]> jfr.im git - yt-dlp.git/blame - youtube_dlc/utils.py
#45 Allow date/time formatting in output template
[yt-dlp.git] / youtube_dlc / utils.py
CommitLineData
d77c3dfd 1#!/usr/bin/env python
dcdb292f 2# coding: utf-8
d77c3dfd 3
ecc0c5ee
PH
4from __future__ import unicode_literals
5
1e399778 6import base64
5bc880b9 7import binascii
912b38b4 8import calendar
676eb3f2 9import codecs
c380cc28 10import collections
62e609ab 11import contextlib
e3946f98 12import ctypes
c496ca96
PH
13import datetime
14import email.utils
0c265486 15import email.header
f45c185f 16import errno
be4a824d 17import functools
d77c3dfd 18import gzip
f74980cb 19import imp
03f9daab 20import io
79a2e94e 21import itertools
f4bfd65f 22import json
d77c3dfd 23import locale
02dbf93f 24import math
347de493 25import operator
d77c3dfd 26import os
c496ca96 27import platform
773f291d 28import random
d77c3dfd 29import re
c496ca96 30import socket
79a2e94e 31import ssl
1c088fa8 32import subprocess
d77c3dfd 33import sys
181c8655 34import tempfile
c380cc28 35import time
01951dda 36import traceback
bcf89ce6 37import xml.etree.ElementTree
d77c3dfd 38import zlib
d77c3dfd 39
8c25f81b 40from .compat import (
b4a3d461 41 compat_HTMLParseError,
8bb56eee 42 compat_HTMLParser,
8f9312c3 43 compat_basestring,
8c25f81b 44 compat_chr,
1bab3437 45 compat_cookiejar,
d7cd9a9e 46 compat_ctypes_WINFUNCTYPE,
36e6f62c 47 compat_etree_fromstring,
51098426 48 compat_expanduser,
8c25f81b 49 compat_html_entities,
55b2f099 50 compat_html_entities_html5,
be4a824d 51 compat_http_client,
42db58ec 52 compat_integer_types,
e29663c6 53 compat_numeric_types,
c86b6142 54 compat_kwargs,
efa97bdc 55 compat_os_name,
8c25f81b 56 compat_parse_qs,
702ccf2d 57 compat_shlex_quote,
8c25f81b 58 compat_str,
edaa23f8 59 compat_struct_pack,
d3f8e038 60 compat_struct_unpack,
8c25f81b
PH
61 compat_urllib_error,
62 compat_urllib_parse,
15707c7e 63 compat_urllib_parse_urlencode,
8c25f81b 64 compat_urllib_parse_urlparse,
732044af 65 compat_urllib_parse_urlunparse,
66 compat_urllib_parse_quote,
67 compat_urllib_parse_quote_plus,
7581bfc9 68 compat_urllib_parse_unquote_plus,
8c25f81b
PH
69 compat_urllib_request,
70 compat_urlparse,
810c10ba 71 compat_xpath,
8c25f81b 72)
4644ac55 73
71aff188
YCH
74from .socks import (
75 ProxyType,
76 sockssocket,
77)
78
4644ac55 79
51fb4995
YCH
80def register_socks_protocols():
81 # "Register" SOCKS protocols
d5ae6bb5
YCH
82 # In Python < 2.6.5, urlsplit() suffers from bug https://bugs.python.org/issue7904
83 # URLs with protocols not in urlparse.uses_netloc are not handled correctly
51fb4995
YCH
84 for scheme in ('socks', 'socks4', 'socks4a', 'socks5'):
85 if scheme not in compat_urlparse.uses_netloc:
86 compat_urlparse.uses_netloc.append(scheme)
87
88
468e2e92
FV
89# This is not clearly defined otherwise
90compiled_regex_type = type(re.compile(''))
91
f7a147e3
S
92
93def random_user_agent():
94 _USER_AGENT_TPL = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/%s Safari/537.36'
95 _CHROME_VERSIONS = (
96 '74.0.3729.129',
97 '76.0.3780.3',
98 '76.0.3780.2',
99 '74.0.3729.128',
100 '76.0.3780.1',
101 '76.0.3780.0',
102 '75.0.3770.15',
103 '74.0.3729.127',
104 '74.0.3729.126',
105 '76.0.3779.1',
106 '76.0.3779.0',
107 '75.0.3770.14',
108 '74.0.3729.125',
109 '76.0.3778.1',
110 '76.0.3778.0',
111 '75.0.3770.13',
112 '74.0.3729.124',
113 '74.0.3729.123',
114 '73.0.3683.121',
115 '76.0.3777.1',
116 '76.0.3777.0',
117 '75.0.3770.12',
118 '74.0.3729.122',
119 '76.0.3776.4',
120 '75.0.3770.11',
121 '74.0.3729.121',
122 '76.0.3776.3',
123 '76.0.3776.2',
124 '73.0.3683.120',
125 '74.0.3729.120',
126 '74.0.3729.119',
127 '74.0.3729.118',
128 '76.0.3776.1',
129 '76.0.3776.0',
130 '76.0.3775.5',
131 '75.0.3770.10',
132 '74.0.3729.117',
133 '76.0.3775.4',
134 '76.0.3775.3',
135 '74.0.3729.116',
136 '75.0.3770.9',
137 '76.0.3775.2',
138 '76.0.3775.1',
139 '76.0.3775.0',
140 '75.0.3770.8',
141 '74.0.3729.115',
142 '74.0.3729.114',
143 '76.0.3774.1',
144 '76.0.3774.0',
145 '75.0.3770.7',
146 '74.0.3729.113',
147 '74.0.3729.112',
148 '74.0.3729.111',
149 '76.0.3773.1',
150 '76.0.3773.0',
151 '75.0.3770.6',
152 '74.0.3729.110',
153 '74.0.3729.109',
154 '76.0.3772.1',
155 '76.0.3772.0',
156 '75.0.3770.5',
157 '74.0.3729.108',
158 '74.0.3729.107',
159 '76.0.3771.1',
160 '76.0.3771.0',
161 '75.0.3770.4',
162 '74.0.3729.106',
163 '74.0.3729.105',
164 '75.0.3770.3',
165 '74.0.3729.104',
166 '74.0.3729.103',
167 '74.0.3729.102',
168 '75.0.3770.2',
169 '74.0.3729.101',
170 '75.0.3770.1',
171 '75.0.3770.0',
172 '74.0.3729.100',
173 '75.0.3769.5',
174 '75.0.3769.4',
175 '74.0.3729.99',
176 '75.0.3769.3',
177 '75.0.3769.2',
178 '75.0.3768.6',
179 '74.0.3729.98',
180 '75.0.3769.1',
181 '75.0.3769.0',
182 '74.0.3729.97',
183 '73.0.3683.119',
184 '73.0.3683.118',
185 '74.0.3729.96',
186 '75.0.3768.5',
187 '75.0.3768.4',
188 '75.0.3768.3',
189 '75.0.3768.2',
190 '74.0.3729.95',
191 '74.0.3729.94',
192 '75.0.3768.1',
193 '75.0.3768.0',
194 '74.0.3729.93',
195 '74.0.3729.92',
196 '73.0.3683.117',
197 '74.0.3729.91',
198 '75.0.3766.3',
199 '74.0.3729.90',
200 '75.0.3767.2',
201 '75.0.3767.1',
202 '75.0.3767.0',
203 '74.0.3729.89',
204 '73.0.3683.116',
205 '75.0.3766.2',
206 '74.0.3729.88',
207 '75.0.3766.1',
208 '75.0.3766.0',
209 '74.0.3729.87',
210 '73.0.3683.115',
211 '74.0.3729.86',
212 '75.0.3765.1',
213 '75.0.3765.0',
214 '74.0.3729.85',
215 '73.0.3683.114',
216 '74.0.3729.84',
217 '75.0.3764.1',
218 '75.0.3764.0',
219 '74.0.3729.83',
220 '73.0.3683.113',
221 '75.0.3763.2',
222 '75.0.3761.4',
223 '74.0.3729.82',
224 '75.0.3763.1',
225 '75.0.3763.0',
226 '74.0.3729.81',
227 '73.0.3683.112',
228 '75.0.3762.1',
229 '75.0.3762.0',
230 '74.0.3729.80',
231 '75.0.3761.3',
232 '74.0.3729.79',
233 '73.0.3683.111',
234 '75.0.3761.2',
235 '74.0.3729.78',
236 '74.0.3729.77',
237 '75.0.3761.1',
238 '75.0.3761.0',
239 '73.0.3683.110',
240 '74.0.3729.76',
241 '74.0.3729.75',
242 '75.0.3760.0',
243 '74.0.3729.74',
244 '75.0.3759.8',
245 '75.0.3759.7',
246 '75.0.3759.6',
247 '74.0.3729.73',
248 '75.0.3759.5',
249 '74.0.3729.72',
250 '73.0.3683.109',
251 '75.0.3759.4',
252 '75.0.3759.3',
253 '74.0.3729.71',
254 '75.0.3759.2',
255 '74.0.3729.70',
256 '73.0.3683.108',
257 '74.0.3729.69',
258 '75.0.3759.1',
259 '75.0.3759.0',
260 '74.0.3729.68',
261 '73.0.3683.107',
262 '74.0.3729.67',
263 '75.0.3758.1',
264 '75.0.3758.0',
265 '74.0.3729.66',
266 '73.0.3683.106',
267 '74.0.3729.65',
268 '75.0.3757.1',
269 '75.0.3757.0',
270 '74.0.3729.64',
271 '73.0.3683.105',
272 '74.0.3729.63',
273 '75.0.3756.1',
274 '75.0.3756.0',
275 '74.0.3729.62',
276 '73.0.3683.104',
277 '75.0.3755.3',
278 '75.0.3755.2',
279 '73.0.3683.103',
280 '75.0.3755.1',
281 '75.0.3755.0',
282 '74.0.3729.61',
283 '73.0.3683.102',
284 '74.0.3729.60',
285 '75.0.3754.2',
286 '74.0.3729.59',
287 '75.0.3753.4',
288 '74.0.3729.58',
289 '75.0.3754.1',
290 '75.0.3754.0',
291 '74.0.3729.57',
292 '73.0.3683.101',
293 '75.0.3753.3',
294 '75.0.3752.2',
295 '75.0.3753.2',
296 '74.0.3729.56',
297 '75.0.3753.1',
298 '75.0.3753.0',
299 '74.0.3729.55',
300 '73.0.3683.100',
301 '74.0.3729.54',
302 '75.0.3752.1',
303 '75.0.3752.0',
304 '74.0.3729.53',
305 '73.0.3683.99',
306 '74.0.3729.52',
307 '75.0.3751.1',
308 '75.0.3751.0',
309 '74.0.3729.51',
310 '73.0.3683.98',
311 '74.0.3729.50',
312 '75.0.3750.0',
313 '74.0.3729.49',
314 '74.0.3729.48',
315 '74.0.3729.47',
316 '75.0.3749.3',
317 '74.0.3729.46',
318 '73.0.3683.97',
319 '75.0.3749.2',
320 '74.0.3729.45',
321 '75.0.3749.1',
322 '75.0.3749.0',
323 '74.0.3729.44',
324 '73.0.3683.96',
325 '74.0.3729.43',
326 '74.0.3729.42',
327 '75.0.3748.1',
328 '75.0.3748.0',
329 '74.0.3729.41',
330 '75.0.3747.1',
331 '73.0.3683.95',
332 '75.0.3746.4',
333 '74.0.3729.40',
334 '74.0.3729.39',
335 '75.0.3747.0',
336 '75.0.3746.3',
337 '75.0.3746.2',
338 '74.0.3729.38',
339 '75.0.3746.1',
340 '75.0.3746.0',
341 '74.0.3729.37',
342 '73.0.3683.94',
343 '75.0.3745.5',
344 '75.0.3745.4',
345 '75.0.3745.3',
346 '75.0.3745.2',
347 '74.0.3729.36',
348 '75.0.3745.1',
349 '75.0.3745.0',
350 '75.0.3744.2',
351 '74.0.3729.35',
352 '73.0.3683.93',
353 '74.0.3729.34',
354 '75.0.3744.1',
355 '75.0.3744.0',
356 '74.0.3729.33',
357 '73.0.3683.92',
358 '74.0.3729.32',
359 '74.0.3729.31',
360 '73.0.3683.91',
361 '75.0.3741.2',
362 '75.0.3740.5',
363 '74.0.3729.30',
364 '75.0.3741.1',
365 '75.0.3741.0',
366 '74.0.3729.29',
367 '75.0.3740.4',
368 '73.0.3683.90',
369 '74.0.3729.28',
370 '75.0.3740.3',
371 '73.0.3683.89',
372 '75.0.3740.2',
373 '74.0.3729.27',
374 '75.0.3740.1',
375 '75.0.3740.0',
376 '74.0.3729.26',
377 '73.0.3683.88',
378 '73.0.3683.87',
379 '74.0.3729.25',
380 '75.0.3739.1',
381 '75.0.3739.0',
382 '73.0.3683.86',
383 '74.0.3729.24',
384 '73.0.3683.85',
385 '75.0.3738.4',
386 '75.0.3738.3',
387 '75.0.3738.2',
388 '75.0.3738.1',
389 '75.0.3738.0',
390 '74.0.3729.23',
391 '73.0.3683.84',
392 '74.0.3729.22',
393 '74.0.3729.21',
394 '75.0.3737.1',
395 '75.0.3737.0',
396 '74.0.3729.20',
397 '73.0.3683.83',
398 '74.0.3729.19',
399 '75.0.3736.1',
400 '75.0.3736.0',
401 '74.0.3729.18',
402 '73.0.3683.82',
403 '74.0.3729.17',
404 '75.0.3735.1',
405 '75.0.3735.0',
406 '74.0.3729.16',
407 '73.0.3683.81',
408 '75.0.3734.1',
409 '75.0.3734.0',
410 '74.0.3729.15',
411 '73.0.3683.80',
412 '74.0.3729.14',
413 '75.0.3733.1',
414 '75.0.3733.0',
415 '75.0.3732.1',
416 '74.0.3729.13',
417 '74.0.3729.12',
418 '73.0.3683.79',
419 '74.0.3729.11',
420 '75.0.3732.0',
421 '74.0.3729.10',
422 '73.0.3683.78',
423 '74.0.3729.9',
424 '74.0.3729.8',
425 '74.0.3729.7',
426 '75.0.3731.3',
427 '75.0.3731.2',
428 '75.0.3731.0',
429 '74.0.3729.6',
430 '73.0.3683.77',
431 '73.0.3683.76',
432 '75.0.3730.5',
433 '75.0.3730.4',
434 '73.0.3683.75',
435 '74.0.3729.5',
436 '73.0.3683.74',
437 '75.0.3730.3',
438 '75.0.3730.2',
439 '74.0.3729.4',
440 '73.0.3683.73',
441 '73.0.3683.72',
442 '75.0.3730.1',
443 '75.0.3730.0',
444 '74.0.3729.3',
445 '73.0.3683.71',
446 '74.0.3729.2',
447 '73.0.3683.70',
448 '74.0.3729.1',
449 '74.0.3729.0',
450 '74.0.3726.4',
451 '73.0.3683.69',
452 '74.0.3726.3',
453 '74.0.3728.0',
454 '74.0.3726.2',
455 '73.0.3683.68',
456 '74.0.3726.1',
457 '74.0.3726.0',
458 '74.0.3725.4',
459 '73.0.3683.67',
460 '73.0.3683.66',
461 '74.0.3725.3',
462 '74.0.3725.2',
463 '74.0.3725.1',
464 '74.0.3724.8',
465 '74.0.3725.0',
466 '73.0.3683.65',
467 '74.0.3724.7',
468 '74.0.3724.6',
469 '74.0.3724.5',
470 '74.0.3724.4',
471 '74.0.3724.3',
472 '74.0.3724.2',
473 '74.0.3724.1',
474 '74.0.3724.0',
475 '73.0.3683.64',
476 '74.0.3723.1',
477 '74.0.3723.0',
478 '73.0.3683.63',
479 '74.0.3722.1',
480 '74.0.3722.0',
481 '73.0.3683.62',
482 '74.0.3718.9',
483 '74.0.3702.3',
484 '74.0.3721.3',
485 '74.0.3721.2',
486 '74.0.3721.1',
487 '74.0.3721.0',
488 '74.0.3720.6',
489 '73.0.3683.61',
490 '72.0.3626.122',
491 '73.0.3683.60',
492 '74.0.3720.5',
493 '72.0.3626.121',
494 '74.0.3718.8',
495 '74.0.3720.4',
496 '74.0.3720.3',
497 '74.0.3718.7',
498 '74.0.3720.2',
499 '74.0.3720.1',
500 '74.0.3720.0',
501 '74.0.3718.6',
502 '74.0.3719.5',
503 '73.0.3683.59',
504 '74.0.3718.5',
505 '74.0.3718.4',
506 '74.0.3719.4',
507 '74.0.3719.3',
508 '74.0.3719.2',
509 '74.0.3719.1',
510 '73.0.3683.58',
511 '74.0.3719.0',
512 '73.0.3683.57',
513 '73.0.3683.56',
514 '74.0.3718.3',
515 '73.0.3683.55',
516 '74.0.3718.2',
517 '74.0.3718.1',
518 '74.0.3718.0',
519 '73.0.3683.54',
520 '74.0.3717.2',
521 '73.0.3683.53',
522 '74.0.3717.1',
523 '74.0.3717.0',
524 '73.0.3683.52',
525 '74.0.3716.1',
526 '74.0.3716.0',
527 '73.0.3683.51',
528 '74.0.3715.1',
529 '74.0.3715.0',
530 '73.0.3683.50',
531 '74.0.3711.2',
532 '74.0.3714.2',
533 '74.0.3713.3',
534 '74.0.3714.1',
535 '74.0.3714.0',
536 '73.0.3683.49',
537 '74.0.3713.1',
538 '74.0.3713.0',
539 '72.0.3626.120',
540 '73.0.3683.48',
541 '74.0.3712.2',
542 '74.0.3712.1',
543 '74.0.3712.0',
544 '73.0.3683.47',
545 '72.0.3626.119',
546 '73.0.3683.46',
547 '74.0.3710.2',
548 '72.0.3626.118',
549 '74.0.3711.1',
550 '74.0.3711.0',
551 '73.0.3683.45',
552 '72.0.3626.117',
553 '74.0.3710.1',
554 '74.0.3710.0',
555 '73.0.3683.44',
556 '72.0.3626.116',
557 '74.0.3709.1',
558 '74.0.3709.0',
559 '74.0.3704.9',
560 '73.0.3683.43',
561 '72.0.3626.115',
562 '74.0.3704.8',
563 '74.0.3704.7',
564 '74.0.3708.0',
565 '74.0.3706.7',
566 '74.0.3704.6',
567 '73.0.3683.42',
568 '72.0.3626.114',
569 '74.0.3706.6',
570 '72.0.3626.113',
571 '74.0.3704.5',
572 '74.0.3706.5',
573 '74.0.3706.4',
574 '74.0.3706.3',
575 '74.0.3706.2',
576 '74.0.3706.1',
577 '74.0.3706.0',
578 '73.0.3683.41',
579 '72.0.3626.112',
580 '74.0.3705.1',
581 '74.0.3705.0',
582 '73.0.3683.40',
583 '72.0.3626.111',
584 '73.0.3683.39',
585 '74.0.3704.4',
586 '73.0.3683.38',
587 '74.0.3704.3',
588 '74.0.3704.2',
589 '74.0.3704.1',
590 '74.0.3704.0',
591 '73.0.3683.37',
592 '72.0.3626.110',
593 '72.0.3626.109',
594 '74.0.3703.3',
595 '74.0.3703.2',
596 '73.0.3683.36',
597 '74.0.3703.1',
598 '74.0.3703.0',
599 '73.0.3683.35',
600 '72.0.3626.108',
601 '74.0.3702.2',
602 '74.0.3699.3',
603 '74.0.3702.1',
604 '74.0.3702.0',
605 '73.0.3683.34',
606 '72.0.3626.107',
607 '73.0.3683.33',
608 '74.0.3701.1',
609 '74.0.3701.0',
610 '73.0.3683.32',
611 '73.0.3683.31',
612 '72.0.3626.105',
613 '74.0.3700.1',
614 '74.0.3700.0',
615 '73.0.3683.29',
616 '72.0.3626.103',
617 '74.0.3699.2',
618 '74.0.3699.1',
619 '74.0.3699.0',
620 '73.0.3683.28',
621 '72.0.3626.102',
622 '73.0.3683.27',
623 '73.0.3683.26',
624 '74.0.3698.0',
625 '74.0.3696.2',
626 '72.0.3626.101',
627 '73.0.3683.25',
628 '74.0.3696.1',
629 '74.0.3696.0',
630 '74.0.3694.8',
631 '72.0.3626.100',
632 '74.0.3694.7',
633 '74.0.3694.6',
634 '74.0.3694.5',
635 '74.0.3694.4',
636 '72.0.3626.99',
637 '72.0.3626.98',
638 '74.0.3694.3',
639 '73.0.3683.24',
640 '72.0.3626.97',
641 '72.0.3626.96',
642 '72.0.3626.95',
643 '73.0.3683.23',
644 '72.0.3626.94',
645 '73.0.3683.22',
646 '73.0.3683.21',
647 '72.0.3626.93',
648 '74.0.3694.2',
649 '72.0.3626.92',
650 '74.0.3694.1',
651 '74.0.3694.0',
652 '74.0.3693.6',
653 '73.0.3683.20',
654 '72.0.3626.91',
655 '74.0.3693.5',
656 '74.0.3693.4',
657 '74.0.3693.3',
658 '74.0.3693.2',
659 '73.0.3683.19',
660 '74.0.3693.1',
661 '74.0.3693.0',
662 '73.0.3683.18',
663 '72.0.3626.90',
664 '74.0.3692.1',
665 '74.0.3692.0',
666 '73.0.3683.17',
667 '72.0.3626.89',
668 '74.0.3687.3',
669 '74.0.3691.1',
670 '74.0.3691.0',
671 '73.0.3683.16',
672 '72.0.3626.88',
673 '72.0.3626.87',
674 '73.0.3683.15',
675 '74.0.3690.1',
676 '74.0.3690.0',
677 '73.0.3683.14',
678 '72.0.3626.86',
679 '73.0.3683.13',
680 '73.0.3683.12',
681 '74.0.3689.1',
682 '74.0.3689.0',
683 '73.0.3683.11',
684 '72.0.3626.85',
685 '73.0.3683.10',
686 '72.0.3626.84',
687 '73.0.3683.9',
688 '74.0.3688.1',
689 '74.0.3688.0',
690 '73.0.3683.8',
691 '72.0.3626.83',
692 '74.0.3687.2',
693 '74.0.3687.1',
694 '74.0.3687.0',
695 '73.0.3683.7',
696 '72.0.3626.82',
697 '74.0.3686.4',
698 '72.0.3626.81',
699 '74.0.3686.3',
700 '74.0.3686.2',
701 '74.0.3686.1',
702 '74.0.3686.0',
703 '73.0.3683.6',
704 '72.0.3626.80',
705 '74.0.3685.1',
706 '74.0.3685.0',
707 '73.0.3683.5',
708 '72.0.3626.79',
709 '74.0.3684.1',
710 '74.0.3684.0',
711 '73.0.3683.4',
712 '72.0.3626.78',
713 '72.0.3626.77',
714 '73.0.3683.3',
715 '73.0.3683.2',
716 '72.0.3626.76',
717 '73.0.3683.1',
718 '73.0.3683.0',
719 '72.0.3626.75',
720 '71.0.3578.141',
721 '73.0.3682.1',
722 '73.0.3682.0',
723 '72.0.3626.74',
724 '71.0.3578.140',
725 '73.0.3681.4',
726 '73.0.3681.3',
727 '73.0.3681.2',
728 '73.0.3681.1',
729 '73.0.3681.0',
730 '72.0.3626.73',
731 '71.0.3578.139',
732 '72.0.3626.72',
733 '72.0.3626.71',
734 '73.0.3680.1',
735 '73.0.3680.0',
736 '72.0.3626.70',
737 '71.0.3578.138',
738 '73.0.3678.2',
739 '73.0.3679.1',
740 '73.0.3679.0',
741 '72.0.3626.69',
742 '71.0.3578.137',
743 '73.0.3678.1',
744 '73.0.3678.0',
745 '71.0.3578.136',
746 '73.0.3677.1',
747 '73.0.3677.0',
748 '72.0.3626.68',
749 '72.0.3626.67',
750 '71.0.3578.135',
751 '73.0.3676.1',
752 '73.0.3676.0',
753 '73.0.3674.2',
754 '72.0.3626.66',
755 '71.0.3578.134',
756 '73.0.3674.1',
757 '73.0.3674.0',
758 '72.0.3626.65',
759 '71.0.3578.133',
760 '73.0.3673.2',
761 '73.0.3673.1',
762 '73.0.3673.0',
763 '72.0.3626.64',
764 '71.0.3578.132',
765 '72.0.3626.63',
766 '72.0.3626.62',
767 '72.0.3626.61',
768 '72.0.3626.60',
769 '73.0.3672.1',
770 '73.0.3672.0',
771 '72.0.3626.59',
772 '71.0.3578.131',
773 '73.0.3671.3',
774 '73.0.3671.2',
775 '73.0.3671.1',
776 '73.0.3671.0',
777 '72.0.3626.58',
778 '71.0.3578.130',
779 '73.0.3670.1',
780 '73.0.3670.0',
781 '72.0.3626.57',
782 '71.0.3578.129',
783 '73.0.3669.1',
784 '73.0.3669.0',
785 '72.0.3626.56',
786 '71.0.3578.128',
787 '73.0.3668.2',
788 '73.0.3668.1',
789 '73.0.3668.0',
790 '72.0.3626.55',
791 '71.0.3578.127',
792 '73.0.3667.2',
793 '73.0.3667.1',
794 '73.0.3667.0',
795 '72.0.3626.54',
796 '71.0.3578.126',
797 '73.0.3666.1',
798 '73.0.3666.0',
799 '72.0.3626.53',
800 '71.0.3578.125',
801 '73.0.3665.4',
802 '73.0.3665.3',
803 '72.0.3626.52',
804 '73.0.3665.2',
805 '73.0.3664.4',
806 '73.0.3665.1',
807 '73.0.3665.0',
808 '72.0.3626.51',
809 '71.0.3578.124',
810 '72.0.3626.50',
811 '73.0.3664.3',
812 '73.0.3664.2',
813 '73.0.3664.1',
814 '73.0.3664.0',
815 '73.0.3663.2',
816 '72.0.3626.49',
817 '71.0.3578.123',
818 '73.0.3663.1',
819 '73.0.3663.0',
820 '72.0.3626.48',
821 '71.0.3578.122',
822 '73.0.3662.1',
823 '73.0.3662.0',
824 '72.0.3626.47',
825 '71.0.3578.121',
826 '73.0.3661.1',
827 '72.0.3626.46',
828 '73.0.3661.0',
829 '72.0.3626.45',
830 '71.0.3578.120',
831 '73.0.3660.2',
832 '73.0.3660.1',
833 '73.0.3660.0',
834 '72.0.3626.44',
835 '71.0.3578.119',
836 '73.0.3659.1',
837 '73.0.3659.0',
838 '72.0.3626.43',
839 '71.0.3578.118',
840 '73.0.3658.1',
841 '73.0.3658.0',
842 '72.0.3626.42',
843 '71.0.3578.117',
844 '73.0.3657.1',
845 '73.0.3657.0',
846 '72.0.3626.41',
847 '71.0.3578.116',
848 '73.0.3656.1',
849 '73.0.3656.0',
850 '72.0.3626.40',
851 '71.0.3578.115',
852 '73.0.3655.1',
853 '73.0.3655.0',
854 '72.0.3626.39',
855 '71.0.3578.114',
856 '73.0.3654.1',
857 '73.0.3654.0',
858 '72.0.3626.38',
859 '71.0.3578.113',
860 '73.0.3653.1',
861 '73.0.3653.0',
862 '72.0.3626.37',
863 '71.0.3578.112',
864 '73.0.3652.1',
865 '73.0.3652.0',
866 '72.0.3626.36',
867 '71.0.3578.111',
868 '73.0.3651.1',
869 '73.0.3651.0',
870 '72.0.3626.35',
871 '71.0.3578.110',
872 '73.0.3650.1',
873 '73.0.3650.0',
874 '72.0.3626.34',
875 '71.0.3578.109',
876 '73.0.3649.1',
877 '73.0.3649.0',
878 '72.0.3626.33',
879 '71.0.3578.108',
880 '73.0.3648.2',
881 '73.0.3648.1',
882 '73.0.3648.0',
883 '72.0.3626.32',
884 '71.0.3578.107',
885 '73.0.3647.2',
886 '73.0.3647.1',
887 '73.0.3647.0',
888 '72.0.3626.31',
889 '71.0.3578.106',
890 '73.0.3635.3',
891 '73.0.3646.2',
892 '73.0.3646.1',
893 '73.0.3646.0',
894 '72.0.3626.30',
895 '71.0.3578.105',
896 '72.0.3626.29',
897 '73.0.3645.2',
898 '73.0.3645.1',
899 '73.0.3645.0',
900 '72.0.3626.28',
901 '71.0.3578.104',
902 '72.0.3626.27',
903 '72.0.3626.26',
904 '72.0.3626.25',
905 '72.0.3626.24',
906 '73.0.3644.0',
907 '73.0.3643.2',
908 '72.0.3626.23',
909 '71.0.3578.103',
910 '73.0.3643.1',
911 '73.0.3643.0',
912 '72.0.3626.22',
913 '71.0.3578.102',
914 '73.0.3642.1',
915 '73.0.3642.0',
