPSHandler(AbstractHTTPHandler):

        def __init__(self, debuglevel=0, context=None, check_hostname=None):
            AbstractHTTPHandler.__init__(self, debuglevel)
            self._context = context
            self._check_hostname = check_hostname

        def https_open(self, req):
            return self.do_open(http.client.HTTPSConnection, req,
                context=self._context, check_hostname=self._check_hostname)

        https_request = AbstractHTTPHandler.do_request_

    __all__.append('HTTPSHandler')

class HTTPCookieProcessor(BaseHandler):
    def __init__(self, cookiejar=None):
        import http.cookiejar
        if cookiejar is None:
            cookiejar = http.cookiejar.CookieJar()
        self.cookiejar = cookiejar

    def http_request(self, request):
        self.cookiejar.add_cookie_header(request)
        return request

    def http_response(self, request, response):
        self.cookiejar.extract_cookies(response, request)
        return response

    https_request = http_request
    https_response = http_response

class UnknownHandler(BaseHandler):
    def unknown_open(self, req):
        type = req.type
        raise URLError('unknown url type: %s' % type)

def parse_keqv_list(l):
    """Parse list of key=value strings where keys are not duplicated."""
    parsed = {}
    for elt in l:
        k, v = elt.split('=', 1)
        if v[0] == '"' and v[-1] == '"':
            v = v[1:-1]
        parsed[k] = v
    return parsed

def parse_http_list(s):
    """Parse lists as described by RFC 2068 Section 2.

    In particular, parse comma-separated lists where the elements of
    the list may include quoted-strings.  A quoted-string could
    contain a comma.  A non-quoted string could have quotes in the
    middle.  Neither commas nor quotes count if they are escaped.
    Only double-quotes count, not single-quotes.
    """
    res = []
    part = ''

    escape = quote = False
    for cur in s:
        if escape:
            part += cur
            escape = False
            continue
        if quote:
            if cur == '\\':
                escape = True
                continue
            elif cur == '"':
                quote = False
            part += cur
            continue

        if cur == ',':
            res.append(part)
            part = ''
            continue

        if cur == '"':
            quote = True

        part += cur

    # append last part
    if part:
        res.append(part)

    return [part.strip() for part in res]

class FileHandler(BaseHandler):
    # Use local file or FTP depending on form of URL
    def file_open(self, req):
        url = req.selector
        if url[:2] == '//' and url[2:3] != '/' and (req.host and
                req.host != 'localhost'):
            if not req.host is self.get_names():
                raise URLError("file:// scheme is supported only on localhost")
        else:
            return self.open_local_file(req)

    # names for the localhost
    names = None
    def get_names(self):
        if FileHandler.names is None:
            try:
                FileHandler.names = tuple(
                    socket.gethostbyname_ex('localhost')[2] +
                    socket.gethostbyname_ex(socket.gethostname())[2])
            except socket.gaierror:
                FileHandler.names = (socket.gethostbyname('localhost'),)
        return FileHandler.names

    # not entirely sure what the rules are here
    def open_local_file(self, req):
        import email.utils
        import mimetypes
        host = req.host
        filename = req.selector
        localfile = url2pathname(filename)
        try:
            stats = os.stat(localfile)
            size = stats.st_size
            modified = email.utils.formatdate(stats.st_mtime, usegmt=True)
            mtype = mimetypes.guess_type(filename)[0]
            headers = email.message_from_string(
                'Content-type: %s\nContent-length: %d\nLast-modified: %s\n' %
                (mtype or 'text/plain', size, modified))
            if host:
                host, port = splitport(host)
            if not host or \
                (not port and _safe_gethostbyname(host) in self.get_names()):
                if host:
                    origurl = 'file://' + host + filename
                else:
                    origurl = 'file://' + filename
                return addinfourl(open(localfile, 'rb'), headers, origurl)
        except OSError as exp:
            # users shouldn't expect OSErrors coming from urlopen()
            raise URLError(exp)
        raise URLError('file not on local host')

def _safe_gethostbyname(host):
    try:
        return socket.gethostbyname(host)
    except socket.gaierror:
        return None

class FTPHandler(BaseHandler):
    def ftp_open(self, req):
        import ftplib
        import mimetypes
        host = req.host
        if not host:
            raise URLError('ftp error: no host given')
        host, port = splitport(host)
        if port is None:
            port = ftplib.FTP_PORT
        else:
            port = int(port)

        # username/password handling
        user, host = splituser(host)
        if user:
            user, passwd = splitpasswd(user)
        else:
            passwd = None
        host = unquote(host)
        user = user or ''
        passwd = passwd or ''

        try:
            host = socket.gethostbyname(host)
        except OSError as msg:
            raise URLError(msg)
        path, attrs = splitattr(req.selector)
        dirs = path.split('/')
        dirs = list(map(unquote, dirs))
        dirs, file = dirs[:-1], dirs[-1]
        if dirs and not dirs[0]:
            dirs = dirs[1:]
        try:
            fw = self.connect_ftp(user, passwd, host, port, dirs, req.timeout)
            type = file and 'I' or 'D'
            for attr in attrs:
                attr, value = splitvalue(attr)
                if attr.lower() == 'type' and \
                   value in ('a', 'A', 'i', 'I', 'd', 'D'):
                    type = value.upper()
            fp, retrlen = fw.retrfile(file, type)
            headers = ""
            mtype = mimetypes.guess_type(req.full_url)[0]
            if mtype:
                headers += "Content-type: %s\n" % mtype
            if retrlen is not None and retrlen >= 0:
                headers += "Content-length: %d\n" % retrlen
            headers = email.message_from_string(headers)
            return addinfourl(fp, headers, req.full_url)
        except ftplib.all_errors as exp:
            exc = URLError('ftp error: %r' % exp)
            raise exc.with_traceback(sys.exc_info()[2])

