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
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
|
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import base64
import binascii
import calendar
import codecs
import contextlib
import ctypes
import datetime
import email.utils
import errno
import functools
import gzip
import io
import itertools
import json
import locale
import math
import operator
import os
import pipes
import platform
import re
import socket
import ssl
import subprocess
import sys
import tempfile
import traceback
import xml.etree.ElementTree
import zlib
from .compat import (
compat_HTMLParser,
compat_basestring,
compat_chr,
compat_etree_fromstring,
compat_html_entities,
compat_http_client,
compat_kwargs,
compat_parse_qs,
compat_shlex_quote,
compat_socket_create_connection,
compat_str,
compat_struct_pack,
compat_urllib_error,
compat_urllib_parse,
compat_urllib_parse_urlencode,
compat_urllib_parse_urlparse,
compat_urllib_request,
compat_urlparse,
compat_xpath,
)
from .socks import (
ProxyType,
sockssocket,
)
def register_socks_protocols():
# "Register" SOCKS protocols
# In Python < 2.6.5, urlsplit() suffers from bug https://bugs.python.org/issue7904
# URLs with protocols not in urlparse.uses_netloc are not handled correctly
for scheme in ('socks', 'socks4', 'socks4a', 'socks5'):
if scheme not in compat_urlparse.uses_netloc:
compat_urlparse.uses_netloc.append(scheme)
# This is not clearly defined otherwise
compiled_regex_type = type(re.compile(''))
std_headers = {
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20150101 Firefox/44.0 (Chrome)',
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate',
'Accept-Language': 'en-us,en;q=0.5',
}
NO_DEFAULT = object()
ENGLISH_MONTH_NAMES = [
'January', 'February', 'March', 'April', 'May', 'June',
'July', 'August', 'September', 'October', 'November', 'December']
KNOWN_EXTENSIONS = (
'mp4', 'm4a', 'm4p', 'm4b', 'm4r', 'm4v', 'aac',
'flv', 'f4v', 'f4a', 'f4b',
'webm', 'ogg', 'ogv', 'oga', 'ogx', 'spx', 'opus',
'mkv', 'mka', 'mk3d',
'avi', 'divx',
'mov',
'asf', 'wmv', 'wma',
'3gp', '3g2',
'mp3',
'flac',
'ape',
'wav',
'f4f', 'f4m', 'm3u8', 'smil')
# needed for sanitizing filenames in restricted mode
ACCENT_CHARS = dict(zip('ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØŒÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõöøœùúûüýþÿ',
itertools.chain('AAAAAA', ['AE'], 'CEEEEIIIIDNOOOOOO', ['OE'], 'UUUUYP', ['ss'],
'aaaaaa', ['ae'], 'ceeeeiiiionoooooo', ['oe'], 'uuuuypy')))
def preferredencoding():
"""Get preferred encoding.
Returns the best encoding scheme for the system, based on
locale.getpreferredencoding() and some further tweaks.
"""
try:
pref = locale.getpreferredencoding()
'TEST'.encode(pref)
except Exception:
pref = 'UTF-8'
return pref
def write_json_file(obj, fn):
""" Encode obj as JSON and write it to fn, atomically if possible """
fn = encodeFilename(fn)
if sys.version_info < (3, 0) and sys.platform != 'win32':
encoding = get_filesystem_encoding()
# os.path.basename returns a bytes object, but NamedTemporaryFile
# will fail if the filename contains non ascii characters unless we
# use a unicode object
path_basename = lambda f: os.path.basename(fn).decode(encoding)
# the same for os.path.dirname
path_dirname = lambda f: os.path.dirname(fn).decode(encoding)
else:
path_basename = os.path.basename
path_dirname = os.path.dirname
args = {
'suffix': '.tmp',
'prefix': path_basename(fn) + '.',
'dir': path_dirname(fn),
'delete': False,
}
# In Python 2.x, json.dump expects a bytestream.
# In Python 3.x, it writes to a character stream
if sys.version_info < (3, 0):
args['mode'] = 'wb'
else:
args.update({
'mode': 'w',
'encoding': 'utf-8',
})
tf = tempfile.NamedTemporaryFile(**compat_kwargs(args))
try:
with tf:
json.dump(obj, tf)
if sys.platform == 'win32':
# Need to remove existing file on Windows, else os.rename raises
# WindowsError or FileExistsError.
try:
os.unlink(fn)
except OSError:
pass
os.rename(tf.name, fn)
except Exception:
try:
os.remove(tf.name)
except OSError:
pass
raise
if sys.version_info >= (2, 7):
def find_xpath_attr(node, xpath, key, val=None):
""" Find the xpath xpath[@key=val] """
assert re.match(r'^[a-zA-Z_-]+$', key)
expr = xpath + ('[@%s]' % key if val is None else "[@%s='%s']" % (key, val))
return node.find(expr)
else:
def find_xpath_attr(node, xpath, key, val=None):
for f in node.findall(compat_xpath(xpath)):
if key not in f.attrib:
continue
if val is None or f.attrib.get(key) == val:
return f
return None
# On python2.6 the xml.etree.ElementTree.Element methods don't support
# the namespace parameter
def xpath_with_ns(path, ns_map):
components = [c.split(':') for c in path.split('/')]
replaced = []
for c in components:
if len(c) == 1:
replaced.append(c[0])
else:
ns, tag = c
replaced.append('{%s}%s' % (ns_map[ns], tag))
return '/'.join(replaced)
def xpath_element(node, xpath, name=None, fatal=False, default=NO_DEFAULT):
def _find_xpath(xpath):
return node.find(compat_xpath(xpath))
if isinstance(xpath, (str, compat_str)):
n = _find_xpath(xpath)
else:
for xp in xpath:
n = _find_xpath(xp)
if n is not None:
break
if n is None:
if default is not NO_DEFAULT:
return default
elif fatal:
name = xpath if name is None else name
raise ExtractorError('Could not find XML element %s' % name)
else:
return None
return n
def xpath_text(node, xpath, name=None, fatal=False, default=NO_DEFAULT):
n = xpath_element(node, xpath, name, fatal=fatal, default=default)
if n is None or n == default:
return n
if n.text is None:
if default is not NO_DEFAULT:
return default
elif fatal:
name = xpath if name is None else name
raise ExtractorError('Could not find XML element\'s text %s' % name)
else:
return None
return n.text
def xpath_attr(node, xpath, key, name=None, fatal=False, default=NO_DEFAULT):
n = find_xpath_attr(node, xpath, key)
if n is None:
if default is not NO_DEFAULT:
return default
elif fatal:
name = '%s[@%s]' % (xpath, key) if name is None else name
raise ExtractorError('Could not find XML attribute %s' % name)
else:
return None
return n.attrib[key]
def get_element_by_id(id, html):
"""Return the content of the tag with the specified ID in the passed HTML document"""
return get_element_by_attribute('id', id, html)
def get_element_by_attribute(attribute, value, html):
"""Return the content of the tag with the specified attribute in the passed HTML document"""
m = re.search(r'''(?xs)
<([a-zA-Z0-9:._-]+)
(?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'))*?
\s+%s=['"]?%s['"]?
(?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'))*?
\s*>
(?P<content>.*?)
</\1>
''' % (re.escape(attribute), re.escape(value)), html)
if not m:
return None
res = m.group('content')
if res.startswith('"') or res.startswith("'"):
res = res[1:-1]
return unescapeHTML(res)
class HTMLAttributeParser(compat_HTMLParser):
"""Trivial HTML parser to gather the attributes for a single element"""
def __init__(self):
self.attrs = {}
compat_HTMLParser.__init__(self)
def handle_starttag(self, tag, attrs):
self.attrs = dict(attrs)
def extract_attributes(html_element):
"""Given a string for an HTML element such as
<el
a="foo" B="bar" c="&98;az" d=boz
empty= noval entity="&"
sq='"' dq="'"
>
Decode and return a dictionary of attributes.
{
'a': 'foo', 'b': 'bar', c: 'baz', d: 'boz',
'empty': '', 'noval': None, 'entity': '&',
'sq': '"', 'dq': '\''
}.
NB HTMLParser is stricter in Python 2.6 & 3.2 than in later versions,
but the cases in the unit test will work for all of 2.6, 2.7, 3.2-3.5.
"""
parser = HTMLAttributeParser()
parser.feed(html_element)
parser.close()
return parser.attrs
def clean_html(html):
"""Clean an HTML snippet into a readable string"""
if html is None: # Convenience for sanitizing descriptions etc.
return html
# Newline vs <br />
html = html.replace('\n', ' ')
html = re.sub(r'\s*<\s*br\s*/?\s*>\s*', '\n', html)
html = re.sub(r'<\s*/\s*p\s*>\s*<\s*p[^>]*>', '\n', html)
# Strip html tags
html = re.sub('<.*?>', '', html)
# Replace html entities
html = unescapeHTML(html)
return html.strip()
def sanitize_open(filename, open_mode):
"""Try to open the given filename, and slightly tweak it if this fails.
Attempts to open the given filename. If this fails, it tries to change
the filename slightly, step by step, until it's either able to open it
or it fails and raises a final exception, like the standard open()
function.
It returns the tuple (stream, definitive_file_name).
"""
try:
if filename == '-':
if sys.platform == 'win32':
import msvcrt
msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
return (sys.stdout.buffer if hasattr(sys.stdout, 'buffer') else sys.stdout, filename)
stream = open(encodeFilename(filename), open_mode)
return (stream, filename)
except (IOError, OSError) as err:
if err.errno in (errno.EACCES,):
raise
# In case of error, try to remove win32 forbidden chars
alt_filename = sanitize_path(filename)
if alt_filename == filename:
raise
else:
# An exception here should be caught in the caller
stream = open(encodeFilename(alt_filename), open_mode)
return (stream, alt_filename)
def timeconvert(timestr):
"""Convert RFC 2822 defined time string into system timestamp"""
timestamp = None
timetuple = email.utils.parsedate_tz(timestr)
if timetuple is not None:
timestamp = email.utils.mktime_tz(timetuple)
return timestamp
def sanitize_filename(s, restricted=False, is_id=False):
"""Sanitizes a string so it could be used as part of a filename.
If restricted is set, use a stricter subset of allowed characters.