916 '72.0.3626.21',
917 '71.0.3578.101',
918 '73.0.3641.1',
919 '73.0.3641.0',
920 '72.0.3626.20',
921 '71.0.3578.100',
922 '72.0.3626.19',
923 '73.0.3640.1',
924 '73.0.3640.0',
925 '72.0.3626.18',
926 '73.0.3639.1',
927 '71.0.3578.99',
928 '73.0.3639.0',
929 '72.0.3626.17',
930 '73.0.3638.2',
931 '72.0.3626.16',
932 '73.0.3638.1',
933 '73.0.3638.0',
934 '72.0.3626.15',
935 '71.0.3578.98',
936 '73.0.3635.2',
937 '71.0.3578.97',
938 '73.0.3637.1',
939 '73.0.3637.0',
940 '72.0.3626.14',
941 '71.0.3578.96',
942 '71.0.3578.95',
943 '72.0.3626.13',
944 '71.0.3578.94',
945 '73.0.3636.2',
946 '71.0.3578.93',
947 '73.0.3636.1',
948 '73.0.3636.0',
949 '72.0.3626.12',
950 '71.0.3578.92',
951 '73.0.3635.1',
952 '73.0.3635.0',
953 '72.0.3626.11',
954 '71.0.3578.91',
955 '73.0.3634.2',
956 '73.0.3634.1',
957 '73.0.3634.0',
958 '72.0.3626.10',
959 '71.0.3578.90',
960 '71.0.3578.89',
961 '73.0.3633.2',
962 '73.0.3633.1',
963 '73.0.3633.0',
964 '72.0.3610.4',
965 '72.0.3626.9',
966 '71.0.3578.88',
967 '73.0.3632.5',
968 '73.0.3632.4',
969 '73.0.3632.3',
970 '73.0.3632.2',
971 '73.0.3632.1',
972 '73.0.3632.0',
973 '72.0.3626.8',
974 '71.0.3578.87',
975 '73.0.3631.2',
976 '73.0.3631.1',
977 '73.0.3631.0',
978 '72.0.3626.7',
979 '71.0.3578.86',
980 '72.0.3626.6',
981 '73.0.3630.1',
982 '73.0.3630.0',
983 '72.0.3626.5',
984 '71.0.3578.85',
985 '72.0.3626.4',
986 '73.0.3628.3',
987 '73.0.3628.2',
988 '73.0.3629.1',
989 '73.0.3629.0',
990 '72.0.3626.3',
991 '71.0.3578.84',
992 '73.0.3628.1',
993 '73.0.3628.0',
994 '71.0.3578.83',
995 '73.0.3627.1',
996 '73.0.3627.0',
997 '72.0.3626.2',
998 '71.0.3578.82',
999 '71.0.3578.81',
1000 '71.0.3578.80',
1001 '72.0.3626.1',
1002 '72.0.3626.0',
1003 '71.0.3578.79',
1004 '70.0.3538.124',
1005 '71.0.3578.78',
1006 '72.0.3623.4',
1007 '72.0.3625.2',
1008 '72.0.3625.1',
1009 '72.0.3625.0',
1010 '71.0.3578.77',
1011 '70.0.3538.123',
1012 '72.0.3624.4',
1013 '72.0.3624.3',
1014 '72.0.3624.2',
1015 '71.0.3578.76',
1016 '72.0.3624.1',
1017 '72.0.3624.0',
1018 '72.0.3623.3',
1019 '71.0.3578.75',
1020 '70.0.3538.122',
1021 '71.0.3578.74',
1022 '72.0.3623.2',
1023 '72.0.3610.3',
1024 '72.0.3623.1',
1025 '72.0.3623.0',
1026 '72.0.3622.3',
1027 '72.0.3622.2',
1028 '71.0.3578.73',
1029 '70.0.3538.121',
1030 '72.0.3622.1',
1031 '72.0.3622.0',
1032 '71.0.3578.72',
1033 '70.0.3538.120',
1034 '72.0.3621.1',
1035 '72.0.3621.0',
1036 '71.0.3578.71',
1037 '70.0.3538.119',
1038 '72.0.3620.1',
1039 '72.0.3620.0',
1040 '71.0.3578.70',
1041 '70.0.3538.118',
1042 '71.0.3578.69',
1043 '72.0.3619.1',
1044 '72.0.3619.0',
1045 '71.0.3578.68',
1046 '70.0.3538.117',
1047 '71.0.3578.67',
1048 '72.0.3618.1',
1049 '72.0.3618.0',
1050 '71.0.3578.66',
1051 '70.0.3538.116',
1052 '72.0.3617.1',
1053 '72.0.3617.0',
1054 '71.0.3578.65',
1055 '70.0.3538.115',
1056 '72.0.3602.3',
1057 '71.0.3578.64',
1058 '72.0.3616.1',
1059 '72.0.3616.0',
1060 '71.0.3578.63',
1061 '70.0.3538.114',
1062 '71.0.3578.62',
1063 '72.0.3615.1',
1064 '72.0.3615.0',
1065 '71.0.3578.61',
1066 '70.0.3538.113',
1067 '72.0.3614.1',
1068 '72.0.3614.0',
1069 '71.0.3578.60',
1070 '70.0.3538.112',
1071 '72.0.3613.1',
1072 '72.0.3613.0',
1073 '71.0.3578.59',
1074 '70.0.3538.111',
1075 '72.0.3612.2',
1076 '72.0.3612.1',
1077 '72.0.3612.0',
1078 '70.0.3538.110',
1079 '71.0.3578.58',
1080 '70.0.3538.109',
1081 '72.0.3611.2',
1082 '72.0.3611.1',
1083 '72.0.3611.0',
1084 '71.0.3578.57',
1085 '70.0.3538.108',
1086 '72.0.3610.2',
1087 '71.0.3578.56',
1088 '71.0.3578.55',
1089 '72.0.3610.1',
1090 '72.0.3610.0',
1091 '71.0.3578.54',
1092 '70.0.3538.107',
1093 '71.0.3578.53',
1094 '72.0.3609.3',
1095 '71.0.3578.52',
1096 '72.0.3609.2',
1097 '71.0.3578.51',
1098 '72.0.3608.5',
1099 '72.0.3609.1',
1100 '72.0.3609.0',
1101 '71.0.3578.50',
1102 '70.0.3538.106',
1103 '72.0.3608.4',
1104 '72.0.3608.3',
1105 '72.0.3608.2',
1106 '71.0.3578.49',
1107 '72.0.3608.1',
1108 '72.0.3608.0',
1109 '70.0.3538.105',
1110 '71.0.3578.48',
1111 '72.0.3607.1',
1112 '72.0.3607.0',
1113 '71.0.3578.47',
1114 '70.0.3538.104',
1115 '72.0.3606.2',
1116 '72.0.3606.1',
1117 '72.0.3606.0',
1118 '71.0.3578.46',
1119 '70.0.3538.103',
1120 '70.0.3538.102',
1121 '72.0.3605.3',
1122 '72.0.3605.2',
1123 '72.0.3605.1',
1124 '72.0.3605.0',
1125 '71.0.3578.45',
1126 '70.0.3538.101',
1127 '71.0.3578.44',
1128 '71.0.3578.43',
1129 '70.0.3538.100',
1130 '70.0.3538.99',
1131 '71.0.3578.42',
1132 '72.0.3604.1',
1133 '72.0.3604.0',
1134 '71.0.3578.41',
1135 '70.0.3538.98',
1136 '71.0.3578.40',
1137 '72.0.3603.2',
1138 '72.0.3603.1',
1139 '72.0.3603.0',
1140 '71.0.3578.39',
1141 '70.0.3538.97',
1142 '72.0.3602.2',
1143 '71.0.3578.38',
1144 '71.0.3578.37',
1145 '72.0.3602.1',
1146 '72.0.3602.0',
1147 '71.0.3578.36',
1148 '70.0.3538.96',
1149 '72.0.3601.1',
1150 '72.0.3601.0',
1151 '71.0.3578.35',
1152 '70.0.3538.95',
1153 '72.0.3600.1',
1154 '72.0.3600.0',
1155 '71.0.3578.34',
1156 '70.0.3538.94',
1157 '72.0.3599.3',
1158 '72.0.3599.2',
1159 '72.0.3599.1',
1160 '72.0.3599.0',
1161 '71.0.3578.33',
1162 '70.0.3538.93',
1163 '72.0.3598.1',
1164 '72.0.3598.0',
1165 '71.0.3578.32',
1166 '70.0.3538.87',
1167 '72.0.3597.1',
1168 '72.0.3597.0',
1169 '72.0.3596.2',
1170 '71.0.3578.31',
1171 '70.0.3538.86',
1172 '71.0.3578.30',
1173 '71.0.3578.29',
1174 '72.0.3596.1',
1175 '72.0.3596.0',
1176 '71.0.3578.28',
1177 '70.0.3538.85',
1178 '72.0.3595.2',
1179 '72.0.3591.3',
1180 '72.0.3595.1',
1181 '72.0.3595.0',
1182 '71.0.3578.27',
1183 '70.0.3538.84',
1184 '72.0.3594.1',
1185 '72.0.3594.0',
1186 '71.0.3578.26',
1187 '70.0.3538.83',
1188 '72.0.3593.2',
1189 '72.0.3593.1',
1190 '72.0.3593.0',
1191 '71.0.3578.25',
1192 '70.0.3538.82',
1193 '72.0.3589.3',
1194 '72.0.3592.2',
1195 '72.0.3592.1',
1196 '72.0.3592.0',
1197 '71.0.3578.24',
1198 '72.0.3589.2',
1199 '70.0.3538.81',
1200 '70.0.3538.80',
1201 '72.0.3591.2',
1202 '72.0.3591.1',
1203 '72.0.3591.0',
1204 '71.0.3578.23',
1205 '70.0.3538.79',
1206 '71.0.3578.22',
1207 '72.0.3590.1',
1208 '72.0.3590.0',
1209 '71.0.3578.21',
1210 '70.0.3538.78',
1211 '70.0.3538.77',
1212 '72.0.3589.1',
1213 '72.0.3589.0',
1214 '71.0.3578.20',
1215 '70.0.3538.76',
1216 '71.0.3578.19',
1217 '70.0.3538.75',
1218 '72.0.3588.1',
1219 '72.0.3588.0',
1220 '71.0.3578.18',
1221 '70.0.3538.74',
1222 '72.0.3586.2',
1223 '72.0.3587.0',
1224 '71.0.3578.17',
1225 '70.0.3538.73',
1226 '72.0.3586.1',
1227 '72.0.3586.0',
1228 '71.0.3578.16',
1229 '70.0.3538.72',
1230 '72.0.3585.1',
1231 '72.0.3585.0',
1232 '71.0.3578.15',
1233 '70.0.3538.71',
1234 '71.0.3578.14',
1235 '72.0.3584.1',
1236 '72.0.3584.0',
1237 '71.0.3578.13',
1238 '70.0.3538.70',
1239 '72.0.3583.2',
1240 '71.0.3578.12',
1241 '72.0.3583.1',
1242 '72.0.3583.0',
1243 '71.0.3578.11',
1244 '70.0.3538.69',
1245 '71.0.3578.10',
1246 '72.0.3582.0',
1247 '72.0.3581.4',
1248 '71.0.3578.9',
1249 '70.0.3538.67',
1250 '72.0.3581.3',
1251 '72.0.3581.2',
1252 '72.0.3581.1',
1253 '72.0.3581.0',
1254 '71.0.3578.8',
1255 '70.0.3538.66',
1256 '72.0.3580.1',
1257 '72.0.3580.0',
1258 '71.0.3578.7',
1259 '70.0.3538.65',
1260 '71.0.3578.6',
1261 '72.0.3579.1',
1262 '72.0.3579.0',
1263 '71.0.3578.5',
1264 '70.0.3538.64',
1265 '71.0.3578.4',
1266 '71.0.3578.3',
1267 '71.0.3578.2',
1268 '71.0.3578.1',
1269 '71.0.3578.0',
1270 '70.0.3538.63',
1271 '69.0.3497.128',
1272 '70.0.3538.62',
1273 '70.0.3538.61',
1274 '70.0.3538.60',
1275 '70.0.3538.59',
1276 '71.0.3577.1',
1277 '71.0.3577.0',
1278 '70.0.3538.58',
1279 '69.0.3497.127',
1280 '71.0.3576.2',
1281 '71.0.3576.1',
1282 '71.0.3576.0',
1283 '70.0.3538.57',
1284 '70.0.3538.56',
1285 '71.0.3575.2',
1286 '70.0.3538.55',
1287 '69.0.3497.126',
1288 '70.0.3538.54',
1289 '71.0.3575.1',
1290 '71.0.3575.0',
1291 '71.0.3574.1',
1292 '71.0.3574.0',
1293 '70.0.3538.53',
1294 '69.0.3497.125',
1295 '70.0.3538.52',
1296 '71.0.3573.1',
1297 '71.0.3573.0',
1298 '70.0.3538.51',
1299 '69.0.3497.124',
1300 '71.0.3572.1',
1301 '71.0.3572.0',
1302 '70.0.3538.50',
1303 '69.0.3497.123',
1304 '71.0.3571.2',
1305 '70.0.3538.49',
1306 '69.0.3497.122',
1307 '71.0.3571.1',
1308 '71.0.3571.0',
1309 '70.0.3538.48',
1310 '69.0.3497.121',
1311 '71.0.3570.1',
1312 '71.0.3570.0',
1313 '70.0.3538.47',
1314 '69.0.3497.120',
1315 '71.0.3568.2',
1316 '71.0.3569.1',
1317 '71.0.3569.0',
1318 '70.0.3538.46',
1319 '69.0.3497.119',
1320 '70.0.3538.45',
1321 '71.0.3568.1',
1322 '71.0.3568.0',
1323 '70.0.3538.44',
1324 '69.0.3497.118',
1325 '70.0.3538.43',
1326 '70.0.3538.42',
1327 '71.0.3567.1',
1328 '71.0.3567.0',
1329 '70.0.3538.41',
1330 '69.0.3497.117',
1331 '71.0.3566.1',
1332 '71.0.3566.0',
1333 '70.0.3538.40',
1334 '69.0.3497.116',
1335 '71.0.3565.1',
1336 '71.0.3565.0',
1337 '70.0.3538.39',
1338 '69.0.3497.115',
1339 '71.0.3564.1',
1340 '71.0.3564.0',
1341 '70.0.3538.38',
1342 '69.0.3497.114',
1343 '71.0.3563.0',
1344 '71.0.3562.2',
1345 '70.0.3538.37',
1346 '69.0.3497.113',
1347 '70.0.3538.36',
1348 '70.0.3538.35',
1349 '71.0.3562.1',
1350 '71.0.3562.0',
1351 '70.0.3538.34',
1352 '69.0.3497.112',
1353 '70.0.3538.33',
1354 '71.0.3561.1',
1355 '71.0.3561.0',
1356 '70.0.3538.32',
1357 '69.0.3497.111',
1358 '71.0.3559.6',
1359 '71.0.3560.1',
1360 '71.0.3560.0',
1361 '71.0.3559.5',
1362 '71.0.3559.4',
1363 '70.0.3538.31',
1364 '69.0.3497.110',
1365 '71.0.3559.3',
1366 '70.0.3538.30',
1367 '69.0.3497.109',
1368 '71.0.3559.2',
1369 '71.0.3559.1',
1370 '71.0.3559.0',
1371 '70.0.3538.29',
1372 '69.0.3497.108',
1373 '71.0.3558.2',
1374 '71.0.3558.1',
1375 '71.0.3558.0',
1376 '70.0.3538.28',
1377 '69.0.3497.107',
1378 '71.0.3557.2',
1379 '71.0.3557.1',
1380 '71.0.3557.0',
1381 '70.0.3538.27',
1382 '69.0.3497.106',
1383 '71.0.3554.4',
1384 '70.0.3538.26',
1385 '71.0.3556.1',
1386 '71.0.3556.0',
1387 '70.0.3538.25',
1388 '71.0.3554.3',
1389 '69.0.3497.105',
1390 '71.0.3554.2',
1391 '70.0.3538.24',
1392 '69.0.3497.104',
1393 '71.0.3555.2',
1394 '70.0.3538.23',
1395 '71.0.3555.1',
1396 '71.0.3555.0',
1397 '70.0.3538.22',
1398 '69.0.3497.103',
1399 '71.0.3554.1',
1400 '71.0.3554.0',
1401 '70.0.3538.21',
1402 '69.0.3497.102',
1403 '71.0.3553.3',
1404 '70.0.3538.20',
1405 '69.0.3497.101',
1406 '71.0.3553.2',
1407 '69.0.3497.100',
1408 '71.0.3553.1',
1409 '71.0.3553.0',
1410 '70.0.3538.19',
1411 '69.0.3497.99',
1412 '69.0.3497.98',
1413 '69.0.3497.97',
1414 '71.0.3552.6',
1415 '71.0.3552.5',
1416 '71.0.3552.4',
1417 '71.0.3552.3',
1418 '71.0.3552.2',
1419 '71.0.3552.1',
1420 '71.0.3552.0',
1421 '70.0.3538.18',
1422 '69.0.3497.96',
1423 '71.0.3551.3',
1424 '71.0.3551.2',
1425 '71.0.3551.1',
1426 '71.0.3551.0',
1427 '70.0.3538.17',
1428 '69.0.3497.95',
1429 '71.0.3550.3',
1430 '71.0.3550.2',
1431 '71.0.3550.1',
1432 '71.0.3550.0',
1433 '70.0.3538.16',
1434 '69.0.3497.94',
1435 '71.0.3549.1',
1436 '71.0.3549.0',
1437 '70.0.3538.15',
1438 '69.0.3497.93',
1439 '69.0.3497.92',
1440 '71.0.3548.1',
1441 '71.0.3548.0',
1442 '70.0.3538.14',
1443 '69.0.3497.91',
1444 '71.0.3547.1',
1445 '71.0.3547.0',
1446 '70.0.3538.13',
1447 '69.0.3497.90',
1448 '71.0.3546.2',
1449 '69.0.3497.89',
1450 '71.0.3546.1',
1451 '71.0.3546.0',
1452 '70.0.3538.12',
1453 '69.0.3497.88',
1454 '71.0.3545.4',
1455 '71.0.3545.3',
1456 '71.0.3545.2',
1457 '71.0.3545.1',
1458 '71.0.3545.0',
1459 '70.0.3538.11',
1460 '69.0.3497.87',
1461 '71.0.3544.5',
1462 '71.0.3544.4',
1463 '71.0.3544.3',
1464 '71.0.3544.2',
1465 '71.0.3544.1',
1466 '71.0.3544.0',
1467 '69.0.3497.86',
1468 '70.0.3538.10',
1469 '69.0.3497.85',
1470 '70.0.3538.9',
1471 '69.0.3497.84',
1472 '71.0.3543.4',
1473 '70.0.3538.8',
1474 '71.0.3543.3',
1475 '71.0.3543.2',
1476 '71.0.3543.1',
1477 '71.0.3543.0',
1478 '70.0.3538.7',
1479 '69.0.3497.83',
1480 '71.0.3542.2',
1481 '71.0.3542.1',
1482 '71.0.3542.0',
1483 '70.0.3538.6',
1484 '69.0.3497.82',
1485 '69.0.3497.81',
1486 '71.0.3541.1',
1487 '71.0.3541.0',
1488 '70.0.3538.5',
1489 '69.0.3497.80',
1490 '71.0.3540.1',
1491 '71.0.3540.0',
1492 '70.0.3538.4',
1493 '69.0.3497.79',
1494 '70.0.3538.3',
1495 '71.0.3539.1',
1496 '71.0.3539.0',
1497 '69.0.3497.78',
1498 '68.0.3440.134',
1499 '69.0.3497.77',
1500 '70.0.3538.2',
1501 '70.0.3538.1',
1502 '70.0.3538.0',
1503 '69.0.3497.76',
1504 '68.0.3440.133',
1505 '69.0.3497.75',
1506 '70.0.3537.2',
1507 '70.0.3537.1',
1508 '70.0.3537.0',
1509 '69.0.3497.74',
1510 '68.0.3440.132',
1511 '70.0.3536.0',
1512 '70.0.3535.5',
1513 '70.0.3535.4',
1514 '70.0.3535.3',
1515 '69.0.3497.73',
1516 '68.0.3440.131',
1517 '70.0.3532.8',
1518 '70.0.3532.7',
1519 '69.0.3497.72',
1520 '69.0.3497.71',
1521 '70.0.3535.2',
1522 '70.0.3535.1',
1523 '70.0.3535.0',
1524 '69.0.3497.70',
1525 '68.0.3440.130',
1526 '69.0.3497.69',
1527 '68.0.3440.129',
1528 '70.0.3534.4',
1529 '70.0.3534.3',
1530 '70.0.3534.2',
1531 '70.0.3534.1',
1532 '70.0.3534.0',
1533 '69.0.3497.68',
1534 '68.0.3440.128',
1535 '70.0.3533.2',
1536 '70.0.3533.1',
1537 '70.0.3533.0',
1538 '69.0.3497.67',
1539 '68.0.3440.127',
1540 '70.0.3532.6',
1541 '70.0.3532.5',
1542 '70.0.3532.4',
1543 '69.0.3497.66',
1544 '68.0.3440.126',
1545 '70.0.3532.3',
1546 '70.0.3532.2',
1547 '70.0.3532.1',
1548 '69.0.3497.60',
1549 '69.0.3497.65',
1550 '69.0.3497.64',
1551 '70.0.3532.0',
1552 '70.0.3531.0',
1553 '70.0.3530.4',
1554 '70.0.3530.3',
1555 '70.0.3530.2',
1556 '69.0.3497.58',
1557 '68.0.3440.125',
1558 '69.0.3497.57',
1559 '69.0.3497.56',
1560 '69.0.3497.55',
1561 '69.0.3497.54',
1562 '70.0.3530.1',
1563 '70.0.3530.0',
1564 '69.0.3497.53',
1565 '68.0.3440.124',
1566 '69.0.3497.52',
1567 '70.0.3529.3',
1568 '70.0.3529.2',
1569 '70.0.3529.1',
1570 '70.0.3529.0',
1571 '69.0.3497.51',
1572 '70.0.3528.4',
1573 '68.0.3440.123',
1574 '70.0.3528.3',
1575 '70.0.3528.2',
1576 '70.0.3528.1',
1577 '70.0.3528.0',
1578 '69.0.3497.50',
1579 '68.0.3440.122',
1580 '70.0.3527.1',
1581 '70.0.3527.0',
1582 '69.0.3497.49',
1583 '68.0.3440.121',
1584 '70.0.3526.1',
1585 '70.0.3526.0',
1586 '68.0.3440.120',
1587 '69.0.3497.48',
1588 '69.0.3497.47',
1589 '68.0.3440.119',
1590 '68.0.3440.118',
1591 '70.0.3525.5',
1592 '70.0.3525.4',
1593 '70.0.3525.3',
1594 '68.0.3440.117',
1595 '69.0.3497.46',
1596 '70.0.3525.2',
1597 '70.0.3525.1',
1598 '70.0.3525.0',
1599 '69.0.3497.45',
1600 '68.0.3440.116',
1601 '70.0.3524.4',
1602 '70.0.3524.3',
1603 '69.0.3497.44',
1604 '70.0.3524.2',
1605 '70.0.3524.1',
1606 '70.0.3524.0',
1607 '70.0.3523.2',
1608 '69.0.3497.43',
1609 '68.0.3440.115',
1610 '70.0.3505.9',
1611 '69.0.3497.42',
1612 '70.0.3505.8',
1613 '70.0.3523.1',
1614 '70.0.3523.0',
1615 '69.0.3497.41',
1616 '68.0.3440.114',
1617 '70.0.3505.7',
1618 '69.0.3497.40',
1619 '70.0.3522.1',
1620 '70.0.3522.0',
1621 '70.0.3521.2',
1622 '69.0.3497.39',
1623 '68.0.3440.113',
1624 '70.0.3505.6',
1625 '70.0.3521.1',
1626 '70.0.3521.0',
1627 '69.0.3497.38',
1628 '68.0.3440.112',
1629 '70.0.3520.1',
1630 '70.0.3520.0',
1631 '69.0.3497.37',
1632 '68.0.3440.111',
1633 '70.0.3519.3',
1634 '70.0.3519.2',
1635 '70.0.3519.1',
1636 '70.0.3519.0',
1637 '69.0.3497.36',
1638 '68.0.3440.110',
1639 '70.0.3518.1',
1640 '70.0.3518.0',
1641 '69.0.3497.35',
1642 '69.0.3497.34',
1643 '68.0.3440.109',
1644 '70.0.3517.1',
1645 '70.0.3517.0',
1646 '69.0.3497.33',
1647 '68.0.3440.108',
1648 '69.0.3497.32',
1649 '70.0.3516.3',
1650 '70.0.3516.2',
1651 '70.0.3516.1',
1652 '70.0.3516.0',
1653 '69.0.3497.31',
1654 '68.0.3440.107',
1655 '70.0.3515.4',
1656 '68.0.3440.106',
1657 '70.0.3515.3',
1658 '70.0.3515.2',
1659 '70.0.3515.1',
1660 '70.0.3515.0',
1661 '69.0.3497.30',
1662 '68.0.3440.105',
1663 '68.0.3440.104',
1664 '70.0.3514.2',
1665 '70.0.3514.1',
1666 '70.0.3514.0',
1667 '69.0.3497.29',
1668 '68.0.3440.103',
1669 '70.0.3513.1',
1670 '70.0.3513.0',
1671 '69.0.3497.28',
1672 )
1673 return _USER_AGENT_TPL % random.choice(_CHROME_VERSIONS)
1674
1675
3e669f36 1676std_headers = {
f7a147e3 1677 'User-Agent': random_user_agent(),
59ae15a5
PH
1678 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
1679 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
1680 'Accept-Encoding': 'gzip, deflate',
1681 'Accept-Language': 'en-us,en;q=0.5',
3e669f36 1682}
f427df17 1683
5f6a1245 1684
fb37eb25
S
1685USER_AGENTS = {
1686 'Safari': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) AppleWebKit/533.20.25 (KHTML, like Gecko) Version/5.0.4 Safari/533.20.27',
1687}
1688
1689
bf42a990
S
1690NO_DEFAULT = object()
1691
7105440c
YCH
1692ENGLISH_MONTH_NAMES = [
1693 'January', 'February', 'March', 'April', 'May', 'June',
1694 'July', 'August', 'September', 'October', 'November', 'December']
1695
f6717dec
S
1696MONTH_NAMES = {
1697 'en': ENGLISH_MONTH_NAMES,
1698 'fr': [
3e4185c3
S
1699 'janvier', 'février', 'mars', 'avril', 'mai', 'juin',
1700 'juillet', 'août', 'septembre', 'octobre', 'novembre', 'décembre'],
f6717dec 1701}
a942d6cb 1702
a7aaa398
S
1703KNOWN_EXTENSIONS = (
1704 'mp4', 'm4a', 'm4p', 'm4b', 'm4r', 'm4v', 'aac',
1705 'flv', 'f4v', 'f4a', 'f4b',
1706 'webm', 'ogg', 'ogv', 'oga', 'ogx', 'spx', 'opus',
1707 'mkv', 'mka', 'mk3d',
1708 'avi', 'divx',
1709 'mov',
1710 'asf', 'wmv', 'wma',
1711 '3gp', '3g2',
1712 'mp3',
1713 'flac',
1714 'ape',
1715 'wav',
1716 'f4f', 'f4m', 'm3u8', 'smil')
1717
c587cbb7 1718# needed for sanitizing filenames in restricted mode
c8827027 1719ACCENT_CHARS = dict(zip('ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖŐØŒÙÚÛÜŰÝÞßàáâãäåæçèéêëìíîïðñòóôõöőøœùúûüűýþÿ',
fd35d8cd
JW
1720 itertools.chain('AAAAAA', ['AE'], 'CEEEEIIIIDNOOOOOOO', ['OE'], 'UUUUUY', ['TH', 'ss'],
1721 'aaaaaa', ['ae'], 'ceeeeiiiionooooooo', ['oe'], 'uuuuuy', ['th'], 'y')))
c587cbb7 1722
46f59e89
S
1723DATE_FORMATS = (
1724 '%d %B %Y',
1725 '%d %b %Y',
1726 '%B %d %Y',
cb655f34
S
1727 '%B %dst %Y',
1728 '%B %dnd %Y',
9d30c213 1729 '%B %drd %Y',
cb655f34 1730 '%B %dth %Y',
46f59e89 1731 '%b %d %Y',
cb655f34
S
1732 '%b %dst %Y',
1733 '%b %dnd %Y',
9d30c213 1734 '%b %drd %Y',
cb655f34 1735 '%b %dth %Y',
46f59e89
S
1736 '%b %dst %Y %I:%M',
1737 '%b %dnd %Y %I:%M',
9d30c213 1738 '%b %drd %Y %I:%M',
46f59e89
S
1739 '%b %dth %Y %I:%M',
1740 '%Y %m %d',
1741 '%Y-%m-%d',
1742 '%Y/%m/%d',
81c13222 1743 '%Y/%m/%d %H:%M',
46f59e89 1744 '%Y/%m/%d %H:%M:%S',
0c1c6f4b 1745 '%Y-%m-%d %H:%M',
46f59e89
S
1746 '%Y-%m-%d %H:%M:%S',
1747 '%Y-%m-%d %H:%M:%S.%f',
1748 '%d.%m.%Y %H:%M',
1749 '%d.%m.%Y %H.%M',
1750 '%Y-%m-%dT%H:%M:%SZ',
1751 '%Y-%m-%dT%H:%M:%S.%fZ',
1752 '%Y-%m-%dT%H:%M:%S.%f0Z',
1753 '%Y-%m-%dT%H:%M:%S',
1754 '%Y-%m-%dT%H:%M:%S.%f',
1755 '%Y-%m-%dT%H:%M',
c6eed6b8
S
1756 '%b %d %Y at %H:%M',
1757 '%b %d %Y at %H:%M:%S',
b555ae9b
S
1758 '%B %d %Y at %H:%M',
1759 '%B %d %Y at %H:%M:%S',
46f59e89
S
1760)
1761
1762DATE_FORMATS_DAY_FIRST = list(DATE_FORMATS)
1763DATE_FORMATS_DAY_FIRST.extend([
1764 '%d-%m-%Y',
1765 '%d.%m.%Y',
1766 '%d.%m.%y',
1767 '%d/%m/%Y',
1768 '%d/%m/%y',
1769 '%d/%m/%Y %H:%M:%S',
1770])
1771
1772DATE_FORMATS_MONTH_FIRST = list(DATE_FORMATS)
1773DATE_FORMATS_MONTH_FIRST.extend([
1774 '%m-%d-%Y',
1775 '%m.%d.%Y',
1776 '%m/%d/%Y',
1777 '%m/%d/%y',
1778 '%m/%d/%Y %H:%M:%S',
1779])
1780
06b3fe29 1781PACKED_CODES_RE = r"}\('(.+)',(\d+),(\d+),'([^']+)'\.split\('\|'\)"
22f5f5c6 1782JSON_LD_RE = r'(?is)<script[^>]+type=(["\']?)application/ld\+json\1[^>]*>(?P<json_ld>.+?)</script>'
06b3fe29 1783
7105440c 1784
d77c3dfd 1785def preferredencoding():
59ae15a5 1786 """Get preferred encoding.