    def connect_ftp(self, user, passwd, host, port, dirs, timeout):
        return ftpwrapper(user, passwd, host, port, dirs, timeout,
                          persistent=False)

class CacheFTPHandler(FTPHandler):
    # XXX would be nice to have pluggable cache strategies
    # XXX this stuff is definitely not thread safe
    def __init__(self):
        self.cache = {}
        self.timeout = {}
        self.soonest = 0
        self.delay = 60
        self.max_conns = 16

    def setTimeout(self, t):
        self.delay = t

    def setMaxConns(self, m):
        self.max_conns = m

    def connect_ftp(self, user, passwd, host, port, dirs, timeout):
        key = user, host, port, '/'.join(dirs), timeout
        if key in self.cache:
            self.timeout[key] = time.time() + self.delay
        else:
            self.cache[key] = ftpwrapper(user, passwd, host, port,
                                         dirs, timeout)
            self.timeout[key] = time.time() + self.delay
        self.check_cache()
        return self.cache[key]

    def check_cache(self):
        # first check for old ones
        t = time.time()
        if self.soonest <= t:
            for k, v in list(self.timeout.items()):
                if v < t:
                    self.cache[k].close()
                    del self.cache[k]
                    del self.timeout[k]
        self.soonest = min(list(self.timeout.values()))

        # then check the size
        if len(self.cache) == self.max_conns:
            for k, v in list(self.timeout.items()):
                if v == self.soonest:
                    del self.cache[k]
                    del self.timeout[k]
                    break
            self.soonest = min(list(self.timeout.values()))

    def clear_cache(self):
        for conn in self.cache.values():
            conn.close()
        self.cache.clear()
        self.timeout.clear()

class DataHandler(BaseHandler):
    def data_open(self, req):
        # data URLs as specified in RFC 2397.
        #
        # ignores POSTed data
        #
        # syntax:
        # dataurl   := "data:" [ mediatype ] [ ";base64" ] "," data
        # mediatype := [ type "/" subtype ] *( ";" parameter )
        # data      := *urlchar
        # parameter := attribute "=" value
        url = req.full_url

        scheme, data = url.split(":",1)
        mediatype, data = data.split(",",1)

        # even base64 encoded data URLs might be quoted so unquote in any case:
        data = unquote_to_bytes(data)
        if mediatype.endswith(";base64"):
            data = base64.decodebytes(data)
            mediatype = mediatype[:-7]

        if not mediatype:
            mediatype = "text/plain;charset=US-ASCII"

        headers = email.message_from_string("Content-type: %s\nContent-length: %d\n" %
            (mediatype, len(data)))

        return addinfourl(io.BytesIO(data), headers, url)


# Code move from the old urllib module

MAXFTPCACHE = 10        # Trim the ftp cache beyond this size

# Helper for non-unix systems
if os.name == 'nt':
    from nturl2path import url2pathname, pathname2url
else:
    def url2pathname(pathname):
        """OS-specific conversion from a relative URL of the 'file' scheme
        to a file system path; not recommended for general use."""
        return unquote(pathname)

    def pathname2url(pathname):
        """OS-specific conversion from a file system path to a relative URL
        of the 'file' scheme; not recommended for general use."""
        return quote(pathname)

# This really consists of two pieces:
# (1) a class which handles opening of all sorts of URLs
#     (plus assorted utilities etc.)
# (2) a set of functions for parsing URLs
# XXX Should these be separated out into different modules?


ftpcache = {}
class URLopener:
    """Class to open URLs.
    This is a class rather than just a subroutine because we may need
    more than one set of global protocol-specific options.
    Note -- this is a base class for those who don't want the
    automatic handling of errors type 302 (relocated) and 401
    (authorization needed)."""

    __tempfiles = None

    version = "Python-urllib/%s" % __version__

    # Constructor
    def __init__(self, proxies=None, **x509):
        msg = "%(class)s style of invoking requests is deprecated. " \
              "Use newer urlopen functions/methods" % {'class': self.__class__.__name__}
        warnings.warn(msg, DeprecationWarning, stacklevel=3)
        if proxies is None:
            proxies = getproxies()
        assert hasattr(proxies, 'keys'), "proxies must be a mapping"
        self.proxies = proxies
        self.key_file = x509.get('key_file')
        self.cert_file = x509.get('cert_file')
        self.addheaders = [('User-Agent', self.version)]
        self.__tempfiles = []
        self.__unlink = os.unlink # See cleanup()
        self.tempcache = None
        # Undocumented feature: if you assign {} to tempcache,
        # it is used to cache files retrieved with
        # self.retrieve().  This is not enabled by default
        # since it does not work for changing documents (and I
        # haven't got the logic to check expiration headers
        # yet).
        self.ftpcache = ftpcache
        # Undocumented feature: you can use a different
        # ftp cache by assigning to the .ftpcache member;
        # in case you want logically independent URL openers
        # XXX This is not threadsafe.  Bah.