Set is_id if this is not an arbitrary string, but an ID that should be kept if possible
"""
def replace_insane(char):
if restricted and char in ACCENT_CHARS:
return ACCENT_CHARS[char]
if char == '?' or ord(char) < 32 or ord(char) == 127:
return ''
elif char == '"':
return '' if restricted else '\''
elif char == ':':
return '_-' if restricted else ' -'
elif char in '\\/|*<>':
return '_'
if restricted and (char in '!&\'()[]{}$;`^,#' or char.isspace()):
return '_'
if restricted and ord(char) > 127:
return '_'
return char
# Handle timestamps
s = re.sub(r'[0-9]+(?::[0-9]+)+', lambda m: m.group(0).replace(':', '_'), s)
result = ''.join(map(replace_insane, s))
if not is_id:
while '__' in result:
result = result.replace('__', '_')
result = result.strip('_')
# Common case of "Foreign band name - English song title"
if restricted and result.startswith('-_'):
result = result[2:]
if result.startswith('-'):
result = '_' + result[len('-'):]
result = result.lstrip('.')
if not result:
result = '_'
return result
def sanitize_path(s):
"""Sanitizes and normalizes path on Windows"""
if sys.platform != 'win32':
return s
drive_or_unc, _ = os.path.splitdrive(s)
if sys.version_info < (2, 7) and not drive_or_unc:
drive_or_unc, _ = os.path.splitunc(s)
norm_path = os.path.normpath(remove_start(s, drive_or_unc)).split(os.path.sep)
if drive_or_unc:
norm_path.pop(0)
sanitized_path = [
path_part if path_part in ['.', '..'] else re.sub('(?:[/<>:"\\|\\\\?\\*]|[\s.]$)', '#', path_part)
for path_part in norm_path]
if drive_or_unc:
sanitized_path.insert(0, drive_or_unc + os.path.sep)
return os.path.join(*sanitized_path)
# Prepend protocol-less URLs with `http:` scheme in order to mitigate the number of
# unwanted failures due to missing protocol
def sanitize_url(url):
return 'http:%s' % url if url.startswith('//') else url
def sanitized_Request(url, *args, **kwargs):
return compat_urllib_request.Request(sanitize_url(url), *args, **kwargs)
def orderedSet(iterable):
""" Remove all duplicates from the input iterable """
res = []
for el in iterable:
if el not in res:
res.append(el)
return res
def _htmlentity_transform(entity):
"""Transforms an HTML entity to a character."""
# Known non-numeric HTML entity
if entity in compat_html_entities.name2codepoint:
return compat_chr(compat_html_entities.name2codepoint[entity])
mobj = re.match(r'#(x[0-9a-fA-F]+|[0-9]+)', entity)
if mobj is not None:
numstr = mobj.group(1)
if numstr.startswith('x'):
base = 16
numstr = '0%s' % numstr
else:
base = 10
# See https://github.com/rg3/youtube-dl/issues/7518
try:
return compat_chr(int(numstr, base))
except ValueError:
pass
# Unknown entity in name, return its literal representation
return '&%s;' % entity
def unescapeHTML(s):
if s is None:
return None
assert type(s) == compat_str
return re.sub(
r'&([^;]+);', lambda m: _htmlentity_transform(m.group(1)), s)
def get_subprocess_encoding():
if sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5:
# For subprocess calls, encode with locale encoding
# Refer to http://stackoverflow.com/a/9951851/35070
encoding = preferredencoding()
else:
encoding = sys.getfilesystemencoding()
if encoding is None:
encoding = 'utf-8'
return encoding
def encodeFilename(s, for_subprocess=False):
"""
@param s The name of the file
"""
assert type(s) == compat_str
# Python 3 has a Unicode API
if sys.version_info >= (3, 0):
return s
# Pass '' directly to use Unicode APIs on Windows 2000 and up
# (Detecting Windows NT 4 is tricky because 'major >= 4' would
# match Windows 9x series as well. Besides, NT 4 is obsolete.)
if not for_subprocess and sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5:
return s
# Jython assumes filenames are Unicode strings though reported as Python 2.x compatible
if sys.platform.startswith('java'):
return s
return s.encode(get_subprocess_encoding(), 'ignore')
def decodeFilename(b, for_subprocess=False):
if sys.version_info >= (3, 0):
return b
if not isinstance(b, bytes):
return b
return b.decode(get_subprocess_encoding(), 'ignore')
def encodeArgument(s):
if not isinstance(s, compat_str):
# Legacy code that uses byte strings
# Uncomment the following line after fixing all post processors
# assert False, 'Internal error: %r should be of type %r, is %r' % (s, compat_str, type(s))
s = s.decode('ascii')
return encodeFilename(s, True)
def decodeArgument(b):
return decodeFilename(b, True)
def decodeOption(optval):
if optval is None:
return optval
if isinstance(optval, bytes):
optval = optval.decode(preferredencoding())
assert isinstance(optval, compat_str)
return optval
def formatSeconds(secs):
if secs > 3600:
return '%d:%02d:%02d' % (secs // 3600, (secs % 3600) // 60, secs % 60)
elif secs > 60:
return '%d:%02d' % (secs // 60, secs % 60)
else:
return '%d' % secs
def make_HTTPS_handler(params, **kwargs):
opts_no_check_certificate = params.get('nocheckcertificate', False)
if hasattr(ssl, 'create_default_context'): # Python >= 3.4 or 2.7.9
context = ssl.create_default_context(ssl.Purpose.SERVER_AUTH)
if opts_no_check_certificate:
context.check_hostname = False
context.verify_mode = ssl.CERT_NONE
try:
return YoutubeDLHTTPSHandler(params, context=context, **kwargs)
except TypeError:
# Python 2.7.8
# (create_default_context present but HTTPSHandler has no context=)
pass
if sys.version_info < (3, 2):
return YoutubeDLHTTPSHandler(params, **kwargs)
else: # Python < 3.4
context = ssl.SSLContext(ssl.PROTOCOL_TLSv1)
context.verify_mode = (ssl.CERT_NONE
if opts_no_check_certificate
else ssl.CERT_REQUIRED)
context.set_default_verify_paths()
return YoutubeDLHTTPSHandler(params, context=context, **kwargs)
def bug_reports_message():
if ytdl_is_updateable():
update_cmd = 'type youtube-dl -U to update'
else:
update_cmd = 'see https://yt-dl.org/update on how to update'
msg = '; please report this issue on https://yt-dl.org/bug .'
msg += ' Make sure you are using the latest version; %s.' % update_cmd
msg += ' Be sure to call youtube-dl with the --verbose flag and include its complete output.'
return msg
class ExtractorError(Exception):
"""Error during info extraction."""
def __init__(self, msg, tb=None, expected=False, cause=None, video_id=None):
""" tb, if given, is the original traceback (so that it can be printed out).
If expected is set, this is a normal error message and most likely not a bug in youtube-dl.
"""
if sys.exc_info()[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError):
expected = True
if video_id is not None:
msg = video_id + ': ' + msg
if cause:
msg += ' (caused by %r)' % cause
if not expected:
msg += bug_reports_message()
super(ExtractorError, self).__init__(msg)
self.traceback = tb
self.exc_info = sys.exc_info() # preserve original exception
self.cause = cause
self.video_id = video_id
def format_traceback(self):
if self.traceback is None:
return None
return ''.join(traceback.format_tb(self.traceback))
class UnsupportedError(ExtractorError):
def __init__(self, url):
super(UnsupportedError, self).__init__(
'Unsupported URL: %s' % url, expected=True)
self.url = url
class RegexNotFoundError(ExtractorError):
"""Error when a regex didn't match"""
pass
class DownloadError(Exception):
"""Download Error exception.
This exception may be thrown by FileDownloader objects if they are not
configured to continue on errors. They will contain the appropriate
error message.
"""
def __init__(self, msg, exc_info=None):
""" exc_info, if given, is the original exception that caused the trouble (as returned by sys.exc_info()). """
super(DownloadError, self).__init__(msg)
self.exc_info = exc_info
class SameFileError(Exception):
"""Same File exception.
This exception will be thrown by FileDownloader objects if they detect
multiple files would have to be downloaded to the same file on disk.
"""
pass
class PostProcessingError(Exception):
"""Post Processing exception.
This exception may be raised by PostProcessor's .run() method to
indicate an error in the postprocessing task.
"""
def __init__(self, msg):
self.msg = msg
class MaxDownloadsReached(Exception):
""" --max-downloads limit has been reached. """
pass
class UnavailableVideoError(Exception):
"""Unavailable Format exception.
This exception will be thrown when a video is requested
in a format that is not available for that video.
"""
pass
class ContentTooShortError(Exception):
"""Content Too Short exception.
This exception may be raised by FileDownloader objects when a file they
download is too small for what the server announced first, indicating
the connection was probably interrupted.
"""
def __init__(self, downloaded, expected):
# Both in bytes
self.downloaded = downloaded
self.expected = expected
def _create_http_connection(ydl_handler, http_class, is_https, *args, **kwargs):
# Working around python 2 bug (see http://bugs.python.org/issue17849) by limiting
# expected HTTP responses to meet HTTP/1.0 or later (see also
# https://github.com/rg3/youtube-dl/issues/6727)
if sys.version_info < (3, 0):
kwargs[b'strict'] = True
hc = http_class(*args, **kwargs)
source_address = ydl_handler._params.get('source_address')
if source_address is not None:
sa = (source_address, 0)
if hasattr(hc, 'source_address'): # Python 2.7+
hc.source_address = sa
else: # Python 2.6
def _hc_connect(self, *args, **kwargs):
sock = compat_socket_create_connection(
(self.host, self.port), self.timeout, sa)
if is_https:
self.sock = ssl.wrap_socket(
sock, self.key_file, self.cert_file,
ssl_version=ssl.PROTOCOL_TLSv1)
else:
self.sock = sock
hc.connect = functools.partial(_hc_connect, hc)
return hc
def handle_youtubedl_headers(headers):
filtered_headers = headers
if 'Youtubedl-no-compression' in filtered_headers:
filtered_headers = dict((k, v) for k, v in filtered_headers.items() if k.lower() != 'accept-encoding')
del filtered_headers['Youtubedl-no-compression']
return filtered_headers
class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
"""Handler for HTTP requests and responses.
This class, when installed with an OpenerDirector, automatically adds
the standard headers to every HTTP request and handles gzipped and
deflated responses from web servers. If compression is to be avoided in
a particular request, the original request in the program code only has
to include the HTTP header "Youtubedl-no-compression", which will be
removed before making the real request.