d77c3dfd 1787
59ae15a5
PH
1788 Returns the best encoding scheme for the system, based on
1789 locale.getpreferredencoding() and some further tweaks.
1790 """
1791 try:
1792 pref = locale.getpreferredencoding()
28e614de 1793 'TEST'.encode(pref)
70a1165b 1794 except Exception:
59ae15a5 1795 pref = 'UTF-8'
bae611f2 1796
59ae15a5 1797 return pref
d77c3dfd 1798
f4bfd65f 1799
181c8655 1800def write_json_file(obj, fn):
1394646a 1801 """ Encode obj as JSON and write it to fn, atomically if possible """
181c8655 1802
92120217 1803 fn = encodeFilename(fn)
61ee5aeb 1804 if sys.version_info < (3, 0) and sys.platform != 'win32':
ec5f6016
JMF
1805 encoding = get_filesystem_encoding()
1806 # os.path.basename returns a bytes object, but NamedTemporaryFile
1807 # will fail if the filename contains non ascii characters unless we
1808 # use a unicode object
1809 path_basename = lambda f: os.path.basename(fn).decode(encoding)
1810 # the same for os.path.dirname
1811 path_dirname = lambda f: os.path.dirname(fn).decode(encoding)
1812 else:
1813 path_basename = os.path.basename
1814 path_dirname = os.path.dirname
1815
73159f99
S
1816 args = {
1817 'suffix': '.tmp',
ec5f6016
JMF
1818 'prefix': path_basename(fn) + '.',
1819 'dir': path_dirname(fn),
73159f99
S
1820 'delete': False,
1821 }
1822
181c8655
PH
1823 # In Python 2.x, json.dump expects a bytestream.
1824 # In Python 3.x, it writes to a character stream
1825 if sys.version_info < (3, 0):
73159f99 1826 args['mode'] = 'wb'
181c8655 1827 else:
73159f99
S
1828 args.update({
1829 'mode': 'w',
1830 'encoding': 'utf-8',
1831 })
1832
c86b6142 1833 tf = tempfile.NamedTemporaryFile(**compat_kwargs(args))
181c8655
PH
1834
1835 try:
1836 with tf:
1837 json.dump(obj, tf)
1394646a
IK
1838 if sys.platform == 'win32':
1839 # Need to remove existing file on Windows, else os.rename raises
1840 # WindowsError or FileExistsError.
1841 try:
1842 os.unlink(fn)
1843 except OSError:
1844 pass
9cd5f54e
R
1845 try:
1846 mask = os.umask(0)
1847 os.umask(mask)
1848 os.chmod(tf.name, 0o666 & ~mask)
1849 except OSError:
1850 pass
181c8655 1851 os.rename(tf.name, fn)
70a1165b 1852 except Exception:
181c8655
PH
1853 try:
1854 os.remove(tf.name)
1855 except OSError:
1856 pass
1857 raise
1858
1859
1860if sys.version_info >= (2, 7):
ee114368 1861 def find_xpath_attr(node, xpath, key, val=None):
59ae56fa 1862 """ Find the xpath xpath[@key=val] """
5d2354f1 1863 assert re.match(r'^[a-zA-Z_-]+$', key)
ee114368 1864 expr = xpath + ('[@%s]' % key if val is None else "[@%s='%s']" % (key, val))
59ae56fa
PH
1865 return node.find(expr)
1866else:
ee114368 1867 def find_xpath_attr(node, xpath, key, val=None):
810c10ba 1868 for f in node.findall(compat_xpath(xpath)):
ee114368
S
1869 if key not in f.attrib:
1870 continue
1871 if val is None or f.attrib.get(key) == val:
59ae56fa
PH
1872 return f
1873 return None
1874
d7e66d39
JMF
1875# On python2.6 the xml.etree.ElementTree.Element methods don't support
1876# the namespace parameter
5f6a1245
JW
1877
1878
d7e66d39
JMF
1879def xpath_with_ns(path, ns_map):
1880 components = [c.split(':') for c in path.split('/')]
1881 replaced = []
1882 for c in components:
1883 if len(c) == 1:
1884 replaced.append(c[0])
1885 else:
1886 ns, tag = c
1887 replaced.append('{%s}%s' % (ns_map[ns], tag))
1888 return '/'.join(replaced)
1889
d77c3dfd 1890
a41fb80c 1891def xpath_element(node, xpath, name=None, fatal=False, default=NO_DEFAULT):
578c0745 1892 def _find_xpath(xpath):
810c10ba 1893 return node.find(compat_xpath(xpath))
578c0745
S
1894
1895 if isinstance(xpath, (str, compat_str)):
1896 n = _find_xpath(xpath)
1897 else:
1898 for xp in xpath:
1899 n = _find_xpath(xp)
1900 if n is not None:
1901 break
d74bebd5 1902
8e636da4 1903 if n is None:
bf42a990
S
1904 if default is not NO_DEFAULT:
1905 return default
1906 elif fatal:
bf0ff932
PH
1907 name = xpath if name is None else name
1908 raise ExtractorError('Could not find XML element %s' % name)
1909 else:
1910 return None
a41fb80c
S
1911 return n
1912
1913
1914def xpath_text(node, xpath, name=None, fatal=False, default=NO_DEFAULT):
8e636da4
S
1915 n = xpath_element(node, xpath, name, fatal=fatal, default=default)
1916 if n is None or n == default:
1917 return n
1918 if n.text is None:
1919 if default is not NO_DEFAULT:
1920 return default
1921 elif fatal:
1922 name = xpath if name is None else name
1923 raise ExtractorError('Could not find XML element\'s text %s' % name)
1924 else:
1925 return None
1926 return n.text
a41fb80c
S
1927
1928
1929def xpath_attr(node, xpath, key, name=None, fatal=False, default=NO_DEFAULT):
1930 n = find_xpath_attr(node, xpath, key)
1931 if n is None:
1932 if default is not NO_DEFAULT:
1933 return default
1934 elif fatal:
1935 name = '%s[@%s]' % (xpath, key) if name is None else name
1936 raise ExtractorError('Could not find XML attribute %s' % name)
1937 else:
1938 return None
1939 return n.attrib[key]
bf0ff932
PH
1940
1941
9e6dd238 1942def get_element_by_id(id, html):
43e8fafd 1943 """Return the content of the tag with the specified ID in the passed HTML document"""
611c1dd9 1944 return get_element_by_attribute('id', id, html)
43e8fafd 1945
12ea2f30 1946
84c237fb 1947def get_element_by_class(class_name, html):
2af12ad9
TC
1948 """Return the content of the first tag with the specified class in the passed HTML document"""
1949 retval = get_elements_by_class(class_name, html)
1950 return retval[0] if retval else None
1951
1952
1953def get_element_by_attribute(attribute, value, html, escape_value=True):
1954 retval = get_elements_by_attribute(attribute, value, html, escape_value)
1955 return retval[0] if retval else None
1956
1957
1958def get_elements_by_class(class_name, html):
1959 """Return the content of all tags with the specified class in the passed HTML document as a list"""
1960 return get_elements_by_attribute(
84c237fb
YCH
1961 'class', r'[^\'"]*\b%s\b[^\'"]*' % re.escape(class_name),
1962 html, escape_value=False)
1963
1964
2af12ad9 1965def get_elements_by_attribute(attribute, value, html, escape_value=True):
43e8fafd 1966 """Return the content of the tag with the specified attribute in the passed HTML document"""
9e6dd238 1967
84c237fb
YCH
1968 value = re.escape(value) if escape_value else value
1969
2af12ad9
TC
1970 retlist = []
1971 for m in re.finditer(r'''(?xs)
38285056 1972 <([a-zA-Z0-9:._-]+)
609ff8ca 1973 (?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'|))*?
38285056 1974 \s+%s=['"]?%s['"]?
609ff8ca 1975 (?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'|))*?
38285056
PH
1976 \s*>
1977 (?P<content>.*?)
1978 </\1>
2af12ad9
TC
1979 ''' % (re.escape(attribute), value), html):
1980 res = m.group('content')
38285056 1981
2af12ad9
TC
1982 if res.startswith('"') or res.startswith("'"):
1983 res = res[1:-1]
38285056 1984
2af12ad9 1985 retlist.append(unescapeHTML(res))
a921f407 1986
2af12ad9 1987 return retlist
a921f407 1988
c5229f39 1989
8bb56eee
BF
1990class HTMLAttributeParser(compat_HTMLParser):
1991 """Trivial HTML parser to gather the attributes for a single element"""
b6e0c7d2 1992
8bb56eee 1993 def __init__(self):
c5229f39 1994 self.attrs = {}
8bb56eee
BF
1995 compat_HTMLParser.__init__(self)
1996
1997 def handle_starttag(self, tag, attrs):
1998 self.attrs = dict(attrs)
1999
c5229f39 2000
8bb56eee
BF
2001def extract_attributes(html_element):
2002 """Given a string for an HTML element such as
2003 <el
2004 a="foo" B="bar" c="&98;az" d=boz
2005 empty= noval entity="&amp;"
2006 sq='"' dq="'"
2007 >
2008 Decode and return a dictionary of attributes.
2009 {
2010 'a': 'foo', 'b': 'bar', c: 'baz', d: 'boz',
2011 'empty': '', 'noval': None, 'entity': '&',
2012 'sq': '"', 'dq': '\''
2013 }.
2014 NB HTMLParser is stricter in Python 2.6 & 3.2 than in later versions,
2015 but the cases in the unit test will work for all of 2.6, 2.7, 3.2-3.5.
2016 """
2017 parser = HTMLAttributeParser()
b4a3d461
S
2018 try:
2019 parser.feed(html_element)
2020 parser.close()
2021 # Older Python may throw HTMLParseError in case of malformed HTML
2022 except compat_HTMLParseError:
2023 pass
8bb56eee 2024 return parser.attrs
9e6dd238 2025
c5229f39 2026
9e6dd238 2027def clean_html(html):
59ae15a5 2028 """Clean an HTML snippet into a readable string"""
dd622d7c
PH
2029
2030 if html is None: # Convenience for sanitizing descriptions etc.
2031 return html
2032
59ae15a5
PH
2033 # Newline vs <br />
2034 html = html.replace('\n', ' ')
edd9221c
TF
2035 html = re.sub(r'(?u)\s*<\s*br\s*/?\s*>\s*', '\n', html)
2036 html = re.sub(r'(?u)<\s*/\s*p\s*>\s*<\s*p[^>]*>', '\n', html)
59ae15a5
PH
2037 # Strip html tags
2038 html = re.sub('<.*?>', '', html)
2039 # Replace html entities
2040 html = unescapeHTML(html)
7decf895 2041 return html.strip()
9e6dd238
FV
2042
2043
d77c3dfd 2044def sanitize_open(filename, open_mode):
59ae15a5
PH
2045 """Try to open the given filename, and slightly tweak it if this fails.
2046
2047 Attempts to open the given filename. If this fails, it tries to change
2048 the filename slightly, step by step, until it's either able to open it
2049 or it fails and raises a final exception, like the standard open()
2050 function.
2051
2052 It returns the tuple (stream, definitive_file_name).
2053 """
2054 try:
28e614de 2055 if filename == '-':
59ae15a5
PH
2056 if sys.platform == 'win32':
2057 import msvcrt
2058 msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
898280a0 2059 return (sys.stdout.buffer if hasattr(sys.stdout, 'buffer') else sys.stdout, filename)
59ae15a5
PH
2060 stream = open(encodeFilename(filename), open_mode)
2061 return (stream, filename)
2062 except (IOError, OSError) as err:
f45c185f
PH
2063 if err.errno in (errno.EACCES,):
2064 raise
59ae15a5 2065
f45c185f 2066 # In case of error, try to remove win32 forbidden chars
d55de57b 2067 alt_filename = sanitize_path(filename)
f45c185f
PH
2068 if alt_filename == filename:
2069 raise
2070 else:
2071 # An exception here should be caught in the caller
d55de57b 2072 stream = open(encodeFilename(alt_filename), open_mode)
f45c185f 2073 return (stream, alt_filename)
d77c3dfd
FV
2074
2075
2076def timeconvert(timestr):
59ae15a5
PH
2077 """Convert RFC 2822 defined time string into system timestamp"""
2078 timestamp = None
2079 timetuple = email.utils.parsedate_tz(timestr)
2080 if timetuple is not None:
2081 timestamp = email.utils.mktime_tz(timetuple)
2082 return timestamp
1c469a94 2083
5f6a1245 2084
796173d0 2085def sanitize_filename(s, restricted=False, is_id=False):
59ae15a5
PH
2086 """Sanitizes a string so it could be used as part of a filename.
2087 If restricted is set, use a stricter subset of allowed characters.
158af524
S
2088 Set is_id if this is not an arbitrary string, but an ID that should be kept
2089 if possible.
59ae15a5
PH
2090 """
2091 def replace_insane(char):
c587cbb7
AT
2092 if restricted and char in ACCENT_CHARS:
2093 return ACCENT_CHARS[char]
59ae15a5
PH
2094 if char == '?' or ord(char) < 32 or ord(char) == 127:
2095 return ''
2096 elif char == '"':
2097 return '' if restricted else '\''
2098 elif char == ':':
2099 return '_-' if restricted else ' -'
2100 elif char in '\\/|*<>':
2101 return '_'
627dcfff 2102 if restricted and (char in '!&\'()[]{}$;`^,#' or char.isspace()):
59ae15a5
PH
2103 return '_'
2104 if restricted and ord(char) > 127:
2105 return '_'
2106 return char
2107
2aeb06d6
PH
2108 # Handle timestamps
2109 s = re.sub(r'[0-9]+(?::[0-9]+)+', lambda m: m.group(0).replace(':', '_'), s)
28e614de 2110 result = ''.join(map(replace_insane, s))
796173d0
PH
2111 if not is_id:
2112 while '__' in result:
2113 result = result.replace('__', '_')
2114 result = result.strip('_')
2115 # Common case of "Foreign band name - English song title"
2116 if restricted and result.startswith('-_'):
2117 result = result[2:]
5a42414b
PH
2118 if result.startswith('-'):
2119 result = '_' + result[len('-'):]
a7440261 2120 result = result.lstrip('.')
796173d0
PH
2121 if not result:
2122 result = '_'
59ae15a5 2123 return result
d77c3dfd 2124
5f6a1245 2125
a2aaf4db
S
2126def sanitize_path(s):
2127 """Sanitizes and normalizes path on Windows"""
2128 if sys.platform != 'win32':
2129 return s
be531ef1
S
2130 drive_or_unc, _ = os.path.splitdrive(s)
2131 if sys.version_info < (2, 7) and not drive_or_unc:
2132 drive_or_unc, _ = os.path.splitunc(s)
2133 norm_path = os.path.normpath(remove_start(s, drive_or_unc)).split(os.path.sep)
2134 if drive_or_unc:
a2aaf4db
S
2135 norm_path.pop(0)
2136 sanitized_path = [
ec85ded8 2137 path_part if path_part in ['.', '..'] else re.sub(r'(?:[/<>:"\|\\?\*]|[\s.]$)', '#', path_part)
a2aaf4db 2138 for path_part in norm_path]
be531ef1
S
2139 if drive_or_unc:
2140 sanitized_path.insert(0, drive_or_unc + os.path.sep)
a2aaf4db
S
2141 return os.path.join(*sanitized_path)
2142
2143
17bcc626 2144def sanitize_url(url):
befa4708
S
2145 # Prepend protocol-less URLs with `http:` scheme in order to mitigate
2146 # the number of unwanted failures due to missing protocol
2147 if url.startswith('//'):
2148 return 'http:%s' % url
2149 # Fix some common typos seen so far
2150 COMMON_TYPOS = (
067aa17e 2151 # https://github.com/ytdl-org/youtube-dl/issues/15649
befa4708
S
2152 (r'^httpss://', r'https://'),
2153 # https://bx1.be/lives/direct-tv/
2154 (r'^rmtp([es]?)://', r'rtmp\1://'),
2155 )
2156 for mistake, fixup in COMMON_TYPOS:
2157 if re.match(mistake, url):
2158 return re.sub(mistake, fixup, url)
2159 return url
17bcc626
S
2160
2161
67dda517 2162def sanitized_Request(url, *args, **kwargs):
17bcc626 2163 return compat_urllib_request.Request(sanitize_url(url), *args, **kwargs)
67dda517
S
2164
2165
51098426
S
2166def expand_path(s):
2167 """Expand shell variables and ~"""
2168 return os.path.expandvars(compat_expanduser(s))
2169
2170
d77c3dfd 2171def orderedSet(iterable):
59ae15a5
PH
2172 """ Remove all duplicates from the input iterable """
2173 res = []
2174 for el in iterable:
2175 if el not in res:
2176 res.append(el)
2177 return res
d77c3dfd 2178
912b38b4 2179
55b2f099 2180def _htmlentity_transform(entity_with_semicolon):
4e408e47 2181 """Transforms an HTML entity to a character."""
55b2f099
YCH
2182 entity = entity_with_semicolon[:-1]
2183
4e408e47
PH
2184 # Known non-numeric HTML entity
2185 if entity in compat_html_entities.name2codepoint:
2186 return compat_chr(compat_html_entities.name2codepoint[entity])
2187
55b2f099
YCH
2188 # TODO: HTML5 allows entities without a semicolon. For example,
2189 # '&Eacuteric' should be decoded as 'Éric'.
2190 if entity_with_semicolon in compat_html_entities_html5:
2191 return compat_html_entities_html5[entity_with_semicolon]
2192
91757b0f 2193 mobj = re.match(r'#(x[0-9a-fA-F]+|[0-9]+)', entity)
4e408e47
PH
2194 if mobj is not None:
2195 numstr = mobj.group(1)
28e614de 2196 if numstr.startswith('x'):
4e408e47 2197 base = 16
28e614de 2198 numstr = '0%s' % numstr
4e408e47
PH
2199 else:
2200 base = 10
067aa17e 2201 # See https://github.com/ytdl-org/youtube-dl/issues/7518
7aefc49c
S
2202 try:
2203 return compat_chr(int(numstr, base))
2204 except ValueError:
2205 pass
4e408e47
PH
2206
2207 # Unknown entity in name, return its literal representation
7a3f0c00 2208 return '&%s;' % entity
4e408e47
PH
2209
2210
d77c3dfd 2211def unescapeHTML(s):
912b38b4
PH
2212 if s is None:
2213 return None
2214 assert type(s) == compat_str
d77c3dfd 2215
4e408e47 2216 return re.sub(
95f3f7c2 2217 r'&([^&;]+;)', lambda m: _htmlentity_transform(m.group(1)), s)
d77c3dfd 2218
8bf48f23 2219
f5b1bca9 2220def process_communicate_or_kill(p, *args, **kwargs):
2221 try:
2222 return p.communicate(*args, **kwargs)
2223 except BaseException: # Including KeyboardInterrupt
2224 p.kill()
2225 p.wait()
2226 raise
2227
2228
aa49acd1
S
2229def get_subprocess_encoding():
2230 if sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5:
2231 # For subprocess calls, encode with locale encoding
2232 # Refer to http://stackoverflow.com/a/9951851/35070
2233 encoding = preferredencoding()
2234 else:
2235 encoding = sys.getfilesystemencoding()
2236 if encoding is None:
2237 encoding = 'utf-8'
2238 return encoding
2239
2240
8bf48f23 2241def encodeFilename(s, for_subprocess=False):
59ae15a5
PH
2242 """
2243 @param s The name of the file
2244 """
d77c3dfd 2245
8bf48f23 2246 assert type(s) == compat_str
d77c3dfd 2247
59ae15a5
PH
2248 # Python 3 has a Unicode API
2249 if sys.version_info >= (3, 0):
2250 return s
0f00efed 2251
aa49acd1
S
2252 # Pass '' directly to use Unicode APIs on Windows 2000 and up
2253 # (Detecting Windows NT 4 is tricky because 'major >= 4' would
2254 # match Windows 9x series as well. Besides, NT 4 is obsolete.)
2255 if not for_subprocess and sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5:
2256 return s
2257
8ee239e9
YCH
2258 # Jython assumes filenames are Unicode strings though reported as Python 2.x compatible
2259 if sys.platform.startswith('java'):
2260 return s
2261
aa49acd1
S
2262 return s.encode(get_subprocess_encoding(), 'ignore')
2263
2264
2265def decodeFilename(b, for_subprocess=False):
2266
2267 if sys.version_info >= (3, 0):
2268 return b
2269
2270 if not isinstance(b, bytes):
2271 return b
2272
2273 return b.decode(get_subprocess_encoding(), 'ignore')
8bf48f23 2274
f07b74fc
PH
2275
2276def encodeArgument(s):
2277 if not isinstance(s, compat_str):
2278 # Legacy code that uses byte strings
2279 # Uncomment the following line after fixing all post processors
7af808a5 2280 # assert False, 'Internal error: %r should be of type %r, is %r' % (s, compat_str, type(s))
f07b74fc
PH
2281 s = s.decode('ascii')
2282 return encodeFilename(s, True)
2283
2284
aa49acd1
S
2285def decodeArgument(b):
2286 return decodeFilename(b, True)
2287
2288
8271226a
PH
2289def decodeOption(optval):
2290 if optval is None:
2291 return optval
2292 if isinstance(optval, bytes):
2293 optval = optval.decode(preferredencoding())
2294
2295 assert isinstance(optval, compat_str)
2296 return optval
1c256f70 2297
5f6a1245 2298
dbbbe555 2299def formatSeconds(secs, delim=':'):
4539dd30 2300 if secs > 3600:
dbbbe555 2301 return '%d%s%02d%s%02d' % (secs // 3600, delim, (secs % 3600) // 60, delim, secs % 60)
4539dd30 2302 elif secs > 60:
dbbbe555 2303 return '%d%s%02d' % (secs // 60, delim, secs % 60)
4539dd30
PH
2304 else:
2305 return '%d' % secs
2306
a0ddb8a2 2307
be4a824d
PH
2308def make_HTTPS_handler(params, **kwargs):
2309 opts_no_check_certificate = params.get('nocheckcertificate', False)
0db261ba 2310 if hasattr(ssl, 'create_default_context'): # Python >= 3.4 or 2.7.9
be5f2c19 2311 context = ssl.create_default_context(ssl.Purpose.SERVER_AUTH)
0db261ba 2312 if opts_no_check_certificate:
be5f2c19 2313 context.check_hostname = False
0db261ba 2314 context.verify_mode = ssl.CERT_NONE
a2366922 2315 try:
be4a824d 2316 return YoutubeDLHTTPSHandler(params, context=context, **kwargs)
a2366922
PH
2317 except TypeError:
2318 # Python 2.7.8
2319 # (create_default_context present but HTTPSHandler has no context=)
2320 pass
2321
2322 if sys.version_info < (3, 2):
d7932313 2323 return YoutubeDLHTTPSHandler(params, **kwargs)
aa37e3d4 2324 else: # Python < 3.4
d7932313 2325 context = ssl.SSLContext(ssl.PROTOCOL_TLSv1)
ea6d901e 2326 context.verify_mode = (ssl.CERT_NONE
dca08720 2327 if opts_no_check_certificate
ea6d901e 2328 else ssl.CERT_REQUIRED)
303b479e 2329 context.set_default_verify_paths()
be4a824d 2330 return YoutubeDLHTTPSHandler(params, context=context, **kwargs)
ea6d901e 2331
732ea2f0 2332
08f2a92c
JMF
2333def bug_reports_message():
2334 if ytdl_is_updateable():
cefecac1 2335 update_cmd = 'type youtube-dlc -U to update'
08f2a92c 2336 else:
17fa3ee2 2337 update_cmd = 'see https://github.com/pukkandan/yt-dlp on how to update'
2338 msg = '; please report this issue on https://github.com/pukkandan/yt-dlp .'