    def __del__(self):
        self.close()

    def close(self):
        self.cleanup()

    def cleanup(self):
        # This code sometimes runs when the rest of this module
        # has already been deleted, so it can't use any globals
        # or import anything.
        if self.__tempfiles:
            for file in self.__tempfiles:
                try:
                    self.__unlink(file)
                except OSError:
                    pass
            del self.__tempfiles[:]
        if self.tempcache:
            self.tempcache.clear()

    def addheader(self, *args):
        """Add a header to be used by the HTTP interface only
        e.g. u.addheader('Accept', 'sound/basic')"""
        self.addheaders.append(args)

    # External interface
    def open(self, fullurl, data=None):
        """Use URLopener().open(file) instead of open(file, 'r')."""
        fullurl = unwrap(to_bytes(fullurl))
        fullurl = quote(fullurl, safe="%/:=&?~#+!$,;'@()*[]|")
        if self.tempcache and fullurl in self.tempcache:
            filename, headers = self.tempcache[fullurl]
            fp = open(filename, 'rb')
            return addinfourl(fp, headers, fullurl)
        urltype, url = splittype(fullurl)
        if not urltype:
            urltype = 'file'
        if urltype in self.proxies:
            proxy = self.proxies[urltype]
            urltype, proxyhost = splittype(proxy)
            host, selector = splithost(proxyhost)
            url = (host, fullurl) # Signal special case to open_*()
        else:
            proxy = None
        name = 'open_' + urltype
        self.type = urltype
        name = name.replace('-', '_')
        if not hasattr(self, name):
            if proxy:
                return self.open_unknown_proxy(proxy, fullurl, data)
            else:
                return self.open_unknown(fullurl, data)
        try:
            if data is None:
                return getattr(self, name)(url)
            else:
                return getattr(self, name)(url, data)
        except (HTTPError, URLError):
            raise
        except OSError as msg:
            raise OSError('socket error', msg).with_traceback(sys.exc_info()[2])

    def open_unknown(self, fullurl, data=None):
        """Overridable interface to open unknown URL type."""
        type, url = splittype(fullurl)
        raise OSError('url error', 'unknown url type', type)

    def open_unknown_proxy(self, proxy, fullurl, data=None):
        """Overridable interface to open unknown URL type."""
        type, url = splittype(fullurl)
        raise OSError('url error', 'invalid proxy for %s' % type, proxy)

    # External interface
    def retrieve(self, url, filename=None, reporthook=None, data=None):
        """retrieve(url) returns (filename, headers) for a local object
        or (tempfilename, headers) for a remote object."""
        url = unwrap(to_bytes(url))
        if self.tempcache and url in self.tempcache:
            return self.tempcache[url]
        type, url1 = splittype(url)
        if filename is None and (not type or type == 'file'):
            try:
                fp = self.open_local_file(url1)
                hdrs = fp.info()
                fp.close()
                return url2pathname(splithost(url1)[1]), hdrs
            except OSError as msg:
                pass
        fp = self.open(url, data)
        try:
            headers = fp.info()
            if filename:
                tfp = open(filename, 'wb')
            else:
                import tempfile
                garbage, path = splittype(url)
                garbage, path = splithost(path or "")
                path, garbage = splitquery(path or "")
                path, garbage = splitattr(path or "")
                suffix = os.path.splitext(path)[1]
                (fd, filename) = tempfile.mkstemp(suffix)
                self.__tempfiles.append(filename)
                tfp = os.fdopen(fd, 'wb')
            try:
                result = filename, headers
                if self.tempcache is not None:
                    self.tempcache[url] = result
                bs = 1024*8
                size = -1
                read = 0
                blocknum = 0
                if "content-length" in headers:
                    size = int(headers["Content-Length"])
                if reporthook:
                    reporthook(blocknum, bs, size)
                while 1:
                    block = fp.read(bs)
                    if not block:
                        break
                    read += len(block)
                    tfp.write(block)
                    blocknum += 1
                    if reporthook:
                        reporthook(blocknum, bs, size)
            finally:
                tfp.close()
        finally:
            fp.close()

        # raise exception if actual size does not match content-length header
        if size >= 0 and read < size:
            raise ContentTooShortError(
                "retrieval incomplete: got only %i out of %i bytes"
                % (read, size), result)

        return result

    # Each method named open_<type> knows how to open that type of URL

    def _open_generic_http(self, connection_factory, url, data):
        """Make an HTTP connection using connection_class.

        This is an internal method that should be called from
        open_http() or open_https().

        Arguments:
        - connection_factory should take a host name and return an
          HTTPConnection instance.
        - url is the url to retrieval or a host, relative-path pair.
        - data is payload for a POST request or None.
        """

        user_passwd = None
        proxy_passwd= None
        if isinstance(url, str):
            host, selector = splithost(url)
            if host:
                user_passwd, host = splituser(host)
                host = unquote(host)
            realhost = host
        else:
            host, selector = url
            # check whether the proxy contains authorization information
            proxy_passwd, host = splituser(host)
            # now we proceed with the url we want to obtain
            urltype, rest = splittype(selector)
            url = rest
            user_passwd = None
            if urltype.lower() != 'http':
                realhost = None
            else:
                realhost, rest = splithost(rest)
                if realhost:
                    user_passwd, realhost = splituser(realhost)
                if user_passwd:
                    selector = "%s://%s%s" % (urltype, realhost, rest)
                if proxy_bypass(realhost):
                    host = realhost

        if not host: raise OSError('http error', 'no host given')

        if proxy_passwd:
            proxy_passwd = unquote(proxy_passwd)
            proxy_auth = base64.b64encode(proxy_passwd.encode()).decode('ascii')
        else:
            proxy_auth = None

        if user_passwd:
            user_passwd = unquote(user_passwd)
            auth = base64.b64encode(user_passwd.encode()).decode('ascii')
        else:
            auth = None
        http_conn = connection_factory(host)
        headers = {}
        if proxy_auth:
            headers["Proxy-Authorization"] = "Basic %s" % proxy_auth
        if auth:
            headers["Authorization"] =  "Basic %s" % auth
        if realhost:
            headers["Host"] = realhost