Part of this code was copied from:
http://techknack.net/python-urllib2-handlers/
Andrew Rowls, the author of that code, agreed to release it to the
public domain.
"""
def __init__(self, params, *args, **kwargs):
compat_urllib_request.HTTPHandler.__init__(self, *args, **kwargs)
self._params = params
def http_open(self, req):
conn_class = compat_http_client.HTTPConnection
socks_proxy = req.headers.get('Ytdl-socks-proxy')
if socks_proxy:
conn_class = make_socks_conn_class(conn_class, socks_proxy)
del req.headers['Ytdl-socks-proxy']
return self.do_open(functools.partial(
_create_http_connection, self, conn_class, False),
req)
@staticmethod
def deflate(data):
try:
return zlib.decompress(data, -zlib.MAX_WBITS)
except zlib.error:
return zlib.decompress(data)
@staticmethod
def addinfourl_wrapper(stream, headers, url, code):
if hasattr(compat_urllib_request.addinfourl, 'getcode'):
return compat_urllib_request.addinfourl(stream, headers, url, code)
ret = compat_urllib_request.addinfourl(stream, headers, url)
ret.code = code
return ret
def http_request(self, req):
# According to RFC 3986, URLs can not contain non-ASCII characters, however this is not
# always respected by websites, some tend to give out URLs with non percent-encoded
# non-ASCII characters (see telemb.py, ard.py [#3412])
# urllib chokes on URLs with non-ASCII characters (see http://bugs.python.org/issue3991)
# To work around aforementioned issue we will replace request's original URL with
# percent-encoded one
# Since redirects are also affected (e.g. http://www.southpark.de/alle-episoden/s18e09)
# the code of this workaround has been moved here from YoutubeDL.urlopen()
url = req.get_full_url()
url_escaped = escape_url(url)
# Substitute URL if any change after escaping
if url != url_escaped:
req = update_Request(req, url=url_escaped)
for h, v in std_headers.items():
# Capitalize is needed because of Python bug 2275: http://bugs.python.org/issue2275
# The dict keys are capitalized because of this bug by urllib
if h.capitalize() not in req.headers:
req.add_header(h, v)
req.headers = handle_youtubedl_headers(req.headers)
if sys.version_info < (2, 7) and '#' in req.get_full_url():
# Python 2.6 is brain-dead when it comes to fragments
req._Request__original = req._Request__original.partition('#')[0]
req._Request__r_type = req._Request__r_type.partition('#')[0]
return req
def http_response(self, req, resp):
old_resp = resp
# gzip
if resp.headers.get('Content-encoding', '') == 'gzip':
content = resp.read()
gz = gzip.GzipFile(fileobj=io.BytesIO(content), mode='rb')
try:
uncompressed = io.BytesIO(gz.read())
except IOError as original_ioerror:
# There may be junk add the end of the file
# See http://stackoverflow.com/q/4928560/35070 for details
for i in range(1, 1024):
try:
gz = gzip.GzipFile(fileobj=io.BytesIO(content[:-i]), mode='rb')
uncompressed = io.BytesIO(gz.read())
except IOError:
continue
break
else:
raise original_ioerror
resp = self.addinfourl_wrapper(uncompressed, old_resp.headers, old_resp.url, old_resp.code)
resp.msg = old_resp.msg
del resp.headers['Content-encoding']
# deflate
if resp.headers.get('Content-encoding', '') == 'deflate':
gz = io.BytesIO(self.deflate(resp.read()))
resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
resp.msg = old_resp.msg
del resp.headers['Content-encoding']
# Percent-encode redirect URL of Location HTTP header to satisfy RFC 3986 (see
# https://github.com/rg3/youtube-dl/issues/6457).
if 300 <= resp.code < 400:
location = resp.headers.get('Location')
if location:
# As of RFC 2616 default charset is iso-8859-1 that is respected by python 3
if sys.version_info >= (3, 0):
location = location.encode('iso-8859-1').decode('utf-8')
location_escaped = escape_url(location)
if location != location_escaped:
del resp.headers['Location']
resp.headers['Location'] = location_escaped
return resp
https_request = http_request
https_response = http_response
def make_socks_conn_class(base_class, socks_proxy):
assert issubclass(base_class, (
compat_http_client.HTTPConnection, compat_http_client.HTTPSConnection))
url_components = compat_urlparse.urlparse(socks_proxy)
if url_components.scheme.lower() == 'socks5':
socks_type = ProxyType.SOCKS5
elif url_components.scheme.lower() in ('socks', 'socks4'):
socks_type = ProxyType.SOCKS4
elif url_components.scheme.lower() == 'socks4a':
socks_type = ProxyType.SOCKS4A
proxy_args = (
socks_type,
url_components.hostname, url_components.port or 1080,
True, # Remote DNS
url_components.username, url_components.password
)
class SocksConnection(base_class):
def connect(self):
self.sock = sockssocket()
self.sock.setproxy(*proxy_args)
if type(self.timeout) in (int, float):
self.sock.settimeout(self.timeout)
self.sock.connect((self.host, self.port))
if isinstance(self, compat_http_client.HTTPSConnection):
if hasattr(self, '_context'): # Python > 2.6
self.sock = self._context.wrap_socket(
self.sock, server_hostname=self.host)
else:
self.sock = ssl.wrap_socket(self.sock)
return SocksConnection
class YoutubeDLHTTPSHandler(compat_urllib_request.HTTPSHandler):
def __init__(self, params, https_conn_class=None, *args, **kwargs):
compat_urllib_request.HTTPSHandler.__init__(self, *args, **kwargs)
self._https_conn_class = https_conn_class or compat_http_client.HTTPSConnection
self._params = params
def https_open(self, req):
kwargs = {}
conn_class = self._https_conn_class
if hasattr(self, '_context'): # python > 2.6
kwargs['context'] = self._context
if hasattr(self, '_check_hostname'): # python 3.x
kwargs['check_hostname'] = self._check_hostname
socks_proxy = req.headers.get('Ytdl-socks-proxy')
if socks_proxy:
conn_class = make_socks_conn_class(conn_class, socks_proxy)
del req.headers['Ytdl-socks-proxy']
return self.do_open(functools.partial(
_create_http_connection, self, conn_class, True),
req, **kwargs)
class YoutubeDLCookieProcessor(compat_urllib_request.HTTPCookieProcessor):
def __init__(self, cookiejar=None):
compat_urllib_request.HTTPCookieProcessor.__init__(self, cookiejar)
def http_response(self, request, response):
# Python 2 will choke on next HTTP request in row if there are non-ASCII
# characters in Set-Cookie HTTP header of last response (see
# https://github.com/rg3/youtube-dl/issues/6769).
# In order to at least prevent crashing we will percent encode Set-Cookie
# header before HTTPCookieProcessor starts processing it.
# if sys.version_info < (3, 0) and response.headers:
# for set_cookie_header in ('Set-Cookie', 'Set-Cookie2'):
# set_cookie = response.headers.get(set_cookie_header)
# if set_cookie:
# set_cookie_escaped = compat_urllib_parse.quote(set_cookie, b"%/;:@&=+$,!~*'()?#[] ")
# if set_cookie != set_cookie_escaped:
# del response.headers[set_cookie_header]
# response.headers[set_cookie_header] = set_cookie_escaped
return compat_urllib_request.HTTPCookieProcessor.http_response(self, request, response)
https_request = compat_urllib_request.HTTPCookieProcessor.http_request
https_response = http_response
def parse_iso8601(date_str, delimiter='T', timezone=None):
""" Return a UNIX timestamp from the given date """
if date_str is None:
return None
date_str = re.sub(r'\.[0-9]+', '', date_str)
if timezone is None:
m = re.search(
r'(?:Z$| ?(?P<sign>\+|-)(?P<hours>[0-9]{2}):?(?P<minutes>[0-9]{2})$)',
date_str)
if not m:
timezone = datetime.timedelta()
else:
date_str = date_str[:-len(m.group(0))]
if not m.group('sign'):
timezone = datetime.timedelta()
else:
sign = 1 if m.group('sign') == '+' else -1
timezone = datetime.timedelta(
hours=sign * int(m.group('hours')),
minutes=sign * int(m.group('minutes')))
try:
date_format = '%Y-%m-%d{0}%H:%M:%S'.format(delimiter)
dt = datetime.datetime.strptime(date_str, date_format) - timezone
return calendar.timegm(dt.timetuple())
except ValueError:
pass
def unified_strdate(date_str, day_first=True):
"""Return a string with the date in the format YYYYMMDD"""
if date_str is None:
return None
upload_date = None
# Replace commas
date_str = date_str.replace(',', ' ')
# %z (UTC offset) is only supported in python>=3.2
if not re.match(r'^[0-9]{1,2}-[0-9]{1,2}-[0-9]{4}$', date_str):
date_str = re.sub(r' ?(\+|-)[0-9]{2}:?[0-9]{2}$', '', date_str)
# Remove AM/PM + timezone
date_str = re.sub(r'(?i)\s*(?:AM|PM)(?:\s+[A-Z]+)?', '', date_str)
format_expressions = [
'%d %B %Y',
'%d %b %Y',
'%B %d %Y',
'%b %d %Y',
'%b %dst %Y %I:%M',
'%b %dnd %Y %I:%M',
'%b %dth %Y %I:%M',
'%Y %m %d',
'%Y-%m-%d',
'%Y/%m/%d',
'%Y/%m/%d %H:%M:%S',
'%Y-%m-%d %H:%M:%S',
'%Y-%m-%d %H:%M:%S.%f',
'%d.%m.%Y %H:%M',
'%d.%m.%Y %H.%M',
'%Y-%m-%dT%H:%M:%SZ',
'%Y-%m-%dT%H:%M:%S.%fZ',
'%Y-%m-%dT%H:%M:%S.%f0Z',
'%Y-%m-%dT%H:%M:%S',
'%Y-%m-%dT%H:%M:%S.%f',
'%Y-%m-%dT%H:%M',
]
if day_first:
format_expressions.extend([
'%d-%m-%Y',
'%d.%m.%Y',
'%d/%m/%Y',
'%d/%m/%y',
'%d/%m/%Y %H:%M:%S',
])
else:
format_expressions.extend([
'%m-%d-%Y',
'%m.%d.%Y',
'%m/%d/%Y',
'%m/%d/%y',
'%m/%d/%Y %H:%M:%S',
])
for expression in format_expressions:
try:
upload_date = datetime.datetime.strptime(date_str, expression).strftime('%Y%m%d')
except ValueError:
pass
if upload_date is None:
timetuple = email.utils.parsedate_tz(date_str)
if timetuple:
upload_date = datetime.datetime(*timetuple[:6]).strftime('%Y%m%d')
if upload_date is not None:
return compat_str(upload_date)
def determine_ext(url, default_ext='unknown_video'):
if url is None:
return default_ext
guess = url.partition('?')[0].rpartition('.')[2]
if re.match(r'^[A-Za-z0-9]+$', guess):
return guess
# Try extract ext from URLs like http://example.com/foo/bar.mp4/?download
elif guess.rstrip('/') in KNOWN_EXTENSIONS:
return guess.rstrip('/')
else:
return default_ext
def subtitles_filename(filename, sub_lang, sub_format):
return filename.rsplit('.', 1)[0] + '.' + sub_lang + '.' + sub_format
def date_from_str(date_str):
"""
Return a datetime object from a string in the format YYYYMMDD or
(now|today)[+-][0-9](day|week|month|year)(s)?"""