08f2a92c 2339 msg += ' Make sure you are using the latest version; %s.' % update_cmd
cefecac1 2340 msg += ' Be sure to call youtube-dlc with the --verbose flag and include its complete output.'
08f2a92c
JMF
2341 return msg
2342
2343
bf5b9d85
PM
2344class YoutubeDLError(Exception):
2345 """Base exception for YoutubeDL errors."""
2346 pass
2347
2348
2349class ExtractorError(YoutubeDLError):
1c256f70 2350 """Error during info extraction."""
5f6a1245 2351
d11271dd 2352 def __init__(self, msg, tb=None, expected=False, cause=None, video_id=None):
9a82b238 2353 """ tb, if given, is the original traceback (so that it can be printed out).
cefecac1 2354 If expected is set, this is a normal error message and most likely not a bug in youtube-dlc.
9a82b238
PH
2355 """
2356
2357 if sys.exc_info()[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError):
2358 expected = True
d11271dd
PH
2359 if video_id is not None:
2360 msg = video_id + ': ' + msg
410f3e73 2361 if cause:
28e614de 2362 msg += ' (caused by %r)' % cause
9a82b238 2363 if not expected:
08f2a92c 2364 msg += bug_reports_message()
1c256f70 2365 super(ExtractorError, self).__init__(msg)
d5979c5d 2366
1c256f70 2367 self.traceback = tb
8cc83b8d 2368 self.exc_info = sys.exc_info() # preserve original exception
2eabb802 2369 self.cause = cause
d11271dd 2370 self.video_id = video_id
1c256f70 2371
01951dda
PH
2372 def format_traceback(self):
2373 if self.traceback is None:
2374 return None
28e614de 2375 return ''.join(traceback.format_tb(self.traceback))
01951dda 2376
1c256f70 2377
416c7fcb
PH
2378class UnsupportedError(ExtractorError):
2379 def __init__(self, url):
2380 super(UnsupportedError, self).__init__(
2381 'Unsupported URL: %s' % url, expected=True)
2382 self.url = url
2383
2384
55b3e45b
JMF
2385class RegexNotFoundError(ExtractorError):
2386 """Error when a regex didn't match"""
2387 pass
2388
2389
773f291d
S
2390class GeoRestrictedError(ExtractorError):
2391 """Geographic restriction Error exception.
2392
2393 This exception may be thrown when a video is not available from your
2394 geographic location due to geographic restrictions imposed by a website.
2395 """
b6e0c7d2 2396
773f291d
S
2397 def __init__(self, msg, countries=None):
2398 super(GeoRestrictedError, self).__init__(msg, expected=True)
2399 self.msg = msg
2400 self.countries = countries
2401
2402
bf5b9d85 2403class DownloadError(YoutubeDLError):
59ae15a5 2404 """Download Error exception.
d77c3dfd 2405
59ae15a5
PH
2406 This exception may be thrown by FileDownloader objects if they are not
2407 configured to continue on errors. They will contain the appropriate
2408 error message.
2409 """
5f6a1245 2410
8cc83b8d
FV
2411 def __init__(self, msg, exc_info=None):
2412 """ exc_info, if given, is the original exception that caused the trouble (as returned by sys.exc_info()). """
2413 super(DownloadError, self).__init__(msg)
2414 self.exc_info = exc_info
d77c3dfd
FV
2415
2416
bf5b9d85 2417class SameFileError(YoutubeDLError):
59ae15a5 2418 """Same File exception.
d77c3dfd 2419
59ae15a5
PH
2420 This exception will be thrown by FileDownloader objects if they detect
2421 multiple files would have to be downloaded to the same file on disk.
2422 """
2423 pass
d77c3dfd
FV
2424
2425
bf5b9d85 2426class PostProcessingError(YoutubeDLError):
59ae15a5 2427 """Post Processing exception.
d77c3dfd 2428
59ae15a5
PH
2429 This exception may be raised by PostProcessor's .run() method to
2430 indicate an error in the postprocessing task.
2431 """
5f6a1245 2432
7851b379 2433 def __init__(self, msg):
bf5b9d85 2434 super(PostProcessingError, self).__init__(msg)
7851b379 2435 self.msg = msg
d77c3dfd 2436
5f6a1245 2437
8b0d7497 2438class ExistingVideoReached(YoutubeDLError):
2439 """ --max-downloads limit has been reached. """
2440 pass
2441
2442
2443class RejectedVideoReached(YoutubeDLError):
2444 """ --max-downloads limit has been reached. """
2445 pass
2446
2447
bf5b9d85 2448class MaxDownloadsReached(YoutubeDLError):
59ae15a5
PH
2449 """ --max-downloads limit has been reached. """
2450 pass
d77c3dfd
FV
2451
2452
bf5b9d85 2453class UnavailableVideoError(YoutubeDLError):
59ae15a5 2454 """Unavailable Format exception.
d77c3dfd 2455
59ae15a5
PH
2456 This exception will be thrown when a video is requested
2457 in a format that is not available for that video.
2458 """
2459 pass
d77c3dfd
FV
2460
2461
bf5b9d85 2462class ContentTooShortError(YoutubeDLError):
59ae15a5 2463 """Content Too Short exception.
d77c3dfd 2464
59ae15a5
PH
2465 This exception may be raised by FileDownloader objects when a file they
2466 download is too small for what the server announced first, indicating
2467 the connection was probably interrupted.
2468 """
d77c3dfd 2469
59ae15a5 2470 def __init__(self, downloaded, expected):
bf5b9d85
PM
2471 super(ContentTooShortError, self).__init__(
2472 'Downloaded {0} bytes, expected {1} bytes'.format(downloaded, expected)
2473 )
2c7ed247 2474 # Both in bytes
59ae15a5
PH
2475 self.downloaded = downloaded
2476 self.expected = expected
d77c3dfd 2477
5f6a1245 2478
bf5b9d85 2479class XAttrMetadataError(YoutubeDLError):
efa97bdc
YCH
2480 def __init__(self, code=None, msg='Unknown error'):
2481 super(XAttrMetadataError, self).__init__(msg)
2482 self.code = code
bd264412 2483 self.msg = msg
efa97bdc
YCH
2484
2485 # Parsing code and msg
3089bc74 2486 if (self.code in (errno.ENOSPC, errno.EDQUOT)
a0566bbf 2487 or 'No space left' in self.msg or 'Disk quota exceeded' in self.msg):
efa97bdc
YCH
2488 self.reason = 'NO_SPACE'
2489 elif self.code == errno.E2BIG or 'Argument list too long' in self.msg:
2490 self.reason = 'VALUE_TOO_LONG'
2491 else:
2492 self.reason = 'NOT_SUPPORTED'
2493
2494
bf5b9d85 2495class XAttrUnavailableError(YoutubeDLError):
efa97bdc
YCH
2496 pass
2497
2498
c5a59d93 2499def _create_http_connection(ydl_handler, http_class, is_https, *args, **kwargs):
e5e78797
S
2500 # Working around python 2 bug (see http://bugs.python.org/issue17849) by limiting
2501 # expected HTTP responses to meet HTTP/1.0 or later (see also
067aa17e 2502 # https://github.com/ytdl-org/youtube-dl/issues/6727)
e5e78797 2503 if sys.version_info < (3, 0):
65220c3b
S
2504 kwargs['strict'] = True
2505 hc = http_class(*args, **compat_kwargs(kwargs))
be4a824d 2506 source_address = ydl_handler._params.get('source_address')
8959018a 2507
be4a824d 2508 if source_address is not None:
8959018a
AU
2509 # This is to workaround _create_connection() from socket where it will try all
2510 # address data from getaddrinfo() including IPv6. This filters the result from
2511 # getaddrinfo() based on the source_address value.
2512 # This is based on the cpython socket.create_connection() function.
2513 # https://github.com/python/cpython/blob/master/Lib/socket.py#L691
2514 def _create_connection(address, timeout=socket._GLOBAL_DEFAULT_TIMEOUT, source_address=None):
2515 host, port = address
2516 err = None
2517 addrs = socket.getaddrinfo(host, port, 0, socket.SOCK_STREAM)
9e21e6d9
S
2518 af = socket.AF_INET if '.' in source_address[0] else socket.AF_INET6
2519 ip_addrs = [addr for addr in addrs if addr[0] == af]
2520 if addrs and not ip_addrs:
2521 ip_version = 'v4' if af == socket.AF_INET else 'v6'
2522 raise socket.error(
2523 "No remote IP%s addresses available for connect, can't use '%s' as source address"
2524 % (ip_version, source_address[0]))
8959018a
AU
2525 for res in ip_addrs:
2526 af, socktype, proto, canonname, sa = res
2527 sock = None
2528 try:
2529 sock = socket.socket(af, socktype, proto)
2530 if timeout is not socket._GLOBAL_DEFAULT_TIMEOUT:
2531 sock.settimeout(timeout)
2532 sock.bind(source_address)
2533 sock.connect(sa)
2534 err = None # Explicitly break reference cycle
2535 return sock
2536 except socket.error as _:
2537 err = _
2538 if sock is not None:
2539 sock.close()
2540 if err is not None:
2541 raise err
2542 else:
9e21e6d9
S
2543 raise socket.error('getaddrinfo returns an empty list')
2544 if hasattr(hc, '_create_connection'):
2545 hc._create_connection = _create_connection
be4a824d
PH
2546 sa = (source_address, 0)
2547 if hasattr(hc, 'source_address'): # Python 2.7+
2548 hc.source_address = sa
2549 else: # Python 2.6
2550 def _hc_connect(self, *args, **kwargs):
9e21e6d9 2551 sock = _create_connection(
be4a824d
PH
2552 (self.host, self.port), self.timeout, sa)
2553 if is_https:
d7932313
PH
2554 self.sock = ssl.wrap_socket(
2555 sock, self.key_file, self.cert_file,
2556 ssl_version=ssl.PROTOCOL_TLSv1)
be4a824d
PH
2557 else:
2558 self.sock = sock
2559 hc.connect = functools.partial(_hc_connect, hc)
2560
2561 return hc
2562
2563
87f0e62d 2564def handle_youtubedl_headers(headers):
992fc9d6
YCH
2565 filtered_headers = headers
2566
2567 if 'Youtubedl-no-compression' in filtered_headers:
2568 filtered_headers = dict((k, v) for k, v in filtered_headers.items() if k.lower() != 'accept-encoding')
87f0e62d 2569 del filtered_headers['Youtubedl-no-compression']
87f0e62d 2570
992fc9d6 2571 return filtered_headers
87f0e62d
YCH
2572
2573
acebc9cd 2574class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
59ae15a5
PH
2575 """Handler for HTTP requests and responses.
2576
2577 This class, when installed with an OpenerDirector, automatically adds
2578 the standard headers to every HTTP request and handles gzipped and
2579 deflated responses from web servers. If compression is to be avoided in
2580 a particular request, the original request in the program code only has
0424ec30 2581 to include the HTTP header "Youtubedl-no-compression", which will be
59ae15a5
PH
2582 removed before making the real request.
2583
2584 Part of this code was copied from:
2585
2586 http://techknack.net/python-urllib2-handlers/
2587
2588 Andrew Rowls, the author of that code, agreed to release it to the
2589 public domain.
2590 """
2591
be4a824d
PH
2592 def __init__(self, params, *args, **kwargs):
2593 compat_urllib_request.HTTPHandler.__init__(self, *args, **kwargs)
2594 self._params = params
2595
2596 def http_open(self, req):
71aff188
YCH
2597 conn_class = compat_http_client.HTTPConnection
2598
2599 socks_proxy = req.headers.get('Ytdl-socks-proxy')
2600 if socks_proxy:
2601 conn_class = make_socks_conn_class(conn_class, socks_proxy)
2602 del req.headers['Ytdl-socks-proxy']
2603
be4a824d 2604 return self.do_open(functools.partial(
71aff188 2605 _create_http_connection, self, conn_class, False),
be4a824d
PH
2606 req)
2607
59ae15a5
PH
2608 @staticmethod
2609 def deflate(data):
2610 try:
2611 return zlib.decompress(data, -zlib.MAX_WBITS)
2612 except zlib.error:
2613 return zlib.decompress(data)
2614
acebc9cd 2615 def http_request(self, req):
51f267d9
S
2616 # According to RFC 3986, URLs can not contain non-ASCII characters, however this is not
2617 # always respected by websites, some tend to give out URLs with non percent-encoded
2618 # non-ASCII characters (see telemb.py, ard.py [#3412])
2619 # urllib chokes on URLs with non-ASCII characters (see http://bugs.python.org/issue3991)
2620 # To work around aforementioned issue we will replace request's original URL with
2621 # percent-encoded one
2622 # Since redirects are also affected (e.g. http://www.southpark.de/alle-episoden/s18e09)
2623 # the code of this workaround has been moved here from YoutubeDL.urlopen()
2624 url = req.get_full_url()
2625 url_escaped = escape_url(url)
2626
2627 # Substitute URL if any change after escaping
2628 if url != url_escaped:
15d260eb 2629 req = update_Request(req, url=url_escaped)
51f267d9 2630
33ac271b 2631 for h, v in std_headers.items():
3d5f7a39
JK
2632 # Capitalize is needed because of Python bug 2275: http://bugs.python.org/issue2275
2633 # The dict keys are capitalized because of this bug by urllib
2634 if h.capitalize() not in req.headers:
33ac271b 2635 req.add_header(h, v)
87f0e62d
YCH
2636
2637 req.headers = handle_youtubedl_headers(req.headers)
989b4b2b
PH
2638
2639 if sys.version_info < (2, 7) and '#' in req.get_full_url():
2640 # Python 2.6 is brain-dead when it comes to fragments
2641 req._Request__original = req._Request__original.partition('#')[0]
2642 req._Request__r_type = req._Request__r_type.partition('#')[0]
2643
59ae15a5
PH
2644 return req
2645
acebc9cd 2646 def http_response(self, req, resp):
59ae15a5
PH
2647 old_resp = resp
2648 # gzip
2649 if resp.headers.get('Content-encoding', '') == 'gzip':
aa3e9507
PH
2650 content = resp.read()
2651 gz = gzip.GzipFile(fileobj=io.BytesIO(content), mode='rb')
2652 try:
2653 uncompressed = io.BytesIO(gz.read())
2654 except IOError as original_ioerror:
2655 # There may be junk add the end of the file
2656 # See http://stackoverflow.com/q/4928560/35070 for details
2657 for i in range(1, 1024):
2658 try:
2659 gz = gzip.GzipFile(fileobj=io.BytesIO(content[:-i]), mode='rb')
2660 uncompressed = io.BytesIO(gz.read())
2661 except IOError:
2662 continue
2663 break
2664 else:
2665 raise original_ioerror
b407d853 2666 resp = compat_urllib_request.addinfourl(uncompressed, old_resp.headers, old_resp.url, old_resp.code)
59ae15a5 2667 resp.msg = old_resp.msg
c047270c 2668 del resp.headers['Content-encoding']
59ae15a5
PH
2669 # deflate
2670 if resp.headers.get('Content-encoding', '') == 'deflate':
2671 gz = io.BytesIO(self.deflate(resp.read()))
b407d853 2672 resp = compat_urllib_request.addinfourl(gz, old_resp.headers, old_resp.url, old_resp.code)
59ae15a5 2673 resp.msg = old_resp.msg
c047270c 2674 del resp.headers['Content-encoding']
ad729172 2675 # Percent-encode redirect URL of Location HTTP header to satisfy RFC 3986 (see
067aa17e 2676 # https://github.com/ytdl-org/youtube-dl/issues/6457).
5a4d9ddb
S
2677 if 300 <= resp.code < 400:
2678 location = resp.headers.get('Location')
2679 if location:
2680 # As of RFC 2616 default charset is iso-8859-1 that is respected by python 3
2681 if sys.version_info >= (3, 0):
2682 location = location.encode('iso-8859-1').decode('utf-8')
0ea59007
YCH
2683 else:
2684 location = location.decode('utf-8')
5a4d9ddb
S
2685 location_escaped = escape_url(location)
2686 if location != location_escaped:
2687 del resp.headers['Location']
9a4aec8b
YCH
2688 if sys.version_info < (3, 0):
2689 location_escaped = location_escaped.encode('utf-8')
5a4d9ddb 2690 resp.headers['Location'] = location_escaped
59ae15a5 2691 return resp
0f8d03f8 2692
acebc9cd
PH
2693 https_request = http_request
2694 https_response = http_response
bf50b038 2695
5de90176 2696
71aff188
YCH
2697def make_socks_conn_class(base_class, socks_proxy):
2698 assert issubclass(base_class, (
2699 compat_http_client.HTTPConnection, compat_http_client.HTTPSConnection))
2700
2701 url_components = compat_urlparse.urlparse(socks_proxy)
2702 if url_components.scheme.lower() == 'socks5':
2703 socks_type = ProxyType.SOCKS5
2704 elif url_components.scheme.lower() in ('socks', 'socks4'):
2705 socks_type = ProxyType.SOCKS4
51fb4995
YCH
2706 elif url_components.scheme.lower() == 'socks4a':
2707 socks_type = ProxyType.SOCKS4A
71aff188 2708
cdd94c2e
YCH
2709 def unquote_if_non_empty(s):
2710 if not s:
2711 return s
2712 return compat_urllib_parse_unquote_plus(s)
2713
71aff188
YCH
2714 proxy_args = (
2715 socks_type,
2716 url_components.hostname, url_components.port or 1080,
2717 True, # Remote DNS
cdd94c2e
YCH
2718 unquote_if_non_empty(url_components.username),
2719 unquote_if_non_empty(url_components.password),
71aff188
YCH
2720 )
2721
2722 class SocksConnection(base_class):
2723 def connect(self):
2724 self.sock = sockssocket()
2725 self.sock.setproxy(*proxy_args)
2726 if type(self.timeout) in (int, float):
2727 self.sock.settimeout(self.timeout)
2728 self.sock.connect((self.host, self.port))
2729
2730 if isinstance(self, compat_http_client.HTTPSConnection):
2731 if hasattr(self, '_context'): # Python > 2.6
2732 self.sock = self._context.wrap_socket(
2733 self.sock, server_hostname=self.host)
2734 else:
2735 self.sock = ssl.wrap_socket(self.sock)
2736
2737 return SocksConnection
2738
2739
be4a824d
PH
2740class YoutubeDLHTTPSHandler(compat_urllib_request.HTTPSHandler):
2741 def __init__(self, params, https_conn_class=None, *args, **kwargs):
2742 compat_urllib_request.HTTPSHandler.__init__(self, *args, **kwargs)
2743 self._https_conn_class = https_conn_class or compat_http_client.HTTPSConnection
2744 self._params = params
2745
2746 def https_open(self, req):
4f264c02 2747 kwargs = {}
71aff188
YCH
2748 conn_class = self._https_conn_class
2749
4f264c02
JMF
2750 if hasattr(self, '_context'): # python > 2.6
2751 kwargs['context'] = self._context
2752 if hasattr(self, '_check_hostname'): # python 3.x
2753 kwargs['check_hostname'] = self._check_hostname
71aff188
YCH
2754
2755 socks_proxy = req.headers.get('Ytdl-socks-proxy')
2756 if socks_proxy:
2757 conn_class = make_socks_conn_class(conn_class, socks_proxy)
2758 del req.headers['Ytdl-socks-proxy']
2759
be4a824d 2760 return self.do_open(functools.partial(
71aff188 2761 _create_http_connection, self, conn_class, True),
4f264c02 2762 req, **kwargs)
be4a824d
PH
2763
2764
1bab3437 2765class YoutubeDLCookieJar(compat_cookiejar.MozillaCookieJar):
f1a8511f
S
2766 """
2767 See [1] for cookie file format.
2768
2769 1. https://curl.haxx.se/docs/http-cookies.html
2770 """
e7e62441 2771 _HTTPONLY_PREFIX = '#HttpOnly_'
c380cc28
S
2772 _ENTRY_LEN = 7
2773 _HEADER = '''# Netscape HTTP Cookie File
cefecac1 2774# This file is generated by youtube-dlc. Do not edit.
c380cc28
S
2775
2776'''
2777 _CookieFileEntry = collections.namedtuple(
2778 'CookieFileEntry',
2779 ('domain_name', 'include_subdomains', 'path', 'https_only', 'expires_at', 'name', 'value'))
e7e62441 2780
1bab3437 2781 def save(self, filename=None, ignore_discard=False, ignore_expires=False):
c380cc28
S
2782 """
2783 Save cookies to a file.
2784
2785 Most of the code is taken from CPython 3.8 and slightly adapted
2786 to support cookie files with UTF-8 in both python 2 and 3.
2787 """
2788 if filename is None:
2789 if self.filename is not None:
2790 filename = self.filename
2791 else:
2792 raise ValueError(compat_cookiejar.MISSING_FILENAME_TEXT)
2793
1bab3437
S
2794 # Store session cookies with `expires` set to 0 instead of an empty
2795 # string
2796 for cookie in self:
2797 if cookie.expires is None:
2798 cookie.expires = 0
c380cc28
S
2799
2800 with io.open(filename, 'w', encoding='utf-8') as f:
2801 f.write(self._HEADER)
2802 now = time.time()
2803 for cookie in self:
2804 if not ignore_discard and cookie.discard:
2805 continue
2806 if not ignore_expires and cookie.is_expired(now):
2807 continue
2808 if cookie.secure:
2809 secure = 'TRUE'
2810 else:
2811 secure = 'FALSE'
2812 if cookie.domain.startswith('.'):
2813 initial_dot = 'TRUE'
2814 else:
2815 initial_dot = 'FALSE'
2816 if cookie.expires is not None:
2817 expires = compat_str(cookie.expires)
2818 else:
2819 expires = ''
2820 if cookie.value is None:
2821 # cookies.txt regards 'Set-Cookie: foo' as a cookie
2822 # with no name, whereas http.cookiejar regards it as a
2823 # cookie with no value.
2824 name = ''
2825 value = cookie.name
2826 else:
2827 name = cookie.name
2828 value = cookie.value
2829 f.write(
2830 '\t'.join([cookie.domain, initial_dot, cookie.path,
2831 secure, expires, name, value]) + '\n')
1bab3437
S
2832
2833 def load(self, filename=None, ignore_discard=False, ignore_expires=False):
e7e62441 2834 """Load cookies from a file."""
2835 if filename is None:
2836 if self.filename is not None:
2837 filename = self.filename
2838 else:
2839 raise ValueError(compat_cookiejar.MISSING_FILENAME_TEXT)
2840
c380cc28
S
2841 def prepare_line(line):
2842 if line.startswith(self._HTTPONLY_PREFIX):
2843 line = line[len(self._HTTPONLY_PREFIX):]
2844 # comments and empty lines are fine
2845 if line.startswith('#') or not line.strip():
2846 return line
2847 cookie_list = line.split('\t')
2848 if len(cookie_list) != self._ENTRY_LEN:
2849 raise compat_cookiejar.LoadError('invalid length %d' % len(cookie_list))
2850 cookie = self._CookieFileEntry(*cookie_list)
2851 if cookie.expires_at and not cookie.expires_at.isdigit():
2852 raise compat_cookiejar.LoadError('invalid expires at %s' % cookie.expires_at)
2853 return line
2854
e7e62441 2855 cf = io.StringIO()
c380cc28 2856 with io.open(filename, encoding='utf-8') as f:
e7e62441 2857 for line in f:
c380cc28
S
2858 try:
2859 cf.write(prepare_line(line))
2860 except compat_cookiejar.LoadError as e:
2861 write_string(
2862 'WARNING: skipping cookie file entry due to %s: %r\n'
2863 % (e, line), sys.stderr)
2864 continue
e7e62441 2865 cf.seek(0)
2866 self._really_load(cf, filename, ignore_discard, ignore_expires)
1bab3437
S
2867 # Session cookies are denoted by either `expires` field set to
2868 # an empty string or 0. MozillaCookieJar only recognizes the former
2869 # (see [1]). So we need force the latter to be recognized as session
2870 # cookies on our own.
2871 # Session cookies may be important for cookies-based authentication,
2872 # e.g. usually, when user does not check 'Remember me' check box while
2873 # logging in on a site, some important cookies are stored as session
2874 # cookies so that not recognizing them will result in failed login.
2875 # 1. https://bugs.python.org/issue17164
2876 for cookie in self:
2877 # Treat `expires=0` cookies as session cookies
2878 if cookie.expires == 0:
2879 cookie.expires = None
2880 cookie.discard = True
2881
2882
a6420bf5
S
2883class YoutubeDLCookieProcessor(compat_urllib_request.HTTPCookieProcessor):
2884 def __init__(self, cookiejar=None):
2885 compat_urllib_request.HTTPCookieProcessor.__init__(self, cookiejar)
2886
2887 def http_response(self, request, response):
2888 # Python 2 will choke on next HTTP request in row if there are non-ASCII
2889 # characters in Set-Cookie HTTP header of last response (see
067aa17e 2890 # https://github.com/ytdl-org/youtube-dl/issues/6769).
a6420bf5
S
2891 # In order to at least prevent crashing we will percent encode Set-Cookie
2892 # header before HTTPCookieProcessor starts processing it.
e28034c5
S
2893 # if sys.version_info < (3, 0) and response.headers:
2894 # for set_cookie_header in ('Set-Cookie', 'Set-Cookie2'):
2895 # set_cookie = response.headers.get(set_cookie_header)
2896 # if set_cookie:
2897 # set_cookie_escaped = compat_urllib_parse.quote(set_cookie, b"%/;:@&=+$,!~*'()?#[] ")
2898 # if set_cookie != set_cookie_escaped:
2899 # del response.headers[set_cookie_header]
2900 # response.headers[set_cookie_header] = set_cookie_escaped
a6420bf5
S
2901 return compat_urllib_request.HTTPCookieProcessor.http_response(self, request, response)
2902
2903 https_request = compat_urllib_request.HTTPCookieProcessor.http_request
2904 https_response = http_response
2905
2906
fca6dba8
S
2907class YoutubeDLRedirectHandler(compat_urllib_request.HTTPRedirectHandler):
2908 if sys.version_info[0] < 3:
2909 def redirect_request(self, req, fp, code, msg, headers, newurl):
2910 # On python 2 urlh.geturl() may sometimes return redirect URL
2911 # as byte string instead of unicode. This workaround allows
2912 # to force it always return unicode.