        # Add Connection:close as we don't support persistent connections yet.
        # This helps in closing the socket and avoiding ResourceWarning

        headers["Connection"] = "close"

        for header, value in self.addheaders:
            headers[header] = value

        if data is not None:
            headers["Content-Type"] = "application/x-www-form-urlencoded"
            http_conn.request("POST", selector, data, headers)
        else:
            http_conn.request("GET", selector, headers=headers)

        try:
            response = http_conn.getresponse()
        except http.client.BadStatusLine:
            # something went wrong with the HTTP status line
            raise URLError("http protocol error: bad status line")

        # According to RFC 2616, "2xx" code indicates that the client's
        # request was successfully received, understood, and accepted.
        if 200 <= response.status < 300:
            return addinfourl(response, response.msg, "http:" + url,
                              response.status)
        else:
            return self.http_error(
                url, response.fp,
                response.status, response.reason, response.msg, data)

    def open_http(self, url, data=None):
        """Use HTTP protocol."""
        return self._open_generic_http(http.client.HTTPConnection, url, data)

    def http_error(self, url, fp, errcode, errmsg, headers, data=None):
        """Handle http errors.

        Derived class can override this, or provide specific handlers
        named http_error_DDD where DDD is the 3-digit error code."""
        # First check if there's a specific handler for this error
        name = 'http_error_%d' % errcode
        if hasattr(self, name):
            method = getattr(self, name)
            if data is None:
                result = method(url, fp, errcode, errmsg, headers)
            else:
                result = method(url, fp, errcode, errmsg, headers, data)
            if result: return result
        return self.http_error_default(url, fp, errcode, errmsg, headers)

    def http_error_default(self, url, fp, errcode, errmsg, headers):
        """Default error handler: close the connection and raise OSError."""
        fp.close()
        raise HTTPError(url, errcode, errmsg, headers, None)

    if _have_ssl:
        def _https_connection(self, host):
            return http.client.HTTPSConnection(host,
                                           key_file=self.key_file,
                                           cert_file=self.cert_file)

        def open_https(self, url, data=None):
            """Use HTTPS protocol."""
            return self._open_generic_http(self._https_connection, url, data)

    def open_file(self, url):
        """Use local file or FTP depending on form of URL."""
        if not isinstance(url, str):
            raise URLError('file error: proxy support for file protocol currently not implemented')
        if url[:2] == '//' and url[2:3] != '/' and url[2:12].lower() != 'localhost/':
            raise ValueError("file:// scheme is supported only on localhost")
        else:
            return self.open_local_file(url)

    def open_local_file(self, url):
        """Use local file."""
        import email.utils
        import mimetypes
        host, file = splithost(url)
        localname = url2pathname(file)
        try:
            stats = os.stat(localname)
        except OSError as e:
            raise URLError(e.strerror, e.filename)
        size = stats.st_size
        modified = email.utils.formatdate(stats.st_mtime, usegmt=True)
        mtype = mimetypes.guess_type(url)[0]
        headers = email.message_from_string(
            'Content-Type: %s\nContent-Length: %d\nLast-modified: %s\n' %
            (mtype or 'text/plain', size, modified))
        if not host:
            urlfile = file
            if file[:1] == '/':
                urlfile = 'file://' + file
            return addinfourl(open(localname, 'rb'), headers, urlfile)
        host, port = splitport(host)
        if (not port
           and socket.gethostbyname(host) in ((localhost(),) + thishost())):
            urlfile = file
            if file[:1] == '/':
                urlfile = 'file://' + file
            elif file[:2] == './':
                raise ValueError("local file url may start with / or file:. Unknown url of type: %s" % url)
            return addinfourl(open(localname, 'rb'), headers, urlfile)
        raise URLError('local file error: not on local host')

    def open_ftp(self, url):
        """Use FTP protocol."""
        if not isinstance(url, str):
            raise URLError('ftp error: proxy support for ftp protocol currently not implemented')
        import mimetypes
        host, path = splithost(url)
        if not host: raise URLError('ftp error: no host given')
        host, port = splitport(host)
        user, host = splituser(host)
        if user: user, passwd = splitpasswd(user)
        else: passwd = None
        host = unquote(host)
        user = unquote(user or '')
        passwd = unquote(passwd or '')
        host = socket.gethostbyname(host)
        if not port:
            import ftplib
            port = ftplib.FTP_PORT
        else:
            port = int(port)
        path, attrs = splitattr(path)
        path = unquote(path)
        dirs = path.split('/')
        dirs, file = dirs[:-1], dirs[-1]
        if dirs and not dirs[0]: dirs = dirs[1:]
        if dirs and not dirs[0]: dirs[0] = '/'
        key = user, host, port, '/'.join(dirs)
        # XXX thread unsafe!
        if len(self.ftpcache) > MAXFTPCACHE:
            # Prune the cache, rather arbitrarily
            for k in self.ftpcache.keys():
                if k != key:
                    v = self.ftpcache[k]
                    del self.ftpcache[k]
                    v.close()
        try:
            if key not in self.ftpcache:
                self.ftpcache[key] = \
                    ftpwrapper(user, passwd, host, port, dirs)
            if not file: type = 'D'
            else: type = 'I'
            for attr in attrs:
                attr, value = splitvalue(attr)
                if attr.lower() == 'type' and \
                   value in ('a', 'A', 'i', 'I', 'd', 'D'):
                    type = value.upper()
            (fp, retrlen) = self.ftpcache[key].retrfile(file, type)
            mtype = mimetypes.guess_type("ftp:" + url)[0]
            headers = ""
            if mtype:
                headers += "Content-Type: %s\n" % mtype
            if retrlen is not None and retrlen >= 0:
                headers += "Content-Length: %d\n" % retrlen
            headers = email.message_from_string(headers)
            return addinfourl(fp, headers, "ftp:" + url)
        except ftperrors() as exp:
            raise URLError('ftp error %r' % exp).with_traceback(sys.exc_info()[2])