today = datetime.date.today()
if date_str in ('now', 'today'):
return today
if date_str == 'yesterday':
return today - datetime.timedelta(days=1)
match = re.match('(now|today)(?P<sign>[+-])(?P<time>\d+)(?P<unit>day|week|month|year)(s)?', date_str)
if match is not None:
sign = match.group('sign')
time = int(match.group('time'))
if sign == '-':
time = -time
unit = match.group('unit')
# A bad approximation?
if unit == 'month':
unit = 'day'
time *= 30
elif unit == 'year':
unit = 'day'
time *= 365
unit += 's'
delta = datetime.timedelta(**{unit: time})
return today + delta
return datetime.datetime.strptime(date_str, '%Y%m%d').date()
def hyphenate_date(date_str):
"""
Convert a date in 'YYYYMMDD' format to 'YYYY-MM-DD' format"""
match = re.match(r'^(\d\d\d\d)(\d\d)(\d\d)$', date_str)
if match is not None:
return '-'.join(match.groups())
else:
return date_str
class DateRange(object):
"""Represents a time interval between two dates"""
def __init__(self, start=None, end=None):
"""start and end must be strings in the format accepted by date"""
if start is not None:
self.start = date_from_str(start)
else:
self.start = datetime.datetime.min.date()
if end is not None:
self.end = date_from_str(end)
else:
self.end = datetime.datetime.max.date()
if self.start > self.end:
raise ValueError('Date range: "%s" , the start date must be before the end date' % self)
@classmethod
def day(cls, day):
"""Returns a range that only contains the given day"""
return cls(day, day)
def __contains__(self, date):
"""Check if the date is in the range"""
if not isinstance(date, datetime.date):
date = date_from_str(date)
return self.start <= date <= self.end
def __str__(self):
return '%s - %s' % (self.start.isoformat(), self.end.isoformat())
def platform_name():
""" Returns the platform name as a compat_str """
res = platform.platform()
if isinstance(res, bytes):
res = res.decode(preferredencoding())
assert isinstance(res, compat_str)
return res
def _windows_write_string(s, out):
""" Returns True if the string was written using special methods,
False if it has yet to be written out."""
# Adapted from http://stackoverflow.com/a/3259271/35070
import ctypes
import ctypes.wintypes
WIN_OUTPUT_IDS = {
1: -11,
2: -12,
}
try:
fileno = out.fileno()
except AttributeError:
# If the output stream doesn't have a fileno, it's virtual
return False
except io.UnsupportedOperation:
# Some strange Windows pseudo files?
return False
if fileno not in WIN_OUTPUT_IDS:
return False
GetStdHandle = ctypes.WINFUNCTYPE(
ctypes.wintypes.HANDLE, ctypes.wintypes.DWORD)(
(b'GetStdHandle', ctypes.windll.kernel32))
h = GetStdHandle(WIN_OUTPUT_IDS[fileno])
WriteConsoleW = ctypes.WINFUNCTYPE(
ctypes.wintypes.BOOL, ctypes.wintypes.HANDLE, ctypes.wintypes.LPWSTR,
ctypes.wintypes.DWORD, ctypes.POINTER(ctypes.wintypes.DWORD),
ctypes.wintypes.LPVOID)((b'WriteConsoleW', ctypes.windll.kernel32))
written = ctypes.wintypes.DWORD(0)
GetFileType = ctypes.WINFUNCTYPE(ctypes.wintypes.DWORD, ctypes.wintypes.DWORD)((b'GetFileType', ctypes.windll.kernel32))
FILE_TYPE_CHAR = 0x0002
FILE_TYPE_REMOTE = 0x8000
GetConsoleMode = ctypes.WINFUNCTYPE(
ctypes.wintypes.BOOL, ctypes.wintypes.HANDLE,
ctypes.POINTER(ctypes.wintypes.DWORD))(
(b'GetConsoleMode', ctypes.windll.kernel32))
INVALID_HANDLE_VALUE = ctypes.wintypes.DWORD(-1).value
def not_a_console(handle):
if handle == INVALID_HANDLE_VALUE or handle is None:
return True
return ((GetFileType(handle) & ~FILE_TYPE_REMOTE) != FILE_TYPE_CHAR or
GetConsoleMode(handle, ctypes.byref(ctypes.wintypes.DWORD())) == 0)
if not_a_console(h):
return False
def next_nonbmp_pos(s):
try:
return next(i for i, c in enumerate(s) if ord(c) > 0xffff)
except StopIteration:
return len(s)
while s:
count = min(next_nonbmp_pos(s), 1024)
ret = WriteConsoleW(
h, s, count if count else 2, ctypes.byref(written), None)
if ret == 0:
raise OSError('Failed to write string')
if not count: # We just wrote a non-BMP character
assert written.value == 2
s = s[1:]
else:
assert written.value > 0
s = s[written.value:]
return True
def write_string(s, out=None, encoding=None):
if out is None:
out = sys.stderr
assert type(s) == compat_str
if sys.platform == 'win32' and encoding is None and hasattr(out, 'fileno'):
if _windows_write_string(s, out):
return
if ('b' in getattr(out, 'mode', '') or
sys.version_info[0] < 3): # Python 2 lies about mode of sys.stderr
byt = s.encode(encoding or preferredencoding(), 'ignore')
out.write(byt)
elif hasattr(out, 'buffer'):
enc = encoding or getattr(out, 'encoding', None) or preferredencoding()
byt = s.encode(enc, 'ignore')
out.buffer.write(byt)
else:
out.write(s)
out.flush()
def bytes_to_intlist(bs):
if not bs:
return []
if isinstance(bs[0], int): # Python 3
return list(bs)
else:
return [ord(c) for c in bs]
def intlist_to_bytes(xs):
if not xs:
return b''
return compat_struct_pack('%dB' % len(xs), *xs)
# Cross-platform file locking
if sys.platform == 'win32':
import ctypes.wintypes
import msvcrt
class OVERLAPPED(ctypes.Structure):
_fields_ = [
('Internal', ctypes.wintypes.LPVOID),
('InternalHigh', ctypes.wintypes.LPVOID),
('Offset', ctypes.wintypes.DWORD),
('OffsetHigh', ctypes.wintypes.DWORD),
('hEvent', ctypes.wintypes.HANDLE),
]
kernel32 = ctypes.windll.kernel32
LockFileEx = kernel32.LockFileEx
LockFileEx.argtypes = [
ctypes.wintypes.HANDLE, # hFile
ctypes.wintypes.DWORD, # dwFlags
ctypes.wintypes.DWORD, # dwReserved
ctypes.wintypes.DWORD, # nNumberOfBytesToLockLow
ctypes.wintypes.DWORD, # nNumberOfBytesToLockHigh
ctypes.POINTER(OVERLAPPED) # Overlapped
]
LockFileEx.restype = ctypes.wintypes.BOOL
UnlockFileEx = kernel32.UnlockFileEx
UnlockFileEx.argtypes = [
ctypes.wintypes.HANDLE, # hFile
ctypes.wintypes.DWORD, # dwReserved
ctypes.wintypes.DWORD, # nNumberOfBytesToLockLow
ctypes.wintypes.DWORD, # nNumberOfBytesToLockHigh
ctypes.POINTER(OVERLAPPED) # Overlapped
]
UnlockFileEx.restype = ctypes.wintypes.BOOL
whole_low = 0xffffffff
whole_high = 0x7fffffff
def _lock_file(f, exclusive):
overlapped = OVERLAPPED()
overlapped.Offset = 0
overlapped.OffsetHigh = 0
overlapped.hEvent = 0
f._lock_file_overlapped_p = ctypes.pointer(overlapped)
handle = msvcrt.get_osfhandle(f.fileno())
if not LockFileEx(handle, 0x2 if exclusive else 0x0, 0,
whole_low, whole_high, f._lock_file_overlapped_p):
raise OSError('Locking file failed: %r' % ctypes.FormatError())
def _unlock_file(f):
assert f._lock_file_overlapped_p
handle = msvcrt.get_osfhandle(f.fileno())
if not UnlockFileEx(handle, 0,
whole_low, whole_high, f._lock_file_overlapped_p):
raise OSError('Unlocking file failed: %r' % ctypes.FormatError())
else:
# Some platforms, such as Jython, is missing fcntl
try:
import fcntl
def _lock_file(f, exclusive):
fcntl.flock(f, fcntl.LOCK_EX if exclusive else fcntl.LOCK_SH)
def _unlock_file(f):
fcntl.flock(f, fcntl.LOCK_UN)
except ImportError:
UNSUPPORTED_MSG = 'file locking is not supported on this platform'
def _lock_file(f, exclusive):
raise IOError(UNSUPPORTED_MSG)
def _unlock_file(f):
raise IOError(UNSUPPORTED_MSG)
class locked_file(object):
def __init__(self, filename, mode, encoding=None):
assert mode in ['r', 'a', 'w']
self.f = io.open(filename, mode, encoding=encoding)
self.mode = mode
def __enter__(self):
exclusive = self.mode != 'r'
try:
_lock_file(self.f, exclusive)
except IOError:
self.f.close()
raise
return self
def __exit__(self, etype, value, traceback):
try:
_unlock_file(self.f)
finally:
self.f.close()
def __iter__(self):
return iter(self.f)
def write(self, *args):
return self.f.write(*args)
def read(self, *args):
return self.f.read(*args)
def get_filesystem_encoding():
encoding = sys.getfilesystemencoding()
return encoding if encoding is not None else 'utf-8'
def shell_quote(args):
quoted_args = []
encoding = get_filesystem_encoding()
for a in args:
if isinstance(a, bytes):
# We may get a filename encoded with 'encodeFilename'
a = a.decode(encoding)
quoted_args.append(pipes.quote(a))
return ' '.join(quoted_args)
def smuggle_url(url, data):
""" Pass additional data in a URL for internal use. """
sdata = compat_urllib_parse_urlencode(
{'__youtubedl_smuggle': json.dumps(data)})
return url + '#' + sdata
def unsmuggle_url(smug_url, default=None):
if '#__youtubedl_smuggle' not in smug_url:
return smug_url, default
url, _, sdata = smug_url.rpartition('#')
jsond = compat_parse_qs(sdata)['__youtubedl_smuggle'][0]
data = json.loads(jsond)
return url, data
def format_bytes(bytes):
if bytes is None:
return 'N/A'
if type(bytes) is str:
bytes = float(bytes)
if bytes == 0.0:
exponent = 0
else:
exponent = int(math.log(bytes, 1024.0))
suffix = ['B', 'KiB', 'MiB', 'GiB', 'TiB', 'PiB', 'EiB', 'ZiB', 'YiB'][exponent]
converted = float(bytes) / float(1024 ** exponent)
return '%.2f%s' % (converted, suffix)
def lookup_unit_table(unit_table, s):
units_re = '|'.join(re.escape(u) for u in unit_table)
m = re.match(
r'(?P<num>[0-9]+(?:[,.][0-9]*)?)\s*(?P<unit>%s)\b' % units_re, s)
if not m:
return None
num_str = m.group('num').replace(',', '.')