2913 return compat_urllib_request.HTTPRedirectHandler.redirect_request(self, req, fp, code, msg, headers, compat_str(newurl))
2914
2915
46f59e89
S
2916def extract_timezone(date_str):
2917 m = re.search(
2918 r'^.{8,}?(?P<tz>Z$| ?(?P<sign>\+|-)(?P<hours>[0-9]{2}):?(?P<minutes>[0-9]{2})$)',
2919 date_str)
2920 if not m:
2921 timezone = datetime.timedelta()
2922 else:
2923 date_str = date_str[:-len(m.group('tz'))]
2924 if not m.group('sign'):
2925 timezone = datetime.timedelta()
2926 else:
2927 sign = 1 if m.group('sign') == '+' else -1
2928 timezone = datetime.timedelta(
2929 hours=sign * int(m.group('hours')),
2930 minutes=sign * int(m.group('minutes')))
2931 return timezone, date_str
2932
2933
08b38d54 2934def parse_iso8601(date_str, delimiter='T', timezone=None):
912b38b4
PH
2935 """ Return a UNIX timestamp from the given date """
2936
2937 if date_str is None:
2938 return None
2939
52c3a6e4
S
2940 date_str = re.sub(r'\.[0-9]+', '', date_str)
2941
08b38d54 2942 if timezone is None:
46f59e89
S
2943 timezone, date_str = extract_timezone(date_str)
2944
52c3a6e4
S
2945 try:
2946 date_format = '%Y-%m-%d{0}%H:%M:%S'.format(delimiter)
2947 dt = datetime.datetime.strptime(date_str, date_format) - timezone
2948 return calendar.timegm(dt.timetuple())
2949 except ValueError:
2950 pass
912b38b4
PH
2951
2952
46f59e89
S
2953def date_formats(day_first=True):
2954 return DATE_FORMATS_DAY_FIRST if day_first else DATE_FORMATS_MONTH_FIRST
2955
2956
42bdd9d0 2957def unified_strdate(date_str, day_first=True):
bf50b038 2958 """Return a string with the date in the format YYYYMMDD"""
64e7ad60
PH
2959
2960 if date_str is None:
2961 return None
bf50b038 2962 upload_date = None
5f6a1245 2963 # Replace commas
026fcc04 2964 date_str = date_str.replace(',', ' ')
42bdd9d0 2965 # Remove AM/PM + timezone
9bb8e0a3 2966 date_str = re.sub(r'(?i)\s*(?:AM|PM)(?:\s+[A-Z]+)?', '', date_str)
46f59e89 2967 _, date_str = extract_timezone(date_str)
42bdd9d0 2968
46f59e89 2969 for expression in date_formats(day_first):
bf50b038
JMF
2970 try:
2971 upload_date = datetime.datetime.strptime(date_str, expression).strftime('%Y%m%d')
5de90176 2972 except ValueError:
bf50b038 2973 pass
42393ce2
PH
2974 if upload_date is None:
2975 timetuple = email.utils.parsedate_tz(date_str)
2976 if timetuple:
c6b9cf05
S
2977 try:
2978 upload_date = datetime.datetime(*timetuple[:6]).strftime('%Y%m%d')
2979 except ValueError:
2980 pass
6a750402
JMF
2981 if upload_date is not None:
2982 return compat_str(upload_date)
bf50b038 2983
5f6a1245 2984
46f59e89
S
2985def unified_timestamp(date_str, day_first=True):
2986 if date_str is None:
2987 return None
2988
2ae2ffda 2989 date_str = re.sub(r'[,|]', '', date_str)
46f59e89 2990
7dc2a74e 2991 pm_delta = 12 if re.search(r'(?i)PM', date_str) else 0
46f59e89
S
2992 timezone, date_str = extract_timezone(date_str)
2993
2994 # Remove AM/PM + timezone
2995 date_str = re.sub(r'(?i)\s*(?:AM|PM)(?:\s+[A-Z]+)?', '', date_str)
2996
deef3195
S
2997 # Remove unrecognized timezones from ISO 8601 alike timestamps
2998 m = re.search(r'\d{1,2}:\d{1,2}(?:\.\d+)?(?P<tz>\s*[A-Z]+)$', date_str)
2999 if m:
3000 date_str = date_str[:-len(m.group('tz'))]
3001
f226880c
PH
3002 # Python only supports microseconds, so remove nanoseconds
3003 m = re.search(r'^([0-9]{4,}-[0-9]{1,2}-[0-9]{1,2}T[0-9]{1,2}:[0-9]{1,2}:[0-9]{1,2}\.[0-9]{6})[0-9]+$', date_str)
3004 if m:
3005 date_str = m.group(1)
3006
46f59e89
S
3007 for expression in date_formats(day_first):
3008 try:
7dc2a74e 3009 dt = datetime.datetime.strptime(date_str, expression) - timezone + datetime.timedelta(hours=pm_delta)
46f59e89
S
3010 return calendar.timegm(dt.timetuple())
3011 except ValueError:
3012 pass
3013 timetuple = email.utils.parsedate_tz(date_str)
3014 if timetuple:
7dc2a74e 3015 return calendar.timegm(timetuple) + pm_delta * 3600
46f59e89
S
3016
3017
28e614de 3018def determine_ext(url, default_ext='unknown_video'):
85750f89 3019 if url is None or '.' not in url:
f4776371 3020 return default_ext
9cb9a5df 3021 guess = url.partition('?')[0].rpartition('.')[2]
73e79f2a
PH
3022 if re.match(r'^[A-Za-z0-9]+$', guess):
3023 return guess
a7aaa398
S
3024 # Try extract ext from URLs like http://example.com/foo/bar.mp4/?download
3025 elif guess.rstrip('/') in KNOWN_EXTENSIONS:
9cb9a5df 3026 return guess.rstrip('/')
73e79f2a 3027 else:
cbdbb766 3028 return default_ext
73e79f2a 3029
5f6a1245 3030
824fa511
S
3031def subtitles_filename(filename, sub_lang, sub_format, expected_real_ext=None):
3032 return replace_extension(filename, sub_lang + '.' + sub_format, expected_real_ext)
d4051a8e 3033
5f6a1245 3034
bd558525 3035def date_from_str(date_str):
37254abc
JMF
3036 """
3037 Return a datetime object from a string in the format YYYYMMDD or
3038 (now|today)[+-][0-9](day|week|month|year)(s)?"""
3039 today = datetime.date.today()
f8795e10 3040 if date_str in ('now', 'today'):
37254abc 3041 return today
f8795e10
PH
3042 if date_str == 'yesterday':
3043 return today - datetime.timedelta(days=1)
ec85ded8 3044 match = re.match(r'(now|today)(?P<sign>[+-])(?P<time>\d+)(?P<unit>day|week|month|year)(s)?', date_str)
37254abc
JMF
3045 if match is not None:
3046 sign = match.group('sign')
3047 time = int(match.group('time'))
3048 if sign == '-':
3049 time = -time
3050 unit = match.group('unit')
dfb1b146 3051 # A bad approximation?
37254abc
JMF
3052 if unit == 'month':
3053 unit = 'day'
3054 time *= 30
3055 elif unit == 'year':
3056 unit = 'day'
3057 time *= 365
3058 unit += 's'
3059 delta = datetime.timedelta(**{unit: time})
3060 return today + delta
611c1dd9 3061 return datetime.datetime.strptime(date_str, '%Y%m%d').date()
5f6a1245
JW
3062
3063
e63fc1be 3064def hyphenate_date(date_str):
3065 """
3066 Convert a date in 'YYYYMMDD' format to 'YYYY-MM-DD' format"""
3067 match = re.match(r'^(\d\d\d\d)(\d\d)(\d\d)$', date_str)
3068 if match is not None:
3069 return '-'.join(match.groups())
3070 else:
3071 return date_str
3072
5f6a1245 3073
bd558525
JMF
3074class DateRange(object):
3075 """Represents a time interval between two dates"""
5f6a1245 3076
bd558525
JMF
3077 def __init__(self, start=None, end=None):
3078 """start and end must be strings in the format accepted by date"""
3079 if start is not None:
3080 self.start = date_from_str(start)
3081 else:
3082 self.start = datetime.datetime.min.date()
3083 if end is not None:
3084 self.end = date_from_str(end)
3085 else:
3086 self.end = datetime.datetime.max.date()
37254abc 3087 if self.start > self.end:
bd558525 3088 raise ValueError('Date range: "%s" , the start date must be before the end date' % self)
5f6a1245 3089
bd558525
JMF
3090 @classmethod
3091 def day(cls, day):
3092 """Returns a range that only contains the given day"""
5f6a1245
JW
3093 return cls(day, day)
3094
bd558525
JMF
3095 def __contains__(self, date):
3096 """Check if the date is in the range"""
37254abc
JMF
3097 if not isinstance(date, datetime.date):
3098 date = date_from_str(date)
3099 return self.start <= date <= self.end
5f6a1245 3100
bd558525 3101 def __str__(self):
5f6a1245 3102 return '%s - %s' % (self.start.isoformat(), self.end.isoformat())
c496ca96
PH
3103
3104
3105def platform_name():
3106 """ Returns the platform name as a compat_str """
3107 res = platform.platform()
3108 if isinstance(res, bytes):
3109 res = res.decode(preferredencoding())
3110
3111 assert isinstance(res, compat_str)
3112 return res
c257baff
PH
3113
3114
b58ddb32
PH
3115def _windows_write_string(s, out):
3116 """ Returns True if the string was written using special methods,
3117 False if it has yet to be written out."""
3118 # Adapted from http://stackoverflow.com/a/3259271/35070
3119
3120 import ctypes
3121 import ctypes.wintypes
3122
3123 WIN_OUTPUT_IDS = {
3124 1: -11,
3125 2: -12,
3126 }
3127
a383a98a
PH
3128 try:
3129 fileno = out.fileno()
3130 except AttributeError:
3131 # If the output stream doesn't have a fileno, it's virtual
3132 return False
aa42e873
PH
3133 except io.UnsupportedOperation:
3134 # Some strange Windows pseudo files?
3135 return False
b58ddb32
PH
3136 if fileno not in WIN_OUTPUT_IDS:
3137 return False
3138
d7cd9a9e 3139 GetStdHandle = compat_ctypes_WINFUNCTYPE(
b58ddb32 3140 ctypes.wintypes.HANDLE, ctypes.wintypes.DWORD)(
d7cd9a9e 3141 ('GetStdHandle', ctypes.windll.kernel32))
b58ddb32
PH
3142 h = GetStdHandle(WIN_OUTPUT_IDS[fileno])
3143
d7cd9a9e 3144 WriteConsoleW = compat_ctypes_WINFUNCTYPE(
b58ddb32
PH
3145 ctypes.wintypes.BOOL, ctypes.wintypes.HANDLE, ctypes.wintypes.LPWSTR,
3146 ctypes.wintypes.DWORD, ctypes.POINTER(ctypes.wintypes.DWORD),
d7cd9a9e 3147 ctypes.wintypes.LPVOID)(('WriteConsoleW', ctypes.windll.kernel32))
b58ddb32
PH
3148 written = ctypes.wintypes.DWORD(0)
3149
d7cd9a9e 3150 GetFileType = compat_ctypes_WINFUNCTYPE(ctypes.wintypes.DWORD, ctypes.wintypes.DWORD)(('GetFileType', ctypes.windll.kernel32))
b58ddb32
PH
3151 FILE_TYPE_CHAR = 0x0002
3152 FILE_TYPE_REMOTE = 0x8000
d7cd9a9e 3153 GetConsoleMode = compat_ctypes_WINFUNCTYPE(
b58ddb32
PH
3154 ctypes.wintypes.BOOL, ctypes.wintypes.HANDLE,
3155 ctypes.POINTER(ctypes.wintypes.DWORD))(
d7cd9a9e 3156 ('GetConsoleMode', ctypes.windll.kernel32))
b58ddb32
PH
3157 INVALID_HANDLE_VALUE = ctypes.wintypes.DWORD(-1).value
3158
3159 def not_a_console(handle):
3160 if handle == INVALID_HANDLE_VALUE or handle is None:
3161 return True
3089bc74
S
3162 return ((GetFileType(handle) & ~FILE_TYPE_REMOTE) != FILE_TYPE_CHAR
3163 or GetConsoleMode(handle, ctypes.byref(ctypes.wintypes.DWORD())) == 0)
b58ddb32
PH
3164
3165 if not_a_console(h):
3166 return False
3167
d1b9c912
PH
3168 def next_nonbmp_pos(s):
3169 try:
3170 return next(i for i, c in enumerate(s) if ord(c) > 0xffff)
3171 except StopIteration:
3172 return len(s)
3173
3174 while s:
3175 count = min(next_nonbmp_pos(s), 1024)
3176
b58ddb32 3177 ret = WriteConsoleW(
d1b9c912 3178 h, s, count if count else 2, ctypes.byref(written), None)
b58ddb32
PH
3179 if ret == 0:
3180 raise OSError('Failed to write string')
d1b9c912
PH
3181 if not count: # We just wrote a non-BMP character
3182 assert written.value == 2
3183 s = s[1:]
3184 else:
3185 assert written.value > 0
3186 s = s[written.value:]
b58ddb32
PH
3187 return True
3188
3189
734f90bb 3190def write_string(s, out=None, encoding=None):
7459e3a2
PH
3191 if out is None:
3192 out = sys.stderr
8bf48f23 3193 assert type(s) == compat_str
7459e3a2 3194
b58ddb32
PH
3195 if sys.platform == 'win32' and encoding is None and hasattr(out, 'fileno'):
3196 if _windows_write_string(s, out):
3197 return
3198
3089bc74
S
3199 if ('b' in getattr(out, 'mode', '')
3200 or sys.version_info[0] < 3): # Python 2 lies about mode of sys.stderr
104aa738
PH
3201 byt = s.encode(encoding or preferredencoding(), 'ignore')
3202 out.write(byt)
3203 elif hasattr(out, 'buffer'):
3204 enc = encoding or getattr(out, 'encoding', None) or preferredencoding()
3205 byt = s.encode(enc, 'ignore')
3206 out.buffer.write(byt)
3207 else:
8bf48f23 3208 out.write(s)
7459e3a2
PH
3209 out.flush()
3210
3211
48ea9cea
PH
3212def bytes_to_intlist(bs):
3213 if not bs:
3214 return []
3215 if isinstance(bs[0], int): # Python 3
3216 return list(bs)
3217 else:
3218 return [ord(c) for c in bs]
3219
c257baff 3220
cba892fa 3221def intlist_to_bytes(xs):
3222 if not xs:
3223 return b''
edaa23f8 3224 return compat_struct_pack('%dB' % len(xs), *xs)
c38b1e77
PH
3225
3226
c1c9a79c
PH
3227# Cross-platform file locking
3228if sys.platform == 'win32':
3229 import ctypes.wintypes
3230 import msvcrt
3231
3232 class OVERLAPPED(ctypes.Structure):
3233 _fields_ = [
3234 ('Internal', ctypes.wintypes.LPVOID),
3235 ('InternalHigh', ctypes.wintypes.LPVOID),
3236 ('Offset', ctypes.wintypes.DWORD),
3237 ('OffsetHigh', ctypes.wintypes.DWORD),
3238 ('hEvent', ctypes.wintypes.HANDLE),
3239 ]
3240
3241 kernel32 = ctypes.windll.kernel32
3242 LockFileEx = kernel32.LockFileEx
3243 LockFileEx.argtypes = [
3244 ctypes.wintypes.HANDLE, # hFile
3245 ctypes.wintypes.DWORD, # dwFlags
3246 ctypes.wintypes.DWORD, # dwReserved
3247 ctypes.wintypes.DWORD, # nNumberOfBytesToLockLow
3248 ctypes.wintypes.DWORD, # nNumberOfBytesToLockHigh
3249 ctypes.POINTER(OVERLAPPED) # Overlapped
3250 ]
3251 LockFileEx.restype = ctypes.wintypes.BOOL
3252 UnlockFileEx = kernel32.UnlockFileEx
3253 UnlockFileEx.argtypes = [
3254 ctypes.wintypes.HANDLE, # hFile
3255 ctypes.wintypes.DWORD, # dwReserved
3256 ctypes.wintypes.DWORD, # nNumberOfBytesToLockLow
3257 ctypes.wintypes.DWORD, # nNumberOfBytesToLockHigh
3258 ctypes.POINTER(OVERLAPPED) # Overlapped
3259 ]
3260 UnlockFileEx.restype = ctypes.wintypes.BOOL
3261 whole_low = 0xffffffff
3262 whole_high = 0x7fffffff
3263
3264 def _lock_file(f, exclusive):
3265 overlapped = OVERLAPPED()
3266 overlapped.Offset = 0
3267 overlapped.OffsetHigh = 0
3268 overlapped.hEvent = 0
3269 f._lock_file_overlapped_p = ctypes.pointer(overlapped)
3270 handle = msvcrt.get_osfhandle(f.fileno())
3271 if not LockFileEx(handle, 0x2 if exclusive else 0x0, 0,
3272 whole_low, whole_high, f._lock_file_overlapped_p):
3273 raise OSError('Locking file failed: %r' % ctypes.FormatError())
3274
3275 def _unlock_file(f):
3276 assert f._lock_file_overlapped_p
3277 handle = msvcrt.get_osfhandle(f.fileno())
3278 if not UnlockFileEx(handle, 0,
3279 whole_low, whole_high, f._lock_file_overlapped_p):
3280 raise OSError('Unlocking file failed: %r' % ctypes.FormatError())
3281
3282else:
399a76e6
YCH
3283 # Some platforms, such as Jython, is missing fcntl
3284 try:
3285 import fcntl
c1c9a79c 3286
399a76e6
YCH
3287 def _lock_file(f, exclusive):
3288 fcntl.flock(f, fcntl.LOCK_EX if exclusive else fcntl.LOCK_SH)
c1c9a79c 3289
399a76e6
YCH
3290 def _unlock_file(f):
3291 fcntl.flock(f, fcntl.LOCK_UN)
3292 except ImportError:
3293 UNSUPPORTED_MSG = 'file locking is not supported on this platform'
3294
3295 def _lock_file(f, exclusive):
3296 raise IOError(UNSUPPORTED_MSG)
3297
3298 def _unlock_file(f):
3299 raise IOError(UNSUPPORTED_MSG)
c1c9a79c
PH
3300
3301
3302class locked_file(object):
3303 def __init__(self, filename, mode, encoding=None):
3304 assert mode in ['r', 'a', 'w']
3305 self.f = io.open(filename, mode, encoding=encoding)
3306 self.mode = mode
3307
3308 def __enter__(self):
3309 exclusive = self.mode != 'r'
3310 try:
3311 _lock_file(self.f, exclusive)
3312 except IOError:
3313 self.f.close()
3314 raise
3315 return self
3316
3317 def __exit__(self, etype, value, traceback):
3318 try:
3319 _unlock_file(self.f)
3320 finally:
3321 self.f.close()
3322
3323 def __iter__(self):
3324 return iter(self.f)
3325
3326 def write(self, *args):
3327 return self.f.write(*args)
3328
3329 def read(self, *args):
3330 return self.f.read(*args)
4eb7f1d1
JMF
3331
3332
4644ac55
S
3333def get_filesystem_encoding():
3334 encoding = sys.getfilesystemencoding()
3335 return encoding if encoding is not None else 'utf-8'
3336
3337
4eb7f1d1 3338def shell_quote(args):
a6a173c2 3339 quoted_args = []
4644ac55 3340 encoding = get_filesystem_encoding()
a6a173c2
JMF
3341 for a in args:
3342 if isinstance(a, bytes):
3343 # We may get a filename encoded with 'encodeFilename'
3344 a = a.decode(encoding)
aefce8e6 3345 quoted_args.append(compat_shlex_quote(a))
28e614de 3346 return ' '.join(quoted_args)
9d4660ca
PH
3347
3348
3349def smuggle_url(url, data):
3350 """ Pass additional data in a URL for internal use. """
3351
81953d1a
RA
3352 url, idata = unsmuggle_url(url, {})
3353 data.update(idata)
15707c7e 3354 sdata = compat_urllib_parse_urlencode(
28e614de
PH
3355 {'__youtubedl_smuggle': json.dumps(data)})
3356 return url + '#' + sdata
9d4660ca
PH
3357
3358
79f82953 3359def unsmuggle_url(smug_url, default=None):
83e865a3 3360 if '#__youtubedl_smuggle' not in smug_url:
79f82953 3361 return smug_url, default
28e614de
PH
3362 url, _, sdata = smug_url.rpartition('#')
3363 jsond = compat_parse_qs(sdata)['__youtubedl_smuggle'][0]
9d4660ca
PH
3364 data = json.loads(jsond)
3365 return url, data
02dbf93f
PH
3366
3367
02dbf93f
PH
3368def format_bytes(bytes):
3369 if bytes is None:
28e614de 3370 return 'N/A'
02dbf93f
PH
3371 if type(bytes) is str:
3372 bytes = float(bytes)
3373 if bytes == 0.0:
3374 exponent = 0
3375 else:
3376 exponent = int(math.log(bytes, 1024.0))
28e614de 3377 suffix = ['B', 'KiB', 'MiB', 'GiB', 'TiB', 'PiB', 'EiB', 'ZiB', 'YiB'][exponent]
02dbf93f 3378 converted = float(bytes) / float(1024 ** exponent)
28e614de 3379 return '%.2f%s' % (converted, suffix)
f53c966a 3380
1c088fa8 3381
fb47597b
S
3382def lookup_unit_table(unit_table, s):
3383 units_re = '|'.join(re.escape(u) for u in unit_table)
3384 m = re.match(
782b1b5b 3385 r'(?P<num>[0-9]+(?:[,.][0-9]*)?)\s*(?P<unit>%s)\b' % units_re, s)
fb47597b
S
3386 if not m:
3387 return None
3388 num_str = m.group('num').replace(',', '.')
3389 mult = unit_table[m.group('unit')]
3390 return int(float(num_str) * mult)
3391
3392
be64b5b0
PH
3393def parse_filesize(s):
3394 if s is None:
3395 return None
3396
dfb1b146 3397 # The lower-case forms are of course incorrect and unofficial,
be64b5b0
PH
3398 # but we support those too
3399 _UNIT_TABLE = {
3400 'B': 1,
3401 'b': 1,
70852b47 3402 'bytes': 1,
be64b5b0
PH
3403 'KiB': 1024,
3404 'KB': 1000,
3405 'kB': 1024,
3406 'Kb': 1000,
13585d76 3407 'kb': 1000,
70852b47
YCH
3408 'kilobytes': 1000,
3409 'kibibytes': 1024,
be64b5b0
PH
3410 'MiB': 1024 ** 2,
3411 'MB': 1000 ** 2,
3412 'mB': 1024 ** 2,
3413 'Mb': 1000 ** 2,
13585d76 3414 'mb': 1000 ** 2,
70852b47
YCH
3415 'megabytes': 1000 ** 2,
3416 'mebibytes': 1024 ** 2,
be64b5b0
PH
3417 'GiB': 1024 ** 3,
3418 'GB': 1000 ** 3,
3419 'gB': 1024 ** 3,
3420 'Gb': 1000 ** 3,
13585d76 3421 'gb': 1000 ** 3,
70852b47
YCH
3422 'gigabytes': 1000 ** 3,
3423 'gibibytes': 1024 ** 3,
be64b5b0
PH
3424 'TiB': 1024 ** 4,
3425 'TB': 1000 ** 4,
3426 'tB': 1024 ** 4,
3427 'Tb': 1000 ** 4,
13585d76 3428 'tb': 1000 ** 4,
70852b47
YCH
3429 'terabytes': 1000 ** 4,
3430 'tebibytes': 1024 ** 4,
be64b5b0
PH
3431 'PiB': 1024 ** 5,
3432 'PB': 1000 ** 5,
3433 'pB': 1024 ** 5,
3434 'Pb': 1000 ** 5,
13585d76 3435 'pb': 1000 ** 5,
70852b47
YCH
3436 'petabytes': 1000 ** 5,
3437 'pebibytes': 1024 ** 5,
be64b5b0
PH
3438 'EiB': 1024 ** 6,
3439 'EB': 1000 ** 6,
3440 'eB': 1024 ** 6,
3441 'Eb': 1000 ** 6,
13585d76 3442 'eb': 1000 ** 6,
70852b47
YCH
3443 'exabytes': 1000 ** 6,
3444 'exbibytes': 1024 ** 6,
be64b5b0
PH
3445 'ZiB': 1024 ** 7,
3446 'ZB': 1000 ** 7,
3447 'zB': 1024 ** 7,
3448 'Zb': 1000 ** 7,
13585d76 3449 'zb': 1000 ** 7,
70852b47
YCH
3450 'zettabytes': 1000 ** 7,
3451 'zebibytes': 1024 ** 7,
be64b5b0
PH
3452 'YiB': 1024 ** 8,
3453 'YB': 1000 ** 8,
3454 'yB': 1024 ** 8,
3455 'Yb': 1000 ** 8,
13585d76 3456 'yb': 1000 ** 8,
70852b47
YCH
3457 'yottabytes': 1000 ** 8,
3458 'yobibytes': 1024 ** 8,
be64b5b0
PH
3459 }
3460
fb47597b
S
3461 return lookup_unit_table(_UNIT_TABLE, s)
3462
3463
3464def parse_count(s):
3465 if s is None:
be64b5b0
PH
3466 return None
3467
fb47597b
S
3468 s = s.strip()
3469
3470 if re.match(r'^[\d,.]+$', s):
3471 return str_to_int(s)
3472
3473 _UNIT_TABLE = {
3474 'k': 1000,
3475 'K': 1000,
3476 'm': 1000 ** 2,
3477 'M': 1000 ** 2,
3478 'kk': 1000 ** 2,
3479 'KK': 1000 ** 2,
3480 }
be64b5b0 3481
fb47597b 3482 return lookup_unit_table(_UNIT_TABLE, s)
be64b5b0 3483
2f7ae819 3484
b871d7e9
S
3485def parse_resolution(s):
3486 if s is None:
3487 return {}
3488
3489 mobj = re.search(r'\b(?P<w>\d+)\s*[xX×]\s*(?P<h>\d+)\b', s)
3490 if mobj:
3491 return {
3492 'width': int(mobj.group('w')),
3493 'height': int(mobj.group('h')),
3494 }
3495
3496 mobj = re.search(r'\b(\d+)[pPiI]\b', s)
3497 if mobj:
3498 return {'height': int(mobj.group(1))}
3499
3500 mobj = re.search(r'\b([48])[kK]\b', s)
3501 if mobj:
3502 return {'height': int(mobj.group(1)) * 540}
3503
3504 return {}
3505
3506
0dc41787
S
3507def parse_bitrate(s):
3508 if not isinstance(s, compat_str):
3509 return
3510 mobj = re.search(r'\b(\d+)\s*kbps', s)
3511 if mobj:
3512 return int(mobj.group(1))
3513
3514
a942d6cb 3515def month_by_name(name, lang='en'):
caefb1de
PH
3516 """ Return the number of a month by (locale-independently) English name """
3517
f6717dec 3518 month_names = MONTH_NAMES.get(lang, MONTH_NAMES['en'])
a942d6cb 3519
caefb1de 3520 try:
f6717dec 3521 return month_names.index(name) + 1
7105440c
YCH
3522 except ValueError:
3523 return None
3524
3525
3526def month_by_abbreviation(abbrev):
3527 """ Return the number of a month by (locale-independently) English
3528 abbreviations """
3529
3530 try:
3531 return [s[:3] for s in ENGLISH_MONTH_NAMES].index(abbrev) + 1
caefb1de
PH
3532 except ValueError:
3533 return None
18258362
JMF
3534
3535
5aafe895 3536def fix_xml_ampersands(xml_str):
18258362 3537 """Replace all the '&' by '&amp;' in XML"""
5aafe895
PH
3538 return re.sub(
3539 r'&(?!amp;|lt;|gt;|apos;|quot;|#x[0-9a-fA-F]{,4};|#[0-9]{,4};)',
28e614de 3540 '&amp;',
5aafe895 3541 xml_str)
e3946f98
PH
3542
3543
3544def setproctitle(title):
8bf48f23 3545 assert isinstance(title, compat_str)
c1c05c67
YCH
3546
3547 # ctypes in Jython is not complete
3548 # http://bugs.jython.org/issue2148
3549 if sys.platform.startswith('java'):
3550 return
3551
e3946f98 3552 try:
611c1dd9 3553 libc = ctypes.cdll.LoadLibrary('libc.so.6')
e3946f98
PH
3554 except OSError:
3555 return
2f49bcd6
RC
3556 except TypeError:
3557 # LoadLibrary in Windows Python 2.7.13 only expects
3558 # a bytestring, but since unicode_literals turns
3559 # every string into a unicode string, it fails.