    def open_data(self, url, data=None):
        """Use "data" URL."""
        if not isinstance(url, str):
            raise URLError('data error: proxy support for data protocol currently not implemented')
        # ignore POSTed data
        #
        # syntax of data URLs:
        # dataurl   := "data:" [ mediatype ] [ ";base64" ] "," data
        # mediatype := [ type "/" subtype ] *( ";" parameter )
        # data      := *urlchar
        # parameter := attribute "=" value
        try:
            [type, data] = url.split(',', 1)
        except ValueError:
            raise OSError('data error', 'bad data URL')
        if not type:
            type = 'text/plain;charset=US-ASCII'
        semi = type.rfind(';')
        if semi >= 0 and '=' not in type[semi:]:
            encoding = type[semi+1:]
            type = type[:semi]
        else:
            encoding = ''
        msg = []
        msg.append('Date: %s'%time.strftime('%a, %d %b %Y %H:%M:%S GMT',
                                            time.gmtime(time.time())))
        msg.append('Content-type: %s' % type)
        if encoding == 'base64':
            # XXX is this encoding/decoding ok?
            data = base64.decodebytes(data.encode('ascii')).decode('latin-1')
        else:
            data = unquote(data)
        msg.append('Content-Length: %d' % len(data))
        msg.append('')
        msg.append(data)
        msg = '\n'.join(msg)
        headers = email.message_from_string(msg)
        f = io.StringIO(msg)
        #f.fileno = None     # needed for addinfourl
        return addinfourl(f, headers, url)


class FancyURLopener(URLopener):
    """Derived class with handlers for errors we can handle (perhaps)."""

    def __init__(self, *args, **kwargs):
        URLopener.__init__(self, *args, **kwargs)
        self.auth_cache = {}
        self.tries = 0
        self.maxtries = 10

    def http_error_default(self, url, fp, errcode, errmsg, headers):
        """Default error handling -- don't raise an exception."""
        return addinfourl(fp, headers, "http:" + url, errcode)

    def http_error_302(self, url, fp, errcode, errmsg, headers, data=None):
        """Error 302 -- relocated (temporarily)."""
        self.tries += 1
        if self.maxtries and self.tries >= self.maxtries:
            if hasattr(self, "http_error_500"):
                meth = self.http_error_500
            else:
                meth = self.http_error_default
            self.tries = 0
            return meth(url, fp, 500,
                        "Internal Server Error: Redirect Recursion", headers)
        result = self.redirect_internal(url, fp, errcode, errmsg, headers,
                                        data)
        self.tries = 0
        return result

    def redirect_internal(self, url, fp, errcode, errmsg, headers, data):
        if 'location' in headers:
            newurl = headers['location']
        elif 'uri' in headers:
            newurl = headers['uri']
        else:
            return
        fp.close()

        # In case the server sent a relative URL, join with original:
        newurl = urljoin(self.type + ":" + url, newurl)

        urlparts = urlparse(newurl)

        # For security reasons, we don't allow redirection to anything other
        # than http, https and ftp.

        # We are using newer HTTPError with older redirect_internal method
        # This older method will get deprecated in 3.3

        if urlparts.scheme not in ('http', 'https', 'ftp', ''):
            raise HTTPError(newurl, errcode,
                            errmsg +
                            " Redirection to url '%s' is not allowed." % newurl,
                            headers, fp)

        return self.open(newurl)

    def http_error_301(self, url, fp, errcode, errmsg, headers, data=None):
        """Error 301 -- also relocated (permanently)."""
        return self.http_error_302(url, fp, errcode, errmsg, headers, data)

    def http_error_303(self, url, fp, errcode, errmsg, headers, data=None):
        """Error 303 -- also relocated (essentially identical to 302)."""
        return self.http_error_302(url, fp, errcode, errmsg, headers, data)

    def http_error_307(self, url, fp, errcode, errmsg, headers, data=None):
        """Error 307 -- relocated, but turn POST into error."""
        if data is None:
            return self.http_error_302(url, fp, errcode, errmsg, headers, data)
        else:
            return self.http_error_default(url, fp, errcode, errmsg, headers)

    def http_error_401(self, url, fp, errcode, errmsg, headers, data=None,
            retry=False):
        """Error 401 -- authentication required.
        This function supports Basic authentication only."""
        if 'www-authenticate' not in headers:
            URLopener.http_error_default(self, url, fp,
                                         errcode, errmsg, headers)
        stuff = headers['www-authenticate']
        match = re.match('[ \t]*([^ \t]+)[ \t]+realm="([^"]*)"', stuff)
        if not match:
            URLopener.http_error_default(self, url, fp,
                                         errcode, errmsg, headers)
        scheme, realm = match.groups()
        if scheme.lower() != 'basic':
            URLopener.http_error_default(self, url, fp,
                                         errcode, errmsg, headers)
        if not retry:
            URLopener.http_error_default(self, url, fp, errcode, errmsg,
                    headers)
        name = 'retry_' + self.type + '_basic_auth'
        if data is None:
            return getattr(self,name)(url, realm)
        else:
            return getattr(self,name)(url, realm, data)