mult = unit_table[m.group('unit')]
return int(float(num_str) * mult)
def parse_filesize(s):
if s is None:
return None
# The lower-case forms are of course incorrect and unofficial,
# but we support those too
_UNIT_TABLE = {
'B': 1,
'b': 1,
'KiB': 1024,
'KB': 1000,
'kB': 1024,
'Kb': 1000,
'MiB': 1024 ** 2,
'MB': 1000 ** 2,
'mB': 1024 ** 2,
'Mb': 1000 ** 2,
'GiB': 1024 ** 3,
'GB': 1000 ** 3,
'gB': 1024 ** 3,
'Gb': 1000 ** 3,
'TiB': 1024 ** 4,
'TB': 1000 ** 4,
'tB': 1024 ** 4,
'Tb': 1000 ** 4,
'PiB': 1024 ** 5,
'PB': 1000 ** 5,
'pB': 1024 ** 5,
'Pb': 1000 ** 5,
'EiB': 1024 ** 6,
'EB': 1000 ** 6,
'eB': 1024 ** 6,
'Eb': 1000 ** 6,
'ZiB': 1024 ** 7,
'ZB': 1000 ** 7,
'zB': 1024 ** 7,
'Zb': 1000 ** 7,
'YiB': 1024 ** 8,
'YB': 1000 ** 8,
'yB': 1024 ** 8,
'Yb': 1000 ** 8,
}
return lookup_unit_table(_UNIT_TABLE, s)
def parse_count(s):
if s is None:
return None
s = s.strip()
if re.match(r'^[\d,.]+$', s):
return str_to_int(s)
_UNIT_TABLE = {
'k': 1000,
'K': 1000,
'm': 1000 ** 2,
'M': 1000 ** 2,
'kk': 1000 ** 2,
'KK': 1000 ** 2,
}
return lookup_unit_table(_UNIT_TABLE, s)
def month_by_name(name):
""" Return the number of a month by (locale-independently) English name """
try:
return ENGLISH_MONTH_NAMES.index(name) + 1
except ValueError:
return None
def month_by_abbreviation(abbrev):
""" Return the number of a month by (locale-independently) English
abbreviations """
try:
return [s[:3] for s in ENGLISH_MONTH_NAMES].index(abbrev) + 1
except ValueError:
return None
def fix_xml_ampersands(xml_str):
"""Replace all the '&' by '&' in XML"""
return re.sub(
r'&(?!amp;|lt;|gt;|apos;|quot;|#x[0-9a-fA-F]{,4};|#[0-9]{,4};)',
'&',
xml_str)
def setproctitle(title):
assert isinstance(title, compat_str)
# ctypes in Jython is not complete
# http://bugs.jython.org/issue2148
if sys.platform.startswith('java'):
return
try:
libc = ctypes.cdll.LoadLibrary('libc.so.6')
except OSError:
return
title_bytes = title.encode('utf-8')
buf = ctypes.create_string_buffer(len(title_bytes))
buf.value = title_bytes
try:
libc.prctl(15, buf, 0, 0, 0)
except AttributeError:
return # Strange libc, just skip this
def remove_start(s, start):
if s.startswith(start):
return s[len(start):]
return s
def remove_end(s, end):
if s.endswith(end):
return s[:-len(end)]
return s
def remove_quotes(s):
if s is None or len(s) < 2:
return s
for quote in ('"', "'", ):
if s[0] == quote and s[-1] == quote:
return s[1:-1]
return s
def url_basename(url):
path = compat_urlparse.urlparse(url).path
return path.strip('/').split('/')[-1]
class HEADRequest(compat_urllib_request.Request):
def get_method(self):
return 'HEAD'
def int_or_none(v, scale=1, default=None, get_attr=None, invscale=1):
if get_attr:
if v is not None:
v = getattr(v, get_attr, None)
if v == '':
v = None
if v is None:
return default
try:
return int(v) * invscale // scale
except ValueError:
return default
def str_or_none(v, default=None):
return default if v is None else compat_str(v)
def str_to_int(int_str):
""" A more relaxed version of int_or_none """
if int_str is None:
return None
int_str = re.sub(r'[,\.\+]', '', int_str)
return int(int_str)
def float_or_none(v, scale=1, invscale=1, default=None):
if v is None:
return default
try:
return float(v) * invscale / scale
except ValueError:
return default
def parse_duration(s):
if not isinstance(s, compat_basestring):
return None
s = s.strip()
days, hours, mins, secs, ms = [None] * 5
m = re.match(r'(?:(?:(?:(?P<days>[0-9]+):)?(?P<hours>[0-9]+):)?(?P<mins>[0-9]+):)?(?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?$', s)
if m:
days, hours, mins, secs, ms = m.groups()
else:
m = re.match(
r'''(?ix)(?:P?T)?
(?:
(?P<days>[0-9]+)\s*d(?:ays?)?\s*
)?
(?:
(?P<hours>[0-9]+)\s*h(?:ours?)?\s*
)?
(?:
(?P<mins>[0-9]+)\s*m(?:in(?:ute)?s?)?\s*
)?
(?:
(?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?\s*s(?:ec(?:ond)?s?)?\s*
)?$''', s)
if m:
days, hours, mins, secs, ms = m.groups()
else:
m = re.match(r'(?i)(?:(?P<hours>[0-9.]+)\s*(?:hours?)|(?P<mins>[0-9.]+)\s*(?:mins?\.?|minutes?)\s*)$', s)
if m:
hours, mins = m.groups()
else:
return None
duration = 0
if secs:
duration += float(secs)
if mins:
duration += float(mins) * 60
if hours:
duration += float(hours) * 60 * 60
if days:
duration += float(days) * 24 * 60 * 60
if ms:
duration += float(ms)
return duration
def prepend_extension(filename, ext, expected_real_ext=None):
name, real_ext = os.path.splitext(filename)
return (
'{0}.{1}{2}'.format(name, ext, real_ext)
if not expected_real_ext or real_ext[1:] == expected_real_ext
else '{0}.{1}'.format(filename, ext))
def replace_extension(filename, ext, expected_real_ext=None):
name, real_ext = os.path.splitext(filename)
return '{0}.{1}'.format(
name if not expected_real_ext or real_ext[1:] == expected_real_ext else filename,
ext)
def check_executable(exe, args=[]):
""" Checks if the given binary is installed somewhere in PATH, and returns its name.
args can be a list of arguments for a short output (like -version) """
try:
subprocess.Popen([exe] + args, stdout=subprocess.PIPE, stderr=subprocess.PIPE).communicate()
except OSError:
return False
return exe
def get_exe_version(exe, args=['--version'],
version_re=None, unrecognized='present'):
""" Returns the version of the specified executable,
or False if the executable is not present """
try:
out, _ = subprocess.Popen(
[encodeArgument(exe)] + args,
stdout=subprocess.PIPE, stderr=subprocess.STDOUT).communicate()
except OSError:
return False
if isinstance(out, bytes): # Python 2.x
out = out.decode('ascii', 'ignore')
return detect_exe_version(out, version_re, unrecognized)
def detect_exe_version(output, version_re=None, unrecognized='present'):
assert isinstance(output, compat_str)
if version_re is None:
version_re = r'version\s+([-0-9._a-zA-Z]+)'
m = re.search(version_re, output)
if m:
return m.group(1)
else:
return unrecognized
class PagedList(object):
def __len__(self):
# This is only useful for tests
return len(self.getslice())
class OnDemandPagedList(PagedList):
def __init__(self, pagefunc, pagesize, use_cache=False):
self._pagefunc = pagefunc
self._pagesize = pagesize
self._use_cache = use_cache
if use_cache:
self._cache = {}
def getslice(self, start=0, end=None):
res = []
for pagenum in itertools.count(start // self._pagesize):
firstid = pagenum * self._pagesize
nextfirstid = pagenum * self._pagesize + self._pagesize
if start >= nextfirstid:
continue
page_results = None
if self._use_cache:
page_results = self._cache.get(pagenum)
if page_results is None:
page_results = list(self._pagefunc(pagenum))
if self._use_cache:
self._cache[pagenum] = page_results
startv = (
start % self._pagesize
if firstid <= start < nextfirstid
else 0)
endv = (
((end - 1) % self._pagesize) + 1
if (end is not None and firstid <= end <= nextfirstid)
else None)
if startv != 0 or endv is not None:
page_results = page_results[startv:endv]
res.extend(page_results)