3560 return
6eefe533
PH
3561 title_bytes = title.encode('utf-8')
3562 buf = ctypes.create_string_buffer(len(title_bytes))
3563 buf.value = title_bytes
e3946f98 3564 try:
6eefe533 3565 libc.prctl(15, buf, 0, 0, 0)
e3946f98
PH
3566 except AttributeError:
3567 return # Strange libc, just skip this
d7dda168
PH
3568
3569
3570def remove_start(s, start):
46bc9b7d 3571 return s[len(start):] if s is not None and s.startswith(start) else s
29eb5174
PH
3572
3573
2b9faf55 3574def remove_end(s, end):
46bc9b7d 3575 return s[:-len(end)] if s is not None and s.endswith(end) else s
2b9faf55
PH
3576
3577
31b2051e
S
3578def remove_quotes(s):
3579 if s is None or len(s) < 2:
3580 return s
3581 for quote in ('"', "'", ):
3582 if s[0] == quote and s[-1] == quote:
3583 return s[1:-1]
3584 return s
3585
3586
b6e0c7d2
U
3587def get_domain(url):
3588 domain = re.match(r'(?:https?:\/\/)?(?:www\.)?(?P<domain>[^\n\/]+\.[^\n\/]+)(?:\/(.*))?', url)
3589 return domain.group('domain') if domain else None
3590
3591
29eb5174 3592def url_basename(url):
9b8aaeed 3593 path = compat_urlparse.urlparse(url).path
28e614de 3594 return path.strip('/').split('/')[-1]
aa94a6d3
PH
3595
3596
02dc0a36
S
3597def base_url(url):
3598 return re.match(r'https?://[^?#&]+/', url).group()
3599
3600
e34c3361 3601def urljoin(base, path):
4b5de77b
S
3602 if isinstance(path, bytes):
3603 path = path.decode('utf-8')
e34c3361
S
3604 if not isinstance(path, compat_str) or not path:
3605 return None
fad4ceb5 3606 if re.match(r'^(?:[a-zA-Z][a-zA-Z0-9+-.]*:)?//', path):
e34c3361 3607 return path
4b5de77b
S
3608 if isinstance(base, bytes):
3609 base = base.decode('utf-8')
3610 if not isinstance(base, compat_str) or not re.match(
3611 r'^(?:https?:)?//', base):
e34c3361
S
3612 return None
3613 return compat_urlparse.urljoin(base, path)
3614
3615
aa94a6d3
PH
3616class HEADRequest(compat_urllib_request.Request):
3617 def get_method(self):
611c1dd9 3618 return 'HEAD'
7217e148
PH
3619
3620
95cf60e8
S
3621class PUTRequest(compat_urllib_request.Request):
3622 def get_method(self):
3623 return 'PUT'
3624
3625
9732d77e 3626def int_or_none(v, scale=1, default=None, get_attr=None, invscale=1):
28746fbd
PH
3627 if get_attr:
3628 if v is not None:
3629 v = getattr(v, get_attr, None)
9572013d
PH
3630 if v == '':
3631 v = None
1812afb7
S
3632 if v is None:
3633 return default
3634 try:
3635 return int(v) * invscale // scale
5e1271c5 3636 except (ValueError, TypeError):
af98f8ff 3637 return default
9732d77e 3638
9572013d 3639
40a90862
JMF
3640def str_or_none(v, default=None):
3641 return default if v is None else compat_str(v)
3642
9732d77e
PH
3643
3644def str_to_int(int_str):
48d4681e 3645 """ A more relaxed version of int_or_none """
42db58ec 3646 if isinstance(int_str, compat_integer_types):
348c6bf1 3647 return int_str
42db58ec
S
3648 elif isinstance(int_str, compat_str):
3649 int_str = re.sub(r'[,\.\+]', '', int_str)
3650 return int_or_none(int_str)
608d11f5
PH
3651
3652
9732d77e 3653def float_or_none(v, scale=1, invscale=1, default=None):
caf80631
S
3654 if v is None:
3655 return default
3656 try:
3657 return float(v) * invscale / scale
5e1271c5 3658 except (ValueError, TypeError):
caf80631 3659 return default
43f775e4
PH
3660
3661
c7e327c4
S
3662def bool_or_none(v, default=None):
3663 return v if isinstance(v, bool) else default
3664
3665
53cd37ba
S
3666def strip_or_none(v, default=None):
3667 return v.strip() if isinstance(v, compat_str) else default
b72b4431
S
3668
3669
af03000a
S
3670def url_or_none(url):
3671 if not url or not isinstance(url, compat_str):
3672 return None
3673 url = url.strip()
29f7c58a 3674 return url if re.match(r'^(?:(?:https?|rt(?:m(?:pt?[es]?|fp)|sp[su]?)|mms|ftps?):)?//', url) else None
af03000a
S
3675
3676
e29663c6 3677def strftime_or_none(timestamp, date_format, default=None):
3678 datetime_object = None
3679 try:
3680 if isinstance(timestamp, compat_numeric_types): # unix timestamp
3681 datetime_object = datetime.datetime.utcfromtimestamp(timestamp)
3682 elif isinstance(timestamp, compat_str): # assume YYYYMMDD
3683 datetime_object = datetime.datetime.strptime(timestamp, '%Y%m%d')
3684 return datetime_object.strftime(date_format)
3685 except (ValueError, TypeError, AttributeError):
3686 return default
3687
3688
608d11f5 3689def parse_duration(s):
8f9312c3 3690 if not isinstance(s, compat_basestring):
608d11f5
PH
3691 return None
3692
ca7b3246
S
3693 s = s.strip()
3694
acaff495 3695 days, hours, mins, secs, ms = [None] * 5
15846398 3696 m = re.match(r'(?:(?:(?:(?P<days>[0-9]+):)?(?P<hours>[0-9]+):)?(?P<mins>[0-9]+):)?(?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?Z?$', s)
acaff495 3697 if m:
3698 days, hours, mins, secs, ms = m.groups()
3699 else:
3700 m = re.match(
056653bb
S
3701 r'''(?ix)(?:P?
3702 (?:
3703 [0-9]+\s*y(?:ears?)?\s*
3704 )?
3705 (?:
3706 [0-9]+\s*m(?:onths?)?\s*
3707 )?
3708 (?:
3709 [0-9]+\s*w(?:eeks?)?\s*
3710 )?
8f4b58d7 3711 (?:
acaff495 3712 (?P<days>[0-9]+)\s*d(?:ays?)?\s*
8f4b58d7 3713 )?
056653bb 3714 T)?
acaff495 3715 (?:
3716 (?P<hours>[0-9]+)\s*h(?:ours?)?\s*
3717 )?
3718 (?:
3719 (?P<mins>[0-9]+)\s*m(?:in(?:ute)?s?)?\s*
3720 )?
3721 (?:
3722 (?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?\s*s(?:ec(?:ond)?s?)?\s*
15846398 3723 )?Z?$''', s)
acaff495 3724 if m:
3725 days, hours, mins, secs, ms = m.groups()
3726 else:
15846398 3727 m = re.match(r'(?i)(?:(?P<hours>[0-9.]+)\s*(?:hours?)|(?P<mins>[0-9.]+)\s*(?:mins?\.?|minutes?)\s*)Z?$', s)
acaff495 3728 if m:
3729 hours, mins = m.groups()
3730 else:
3731 return None
3732
3733 duration = 0
3734 if secs:
3735 duration += float(secs)
3736 if mins:
3737 duration += float(mins) * 60
3738 if hours:
3739 duration += float(hours) * 60 * 60
3740 if days:
3741 duration += float(days) * 24 * 60 * 60
3742 if ms:
3743 duration += float(ms)
3744 return duration
91d7d0b3
JMF
3745
3746
e65e4c88 3747def prepend_extension(filename, ext, expected_real_ext=None):
5f6a1245 3748 name, real_ext = os.path.splitext(filename)
e65e4c88
S
3749 return (
3750 '{0}.{1}{2}'.format(name, ext, real_ext)
3751 if not expected_real_ext or real_ext[1:] == expected_real_ext
3752 else '{0}.{1}'.format(filename, ext))
d70ad093
PH
3753
3754
b3ed15b7
S
3755def replace_extension(filename, ext, expected_real_ext=None):
3756 name, real_ext = os.path.splitext(filename)
3757 return '{0}.{1}'.format(
3758 name if not expected_real_ext or real_ext[1:] == expected_real_ext else filename,
3759 ext)
3760
3761
d70ad093
PH
3762def check_executable(exe, args=[]):
3763 """ Checks if the given binary is installed somewhere in PATH, and returns its name.
3764 args can be a list of arguments for a short output (like -version) """
3765 try:
f5b1bca9 3766 process_communicate_or_kill(subprocess.Popen(
3767 [exe] + args, stdout=subprocess.PIPE, stderr=subprocess.PIPE))
d70ad093
PH
3768 except OSError:
3769 return False
3770 return exe
b7ab0590
PH
3771
3772
95807118 3773def get_exe_version(exe, args=['--version'],
cae97f65 3774 version_re=None, unrecognized='present'):
95807118
PH
3775 """ Returns the version of the specified executable,
3776 or False if the executable is not present """
3777 try:
b64d04c1 3778 # STDIN should be redirected too. On UNIX-like systems, ffmpeg triggers
cefecac1 3779 # SIGTTOU if youtube-dlc is run in the background.
067aa17e 3780 # See https://github.com/ytdl-org/youtube-dl/issues/955#issuecomment-209789656
f5b1bca9 3781 out, _ = process_communicate_or_kill(subprocess.Popen(
54116803 3782 [encodeArgument(exe)] + args,
00ca7552 3783 stdin=subprocess.PIPE,
f5b1bca9 3784 stdout=subprocess.PIPE, stderr=subprocess.STDOUT))
95807118
PH
3785 except OSError:
3786 return False
cae97f65
PH
3787 if isinstance(out, bytes): # Python 2.x
3788 out = out.decode('ascii', 'ignore')
3789 return detect_exe_version(out, version_re, unrecognized)
3790
3791
3792def detect_exe_version(output, version_re=None, unrecognized='present'):
3793 assert isinstance(output, compat_str)
3794 if version_re is None:
3795 version_re = r'version\s+([-0-9._a-zA-Z]+)'
3796 m = re.search(version_re, output)
95807118
PH
3797 if m:
3798 return m.group(1)
3799 else:
3800 return unrecognized
3801
3802
b7ab0590 3803class PagedList(object):
dd26ced1
PH
3804 def __len__(self):
3805 # This is only useful for tests
3806 return len(self.getslice())
3807
9c44d242
PH
3808
3809class OnDemandPagedList(PagedList):
6be08ce6 3810 def __init__(self, pagefunc, pagesize, use_cache=True):
9c44d242
PH
3811 self._pagefunc = pagefunc
3812 self._pagesize = pagesize
b95dc034
YCH
3813 self._use_cache = use_cache
3814 if use_cache:
3815 self._cache = {}
9c44d242 3816
b7ab0590
PH
3817 def getslice(self, start=0, end=None):
3818 res = []
3819 for pagenum in itertools.count(start // self._pagesize):
3820 firstid = pagenum * self._pagesize
3821 nextfirstid = pagenum * self._pagesize + self._pagesize
3822 if start >= nextfirstid:
3823 continue
3824
b95dc034
YCH
3825 page_results = None
3826 if self._use_cache:
3827 page_results = self._cache.get(pagenum)
3828 if page_results is None:
3829 page_results = list(self._pagefunc(pagenum))
3830 if self._use_cache:
3831 self._cache[pagenum] = page_results
b7ab0590
PH
3832
3833 startv = (
3834 start % self._pagesize
3835 if firstid <= start < nextfirstid
3836 else 0)
3837
3838 endv = (
3839 ((end - 1) % self._pagesize) + 1
3840 if (end is not None and firstid <= end <= nextfirstid)
3841 else None)
3842
3843 if startv != 0 or endv is not None:
3844 page_results = page_results[startv:endv]
3845 res.extend(page_results)
3846
3847 # A little optimization - if current page is not "full", ie. does
3848 # not contain page_size videos then we can assume that this page
3849 # is the last one - there are no more ids on further pages -
3850 # i.e. no need to query again.
3851 if len(page_results) + startv < self._pagesize:
3852 break
3853
3854 # If we got the whole page, but the next page is not interesting,
3855 # break out early as well
3856 if end == nextfirstid:
3857 break
3858 return res
81c2f20b
PH
3859
3860
9c44d242
PH
3861class InAdvancePagedList(PagedList):
3862 def __init__(self, pagefunc, pagecount, pagesize):
3863 self._pagefunc = pagefunc
3864 self._pagecount = pagecount
3865 self._pagesize = pagesize
3866
3867 def getslice(self, start=0, end=None):
3868 res = []
3869 start_page = start // self._pagesize
3870 end_page = (
3871 self._pagecount if end is None else (end // self._pagesize + 1))
3872 skip_elems = start - start_page * self._pagesize
3873 only_more = None if end is None else end - start
3874 for pagenum in range(start_page, end_page):
3875 page = list(self._pagefunc(pagenum))
3876 if skip_elems:
3877 page = page[skip_elems:]
3878 skip_elems = None
3879 if only_more is not None:
3880 if len(page) < only_more:
3881 only_more -= len(page)
3882 else:
3883 page = page[:only_more]
3884 res.extend(page)
3885 break
3886 res.extend(page)
3887 return res
3888
3889
81c2f20b 3890def uppercase_escape(s):
676eb3f2 3891 unicode_escape = codecs.getdecoder('unicode_escape')
81c2f20b 3892 return re.sub(
a612753d 3893 r'\\U[0-9a-fA-F]{8}',
676eb3f2
PH
3894 lambda m: unicode_escape(m.group(0))[0],
3895 s)
0fe2ff78
YCH
3896
3897
3898def lowercase_escape(s):
3899 unicode_escape = codecs.getdecoder('unicode_escape')
3900 return re.sub(
3901 r'\\u[0-9a-fA-F]{4}',
3902 lambda m: unicode_escape(m.group(0))[0],
3903 s)
b53466e1 3904
d05cfe06
S
3905
3906def escape_rfc3986(s):
3907 """Escape non-ASCII characters as suggested by RFC 3986"""
8f9312c3 3908 if sys.version_info < (3, 0) and isinstance(s, compat_str):
d05cfe06 3909 s = s.encode('utf-8')
ecc0c5ee 3910 return compat_urllib_parse.quote(s, b"%/;:@&=+$,!~*'()?#[]")
d05cfe06
S
3911
3912
3913def escape_url(url):
3914 """Escape URL as suggested by RFC 3986"""
3915 url_parsed = compat_urllib_parse_urlparse(url)
3916 return url_parsed._replace(
efbed08d 3917 netloc=url_parsed.netloc.encode('idna').decode('ascii'),
d05cfe06
S
3918 path=escape_rfc3986(url_parsed.path),
3919 params=escape_rfc3986(url_parsed.params),
3920 query=escape_rfc3986(url_parsed.query),
3921 fragment=escape_rfc3986(url_parsed.fragment)
3922 ).geturl()
3923
62e609ab
PH
3924
3925def read_batch_urls(batch_fd):
3926 def fixup(url):
3927 if not isinstance(url, compat_str):
3928 url = url.decode('utf-8', 'replace')
8c04f0be 3929 BOM_UTF8 = ('\xef\xbb\xbf', '\ufeff')
3930 for bom in BOM_UTF8:
3931 if url.startswith(bom):
3932 url = url[len(bom):]
3933 url = url.lstrip()
3934 if not url or url.startswith(('#', ';', ']')):
62e609ab 3935 return False
8c04f0be 3936 # "#" cannot be stripped out since it is part of the URI
3937 # However, it can be safely stipped out if follwing a whitespace
3938 return re.split(r'\s#', url, 1)[0].rstrip()
62e609ab
PH
3939
3940 with contextlib.closing(batch_fd) as fd:
3941 return [url for url in map(fixup, fd) if url]
b74fa8cd
JMF
3942
3943
3944def urlencode_postdata(*args, **kargs):
15707c7e 3945 return compat_urllib_parse_urlencode(*args, **kargs).encode('ascii')
bcf89ce6
PH
3946
3947
38f9ef31 3948def update_url_query(url, query):
cacd9966
YCH
3949 if not query:
3950 return url
38f9ef31 3951 parsed_url = compat_urlparse.urlparse(url)
3952 qs = compat_parse_qs(parsed_url.query)
3953 qs.update(query)
3954 return compat_urlparse.urlunparse(parsed_url._replace(
15707c7e 3955 query=compat_urllib_parse_urlencode(qs, True)))
16392824 3956
8e60dc75 3957
ed0291d1
S
3958def update_Request(req, url=None, data=None, headers={}, query={}):
3959 req_headers = req.headers.copy()
3960 req_headers.update(headers)
3961 req_data = data or req.data
3962 req_url = update_url_query(url or req.get_full_url(), query)
95cf60e8
S
3963 req_get_method = req.get_method()
3964 if req_get_method == 'HEAD':
3965 req_type = HEADRequest
3966 elif req_get_method == 'PUT':
3967 req_type = PUTRequest
3968 else:
3969 req_type = compat_urllib_request.Request
ed0291d1
S
3970 new_req = req_type(
3971 req_url, data=req_data, headers=req_headers,
3972 origin_req_host=req.origin_req_host, unverifiable=req.unverifiable)
3973 if hasattr(req, 'timeout'):
3974 new_req.timeout = req.timeout
3975 return new_req
3976
3977
10c87c15 3978def _multipart_encode_impl(data, boundary):
0c265486
YCH
3979 content_type = 'multipart/form-data; boundary=%s' % boundary
3980
3981 out = b''
3982 for k, v in data.items():
3983 out += b'--' + boundary.encode('ascii') + b'\r\n'
3984 if isinstance(k, compat_str):
3985 k = k.encode('utf-8')
3986 if isinstance(v, compat_str):
3987 v = v.encode('utf-8')
3988 # RFC 2047 requires non-ASCII field names to be encoded, while RFC 7578
3989 # suggests sending UTF-8 directly. Firefox sends UTF-8, too
b2ad479d 3990 content = b'Content-Disposition: form-data; name="' + k + b'"\r\n\r\n' + v + b'\r\n'
0c265486
YCH
3991 if boundary.encode('ascii') in content:
3992 raise ValueError('Boundary overlaps with data')
3993 out += content
3994
3995 out += b'--' + boundary.encode('ascii') + b'--\r\n'
3996
3997 return out, content_type
3998
3999
4000def multipart_encode(data, boundary=None):
4001 '''
4002 Encode a dict to RFC 7578-compliant form-data
4003
4004 data:
4005 A dict where keys and values can be either Unicode or bytes-like
4006 objects.
4007 boundary:
4008 If specified a Unicode object, it's used as the boundary. Otherwise
4009 a random boundary is generated.
4010
4011 Reference: https://tools.ietf.org/html/rfc7578
4012 '''
4013 has_specified_boundary = boundary is not None
4014
4015 while True:
4016 if boundary is None:
4017 boundary = '---------------' + str(random.randrange(0x0fffffff, 0xffffffff))
4018
4019 try:
10c87c15 4020 out, content_type = _multipart_encode_impl(data, boundary)
0c265486
YCH
4021 break
4022 except ValueError:
4023 if has_specified_boundary:
4024 raise
4025 boundary = None
4026
4027 return out, content_type
4028
4029
86296ad2 4030def dict_get(d, key_or_keys, default=None, skip_false_values=True):
cbecc9b9
S
4031 if isinstance(key_or_keys, (list, tuple)):
4032 for key in key_or_keys:
86296ad2
S
4033 if key not in d or d[key] is None or skip_false_values and not d[key]:
4034 continue
4035 return d[key]
cbecc9b9
S
4036 return default
4037 return d.get(key_or_keys, default)
4038
4039
329ca3be 4040def try_get(src, getter, expected_type=None):
a32a9a7e
S
4041 if not isinstance(getter, (list, tuple)):
4042 getter = [getter]
4043 for get in getter:
4044 try:
4045 v = get(src)
4046 except (AttributeError, KeyError, TypeError, IndexError):
4047 pass
4048 else:
4049 if expected_type is None or isinstance(v, expected_type):
4050 return v
329ca3be
S
4051
4052
6cc62232
S
4053def merge_dicts(*dicts):
4054 merged = {}
4055 for a_dict in dicts:
4056 for k, v in a_dict.items():
4057 if v is None:
4058 continue
3089bc74
S
4059 if (k not in merged
4060 or (isinstance(v, compat_str) and v
4061 and isinstance(merged[k], compat_str)
4062 and not merged[k])):
6cc62232
S
4063 merged[k] = v
4064 return merged
4065
4066
8e60dc75
S
4067def encode_compat_str(string, encoding=preferredencoding(), errors='strict'):
4068 return string if isinstance(string, compat_str) else compat_str(string, encoding, errors)
4069
16392824 4070
a1a530b0
PH
4071US_RATINGS = {
4072 'G': 0,
4073 'PG': 10,
4074 'PG-13': 13,
4075 'R': 16,
4076 'NC': 18,
4077}
fac55558
PH
4078
4079
a8795327 4080TV_PARENTAL_GUIDELINES = {
5a16c9d9
RA
4081 'TV-Y': 0,
4082 'TV-Y7': 7,
4083 'TV-G': 0,
4084 'TV-PG': 0,
4085 'TV-14': 14,
4086 'TV-MA': 17,
a8795327
S
4087}
4088
4089
146c80e2 4090def parse_age_limit(s):
a8795327
S
4091 if type(s) == int:
4092 return s if 0 <= s <= 21 else None
4093 if not isinstance(s, compat_basestring):
d838b1bd 4094 return None
146c80e2 4095 m = re.match(r'^(?P<age>\d{1,2})\+?$', s)
a8795327
S
4096 if m:
4097 return int(m.group('age'))
4098 if s in US_RATINGS:
4099 return US_RATINGS[s]
5a16c9d9 4100 m = re.match(r'^TV[_-]?(%s)$' % '|'.join(k[3:] for k in TV_PARENTAL_GUIDELINES), s)
b8361187 4101 if m:
5a16c9d9 4102 return TV_PARENTAL_GUIDELINES['TV-' + m.group(1)]
b8361187 4103 return None
146c80e2
S
4104
4105
fac55558 4106def strip_jsonp(code):
609a61e3 4107 return re.sub(
5552c9eb 4108 r'''(?sx)^
e9c671d5 4109 (?:window\.)?(?P<func_name>[a-zA-Z0-9_.$]*)
5552c9eb
YCH
4110 (?:\s*&&\s*(?P=func_name))?
4111 \s*\(\s*(?P<callback_data>.*)\);?
4112 \s*?(?://[^\n]*)*$''',
4113 r'\g<callback_data>', code)
478c2c61
PH
4114
4115
5c610515 4116def js_to_json(code, vars={}):
4117 # vars is a dict of var, val pairs to substitute
4195096e
S
4118 COMMENT_RE = r'/\*(?:(?!\*/).)*?\*/|//[^\n]*'
4119 SKIP_RE = r'\s*(?:{comment})?\s*'.format(comment=COMMENT_RE)
4120 INTEGER_TABLE = (
4121 (r'(?s)^(0[xX][0-9a-fA-F]+){skip}:?$'.format(skip=SKIP_RE), 16),
4122 (r'(?s)^(0+[0-7]+){skip}:?$'.format(skip=SKIP_RE), 8),
4123 )
4124
e05f6939 4125 def fix_kv(m):
e7b6d122
PH
4126 v = m.group(0)
4127 if v in ('true', 'false', 'null'):
4128 return v
8bdd16b4 4129 elif v.startswith('/*') or v.startswith('//') or v.startswith('!') or v == ',':
bd1e4844 4130 return ""
4131
4132 if v[0] in ("'", '"'):
4133 v = re.sub(r'(?s)\\.|"', lambda m: {
e7b6d122 4134 '"': '\\"',
bd1e4844 4135 "\\'": "'",
4136 '\\\n': '',
4137 '\\x': '\\u00',
4138 }.get(m.group(0), m.group(0)), v[1:-1])
8bdd16b4 4139 else:
4140 for regex, base in INTEGER_TABLE:
4141 im = re.match(regex, v)
4142 if im:
4143 i = int(im.group(1), base)
4144 return '"%d":' % i if v.endswith(':') else '%d' % i
89ac4a19 4145
5c610515 4146 if v in vars:
4147 return vars[v]
4148
e7b6d122 4149 return '"%s"' % v
e05f6939 4150
bd1e4844 4151 return re.sub(r'''(?sx)
4152 "(?:[^"\\]*(?:\\\\|\\['"nurtbfx/\n]))*[^"\\]*"|
4153 '(?:[^'\\]*(?:\\\\|\\['"nurtbfx/\n]))*[^'\\]*'|
4195096e 4154 {comment}|,(?={skip}[\]}}])|
c384d537 4155 (?:(?<![0-9])[eE]|[a-df-zA-DF-Z_])[.a-zA-Z_0-9]*|
4195096e 4156 \b(?:0[xX][0-9a-fA-F]+|0+[0-7]+)(?:{skip}:)?|
8bdd16b4 4157 [0-9]+(?={skip}:)|
4158 !+
4195096e 4159 '''.format(comment=COMMENT_RE, skip=SKIP_RE), fix_kv, code)
e05f6939
PH
4160
4161
478c2c61
PH
4162def qualities(quality_ids):
4163 """ Get a numeric quality value out of a list of possible values """
4164 def q(qid):
4165 try:
4166 return quality_ids.index(qid)
4167 except ValueError:
4168 return -1
4169 return q
4170
acd69589 4171
91ebc640 4172DEFAULT_OUTTMPL = '%(title)s [%(id)s].%(ext)s'
0a871f68 4173
a020a0dc
PH
4174
4175def limit_length(s, length):
4176 """ Add ellipses to overly long strings """
4177 if s is None:
4178 return None
4179 ELLIPSES = '...'
4180 if len(s) > length:
4181 return s[:length - len(ELLIPSES)] + ELLIPSES
4182 return s
48844745
PH
4183
4184
4185def version_tuple(v):
5f9b8394 4186 return tuple(int(e) for e in re.split(r'[-.]', v))
48844745
PH
4187
4188
4189def is_outdated_version(version, limit, assume_new=True):
4190 if not version:
4191 return not assume_new
4192 try:
4193 return version_tuple(version) < version_tuple(limit)
4194 except ValueError:
4195 return not assume_new
732ea2f0
PH
4196
4197
4198def ytdl_is_updateable():
cefecac1 4199 """ Returns if youtube-dlc can be updated with -U """
735d865e 4200 return False
4201
732ea2f0
PH
4202 from zipimport import zipimporter
4203
4204 return isinstance(globals().get('__loader__'), zipimporter) or hasattr(sys, 'frozen')
7d4111ed
PH
4205
4206
4207def args_to_str(args):
4208 # Get a short string representation for a subprocess command
702ccf2d 4209 return ' '.join(compat_shlex_quote(a) for a in args)
2ccd1b10
PH
4210
4211
9b9c5355 4212def error_to_compat_str(err):
fdae2358
S
4213 err_str = str(err)
4214 # On python 2 error byte string must be decoded with proper
4215 # encoding rather than ascii
4216 if sys.version_info[0] < 3:
4217 err_str = err_str.decode(preferredencoding())
4218 return err_str
4219
4220
c460bdd5 4221def mimetype2ext(mt):
eb9ee194
S
4222 if mt is None:
4223 return None
4224
765ac263
JMF
4225 ext = {
4226 'audio/mp4': 'm4a',
6c33d24b
YCH
4227 # Per RFC 3003, audio/mpeg can be .mp1, .mp2 or .mp3. Here use .mp3 as
4228 # it's the most popular one
4229 'audio/mpeg': 'mp3',
ba39289d 4230 'audio/x-wav': 'wav',
765ac263
JMF
4231 }.get(mt)
4232 if ext is not None:
4233 return ext
4234
c460bdd5 4235 _, _, res = mt.rpartition('/')
6562d34a 4236 res = res.split(';')[0].strip().lower()
c460bdd5
PH
4237
4238 return {
f6861ec9 4239 '3gpp': '3gp',
cafcf657 4240 'smptett+xml': 'tt',
cafcf657 4241 'ttaf+xml': 'dfxp',
a0d8d704 4242 'ttml+xml': 'ttml',
f6861ec9 4243 'x-flv': 'flv',
a0d8d704 4244 'x-mp4-fragmented': 'mp4',
d4f05d47 4245 'x-ms-sami': 'sami',
a0d8d704 4246 'x-ms-wmv': 'wmv',
b4173f15
RA
4247 'mpegurl': 'm3u8',
4248 'x-mpegurl': 'm3u8',
4249 'vnd.apple.mpegurl': 'm3u8',
4250 'dash+xml': 'mpd',
b4173f15 4251 'f4m+xml': 'f4m',
f164b971 4252 'hds+xml': 'f4m',
e910fe2f 4253 'vnd.ms-sstr+xml': 'ism',
c2b2c7e1 4254 'quicktime': 'mov',
98ce1a3f 4255 'mp2t': 'ts',
39e7107d 4256 'x-wav': 'wav',
c460bdd5
PH
4257 }.get(res, res)
4258
4259
4f3c5e06 4260def parse_codecs(codecs_str):
4261 # http://tools.ietf.org/html/rfc6381
4262 if not codecs_str:
4263 return {}
a0566bbf 4264 split_codecs = list(filter(None, map(
4f3c5e06 4265 lambda str: str.strip(), codecs_str.strip().strip(',').split(','))))
4266 vcodec, acodec = None, None
a0566bbf 4267 for full_codec in split_codecs:
4f3c5e06 4268 codec = full_codec.split('.')[0]
28cc2241 4269 if codec in ('avc1', 'avc2', 'avc3', 'avc4', 'vp9', 'vp8', 'hev1', 'hev2', 'h263', 'h264', 'mp4v', 'hvc1', 'av01', 'theora'):
4f3c5e06 4270 if not vcodec:
4271 vcodec = full_codec
60f5c9fb 4272 elif codec in ('mp4a', 'opus', 'vorbis', 'mp3', 'aac', 'ac-3', 'ec-3', 'eac3', 'dtsc', 'dtse', 'dtsh', 'dtsl'):
4f3c5e06 4273 if not acodec:
4274 acodec = full_codec
4275 else:
60f5c9fb 4276 write_string('WARNING: Unknown codec %s\n' % full_codec, sys.stderr)
4f3c5e06 4277 if not vcodec and not acodec:
a0566bbf 4278 if len(split_codecs) == 2:
4f3c5e06 4279 return {
a0566bbf 4280 'vcodec': split_codecs[0],
4281 'acodec': split_codecs[1],
4f3c5e06 4282 }
4283 else:
4284 return {
4285 'vcodec': vcodec or 'none',
4286 'acodec': acodec or 'none',
4287 }
4288 return {}
4289
4290
2ccd1b10 4291def urlhandle_detect_ext(url_handle):
79298173 4292 getheader = url_handle.headers.get
2ccd1b10 4293
b55ee18f
PH
4294 cd = getheader('Content-Disposition')
4295 if cd:
4296 m = re.match(r'attachment;\s*filename="(?P<filename>[^"]+)"', cd)
4297 if m:
4298 e = determine_ext(m.group('filename'), default_ext=None)
4299 if e:
4300 return e
4301
c460bdd5 4302 return mimetype2ext(getheader('Content-Type'))
05900629
PH
4303
4304
1e399778
YCH
4305def encode_data_uri(data, mime_type):
4306 return 'data:%s;base64,%s' % (mime_type, base64.b64encode(data).decode('ascii'))
4307
4308
05900629 4309def age_restricted(content_limit, age_limit):
6ec6cb4e 4310 """ Returns True iff the content should be blocked """
05900629
PH
4311
4312 if age_limit is None: # No limit set
4313 return False
4314 if content_limit is None:
4315 return False # Content available for everyone
4316 return age_limit < content_limit
61ca9a80
PH
4317
4318
4319def is_html(first_bytes):
4320 """ Detect whether a file contains HTML by examining its first bytes. """
4321
4322 BOMS = [
4323 (b'\xef\xbb\xbf', 'utf-8'),
4324 (b'\x00\x00\xfe\xff', 'utf-32-be'),
4325 (b'\xff\xfe\x00\x00', 'utf-32-le'),
4326 (b'\xff\xfe', 'utf-16-le'),
4327 (b'\xfe\xff', 'utf-16-be'),
4328 ]
4329 for bom, enc in BOMS:
4330 if first_bytes.startswith(bom):
4331 s = first_bytes[len(bom):].decode(enc, 'replace')
4332 break
4333 else:
4334 s = first_bytes.decode('utf-8', 'replace')
4335
4336 return re.match(r'^\s*<', s)
a055469f
PH
4337
4338
4339def determine_protocol(info_dict):
4340 protocol = info_dict.get('protocol')
4341 if protocol is not None:
4342 return protocol
4343
4344 url = info_dict['url']
4345 if url.startswith('rtmp'):
4346 return 'rtmp'
4347 elif url.startswith('mms'):
4348 return 'mms'
4349 elif url.startswith('rtsp'):
4350 return 'rtsp'
4351
4352 ext = determine_ext(url)
4353 if ext == 'm3u8':
4354 return 'm3u8'
4355 elif ext == 'f4m':
4356 return 'f4m'
4357
4358 return compat_urllib_parse_urlparse(url).scheme
cfb56d1a
PH
4359
4360
76d321f6 4361def render_table(header_row, data, delim=False, extraGap=0, hideEmpty=False):
cfb56d1a 4362 """ Render a list of rows, each as a list of values """
76d321f6 4363
4364 def get_max_lens(table):
4365 return [max(len(compat_str(v)) for v in col) for col in zip(*table)]
4366
4367 def filter_using_list(row, filterArray):
4368 return [col for (take, col) in zip(filterArray, row) if take]
4369
4370 if hideEmpty:
4371 max_lens = get_max_lens(data)
4372 header_row = filter_using_list(header_row, max_lens)
4373 data = [filter_using_list(row, max_lens) for row in data]
4374
cfb56d1a 4375 table = [header_row] + data
76d321f6 4376 max_lens = get_max_lens(table)
4377 if delim:
4378 table = [header_row] + [['-' * ml for ml in max_lens]] + data
4379 format_str = ' '.join('%-' + compat_str(ml + extraGap) + 's' for ml in max_lens[:-1]) + ' %s'
cfb56d1a 4380 return '\n'.join(format_str % tuple(row) for row in table)
347de493
PH
4381
4382
4383def _match_one(filter_part, dct):
4384 COMPARISON_OPERATORS = {
4385 '<': operator.lt,
4386 '<=': operator.le,
4387 '>': operator.gt,
4388 '>=': operator.ge,
4389 '=': operator.eq,
4390 '!=': operator.ne,
4391 }
4392 operator_rex = re.compile(r'''(?x)\s*
4393 (?P<key>[a-z_]+)
4394 \s*(?P<op>%s)(?P<none_inclusive>\s*\?)?\s*
4395 (?:
4396 (?P<intval>[0-9.]+(?:[kKmMgGtTpPeEzZyY]i?[Bb]?)?)|
db13c16e 4397 (?P<quote>["\'])(?P<quotedstrval>(?:\\.|(?!(?P=quote)|\\).)+?)(?P=quote)|
347de493
PH
4398 (?P<strval>(?![0-9.])[a-z0-9A-Z]*)
4399 )
4400 \s*$
4401 ''' % '|'.join(map(re.escape, COMPARISON_OPERATORS.keys())))
4402 m = operator_rex.search(filter_part)
4403 if m:
4404 op = COMPARISON_OPERATORS[m.group('op')]
e5a088dc 4405 actual_value = dct.get(m.group('key'))
3089bc74
S
4406 if (m.group('quotedstrval') is not None
4407 or m.group('strval') is not None
e5a088dc
S
4408 # If the original field is a string and matching comparisonvalue is
4409 # a number we should respect the origin of the original field
4410 # and process comparison value as a string (see
067aa17e 4411 # https://github.com/ytdl-org/youtube-dl/issues/11082).
3089bc74
S
4412 or actual_value is not None and m.group('intval') is not None
4413 and isinstance(actual_value, compat_str)):
347de493
PH
4414 if m.group('op') not in ('=', '!='):
4415 raise ValueError(
4416 'Operator %s does not support string values!' % m.group('op'))
db13c16e
S
4417 comparison_value = m.group('quotedstrval') or m.group('strval') or m.group('intval')
4418 quote = m.group('quote')
4419 if quote is not None:
4420 comparison_value = comparison_value.replace(r'\%s' % quote, quote)
347de493
PH
4421 else:
4422 try:
4423 comparison_value = int(m.group('intval'))
4424 except ValueError:
4425 comparison_value = parse_filesize(m.group('intval'))
4426 if comparison_value is None:
4427 comparison_value = parse_filesize(m.group('intval') + 'B')
4428 if comparison_value is None:
4429 raise ValueError(
4430 'Invalid integer value %r in filter part %r' % (
4431 m.group('intval'), filter_part))
347de493
PH
4432 if actual_value is None:
4433 return m.group('none_inclusive')
4434 return op(actual_value, comparison_value)
4435
4436 UNARY_OPERATORS = {
1cc47c66
S
4437 '': lambda v: (v is True) if isinstance(v, bool) else (v is not None),
4438 '!': lambda v: (v is False) if isinstance(v, bool) else (v is None),
347de493
PH
4439 }
4440 operator_rex = re.compile(r'''(?x)\s*
4441 (?P<op>%s)\s*(?P<key>[a-z_]+)
4442 \s*$
4443 ''' % '|'.join(map(re.escape, UNARY_OPERATORS.keys())))
4444 m = operator_rex.search(filter_part)
4445 if m:
4446 op = UNARY_OPERATORS[m.group('op')]
4447 actual_value = dct.get(m.group('key'))
4448 return op(actual_value)
4449
4450 raise ValueError('Invalid filter part %r' % filter_part)
4451
4452
4453def match_str(filter_str, dct):
4454 """ Filter a dictionary with a simple string syntax. Returns True (=passes filter) or false """
4455
4456 return all(
4457 _match_one(filter_part, dct) for filter_part in filter_str.split('&'))
4458
4459
4460def match_filter_func(filter_str):
4461 def _match_func(info_dict):
4462 if match_str(filter_str, info_dict):
4463 return None
4464 else:
4465 video_title = info_dict.get('title', info_dict.get('id', 'video'))
4466 return '%s does not pass filter %s, skipping ..' % (video_title, filter_str)
4467 return _match_func
91410c9b
PH
4468
4469
bf6427d2
YCH
4470def parse_dfxp_time_expr(time_expr):
4471 if not time_expr:
d631d5f9 4472 return
bf6427d2
YCH
4473
4474 mobj = re.match(r'^(?P<time_offset>\d+(?:\.\d+)?)s?$', time_expr)
4475 if mobj:
4476 return float(mobj.group('time_offset'))
4477
db2fe38b 4478 mobj = re.match(r'^(\d+):(\d\d):(\d\d(?:(?:\.|:)\d+)?)$', time_expr)
bf6427d2 4479 if mobj:
db2fe38b 4480 return 3600 * int(mobj.group(1)) + 60 * int(mobj.group(2)) + float(mobj.group(3).replace(':', '.'))
bf6427d2
YCH
4481
4482
c1c924ab
YCH
4483def srt_subtitles_timecode(seconds):
4484 return '%02d:%02d:%02d,%03d' % (seconds / 3600, (seconds % 3600) / 60, seconds % 60, (seconds % 1) * 1000)
bf6427d2
YCH
4485
4486
4487def dfxp2srt(dfxp_data):
3869028f
YCH
4488 '''
4489 @param dfxp_data A bytes-like object containing DFXP data
4490 @returns A unicode object containing converted SRT data
4491 '''
5b995f71 4492 LEGACY_NAMESPACES = (
3869028f
YCH
4493 (b'http://www.w3.org/ns/ttml', [
4494 b'http://www.w3.org/2004/11/ttaf1',
4495 b'http://www.w3.org/2006/04/ttaf1',
4496 b'http://www.w3.org/2006/10/ttaf1',
5b995f71 4497 ]),
3869028f
YCH
4498 (b'http://www.w3.org/ns/ttml#styling', [
4499 b'http://www.w3.org/ns/ttml#style',
5b995f71
RA
4500 ]),
4501 )
4502
4503 SUPPORTED_STYLING = [
4504 'color',
4505 'fontFamily',
4506 'fontSize',
4507 'fontStyle',
4508 'fontWeight',
4509 'textDecoration'
4510 ]
4511
4e335771 4512 _x = functools.partial(xpath_with_ns, ns_map={
261f4730 4513 'xml': 'http://www.w3.org/XML/1998/namespace',
4e335771 4514 'ttml': 'http://www.w3.org/ns/ttml',
5b995f71 4515 'tts': 'http://www.w3.org/ns/ttml#styling',
4e335771 4516 })
bf6427d2 4517
5b995f71
RA
4518 styles = {}
4519 default_style = {}
4520
87de7069 4521 class TTMLPElementParser(object):
5b995f71
RA
4522 _out = ''
4523 _unclosed_elements = []
4524 _applied_styles = []
bf6427d2 4525
2b14cb56 4526 def start(self, tag, attrib):
5b995f71
RA
4527 if tag in (_x('ttml:br'), 'br'):
4528 self._out += '\n'
4529 else:
4530 unclosed_elements = []
4531 style = {}
4532 element_style_id = attrib.get('style')
4533 if default_style:
4534 style.update(default_style)
4535 if element_style_id:
4536 style.update(styles.get(element_style_id, {}))
4537 for prop in SUPPORTED_STYLING:
4538 prop_val = attrib.get(_x('tts:' + prop))
4539 if prop_val:
4540 style[prop] = prop_val
4541 if style:
4542 font = ''
4543 for k, v in sorted(style.items()):
4544 if self._applied_styles and self._applied_styles[-1].get(k) == v:
4545 continue
4546 if k == 'color':
4547 font += ' color="%s"' % v
4548 elif k == 'fontSize':
4549 font += ' size="%s"' % v
4550 elif k == 'fontFamily':
4551 font += ' face="%s"' % v
4552 elif k == 'fontWeight' and v == 'bold':
4553 self._out += '<b>'
4554 unclosed_elements.append('b')
4555 elif k == 'fontStyle' and v == 'italic':
4556 self._out += '<i>'
4557 unclosed_elements.append('i')
4558 elif k == 'textDecoration' and v == 'underline':
4559 self._out += '<u>'
4560 unclosed_elements.append('u')
4561 if font:
4562 self._out += '<font' + font + '>'
4563 unclosed_elements.append('font')
4564 applied_style = {}
4565 if self._applied_styles:
4566 applied_style.update(self._applied_styles[-1])
4567 applied_style.update(style)
4568 self._applied_styles.append(applied_style)
4569 self._unclosed_elements.append(unclosed_elements)
bf6427d2 4570
2b14cb56 4571 def end(self, tag):
5b995f71
RA
4572 if tag not in (_x('ttml:br'), 'br'):
4573 unclosed_elements = self._unclosed_elements.pop()
4574 for element in reversed(unclosed_elements):
4575 self._out += '</%s>' % element
4576 if unclosed_elements and self._applied_styles:
4577 self._applied_styles.pop()
bf6427d2 4578
2b14cb56 4579 def data(self, data):
5b995f71 4580 self._out += data
2b14cb56 4581
4582 def close(self):
5b995f71 4583 return self._out.strip()
2b14cb56 4584
4585 def parse_node(node):
4586 target = TTMLPElementParser()
4587 parser = xml.etree.ElementTree.XMLParser(target=target)
4588 parser.feed(xml.etree.ElementTree.tostring(node))
4589 return parser.close()
bf6427d2 4590
5b995f71
RA
4591 for k, v in LEGACY_NAMESPACES:
4592 for ns in v:
4593 dfxp_data = dfxp_data.replace(ns, k)
4594
3869028f 4595 dfxp = compat_etree_fromstring(dfxp_data)
bf6427d2 4596 out = []
5b995f71 4597 paras = dfxp.findall(_x('.//ttml:p')) or dfxp.findall('.//p')
1b0427e6
YCH
4598
4599 if not paras:
4600 raise ValueError('Invalid dfxp/TTML subtitle')
bf6427d2 4601
5b995f71
RA
4602 repeat = False
4603 while True:
4604 for style in dfxp.findall(_x('.//ttml:style')):
261f4730
RA
4605 style_id = style.get('id') or style.get(_x('xml:id'))
4606 if not style_id:
4607 continue
5b995f71
RA
4608 parent_style_id = style.get('style')
4609 if parent_style_id:
4610 if parent_style_id not in styles:
4611 repeat = True
4612 continue
4613 styles[style_id] = styles[parent_style_id].copy()
4614 for prop in SUPPORTED_STYLING:
4615 prop_val = style.get(_x('tts:' + prop))
4616 if prop_val:
4617 styles.setdefault(style_id, {})[prop] = prop_val
4618 if repeat:
4619 repeat = False
4620 else:
4621 break
4622
4623 for p in ('body', 'div'):
4624 ele = xpath_element(dfxp, [_x('.//ttml:' + p), './/' + p])
4625 if ele is None:
4626 continue
4627 style = styles.get(ele.get('style'))
4628 if not style:
4629 continue
4630 default_style.update(style)
4631
bf6427d2 4632 for para, index in zip(paras, itertools.count(1)):
d631d5f9 4633 begin_time = parse_dfxp_time_expr(para.attrib.get('begin'))
7dff0363 4634 end_time = parse_dfxp_time_expr(para.attrib.get('end'))
d631d5f9
YCH
4635 dur = parse_dfxp_time_expr(para.attrib.get('dur'))
4636 if begin_time is None:
4637 continue
7dff0363 4638 if not end_time:
d631d5f9
YCH
4639 if not dur:
4640 continue
4641 end_time = begin_time + dur
bf6427d2
YCH
4642 out.append('%d\n%s --> %s\n%s\n\n' % (
4643 index,
c1c924ab
YCH
4644 srt_subtitles_timecode(begin_time),
4645 srt_subtitles_timecode(end_time),
bf6427d2
YCH
4646 parse_node(para)))
4647
4648 return ''.join(out)
4649
4650
66e289ba
S
4651def cli_option(params, command_option, param):
4652 param = params.get(param)
98e698f1
RA
4653 if param:
4654 param = compat_str(param)
66e289ba
S
4655 return [command_option, param] if param is not None else []
4656
4657
4658def cli_bool_option(params, command_option, param, true_value='true', false_value='false', separator=None):
4659 param = params.get(param)
5b232f46
S
4660 if param is None:
4661 return []
66e289ba
S
4662 assert isinstance(param, bool)
4663 if separator:
4664 return [command_option + separator + (true_value if param else false_value)]
4665 return [command_option, true_value if param else false_value]
4666
4667
4668def cli_valueless_option(params, command_option, param, expected_value=True):
4669 param = params.get(param)
4670 return [command_option] if param == expected_value else []
4671
4672
eab9b2bc 4673def cli_configuration_args(params, arg_name, key, default=[], exe=None): # returns arg, for_compat
4674 argdict = params.get(arg_name, {})
4675 if isinstance(argdict, (list, tuple)): # for backward compatibility
4676 return argdict, True
4677
4678 if argdict is None:
4679 return default, False
4680 assert isinstance(argdict, dict)
4681
4682 assert isinstance(key, compat_str)
4683 key = key.lower()
4684
4685 args = exe_args = None
4686 if exe is not None:
4687 assert isinstance(exe, compat_str)
4688 exe = exe.lower()
4689 args = argdict.get('%s+%s' % (key, exe))
4690 if args is None:
4691 exe_args = argdict.get(exe)
4692
4693 if args is None:
4694 args = argdict.get(key) if key != exe else None
4695 if args is None and exe_args is None:
4696 args = argdict.get('default', default)
4697
4698 args, exe_args = args or [], exe_args or []
4699 assert isinstance(args, (list, tuple))
4700 assert isinstance(exe_args, (list, tuple))
4701 return args + exe_args, False
66e289ba
S
4702
4703
39672624
YCH
4704class ISO639Utils(object):
4705 # See http://www.loc.gov/standards/iso639-2/ISO-639-2_utf-8.txt
4706 _lang_map = {
4707 'aa': 'aar',
4708 'ab': 'abk',
4709 'ae': 'ave',
4710 'af': 'afr',
4711 'ak': 'aka',
4712 'am': 'amh',
4713 'an': 'arg',
4714 'ar': 'ara',
4715 'as': 'asm',
4716 'av': 'ava',
4717 'ay': 'aym',
4718 'az': 'aze',
4719 'ba': 'bak',
4720 'be': 'bel',
4721 'bg': 'bul',
4722 'bh': 'bih',
4723 'bi': 'bis',
4724 'bm': 'bam',
4725 'bn': 'ben',
4726 'bo': 'bod',
4727 'br': 'bre',
4728 'bs': 'bos',
4729 'ca': 'cat',
4730 'ce': 'che',
4731 'ch': 'cha',
4732 'co': 'cos',
4733 'cr': 'cre',
4734 'cs': 'ces',
4735 'cu': 'chu',
4736 'cv': 'chv',
4737 'cy': 'cym',
4738 'da': 'dan',
4739 'de': 'deu',
4740 'dv': 'div',
4741 'dz': 'dzo',
4742 'ee': 'ewe',
4743 'el': 'ell',
4744 'en': 'eng',
4745 'eo': 'epo',
4746 'es': 'spa',
4747 'et': 'est',
4748 'eu': 'eus',
4749 'fa': 'fas',
4750 'ff': 'ful',
4751 'fi': 'fin',
4752 'fj': 'fij',
4753 'fo': 'fao',
4754 'fr': 'fra',
4755 'fy': 'fry',
4756 'ga': 'gle',
4757 'gd': 'gla',
4758 'gl': 'glg',
4759 'gn': 'grn',
4760 'gu': 'guj',
4761 'gv': 'glv',
4762 'ha': 'hau',
4763 'he': 'heb',
b7acc835 4764 'iw': 'heb', # Replaced by he in 1989 revision
39672624
YCH
4765 'hi': 'hin',
4766 'ho': 'hmo',
4767 'hr': 'hrv',
4768 'ht': 'hat',
4769 'hu': 'hun',
4770 'hy': 'hye',
4771 'hz': 'her',
4772 'ia': 'ina',
4773 'id': 'ind',
b7acc835 4774 'in': 'ind', # Replaced by id in 1989 revision
39672624
YCH
4775 'ie': 'ile',
4776 'ig': 'ibo',
4777 'ii': 'iii',
4778 'ik': 'ipk',
4779 'io': 'ido',
4780 'is': 'isl',
4781 'it': 'ita',
4782 'iu': 'iku',
4783 'ja': 'jpn',
4784 'jv': 'jav',
4785 'ka': 'kat',
4786 'kg': 'kon',
4787 'ki': 'kik',
4788 'kj': 'kua',
4789 'kk': 'kaz',
4790 'kl': 'kal',
4791 'km': 'khm',
4792 'kn': 'kan',
4793 'ko': 'kor',
4794 'kr': 'kau',
4795 'ks': 'kas',
4796 'ku': 'kur',
4797 'kv': 'kom',
4798 'kw': 'cor',
4799 'ky': 'kir',
4800 'la': 'lat',
4801 'lb': 'ltz',
4802 'lg': 'lug',
4803 'li': 'lim',
4804 'ln': 'lin',
4805 'lo': 'lao',
4806 'lt': 'lit',
4807 'lu': 'lub',
4808 'lv': 'lav',
4809 'mg': 'mlg',
4810 'mh': 'mah',
4811 'mi': 'mri',
4812 'mk': 'mkd',
4813 'ml': 'mal',
4814 'mn': 'mon',
4815 'mr': 'mar',
4816 'ms': 'msa',
4817 'mt': 'mlt',
4818 'my': 'mya',
4819 'na': 'nau',
4820 'nb': 'nob',
4821 'nd': 'nde',