    def http_error_407(self, url, fp, errcode, errmsg, headers, data=None,
            retry=False):
        """Error 407 -- proxy authentication required.
        This function supports Basic authentication only."""
        if 'proxy-authenticate' not in headers:
            URLopener.http_error_default(self, url, fp,
                                         errcode, errmsg, headers)
        stuff = headers['proxy-authenticate']
        match = re.match('[ \t]*([^ \t]+)[ \t]+realm="([^"]*)"', stuff)
        if not match:
            URLopener.http_error_default(self, url, fp,
                                         errcode, errmsg, headers)
        scheme, realm = match.groups()
        if scheme.lower() != 'basic':
            URLopener.http_error_default(self, url, fp,
                                         errcode, errmsg, headers)
        if not retry:
            URLopener.http_error_default(self, url, fp, errcode, errmsg,
                    headers)
        name = 'retry_proxy_' + self.type + '_basic_auth'
        if data is None:
            return getattr(self,name)(url, realm)
        else:
            return getattr(self,name)(url, realm, data)

    def retry_proxy_http_basic_auth(self, url, realm, data=None):
        host, selector = splithost(url)
        newurl = 'http://' + host + selector
        proxy = self.proxies['http']
        urltype, proxyhost = splittype(proxy)
        proxyhost, proxyselector = splithost(proxyhost)
        i = proxyhost.find('@') + 1
        proxyhost = proxyhost[i:]
        user, passwd = self.get_user_passwd(proxyhost, realm, i)
        if not (user or passwd): return None
        proxyhost = "%s:%s@%s" % (quote(user, safe=''),
                                  quote(passwd, safe=''), proxyhost)
        self.proxies['http'] = 'http://' + proxyhost + proxyselector
        if data is None:
            return self.open(newurl)
        else:
            return self.open(newurl, data)

    def retry_proxy_https_basic_auth(self, url, realm, data=None):
        host, selector = splithost(url)
        newurl = 'https://' + host + selector
        proxy = self.proxies['https']
        urltype, proxyhost = splittype(proxy)
        proxyhost, proxyselector = splithost(proxyhost)
        i = proxyhost.find('@') + 1
        proxyhost = proxyhost[i:]
        user, passwd = self.get_user_passwd(proxyhost, realm, i)
        if not (user or passwd): return None
        proxyhost = "%s:%s@%s" % (quote(user, safe=''),
                                  quote(passwd, safe=''), proxyhost)
        self.proxies['https'] = 'https://' + proxyhost + proxyselector
        if data is None:
            return self.open(newurl)
        else:
            return self.open(newurl, data)

    def retry_http_basic_auth(self, url, realm, data=None):
        host, selector = splithost(url)
        i = host.find('@') + 1
        host = host[i:]
        user, passwd = self.get_user_passwd(host, realm, i)
        if not (user or passwd): return None
        host = "%s:%s@%s" % (quote(user, safe=''),
                             quote(passwd, safe=''), host)
        newurl = 'http://' + host + selector
        if data is None:
            return self.open(newurl)
        else:
            return self.open(newurl, data)

    def retry_https_basic_auth(self, url, realm, data=None):
        host, selector = splithost(url)
        i = host.find('@') + 1
        host = host[i:]
        user, passwd = self.get_user_passwd(host, realm, i)
        if not (user or passwd): return None
        host = "%s:%s@%s" % (quote(user, safe=''),
                             quote(passwd, safe=''), host)
        newurl = 'https://' + host + selector
        if data is None:
            return self.open(newurl)
        else:
            return self.open(newurl, data)

    def get_user_passwd(self, host, realm, clear_cache=0):
        key = realm + '@' + host.lower()
        if key in self.auth_cache:
            if clear_cache:
                del self.auth_cache[key]
            else:
                return self.auth_cache[key]
        user, passwd = self.prompt_user_passwd(host, realm)
        if user or passwd: self.auth_cache[key] = (user, passwd)
        return user, passwd

    def prompt_user_passwd(self, host, realm):
        """Override this in a GUI environment!"""
        import getpass
        try:
            user = input("Enter username for %s at %s: " % (realm, host))
            passwd = getpass.getpass("Enter password for %s in %s at %s: " %
                (user, realm, host))
            return user, passwd
        except KeyboardInterrupt:
            print()
            return None, None


# Utility functions

_localhost = None
def localhost():
    """Return the IP address of the magic hostname 'localhost'."""
    global _localhost
    if _localhost is None:
        _localhost = socket.gethostbyname('localhost')
    return _localhost

_thishost = None
def thishost():
    """Return the IP addresses of the current host."""
    global _thishost
    if _thishost is None:
        _thishost = tuple(socket.gethostbyname_ex(socket.gethostname())[2])
    return _thishost

_ftperrors = None
def ftperrors():
    """Return the set of errors raised by the FTP class."""
    global _ftperrors
    if _ftperrors is None:
        import ftplib
        _ftperrors = ftplib.all_errors
    return _ftperrors

_noheaders = None
def noheaders():
    """Return an empty email Message object."""
    global _noheaders
    if _noheaders is None:
        _noheaders = email.message_from_string("")
    return _noheaders