# A little optimization - if current page is not "full", ie. does
# not contain page_size videos then we can assume that this page
# is the last one - there are no more ids on further pages -
# i.e. no need to query again.
if len(page_results) + startv < self._pagesize:
break
# If we got the whole page, but the next page is not interesting,
# break out early as well
if end == nextfirstid:
break
return res
class InAdvancePagedList(PagedList):
def __init__(self, pagefunc, pagecount, pagesize):
self._pagefunc = pagefunc
self._pagecount = pagecount
self._pagesize = pagesize
def getslice(self, start=0, end=None):
res = []
start_page = start // self._pagesize
end_page = (
self._pagecount if end is None else (end // self._pagesize + 1))
skip_elems = start - start_page * self._pagesize
only_more = None if end is None else end - start
for pagenum in range(start_page, end_page):
page = list(self._pagefunc(pagenum))
if skip_elems:
page = page[skip_elems:]
skip_elems = None
if only_more is not None:
if len(page) < only_more:
only_more -= len(page)
else:
page = page[:only_more]
res.extend(page)
break
res.extend(page)
return res
def uppercase_escape(s):
unicode_escape = codecs.getdecoder('unicode_escape')
return re.sub(
r'\\U[0-9a-fA-F]{8}',
lambda m: unicode_escape(m.group(0))[0],
s)
def lowercase_escape(s):
unicode_escape = codecs.getdecoder('unicode_escape')
return re.sub(
r'\\u[0-9a-fA-F]{4}',
lambda m: unicode_escape(m.group(0))[0],
s)
def escape_rfc3986(s):
"""Escape non-ASCII characters as suggested by RFC 3986"""
if sys.version_info < (3, 0) and isinstance(s, compat_str):
s = s.encode('utf-8')
return compat_urllib_parse.quote(s, b"%/;:@&=+$,!~*'()?#[]")
def escape_url(url):
"""Escape URL as suggested by RFC 3986"""
url_parsed = compat_urllib_parse_urlparse(url)
return url_parsed._replace(
netloc=url_parsed.netloc.encode('idna').decode('ascii'),
path=escape_rfc3986(url_parsed.path),
params=escape_rfc3986(url_parsed.params),
query=escape_rfc3986(url_parsed.query),
fragment=escape_rfc3986(url_parsed.fragment)
).geturl()
def read_batch_urls(batch_fd):
def fixup(url):
if not isinstance(url, compat_str):
url = url.decode('utf-8', 'replace')
BOM_UTF8 = '\xef\xbb\xbf'
if url.startswith(BOM_UTF8):
url = url[len(BOM_UTF8):]
url = url.strip()
if url.startswith(('#', ';', ']')):
return False
return url
with contextlib.closing(batch_fd) as fd:
return [url for url in map(fixup, fd) if url]
def urlencode_postdata(*args, **kargs):
return compat_urllib_parse_urlencode(*args, **kargs).encode('ascii')
def update_url_query(url, query):
if not query:
return url
parsed_url = compat_urlparse.urlparse(url)
qs = compat_parse_qs(parsed_url.query)
qs.update(query)
return compat_urlparse.urlunparse(parsed_url._replace(
query=compat_urllib_parse_urlencode(qs, True)))
def update_Request(req, url=None, data=None, headers={}, query={}):
req_headers = req.headers.copy()
req_headers.update(headers)
req_data = data or req.data
req_url = update_url_query(url or req.get_full_url(), query)
req_type = HEADRequest if req.get_method() == 'HEAD' else compat_urllib_request.Request
new_req = req_type(
req_url, data=req_data, headers=req_headers,
origin_req_host=req.origin_req_host, unverifiable=req.unverifiable)
if hasattr(req, 'timeout'):
new_req.timeout = req.timeout
return new_req
def dict_get(d, key_or_keys, default=None, skip_false_values=True):
if isinstance(key_or_keys, (list, tuple)):
for key in key_or_keys:
if key not in d or d[key] is None or skip_false_values and not d[key]:
continue
return d[key]
return default
return d.get(key_or_keys, default)
def encode_compat_str(string, encoding=preferredencoding(), errors='strict'):
return string if isinstance(string, compat_str) else compat_str(string, encoding, errors)
US_RATINGS = {
'G': 0,
'PG': 10,
'PG-13': 13,
'R': 16,
'NC': 18,
}
def parse_age_limit(s):
if s is None:
return None
m = re.match(r'^(?P<age>\d{1,2})\+?$', s)
return int(m.group('age')) if m else US_RATINGS.get(s)
def strip_jsonp(code):
return re.sub(
r'(?s)^[a-zA-Z0-9_.]+\s*\(\s*(.*)\);?\s*?(?://[^\n]*)*$', r'\1', code)
def js_to_json(code):
def fix_kv(m):
v = m.group(0)
if v in ('true', 'false', 'null'):
return v
if v.startswith('"'):
v = re.sub(r"\\'", "'", v[1:-1])
elif v.startswith("'"):
v = v[1:-1]
v = re.sub(r"\\\\|\\'|\"", lambda m: {
'\\\\': '\\\\',
"\\'": "'",
'"': '\\"',
}[m.group(0)], v)
return '"%s"' % v
res = re.sub(r'''(?x)
"(?:[^"\\]*(?:\\\\|\\['"nu]))*[^"\\]*"|
'(?:[^'\\]*(?:\\\\|\\['"nu]))*[^'\\]*'|
[a-zA-Z_][.a-zA-Z_0-9]*
''', fix_kv, code)
res = re.sub(r',(\s*[\]}])', lambda m: m.group(1), res)
return res
def qualities(quality_ids):
""" Get a numeric quality value out of a list of possible values """
def q(qid):
try:
return quality_ids.index(qid)
except ValueError:
return -1
return q
DEFAULT_OUTTMPL = '%(title)s-%(id)s.%(ext)s'
def limit_length(s, length):
""" Add ellipses to overly long strings """
if s is None:
return None
ELLIPSES = '...'
if len(s) > length:
return s[:length - len(ELLIPSES)] + ELLIPSES
return s
def version_tuple(v):
return tuple(int(e) for e in re.split(r'[-.]', v))
def is_outdated_version(version, limit, assume_new=True):
if not version:
return not assume_new
try:
return version_tuple(version) < version_tuple(limit)
except ValueError:
return not assume_new
def ytdl_is_updateable():
""" Returns if youtube-dl can be updated with -U """
from zipimport import zipimporter
return isinstance(globals().get('__loader__'), zipimporter) or hasattr(sys, 'frozen')
def args_to_str(args):
# Get a short string representation for a subprocess command
return ' '.join(compat_shlex_quote(a) for a in args)
def error_to_compat_str(err):
err_str = str(err)
# On python 2 error byte string must be decoded with proper
# encoding rather than ascii
if sys.version_info[0] < 3:
err_str = err_str.decode(preferredencoding())
return err_str
def mimetype2ext(mt):
if mt is None:
return None
ext = {
'audio/mp4': 'm4a',
}.get(mt)
if ext is not None:
return ext
_, _, res = mt.rpartition('/')
return {
'3gpp': '3gp',
'smptett+xml': 'tt',
'srt': 'srt',
'ttaf+xml': 'dfxp',
'ttml+xml': 'ttml',
'vtt': 'vtt',
'x-flv': 'flv',
'x-mp4-fragmented': 'mp4',
'x-ms-wmv': 'wmv',
}.get(res, res)
def urlhandle_detect_ext(url_handle):
try:
url_handle.headers
getheader = lambda h: url_handle.headers[h]
except AttributeError: # Python < 3
getheader = url_handle.info().getheader
cd = getheader('Content-Disposition')
if cd:
m = re.match(r'attachment;\s*filename="(?P<filename>[^"]+)"', cd)
if m:
e = determine_ext(m.group('filename'), default_ext=None)
if e:
return e
return mimetype2ext(getheader('Content-Type'))
def encode_data_uri(data, mime_type):
return 'data:%s;base64,%s' % (mime_type, base64.b64encode(data).decode('ascii'))
def age_restricted(content_limit, age_limit):
""" Returns True iff the content should be blocked """
if age_limit is None: # No limit set
return False
if content_limit is None:
return False # Content available for everyone
return age_limit < content_limit
def is_html(first_bytes):
""" Detect whether a file contains HTML by examining its first bytes. """
BOMS = [
(b'\xef\xbb\xbf', 'utf-8'),
(b'\x00\x00\xfe\xff', 'utf-32-be'),
(b'\xff\xfe\x00\x00', 'utf-32-le'),
(b'\xff\xfe', 'utf-16-le'),
(b'\xfe\xff', 'utf-16-be'),
]
for bom, enc in BOMS:
if first_bytes.startswith(bom):
s = first_bytes[len(bom):].decode(enc, 'replace')
break
else:
s = first_bytes.decode('utf-8', 'replace')
return re.match(r'^\s*<', s)
def determine_protocol(info_dict):
protocol = info_dict.get('protocol')
if protocol is not None:
return protocol
url = info_dict['url']
if url.startswith('rtmp'):
return 'rtmp'
elif url.startswith('mms'):
return 'mms'
elif url.startswith('rtsp'):
return 'rtsp'
ext = determine_ext(url)
if ext == 'm3u8':
return 'm3u8'
elif ext == 'f4m':
return 'f4m'
return compat_urllib_parse_urlparse(url).scheme
def render_table(header_row, data):
""" Render a list of rows, each as a list of values """
table = [header_row] + data
max_lens = [max(len(compat_str(v)) for v in col) for col in zip(*table)]
format_str = ' '.join('%-' + compat_str(ml + 1) + 's' for ml in max_lens[:-1]) + '%s'
return '\n'.join(format_str % tuple(row) for row in table)
def _match_one(filter_part, dct):
COMPARISON_OPERATORS = {
'<': operator.lt,
'<=': operator.le,
'>': operator.gt,
'>=': operator.ge,
'=': operator.eq,
'!=': operator.ne,
}
operator_rex = re.compile(r'''(?x)\s*
(?P<key>[a-z_]+)
\s*(?P<op>%s)(?P<none_inclusive>\s*\?)?\s*
(?:
(?P<intval>[0-9.]+(?:[kKmMgGtTpPeEzZyY]i?[Bb]?)?)|
(?P<strval>(?![0-9.])[a-z0-9A-Z]*)
)
\s*$
''' % '|'.join(map(re.escape, COMPARISON_OPERATORS.keys())))
m = operator_rex.search(filter_part)
if m:
op = COMPARISON_OPERATORS[m.group('op')]
if m.group('strval') is not None:
if m.group('op') not in ('=', '!='):
raise ValueError(
'Operator %s does not support string values!' % m.group('op'))
comparison_value = m.group('strval')
else:
try:
comparison_value = int(m.group('intval'))
except ValueError:
comparison_value = parse_filesize(m.group('intval'))
if comparison_value is None:
comparison_value = parse_filesize(m.group('intval') + 'B')
if comparison_value is None:
raise ValueError(
'Invalid integer value %r in filter part %r' % (
m.group('intval'), filter_part))
actual_value = dct.get(m.group('key'))
if actual_value is None:
return m.group('none_inclusive')
return op(actual_value, comparison_value)
UNARY_OPERATORS = {
'': lambda v: v is not None,
'!': lambda v: v is None,
}
operator_rex = re.compile(r'''(?x)\s*
(?P<op>%s)\s*(?P<key>[a-z_]+)
\s*$
''' % '|'.join(map(re.escape, UNARY_OPERATORS.keys())))
m = operator_rex.search(filter_part)
if m:
op = UNARY_OPERATORS[m.group('op')]
actual_value = dct.get(m.group('key'))
return op(actual_value)
raise ValueError('Invalid filter part %r' % filter_part)
def match_str(filter_str, dct):
""" Filter a dictionary with a simple string syntax. Returns True (=passes filter) or false """
return all(
_match_one(filter_part, dct) for filter_part in filter_str.split('&'))
def match_filter_func(filter_str):
def _match_func(info_dict):
if match_str(filter_str, info_dict):
return None
else:
video_title = info_dict.get('title', info_dict.get('id', 'video'))
return '%s does not pass filter %s, skipping ..' % (video_title, filter_str)
return _match_func
def parse_dfxp_time_expr(time_expr):
if not time_expr:
return
mobj = re.match(r'^(?P<time_offset>\d+(?:\.\d+)?)s?$', time_expr)
if mobj:
return float(mobj.group('time_offset'))
mobj = re.match(r'^(\d+):(\d\d):(\d\d(?:(?:\.|:)\d+)?)$', time_expr)
if mobj:
return 3600 * int(mobj.group(1)) + 60 * int(mobj.group(2)) + float(mobj.group(3).replace(':', '.'))