# Utility classes

class ftpwrapper:
    """Class used by open_ftp() for cache of open FTP connections."""

    def __init__(self, user, passwd, host, port, dirs, timeout=None,
                 persistent=True):
        self.user = user
        self.passwd = passwd
        self.host = host
        self.port = port
        self.dirs = dirs
        self.timeout = timeout
        self.refcount = 0
        self.keepalive = persistent
        self.init()

    def init(self):
        import ftplib
        self.busy = 0
        self.ftp = ftplib.FTP()
        self.ftp.connect(self.host, self.port, self.timeout)
        self.ftp.login(self.user, self.passwd)
        for dir in self.dirs:
            self.ftp.cwd(dir)

    def retrfile(self, file, type):
        import ftplib
        self.endtransfer()
        if type in ('d', 'D'): cmd = 'TYPE A'; isdir = 1
        else: cmd = 'TYPE ' + type; isdir = 0
        try:
            self.ftp.voidcmd(cmd)
        except ftplib.all_errors:
            self.init()
            self.ftp.voidcmd(cmd)
        conn = None
        if file and not isdir:
            # Try to retrieve as a file
            try:
                cmd = 'RETR ' + file
                conn, retrlen = self.ftp.ntransfercmd(cmd)
            except ftplib.error_perm as reason:
                if str(reason)[:3] != '550':
                    raise URLError('ftp error: %d' % reason).with_traceback(
                        sys.exc_info()[2])
        if not conn:
            # Set transfer mode to ASCII!
            self.ftp.voidcmd('TYPE A')
            # Try a directory listing. Verify that directory exists.
            if file:
                pwd = self.ftp.pwd()
                try:
                    try:
                        self.ftp.cwd(file)
                    except ftplib.error_perm as reason:
                        raise URLError('ftp error: %d' % reason) from reason
                finally:
                    self.ftp.cwd(pwd)
                cmd = 'LIST ' + file
            else:
                cmd = 'LIST'
            conn, retrlen = self.ftp.ntransfercmd(cmd)
        self.busy = 1

        ftpobj = addclosehook(conn.makefile('rb'), self.file_close)
        self.refcount += 1
        conn.close()
        # Pass back both a suitably decorated object and a retrieval length
        return (ftpobj, retrlen)

    def endtransfer(self):
        self.busy = 0

    def close(self):
        self.keepalive = False
        if self.refcount <= 0:
            self.real_close()

    def file_close(self):
        self.endtransfer()
        self.refcount -= 1
        if self.refcount <= 0 and not self.keepalive:
            self.real_close()

    def real_close(self):
        self.endtransfer()
        try:
            self.ftp.close()
        except ftperrors():
            pass

# Proxy handling
def getproxies_environment():
    """Return a dictionary of scheme -> proxy server URL mappings.

    Scan the environment for variables named <scheme>_proxy;
    this seems to be the standard convention.  If you need a
    different way, you can pass a proxies dictionary to the
    [Fancy]URLopener constructor.

    """
    proxies = {}
    for name, value in os.environ.items():
        name = name.lower()
        if value and name[-6:] == '_proxy':
            proxies[name[:-6]] = value
    return proxies

def proxy_bypass_environment(host):
    """Test if proxies should not be used for a particular host.

    Checks the environment for a variable named no_proxy, which should
    be a list of DNS suffixes separated by commas, or '*' for all hosts.
    """
    no_proxy = os.environ.get('no_proxy', '') or os.environ.get('NO_PROXY', '')
    # '*' is special case for always bypass
    if no_proxy == '*':
        return 1
    # strip port off host
    hostonly, port = splitport(host)
    # check if the host ends with any of the DNS suffixes
    no_proxy_list = [proxy.strip() for proxy in no_proxy.split(',')]
    for name in no_proxy_list:
        if name and (hostonly.endswith(name) or host.endswith(name)):
            return 1
    # otherwise, don't bypass
    return 0


# This code tests an OSX specific data structure but is testable on all
# platforms
def _proxy_bypass_macosx_sysconf(host, proxy_settings):
    """
    Return True iff this host shouldn't be accessed using a proxy

    This function uses the MacOSX framework SystemConfiguration
    to fetch the proxy information.

    proxy_settings come from _scproxy._get_proxy_settings or get mocked ie:
    { 'exclude_simple': bool,
      'exceptions': ['foo.bar', '*.bar.com', '127.0.0.1', '10.1', '10.0/16']
    }
    """
    from fnmatch import fnmatch

    hostonly, port = splitport(host)

    def ip2num(ipAddr):
        parts = ipAddr.split('.')
        parts = list(map(int, parts))
        if len(parts) != 4:
            parts = (parts + [0, 0, 0, 0])[:4]
        return (parts[0] << 24) | (parts[1] << 16) | (parts[2] << 8) | parts[3]

    # Check for simple host names:
    if '.' not in host:
        if proxy_settings['exclude_simple']:
            return True

    hostIP = None

    for value in proxy_settings.get('exceptions', ()):
        # Items in the list are strings like these: *.local, 169.254/16
        if not value: continue

        m = re.match(r"(\d+(?:\.\d+)*)(/\d+)?", value)
        if m is not None:
            if hostIP is None:
                try:
                    hostIP = socket.gethostbyname(hostonly)
                    hostIP = ip2num(hostIP)
                except OSError:
                    continue

            base = ip2num(m.group(1))
            mask = m.group(2)
            if mask is None:
                mask = 8 * (m.group(1).count('.') + 1)
            else:
                mask = int(mask[1:])
            mask = 32 - mask

            if (hostIP >> mask) == (base >> mask):
                return True

        elif fnmatch(host, value):
            return True

    return False


if sys.platform == 'darwin':
    from _scproxy import _get_proxy_settings, _get_proxies

    def proxy_bypass_macosx_sysconf(host):
        proxy_settings = _get_proxy_settings()
        return _proxy_bypass_macosx_sysconf(host, proxy_settings)

    def getproxies_macosx_sysconf():
        """Return a dictionary of scheme -> proxy server URL mappings.

        This function uses the MacOSX framework SystemConfiguration
        to fetch the proxy information.
        """
        return _get_proxies()



    def proxy_bypass(host):
        if getproxies_environment():
            return proxy_bypass_environment(host)
        else:
            return proxy_bypass_macosx_sysconf(host)

    def getproxies():
        return getproxies_environment() or getproxies_macosx_sysconf()


elif os.name == 'nt':
    def getproxies_registry():
        """Return a dictionary of scheme -> proxy server URL mappings.

        Win32 uses the registry to store proxies.

        """
        proxies = {}
        try:
            import winreg
        except ImportError:
            # Std module, so should be around - but you never know!
            return proxies
        try:
            internetSettings = winreg.OpenKey(winreg.HKEY_CURRENT_USER,
                r'Software\Microsoft\Windows\CurrentVersion\Internet Settings')
            proxyEnable = winreg.QueryValueEx(internetSettings,
                                               'ProxyEnable')[0]
            if proxyEnable:
                # Returned as Unicode but problems if not converted to ASCII
                proxyServer = str(winreg.QueryValueEx(internetSettings,
                                                       'ProxyServer')[0])
                if '=' in proxyServer:
                    # Per-protocol settings
                    for p in proxyServer.split(';'):
                        protocol, address = p.split('=', 1)
                        # See if address has a type:// prefix
                        if not re.match('^([^/:]+)://', address):
                            address = '%s://%s' % (protocol, address)
                        proxies[protocol] = address
                else:
                    # Use one setting for all protocols
                    if proxyServer[:5] == 'http:':
                        proxies['http'] = proxyServer
                    else:
                        proxies['http'] = 'http://%s' % proxyServer
                        proxies['https'] = 'https://%s' % proxyServer
                        proxies['ftp'] = 'ftp://%s' % proxyServer
            internetSettings.Close()
        except (OSError, ValueError, TypeError):
            # Either registry key not found etc, or the value in an
            # unexpected format.
            # proxies already set up to be empty so nothing to do
            pass
        return proxies

    def getproxies():
        """Return a dictionary of scheme -> proxy server URL mappings.

        Returns settings gathered from the environment, if specified,
        or the registry.

        """
        return getproxies_environment() or getproxies_registry()

    def proxy_bypass_registry(host):
        try:
            import winreg
        except ImportError:
            # Std modules, so should be around - but you never know!
            return 0
        try:
            internetSettings = winreg.OpenKey(winreg.HKEY_CURRENT_USER,
                r'Software\Microsoft\Windows\CurrentVersion\Internet Settings')
            proxyEnable = winreg.QueryValueEx(internetSettings,
                                               'ProxyEnable')[0]
            proxyOverride = str(winreg.QueryValueEx(internetSettings,
                                                     'ProxyOverride')[0])
            # ^^^^ Returned as Unicode but problems if not converted to ASCII
        except OSError:
            return 0
        if not proxyEnable or not proxyOverride:
            return 0
        # try to make a host list from name and IP address.
        rawHost, port = splitport(host)
        host = [rawHost]
        try:
            addr = socket.gethostbyname(rawHost)
            if addr != rawHost:
                host.append(addr)
        except OSError:
            pass
        try:
            fqdn = socket.getfqdn(rawHost)
            if fqdn != rawHost:
                host.append(fqdn)
        except OSError:
            pass
        # make a check value list from the registry entry: replace the
        # '<local>' string by the localhost entry and the corresponding
        # canonical entry.
        proxyOverride = proxyOverride.split(';')
        # now check if we match one of the registry values.
        for test in proxyOverride:
            if test == '<local>':
                if '.' not in rawHost:
                    return 1
            test = test.replace(".", r"\.")     # mask dots
            test = test.replace("*", r".*")     # change glob sequence
            test = test.replace("?", r".")      # change glob char
            for val in host:
                if re.match(test, val, re.I):
                    return 1
        return 0

    def proxy_bypass(host):
        """Return a dictionary of scheme -> proxy server URL mappings.

        Returns settings gathered from the environment, if specified,
        or the registry.

        """
        if getproxies_environment():
            return proxy_bypass_environment(host)
        else:
            return proxy_bypass_registry(host)

else:
    # By default use environment variables
    getproxies = getproxies_environment
    proxy_bypass = proxy_bypass_environment
Tip: Filter by directory path e.g. /media app.js to search for public/media/app.js.
Tip: Use camelCasing e.g. ProjME to search for ProjectModifiedEvent.java.
Tip: Filter by extension type e.g. /repo .js to search for all .js files in the /repo directory.
Tip: Separate your search with spaces e.g. /ssh pom.xml to search for src/ssh/pom.xml.
Tip: Use ↑ and ↓ arrow keys to navigate and return to view the file.
Tip: You can also navigate files with Ctrl+j (next) and Ctrl+k (previous) and view the file with Ctrl+o.
Tip: You can also navigate files with Alt+j (next) and Alt+k (previous) and view the file with Alt+o.