def srt_subtitles_timecode(seconds):
return '%02d:%02d:%02d,%03d' % (seconds / 3600, (seconds % 3600) / 60, seconds % 60, (seconds % 1) * 1000)
def dfxp2srt(dfxp_data):
_x = functools.partial(xpath_with_ns, ns_map={
'ttml': 'http://www.w3.org/ns/ttml',
'ttaf1': 'http://www.w3.org/2006/10/ttaf1',
'ttaf1_0604': 'http://www.w3.org/2006/04/ttaf1',
})
class TTMLPElementParser(object):
out = ''
def start(self, tag, attrib):
if tag in (_x('ttml:br'), _x('ttaf1:br'), 'br'):
self.out += '\n'
def end(self, tag):
pass
def data(self, data):
self.out += data
def close(self):
return self.out.strip()
def parse_node(node):
target = TTMLPElementParser()
parser = xml.etree.ElementTree.XMLParser(target=target)
parser.feed(xml.etree.ElementTree.tostring(node))
return parser.close()
dfxp = compat_etree_fromstring(dfxp_data.encode('utf-8'))
out = []
paras = dfxp.findall(_x('.//ttml:p')) or dfxp.findall(_x('.//ttaf1:p')) or dfxp.findall(_x('.//ttaf1_0604:p')) or dfxp.findall('.//p')
if not paras:
raise ValueError('Invalid dfxp/TTML subtitle')
for para, index in zip(paras, itertools.count(1)):
begin_time = parse_dfxp_time_expr(para.attrib.get('begin'))
end_time = parse_dfxp_time_expr(para.attrib.get('end'))
dur = parse_dfxp_time_expr(para.attrib.get('dur'))
if begin_time is None:
continue
if not end_time:
if not dur:
continue
end_time = begin_time + dur
out.append('%d\n%s --> %s\n%s\n\n' % (
index,
srt_subtitles_timecode(begin_time),
srt_subtitles_timecode(end_time),
parse_node(para)))
return ''.join(out)
def cli_option(params, command_option, param):
param = params.get(param)
return [command_option, param] if param is not None else []
def cli_bool_option(params, command_option, param, true_value='true', false_value='false', separator=None):
param = params.get(param)
assert isinstance(param, bool)
if separator:
return [command_option + separator + (true_value if param else false_value)]
return [command_option, true_value if param else false_value]
def cli_valueless_option(params, command_option, param, expected_value=True):
param = params.get(param)
return [command_option] if param == expected_value else []
def cli_configuration_args(params, param, default=[]):
ex_args = params.get(param)
if ex_args is None:
return default
assert isinstance(ex_args, list)
return ex_args
class ISO639Utils(object):
# See http://www.loc.gov/standards/iso639-2/ISO-639-2_utf-8.txt
_lang_map = {
'aa': 'aar',
'ab': 'abk',
'ae': 'ave',
'af': 'afr',
'ak': 'aka',
'am': 'amh',
'an': 'arg',
'ar': 'ara',
'as': 'asm',
'av': 'ava',
'ay': 'aym',
'az': 'aze',
'ba': 'bak',
'be': 'bel',
'bg': 'bul',
'bh': 'bih',
'bi': 'bis',
'bm': 'bam',
'bn': 'ben',
'bo': 'bod',
'br': 'bre',
'bs': 'bos',
'ca': 'cat',
'ce': 'che',
'ch': 'cha',
'co': 'cos',
'cr': 'cre',
'cs': 'ces',
'cu': 'chu',
'cv': 'chv',
'cy': 'cym',
'da': 'dan',
'de': 'deu',
'dv': 'div',
'dz': 'dzo',
'ee': 'ewe',
'el': 'ell',
'en': 'eng',
'eo': 'epo',
'es': 'spa',
'et': 'est',
'eu': 'eus',
'fa': 'fas',
'ff': 'ful',
'fi': 'fin',
'fj': 'fij',
'fo': 'fao',
'fr': 'fra',
'fy': 'fry',
'ga': 'gle',
'gd': 'gla',
'gl': 'glg',
'gn': 'grn',
'gu': 'guj',
'gv': 'glv',
'ha': 'hau',
'he': 'heb',
'hi': 'hin',
'ho': 'hmo',
'hr': 'hrv',
'ht': 'hat',
'hu': 'hun',
'hy': 'hye',
'hz': 'her',
'ia': 'ina',
'id': 'ind',
'ie': 'ile',
'ig': 'ibo',
'ii': 'iii',
'ik': 'ipk',
'io': 'ido',
'is': 'isl',
'it': 'ita',
'iu': 'iku',
'ja': 'jpn',
'jv': 'jav',
'ka': 'kat',
'kg': 'kon',
'ki': 'kik',
'kj': 'kua',
'kk': 'kaz',
'kl': 'kal',
'km': 'khm',
'kn': 'kan',
'ko': 'kor',
'kr': 'kau',
'ks': 'kas',
'ku': 'kur',
'kv': 'kom',
'kw': 'cor',
'ky': 'kir',
'la': 'lat',
'lb': 'ltz',
'lg': 'lug',
'li': 'lim',
'ln': 'lin',
'lo': 'lao',
'lt': 'lit',
'lu': 'lub',
'lv': 'lav',
'mg': 'mlg',
'mh': 'mah',
'mi': 'mri',
'mk': 'mkd',
'ml': 'mal',
'mn': 'mon',
'mr': 'mar',
'ms': 'msa',
'mt': 'mlt',
'my': 'mya',
'na': 'nau',
'nb': 'nob',
'nd': 'nde',
'ne': 'nep',
'ng': 'ndo',
'nl': 'nld',
'nn': 'nno',
'no': 'nor',
'nr': 'nbl',
'nv': 'nav',
'ny': 'nya',
'oc': 'oci',
'oj': 'oji',
'om': 'orm',
'or': 'ori',
'os': 'oss',
'pa': 'pan',
'pi': 'pli',
'pl': 'pol',
'ps': 'pus',
'pt': 'por',
'qu': 'que',
'rm': 'roh',
'rn': 'run',
'ro': 'ron',
'ru': 'rus',
'rw': 'kin',
'sa': 'san',
'sc': 'srd',
'sd': 'snd',
'se': 'sme',
'sg': 'sag',
'si': 'sin',
'sk': 'slk',
'sl': 'slv',
'sm': 'smo',
'sn': 'sna',
'so': 'som',
'sq': 'sqi',
'sr': 'srp',
'ss': 'ssw',
'st': 'sot',
'su': 'sun',
'sv': 'swe',
'sw': 'swa',
'ta': 'tam',
'te': 'tel',
'tg': 'tgk',
'th': 'tha',
'ti': 'tir',
'tk': 'tuk',
'tl': 'tgl',
'tn': 'tsn',
'to': 'ton',
'tr': 'tur',
'ts': 'tso',
'tt': 'tat',
'tw': 'twi',
'ty': 'tah',
'ug': 'uig',
'uk': 'ukr',
'ur': 'urd',
'uz': 'uzb',
've': 'ven',
'vi': 'vie',
'vo': 'vol',
'wa': 'wln',
'wo': 'wol',
'xh': 'xho',
'yi': 'yid',
'yo': 'yor',
'za': 'zha',
'zh': 'zho',
'zu': 'zul',
}
@classmethod
def short2long(cls, code):
"""Convert language code from ISO 639-1 to ISO 639-2/T"""
return cls._lang_map.get(code[:2])
@classmethod
def long2short(cls, code):
"""Convert language code from ISO 639-2/T to ISO 639-1"""
for short_name, long_name in cls._lang_map.items():
if long_name == code:
return short_name
class ISO3166Utils(object):
# From http://data.okfn.org/data/core/country-list
_country_map = {
'AF': 'Afghanistan',
'AX': 'Åland Islands',
'AL': 'Albania',
'DZ': 'Algeria',
'AS': 'American Samoa',
'AD': 'Andorra',
'AO': 'Angola',
'AI': 'Anguilla',
'AQ': 'Antarctica',
'AG': 'Antigua and Barbuda',
'AR': 'Argentina',
'AM': 'Armenia',
'AW': 'Aruba',
'AU': 'Australia',
'AT': 'Austria',
'AZ': 'Azerbaijan',
'BS': 'Bahamas',
'BH': 'Bahrain',
'BD': 'Bangladesh',
'BB': 'Barbados',
'BY': 'Belarus',
'BE': 'Belgium',
'BZ': 'Belize',
'BJ': 'Benin',
'BM': 'Bermuda',
'BT': 'Bhutan',
'BO': 'Bolivia, Plurinational State of',
'BQ': 'Bonaire, Sint Eustatius and Saba',
'BA': 'Bosnia and Herzegovina',
'BW': 'Botswana',
'BV': 'Bouvet Island',
'BR': 'Brazil',
'IO': 'British Indian Ocean Territory',
'BN': 'Brunei Darussalam',
'BG': 'Bulgaria',
'BF': 'Burkina Faso',
'BI': 'Burundi',
'KH': 'Cambodia',
'CM': 'Cameroon',
'CA': 'Canada',
'CV': 'Cape Verde',
'KY': 'Cayman Islands',
'CF': 'Central African Republic',
'TD': 'Chad',
'CL': 'Chile',
'CN': 'China',
'CX': 'Christmas Island',
'CC': 'Cocos (Keeling) Islands',
'CO': 'Colombia',
'KM': 'Comoros',
'CG': 'Congo',
'CD': 'Congo, the Democratic Republic of the',
'CK': 'Cook Islands',
'CR': 'Costa Rica',
'CI': 'Côte d\'Ivoire',
'HR': 'Croatia',
'CU': 'Cuba',
'CW': 'Curaçao',
'CY': 'Cyprus',
'CZ': 'Czech Republic',
'DK': 'Denmark',
'DJ': 'Djibouti',
'DM': 'Dominica',
'DO': 'Dominican Republic',
'EC': 'Ecuador',
'EG': 'Egypt',
'SV': 'El Salvador',
'GQ': 'Equatorial Guinea',
'ER': 'Eritrea',
'EE': 'Estonia',
'ET': 'Ethiopia',
'FK': 'Falkland Islands (Malvinas)',
'FO': 'Faroe Islands',
'FJ': 'Fiji',
'FI': 'Finland',
'FR': 'France',
'GF': 'French Guiana',
'PF': 'French Polynesia',
'TF': 'French Southern Territories',
'GA': 'Gabon',
'GM': 'Gambia',
'GE': 'Georgia',
'DE': 'Germany',
'GH': 'Ghana',
'GI': 'Gibraltar',
'GR': 'Greece',
'GL': 'Greenland',
'GD': 'Grenada',
'GP': 'Guadeloupe',
'GU': 'Guam',
'GT': 'Guatemala',
'GG': 'Guernsey',
'GN': 'Guinea',
'GW': 'Guinea-Bissau',
'GY': 'Guyana',
'HT': 'Haiti',
'HM': 'Heard Island and McDonald Islands',
'VA': 'Holy See (Vatican City State)',
'HN': 'Honduras',
'HK': 'Hong Kong',
'HU': 'Hungary',
'IS': 'Iceland',
'IN': 'India',
'ID': 'Indonesia',
'IR': 'Iran, Islamic Republic of',
'IQ': 'Iraq',
'IE': 'Ireland',
'IM': 'Isle of Man',
'IL': 'Israel',
'IT': 'Italy',
'JM': 'Jamaica',
'JP': 'Japan',
'JE': 'Jersey',
'JO': 'Jordan',
'KZ': 'Kazakhstan',
'KE': 'Kenya',
'KI': 'Kiribati',
'KP': 'Korea, Democratic People\'s Republic of',
'KR': 'Korea, Republic of',
'KW': 'Kuwait',
'KG': 'Kyrgyzstan',
'LA': 'Lao People\'s Democratic Republic',
'LV': 'Latvia',
'LB': 'Lebanon',
'LS': 'Lesotho',
'LR': 'Liberia',
'LY': 'Libya',
'LI': 'Liechtenstein',
'LT': 'Lithuania',
'LU': 'Luxembourg',
'MO': 'Macao',
'MK': 'Macedonia, the Former Yugoslav Republic of',
'MG': 'Madagascar',
'MW': 'Malawi',
'MY': 'Malaysia',
'MV': 'Maldives',
'ML': 'Mali',
'MT': 'Malta',
'MH': 'Marshall Islands',
'MQ': 'Martinique',
'MR': 'Mauritania',
'MU': 'Mauritius',
'YT': 'Mayotte',
'MX': 'Mexico',
'FM': 'Micronesia, Federated States of',
'MD': 'Moldova, Republic of',
'MC': 'Monaco',
'MN': 'Mongolia',
'ME': 'Montenegro',
'MS': 'Montserrat',
'MA': 'Morocco',
'MZ': 'Mozambique',
'MM': 'Myanmar',
'NA': 'Namibia',
'NR': 'Nauru',
'NP': 'Nepal',
'NL': 'Netherlands',
'NC': 'New Caledonia',
'NZ': 'New Zealand',
'NI': 'Nicaragua',
'NE': 'Niger',
'NG': 'Nigeria',
'NU': 'Niue',
'NF': 'Norfolk Island',
'MP': 'Northern Mariana Islands',
'NO': 'Norway',
'OM': 'Oman',
'PK': 'Pakistan',
'PW': 'Palau',
'PS': 'Palestine, State of',
'PA': 'Panama',
'PG': 'Papua New Guinea',
'PY': 'Paraguay',
'PE': 'Peru',
'PH': 'Philippines',
'PN': 'Pitcairn',
'PL': 'Poland',
'PT': 'Portugal',
'PR': 'Puerto Rico',
'QA': 'Qatar',
'RE': 'Réunion',
'RO': 'Romania',
'RU': 'Russian Federation',
'RW': 'Rwanda',
'BL': 'Saint Barthélemy',
'SH': 'Saint Helena, Ascension and Tristan da Cunha',
'KN': 'Saint Kitts and Nevis',
'LC': 'Saint Lucia',
'MF': 'Saint Martin (French part)',
'PM': 'Saint Pierre and Miquelon',
'VC': 'Saint Vincent and the Grenadines',
'WS': 'Samoa',
'SM': 'San Marino',
'ST': 'Sao Tome and Principe',
'SA': 'Saudi Arabia',
'SN': 'Senegal',
'RS': 'Serbia',
'SC': 'Seychelles',
'SL': 'Sierra Leone',
'SG': 'Singapore',
'SX': 'Sint Maarten (Dutch part)',
'SK': 'Slovakia',
'SI': 'Slovenia',
'SB': 'Solomon Islands',
'SO': 'Somalia',
'ZA': 'South Africa',
'GS': 'South Georgia and the South Sandwich Islands',
'SS': 'South Sudan',
'ES': 'Spain',
'LK': 'Sri Lanka',
'SD': 'Sudan',
'SR': 'Suriname',
'SJ': 'Svalbard and Jan Mayen',
'SZ': 'Swaziland',
'SE': 'Sweden',
'CH': 'Switzerland',
'SY': 'Syrian Arab Republic',
'TW': 'Taiwan, Province of China',
'TJ': 'Tajikistan',
'TZ': 'Tanzania, United Republic of',
'TH': 'Thailand',
'TL': 'Timor-Leste',
'TG': 'Togo',
'TK': 'Tokelau',
'TO': 'Tonga',
'TT': 'Trinidad and Tobago',
'TN': 'Tunisia',
'TR': 'Turkey',
'TM': 'Turkmenistan',
'TC': 'Turks and Caicos Islands',
'TV': 'Tuvalu',
'UG': 'Uganda',
'UA': 'Ukraine',
'AE': 'United Arab Emirates',
'GB': 'United Kingdom',
'US': 'United States',
'UM': 'United States Minor Outlying Islands',
'UY': 'Uruguay',
'UZ': 'Uzbekistan',
'VU': 'Vanuatu',
'VE': 'Venezuela, Bolivarian Republic of',
'VN': 'Viet Nam',
'VG': 'Virgin Islands, British',
'VI': 'Virgin Islands, U.S.',
'WF': 'Wallis and Futuna',
'EH': 'Western Sahara',
'YE': 'Yemen',
'ZM': 'Zambia',
'ZW': 'Zimbabwe',
}
@classmethod
def short2full(cls, code):
"""Convert an ISO 3166-2 country code to the corresponding full name"""
return cls._country_map.get(code.upper())
class PerRequestProxyHandler(compat_urllib_request.ProxyHandler):
def __init__(self, proxies=None):
# Set default handlers
for type in ('http', 'https'):
setattr(self, '%s_open' % type,
lambda r, proxy='__noproxy__', type=type, meth=self.proxy_open:
meth(r, proxy, type))
return compat_urllib_request.ProxyHandler.__init__(self, proxies)
def proxy_open(self, req, proxy, type):
req_proxy = req.headers.get('Ytdl-request-proxy')
if req_proxy is not None:
proxy = req_proxy
del req.headers['Ytdl-request-proxy']
if proxy == '__noproxy__':
return None # No Proxy
if compat_urlparse.urlparse(proxy).scheme.lower() in ('socks', 'socks4', 'socks4a', 'socks5'):
req.add_header('Ytdl-socks-proxy', proxy)
# youtube-dl's http/https handlers do wrapping the socket with socks
return None
return compat_urllib_request.ProxyHandler.proxy_open(
self, req, proxy, type)
def ohdave_rsa_encrypt(data, exponent, modulus):
'''
Implement OHDave's RSA algorithm. See http://www.ohdave.com/rsa/
Input:
data: data to encrypt, bytes-like object
exponent, modulus: parameter e and N of RSA algorithm, both integer
Output: hex string of encrypted data
Limitation: supports one block encryption only
'''
payload = int(binascii.hexlify(data[::-1]), 16)
encrypted = pow(payload, exponent, modulus)
return '%x' % encrypted
def encode_base_n(num, n, table=None):
FULL_TABLE = '0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ'
if not table:
table = FULL_TABLE[:n]
if n > len(table):
raise ValueError('base %d exceeds table length %d' % (n, len(table)))
if num == 0:
return table[0]
ret = ''
while num:
ret = table[num % n] + ret
num = num // n
return ret
def decode_packed_codes(code):
mobj = re.search(
r"}\('(.+)',(\d+),(\d+),'([^']+)'\.split\('\|'\)",
code)
obfucasted_code, base, count, symbols = mobj.groups()
base = int(base)
count = int(count)
symbols = symbols.split('|')
symbol_table = {}
while count:
count -= 1
base_n_count = encode_base_n(count, base)
symbol_table[base_n_count] = symbols[count] or base_n_count
return re.sub(
r'\b(\w+)\b', lambda mobj: symbol_table[mobj.group(0)],
obfucasted_code)
|