4822 'ne': 'nep',
4823 'ng': 'ndo',
4824 'nl': 'nld',
4825 'nn': 'nno',
4826 'no': 'nor',
4827 'nr': 'nbl',
4828 'nv': 'nav',
4829 'ny': 'nya',
4830 'oc': 'oci',
4831 'oj': 'oji',
4832 'om': 'orm',
4833 'or': 'ori',
4834 'os': 'oss',
4835 'pa': 'pan',
4836 'pi': 'pli',
4837 'pl': 'pol',
4838 'ps': 'pus',
4839 'pt': 'por',
4840 'qu': 'que',
4841 'rm': 'roh',
4842 'rn': 'run',
4843 'ro': 'ron',
4844 'ru': 'rus',
4845 'rw': 'kin',
4846 'sa': 'san',
4847 'sc': 'srd',
4848 'sd': 'snd',
4849 'se': 'sme',
4850 'sg': 'sag',
4851 'si': 'sin',
4852 'sk': 'slk',
4853 'sl': 'slv',
4854 'sm': 'smo',
4855 'sn': 'sna',
4856 'so': 'som',
4857 'sq': 'sqi',
4858 'sr': 'srp',
4859 'ss': 'ssw',
4860 'st': 'sot',
4861 'su': 'sun',
4862 'sv': 'swe',
4863 'sw': 'swa',
4864 'ta': 'tam',
4865 'te': 'tel',
4866 'tg': 'tgk',
4867 'th': 'tha',
4868 'ti': 'tir',
4869 'tk': 'tuk',
4870 'tl': 'tgl',
4871 'tn': 'tsn',
4872 'to': 'ton',
4873 'tr': 'tur',
4874 'ts': 'tso',
4875 'tt': 'tat',
4876 'tw': 'twi',
4877 'ty': 'tah',
4878 'ug': 'uig',
4879 'uk': 'ukr',
4880 'ur': 'urd',
4881 'uz': 'uzb',
4882 've': 'ven',
4883 'vi': 'vie',
4884 'vo': 'vol',
4885 'wa': 'wln',
4886 'wo': 'wol',
4887 'xh': 'xho',
4888 'yi': 'yid',
e9a50fba 4889 'ji': 'yid', # Replaced by yi in 1989 revision
39672624
YCH
4890 'yo': 'yor',
4891 'za': 'zha',
4892 'zh': 'zho',
4893 'zu': 'zul',
4894 }
4895
4896 @classmethod
4897 def short2long(cls, code):
4898 """Convert language code from ISO 639-1 to ISO 639-2/T"""
4899 return cls._lang_map.get(code[:2])
4900
4901 @classmethod
4902 def long2short(cls, code):
4903 """Convert language code from ISO 639-2/T to ISO 639-1"""
4904 for short_name, long_name in cls._lang_map.items():
4905 if long_name == code:
4906 return short_name
4907
4908
4eb10f66
YCH
4909class ISO3166Utils(object):
4910 # From http://data.okfn.org/data/core/country-list
4911 _country_map = {
4912 'AF': 'Afghanistan',
4913 'AX': 'Åland Islands',
4914 'AL': 'Albania',
4915 'DZ': 'Algeria',
4916 'AS': 'American Samoa',
4917 'AD': 'Andorra',
4918 'AO': 'Angola',
4919 'AI': 'Anguilla',
4920 'AQ': 'Antarctica',
4921 'AG': 'Antigua and Barbuda',
4922 'AR': 'Argentina',
4923 'AM': 'Armenia',
4924 'AW': 'Aruba',
4925 'AU': 'Australia',
4926 'AT': 'Austria',
4927 'AZ': 'Azerbaijan',
4928 'BS': 'Bahamas',
4929 'BH': 'Bahrain',
4930 'BD': 'Bangladesh',
4931 'BB': 'Barbados',
4932 'BY': 'Belarus',
4933 'BE': 'Belgium',
4934 'BZ': 'Belize',
4935 'BJ': 'Benin',
4936 'BM': 'Bermuda',
4937 'BT': 'Bhutan',
4938 'BO': 'Bolivia, Plurinational State of',
4939 'BQ': 'Bonaire, Sint Eustatius and Saba',
4940 'BA': 'Bosnia and Herzegovina',
4941 'BW': 'Botswana',
4942 'BV': 'Bouvet Island',
4943 'BR': 'Brazil',
4944 'IO': 'British Indian Ocean Territory',
4945 'BN': 'Brunei Darussalam',
4946 'BG': 'Bulgaria',
4947 'BF': 'Burkina Faso',
4948 'BI': 'Burundi',
4949 'KH': 'Cambodia',
4950 'CM': 'Cameroon',
4951 'CA': 'Canada',
4952 'CV': 'Cape Verde',
4953 'KY': 'Cayman Islands',
4954 'CF': 'Central African Republic',
4955 'TD': 'Chad',
4956 'CL': 'Chile',
4957 'CN': 'China',
4958 'CX': 'Christmas Island',
4959 'CC': 'Cocos (Keeling) Islands',
4960 'CO': 'Colombia',
4961 'KM': 'Comoros',
4962 'CG': 'Congo',
4963 'CD': 'Congo, the Democratic Republic of the',
4964 'CK': 'Cook Islands',
4965 'CR': 'Costa Rica',
4966 'CI': 'Côte d\'Ivoire',
4967 'HR': 'Croatia',
4968 'CU': 'Cuba',
4969 'CW': 'Curaçao',
4970 'CY': 'Cyprus',
4971 'CZ': 'Czech Republic',
4972 'DK': 'Denmark',
4973 'DJ': 'Djibouti',
4974 'DM': 'Dominica',
4975 'DO': 'Dominican Republic',
4976 'EC': 'Ecuador',
4977 'EG': 'Egypt',
4978 'SV': 'El Salvador',
4979 'GQ': 'Equatorial Guinea',
4980 'ER': 'Eritrea',
4981 'EE': 'Estonia',
4982 'ET': 'Ethiopia',
4983 'FK': 'Falkland Islands (Malvinas)',
4984 'FO': 'Faroe Islands',
4985 'FJ': 'Fiji',
4986 'FI': 'Finland',
4987 'FR': 'France',
4988 'GF': 'French Guiana',
4989 'PF': 'French Polynesia',
4990 'TF': 'French Southern Territories',
4991 'GA': 'Gabon',
4992 'GM': 'Gambia',
4993 'GE': 'Georgia',
4994 'DE': 'Germany',
4995 'GH': 'Ghana',
4996 'GI': 'Gibraltar',
4997 'GR': 'Greece',
4998 'GL': 'Greenland',
4999 'GD': 'Grenada',
5000 'GP': 'Guadeloupe',
5001 'GU': 'Guam',
5002 'GT': 'Guatemala',
5003 'GG': 'Guernsey',
5004 'GN': 'Guinea',
5005 'GW': 'Guinea-Bissau',
5006 'GY': 'Guyana',
5007 'HT': 'Haiti',
5008 'HM': 'Heard Island and McDonald Islands',
5009 'VA': 'Holy See (Vatican City State)',
5010 'HN': 'Honduras',
5011 'HK': 'Hong Kong',
5012 'HU': 'Hungary',
5013 'IS': 'Iceland',
5014 'IN': 'India',
5015 'ID': 'Indonesia',
5016 'IR': 'Iran, Islamic Republic of',
5017 'IQ': 'Iraq',
5018 'IE': 'Ireland',
5019 'IM': 'Isle of Man',
5020 'IL': 'Israel',
5021 'IT': 'Italy',
5022 'JM': 'Jamaica',
5023 'JP': 'Japan',
5024 'JE': 'Jersey',
5025 'JO': 'Jordan',
5026 'KZ': 'Kazakhstan',
5027 'KE': 'Kenya',
5028 'KI': 'Kiribati',
5029 'KP': 'Korea, Democratic People\'s Republic of',
5030 'KR': 'Korea, Republic of',
5031 'KW': 'Kuwait',
5032 'KG': 'Kyrgyzstan',
5033 'LA': 'Lao People\'s Democratic Republic',
5034 'LV': 'Latvia',
5035 'LB': 'Lebanon',
5036 'LS': 'Lesotho',
5037 'LR': 'Liberia',
5038 'LY': 'Libya',
5039 'LI': 'Liechtenstein',
5040 'LT': 'Lithuania',
5041 'LU': 'Luxembourg',
5042 'MO': 'Macao',
5043 'MK': 'Macedonia, the Former Yugoslav Republic of',
5044 'MG': 'Madagascar',
5045 'MW': 'Malawi',
5046 'MY': 'Malaysia',
5047 'MV': 'Maldives',
5048 'ML': 'Mali',
5049 'MT': 'Malta',
5050 'MH': 'Marshall Islands',
5051 'MQ': 'Martinique',
5052 'MR': 'Mauritania',
5053 'MU': 'Mauritius',
5054 'YT': 'Mayotte',
5055 'MX': 'Mexico',
5056 'FM': 'Micronesia, Federated States of',
5057 'MD': 'Moldova, Republic of',
5058 'MC': 'Monaco',
5059 'MN': 'Mongolia',
5060 'ME': 'Montenegro',
5061 'MS': 'Montserrat',
5062 'MA': 'Morocco',
5063 'MZ': 'Mozambique',
5064 'MM': 'Myanmar',
5065 'NA': 'Namibia',
5066 'NR': 'Nauru',
5067 'NP': 'Nepal',
5068 'NL': 'Netherlands',
5069 'NC': 'New Caledonia',
5070 'NZ': 'New Zealand',
5071 'NI': 'Nicaragua',
5072 'NE': 'Niger',
5073 'NG': 'Nigeria',
5074 'NU': 'Niue',
5075 'NF': 'Norfolk Island',
5076 'MP': 'Northern Mariana Islands',
5077 'NO': 'Norway',
5078 'OM': 'Oman',
5079 'PK': 'Pakistan',
5080 'PW': 'Palau',
5081 'PS': 'Palestine, State of',
5082 'PA': 'Panama',
5083 'PG': 'Papua New Guinea',
5084 'PY': 'Paraguay',
5085 'PE': 'Peru',
5086 'PH': 'Philippines',
5087 'PN': 'Pitcairn',
5088 'PL': 'Poland',
5089 'PT': 'Portugal',
5090 'PR': 'Puerto Rico',
5091 'QA': 'Qatar',
5092 'RE': 'Réunion',
5093 'RO': 'Romania',
5094 'RU': 'Russian Federation',
5095 'RW': 'Rwanda',
5096 'BL': 'Saint Barthélemy',
5097 'SH': 'Saint Helena, Ascension and Tristan da Cunha',
5098 'KN': 'Saint Kitts and Nevis',
5099 'LC': 'Saint Lucia',
5100 'MF': 'Saint Martin (French part)',
5101 'PM': 'Saint Pierre and Miquelon',
5102 'VC': 'Saint Vincent and the Grenadines',
5103 'WS': 'Samoa',
5104 'SM': 'San Marino',
5105 'ST': 'Sao Tome and Principe',
5106 'SA': 'Saudi Arabia',
5107 'SN': 'Senegal',
5108 'RS': 'Serbia',
5109 'SC': 'Seychelles',
5110 'SL': 'Sierra Leone',
5111 'SG': 'Singapore',
5112 'SX': 'Sint Maarten (Dutch part)',
5113 'SK': 'Slovakia',
5114 'SI': 'Slovenia',
5115 'SB': 'Solomon Islands',
5116 'SO': 'Somalia',
5117 'ZA': 'South Africa',
5118 'GS': 'South Georgia and the South Sandwich Islands',
5119 'SS': 'South Sudan',
5120 'ES': 'Spain',
5121 'LK': 'Sri Lanka',
5122 'SD': 'Sudan',
5123 'SR': 'Suriname',
5124 'SJ': 'Svalbard and Jan Mayen',
5125 'SZ': 'Swaziland',
5126 'SE': 'Sweden',
5127 'CH': 'Switzerland',
5128 'SY': 'Syrian Arab Republic',
5129 'TW': 'Taiwan, Province of China',
5130 'TJ': 'Tajikistan',
5131 'TZ': 'Tanzania, United Republic of',
5132 'TH': 'Thailand',
5133 'TL': 'Timor-Leste',
5134 'TG': 'Togo',
5135 'TK': 'Tokelau',
5136 'TO': 'Tonga',
5137 'TT': 'Trinidad and Tobago',
5138 'TN': 'Tunisia',
5139 'TR': 'Turkey',
5140 'TM': 'Turkmenistan',
5141 'TC': 'Turks and Caicos Islands',
5142 'TV': 'Tuvalu',
5143 'UG': 'Uganda',
5144 'UA': 'Ukraine',
5145 'AE': 'United Arab Emirates',
5146 'GB': 'United Kingdom',
5147 'US': 'United States',
5148 'UM': 'United States Minor Outlying Islands',
5149 'UY': 'Uruguay',
5150 'UZ': 'Uzbekistan',
5151 'VU': 'Vanuatu',
5152 'VE': 'Venezuela, Bolivarian Republic of',
5153 'VN': 'Viet Nam',
5154 'VG': 'Virgin Islands, British',
5155 'VI': 'Virgin Islands, U.S.',
5156 'WF': 'Wallis and Futuna',
5157 'EH': 'Western Sahara',
5158 'YE': 'Yemen',
5159 'ZM': 'Zambia',
5160 'ZW': 'Zimbabwe',
5161 }
5162
5163 @classmethod
5164 def short2full(cls, code):
5165 """Convert an ISO 3166-2 country code to the corresponding full name"""
5166 return cls._country_map.get(code.upper())
5167
5168
773f291d
S
5169class GeoUtils(object):
5170 # Major IPv4 address blocks per country
5171 _country_ip_map = {
53896ca5 5172 'AD': '46.172.224.0/19',
773f291d
S
5173 'AE': '94.200.0.0/13',
5174 'AF': '149.54.0.0/17',
5175 'AG': '209.59.64.0/18',
5176 'AI': '204.14.248.0/21',
5177 'AL': '46.99.0.0/16',
5178 'AM': '46.70.0.0/15',
5179 'AO': '105.168.0.0/13',
53896ca5
S
5180 'AP': '182.50.184.0/21',
5181 'AQ': '23.154.160.0/24',
773f291d
S
5182 'AR': '181.0.0.0/12',
5183 'AS': '202.70.112.0/20',
53896ca5 5184 'AT': '77.116.0.0/14',
773f291d
S
5185 'AU': '1.128.0.0/11',
5186 'AW': '181.41.0.0/18',
53896ca5
S
5187 'AX': '185.217.4.0/22',
5188 'AZ': '5.197.0.0/16',
773f291d
S
5189 'BA': '31.176.128.0/17',
5190 'BB': '65.48.128.0/17',
5191 'BD': '114.130.0.0/16',
5192 'BE': '57.0.0.0/8',
53896ca5 5193 'BF': '102.178.0.0/15',
773f291d
S
5194 'BG': '95.42.0.0/15',
5195 'BH': '37.131.0.0/17',
5196 'BI': '154.117.192.0/18',
5197 'BJ': '137.255.0.0/16',
53896ca5 5198 'BL': '185.212.72.0/23',
773f291d
S
5199 'BM': '196.12.64.0/18',
5200 'BN': '156.31.0.0/16',
5201 'BO': '161.56.0.0/16',
5202 'BQ': '161.0.80.0/20',
53896ca5 5203 'BR': '191.128.0.0/12',
773f291d
S
5204 'BS': '24.51.64.0/18',
5205 'BT': '119.2.96.0/19',
5206 'BW': '168.167.0.0/16',
5207 'BY': '178.120.0.0/13',
5208 'BZ': '179.42.192.0/18',
5209 'CA': '99.224.0.0/11',
5210 'CD': '41.243.0.0/16',
53896ca5
S
5211 'CF': '197.242.176.0/21',
5212 'CG': '160.113.0.0/16',
773f291d 5213 'CH': '85.0.0.0/13',
53896ca5 5214 'CI': '102.136.0.0/14',
773f291d
S
5215 'CK': '202.65.32.0/19',
5216 'CL': '152.172.0.0/14',
53896ca5 5217 'CM': '102.244.0.0/14',
773f291d
S
5218 'CN': '36.128.0.0/10',
5219 'CO': '181.240.0.0/12',
5220 'CR': '201.192.0.0/12',
5221 'CU': '152.206.0.0/15',
5222 'CV': '165.90.96.0/19',
5223 'CW': '190.88.128.0/17',
53896ca5 5224 'CY': '31.153.0.0/16',
773f291d
S
5225 'CZ': '88.100.0.0/14',
5226 'DE': '53.0.0.0/8',
5227 'DJ': '197.241.0.0/17',
5228 'DK': '87.48.0.0/12',
5229 'DM': '192.243.48.0/20',
5230 'DO': '152.166.0.0/15',
5231 'DZ': '41.96.0.0/12',
5232 'EC': '186.68.0.0/15',
5233 'EE': '90.190.0.0/15',
5234 'EG': '156.160.0.0/11',
5235 'ER': '196.200.96.0/20',
5236 'ES': '88.0.0.0/11',
5237 'ET': '196.188.0.0/14',
5238 'EU': '2.16.0.0/13',
5239 'FI': '91.152.0.0/13',
5240 'FJ': '144.120.0.0/16',
53896ca5 5241 'FK': '80.73.208.0/21',
773f291d
S
5242 'FM': '119.252.112.0/20',
5243 'FO': '88.85.32.0/19',
5244 'FR': '90.0.0.0/9',
5245 'GA': '41.158.0.0/15',
5246 'GB': '25.0.0.0/8',
5247 'GD': '74.122.88.0/21',
5248 'GE': '31.146.0.0/16',
5249 'GF': '161.22.64.0/18',
5250 'GG': '62.68.160.0/19',
53896ca5
S
5251 'GH': '154.160.0.0/12',
5252 'GI': '95.164.0.0/16',
773f291d
S
5253 'GL': '88.83.0.0/19',
5254 'GM': '160.182.0.0/15',
5255 'GN': '197.149.192.0/18',
5256 'GP': '104.250.0.0/19',
5257 'GQ': '105.235.224.0/20',
5258 'GR': '94.64.0.0/13',
5259 'GT': '168.234.0.0/16',
5260 'GU': '168.123.0.0/16',
5261 'GW': '197.214.80.0/20',
5262 'GY': '181.41.64.0/18',
5263 'HK': '113.252.0.0/14',
5264 'HN': '181.210.0.0/16',
5265 'HR': '93.136.0.0/13',
5266 'HT': '148.102.128.0/17',
5267 'HU': '84.0.0.0/14',
5268 'ID': '39.192.0.0/10',
5269 'IE': '87.32.0.0/12',
5270 'IL': '79.176.0.0/13',
5271 'IM': '5.62.80.0/20',
5272 'IN': '117.192.0.0/10',
5273 'IO': '203.83.48.0/21',
5274 'IQ': '37.236.0.0/14',
5275 'IR': '2.176.0.0/12',
5276 'IS': '82.221.0.0/16',
5277 'IT': '79.0.0.0/10',
5278 'JE': '87.244.64.0/18',
5279 'JM': '72.27.0.0/17',
5280 'JO': '176.29.0.0/16',
53896ca5 5281 'JP': '133.0.0.0/8',
773f291d
S
5282 'KE': '105.48.0.0/12',
5283 'KG': '158.181.128.0/17',
5284 'KH': '36.37.128.0/17',
5285 'KI': '103.25.140.0/22',
5286 'KM': '197.255.224.0/20',
53896ca5 5287 'KN': '198.167.192.0/19',
773f291d
S
5288 'KP': '175.45.176.0/22',
5289 'KR': '175.192.0.0/10',
5290 'KW': '37.36.0.0/14',
5291 'KY': '64.96.0.0/15',
5292 'KZ': '2.72.0.0/13',
5293 'LA': '115.84.64.0/18',
5294 'LB': '178.135.0.0/16',
53896ca5 5295 'LC': '24.92.144.0/20',
773f291d
S
5296 'LI': '82.117.0.0/19',
5297 'LK': '112.134.0.0/15',
53896ca5 5298 'LR': '102.183.0.0/16',
773f291d
S
5299 'LS': '129.232.0.0/17',
5300 'LT': '78.56.0.0/13',
5301 'LU': '188.42.0.0/16',
5302 'LV': '46.109.0.0/16',
5303 'LY': '41.252.0.0/14',
5304 'MA': '105.128.0.0/11',
5305 'MC': '88.209.64.0/18',
5306 'MD': '37.246.0.0/16',
5307 'ME': '178.175.0.0/17',
5308 'MF': '74.112.232.0/21',
5309 'MG': '154.126.0.0/17',
5310 'MH': '117.103.88.0/21',
5311 'MK': '77.28.0.0/15',
5312 'ML': '154.118.128.0/18',
5313 'MM': '37.111.0.0/17',
5314 'MN': '49.0.128.0/17',
5315 'MO': '60.246.0.0/16',
5316 'MP': '202.88.64.0/20',
5317 'MQ': '109.203.224.0/19',
5318 'MR': '41.188.64.0/18',
5319 'MS': '208.90.112.0/22',
5320 'MT': '46.11.0.0/16',
5321 'MU': '105.16.0.0/12',
5322 'MV': '27.114.128.0/18',
53896ca5 5323 'MW': '102.70.0.0/15',
773f291d
S
5324 'MX': '187.192.0.0/11',
5325 'MY': '175.136.0.0/13',
5326 'MZ': '197.218.0.0/15',
5327 'NA': '41.182.0.0/16',
5328 'NC': '101.101.0.0/18',
5329 'NE': '197.214.0.0/18',
5330 'NF': '203.17.240.0/22',
5331 'NG': '105.112.0.0/12',
5332 'NI': '186.76.0.0/15',
5333 'NL': '145.96.0.0/11',
5334 'NO': '84.208.0.0/13',
5335 'NP': '36.252.0.0/15',
5336 'NR': '203.98.224.0/19',
5337 'NU': '49.156.48.0/22',
5338 'NZ': '49.224.0.0/14',
5339 'OM': '5.36.0.0/15',
5340 'PA': '186.72.0.0/15',
5341 'PE': '186.160.0.0/14',
5342 'PF': '123.50.64.0/18',
5343 'PG': '124.240.192.0/19',
5344 'PH': '49.144.0.0/13',
5345 'PK': '39.32.0.0/11',
5346 'PL': '83.0.0.0/11',
5347 'PM': '70.36.0.0/20',
5348 'PR': '66.50.0.0/16',
5349 'PS': '188.161.0.0/16',
5350 'PT': '85.240.0.0/13',
5351 'PW': '202.124.224.0/20',
5352 'PY': '181.120.0.0/14',
5353 'QA': '37.210.0.0/15',
53896ca5 5354 'RE': '102.35.0.0/16',
773f291d 5355 'RO': '79.112.0.0/13',
53896ca5 5356 'RS': '93.86.0.0/15',
773f291d 5357 'RU': '5.136.0.0/13',
53896ca5 5358 'RW': '41.186.0.0/16',
773f291d
S
5359 'SA': '188.48.0.0/13',
5360 'SB': '202.1.160.0/19',
5361 'SC': '154.192.0.0/11',
53896ca5 5362 'SD': '102.120.0.0/13',
773f291d 5363 'SE': '78.64.0.0/12',
53896ca5 5364 'SG': '8.128.0.0/10',
773f291d
S
5365 'SI': '188.196.0.0/14',
5366 'SK': '78.98.0.0/15',
53896ca5 5367 'SL': '102.143.0.0/17',
773f291d
S
5368 'SM': '89.186.32.0/19',
5369 'SN': '41.82.0.0/15',
53896ca5 5370 'SO': '154.115.192.0/18',
773f291d
S
5371 'SR': '186.179.128.0/17',
5372 'SS': '105.235.208.0/21',
5373 'ST': '197.159.160.0/19',
5374 'SV': '168.243.0.0/16',
5375 'SX': '190.102.0.0/20',
5376 'SY': '5.0.0.0/16',
5377 'SZ': '41.84.224.0/19',
5378 'TC': '65.255.48.0/20',
5379 'TD': '154.68.128.0/19',
5380 'TG': '196.168.0.0/14',
5381 'TH': '171.96.0.0/13',
5382 'TJ': '85.9.128.0/18',
5383 'TK': '27.96.24.0/21',
5384 'TL': '180.189.160.0/20',
5385 'TM': '95.85.96.0/19',
5386 'TN': '197.0.0.0/11',
5387 'TO': '175.176.144.0/21',
5388 'TR': '78.160.0.0/11',
5389 'TT': '186.44.0.0/15',
5390 'TV': '202.2.96.0/19',
5391 'TW': '120.96.0.0/11',
5392 'TZ': '156.156.0.0/14',
53896ca5
S
5393 'UA': '37.52.0.0/14',
5394 'UG': '102.80.0.0/13',
5395 'US': '6.0.0.0/8',
773f291d 5396 'UY': '167.56.0.0/13',
53896ca5 5397 'UZ': '84.54.64.0/18',
773f291d 5398 'VA': '212.77.0.0/19',
53896ca5 5399 'VC': '207.191.240.0/21',
773f291d 5400 'VE': '186.88.0.0/13',
53896ca5 5401 'VG': '66.81.192.0/20',
773f291d
S
5402 'VI': '146.226.0.0/16',
5403 'VN': '14.160.0.0/11',
5404 'VU': '202.80.32.0/20',
5405 'WF': '117.20.32.0/21',
5406 'WS': '202.4.32.0/19',
5407 'YE': '134.35.0.0/16',
5408 'YT': '41.242.116.0/22',
5409 'ZA': '41.0.0.0/11',
53896ca5
S
5410 'ZM': '102.144.0.0/13',
5411 'ZW': '102.177.192.0/18',
773f291d
S
5412 }
5413
5414 @classmethod
5f95927a
S
5415 def random_ipv4(cls, code_or_block):
5416 if len(code_or_block) == 2:
5417 block = cls._country_ip_map.get(code_or_block.upper())
5418 if not block:
5419 return None
5420 else:
5421 block = code_or_block
773f291d
S
5422 addr, preflen = block.split('/')
5423 addr_min = compat_struct_unpack('!L', socket.inet_aton(addr))[0]
5424 addr_max = addr_min | (0xffffffff >> int(preflen))
18a0defa 5425 return compat_str(socket.inet_ntoa(
4248dad9 5426 compat_struct_pack('!L', random.randint(addr_min, addr_max))))
773f291d
S
5427
5428
91410c9b 5429class PerRequestProxyHandler(compat_urllib_request.ProxyHandler):
2461f79d
PH
5430 def __init__(self, proxies=None):
5431 # Set default handlers
5432 for type in ('http', 'https'):
5433 setattr(self, '%s_open' % type,
5434 lambda r, proxy='__noproxy__', type=type, meth=self.proxy_open:
5435 meth(r, proxy, type))
38e87f6c 5436 compat_urllib_request.ProxyHandler.__init__(self, proxies)
2461f79d 5437
91410c9b 5438 def proxy_open(self, req, proxy, type):
2461f79d 5439 req_proxy = req.headers.get('Ytdl-request-proxy')
91410c9b
PH
5440 if req_proxy is not None:
5441 proxy = req_proxy
2461f79d
PH
5442 del req.headers['Ytdl-request-proxy']
5443
5444 if proxy == '__noproxy__':
5445 return None # No Proxy
51fb4995 5446 if compat_urlparse.urlparse(proxy).scheme.lower() in ('socks', 'socks4', 'socks4a', 'socks5'):
71aff188 5447 req.add_header('Ytdl-socks-proxy', proxy)
cefecac1 5448 # youtube-dlc's http/https handlers do wrapping the socket with socks
71aff188 5449 return None
91410c9b
PH
5450 return compat_urllib_request.ProxyHandler.proxy_open(
5451 self, req, proxy, type)
5bc880b9
YCH
5452
5453
0a5445dd
YCH
5454# Both long_to_bytes and bytes_to_long are adapted from PyCrypto, which is
5455# released into Public Domain
5456# https://github.com/dlitz/pycrypto/blob/master/lib/Crypto/Util/number.py#L387
5457
5458def long_to_bytes(n, blocksize=0):
5459 """long_to_bytes(n:long, blocksize:int) : string
5460 Convert a long integer to a byte string.
5461
5462 If optional blocksize is given and greater than zero, pad the front of the
5463 byte string with binary zeros so that the length is a multiple of
5464 blocksize.
5465 """
5466 # after much testing, this algorithm was deemed to be the fastest
5467 s = b''
5468 n = int(n)
5469 while n > 0:
5470 s = compat_struct_pack('>I', n & 0xffffffff) + s
5471 n = n >> 32
5472 # strip off leading zeros
5473 for i in range(len(s)):
5474 if s[i] != b'\000'[0]:
5475 break
5476 else:
5477 # only happens when n == 0
5478 s = b'\000'
5479 i = 0
5480 s = s[i:]
5481 # add back some pad bytes. this could be done more efficiently w.r.t. the
5482 # de-padding being done above, but sigh...
5483 if blocksize > 0 and len(s) % blocksize:
5484 s = (blocksize - len(s) % blocksize) * b'\000' + s
5485 return s
5486
5487
5488def bytes_to_long(s):
5489 """bytes_to_long(string) : long
5490 Convert a byte string to a long integer.
5491
5492 This is (essentially) the inverse of long_to_bytes().
5493 """
5494 acc = 0
5495 length = len(s)
5496 if length % 4:
5497 extra = (4 - length % 4)
5498 s = b'\000' * extra + s
5499 length = length + extra
5500 for i in range(0, length, 4):
5501 acc = (acc << 32) + compat_struct_unpack('>I', s[i:i + 4])[0]
5502 return acc
5503
5504
5bc880b9
YCH
5505def ohdave_rsa_encrypt(data, exponent, modulus):
5506 '''
5507 Implement OHDave's RSA algorithm. See http://www.ohdave.com/rsa/
5508
5509 Input:
5510 data: data to encrypt, bytes-like object
5511 exponent, modulus: parameter e and N of RSA algorithm, both integer
5512 Output: hex string of encrypted data
5513
5514 Limitation: supports one block encryption only
5515 '''
5516
5517 payload = int(binascii.hexlify(data[::-1]), 16)
5518 encrypted = pow(payload, exponent, modulus)
5519 return '%x' % encrypted
81bdc8fd
YCH
5520
5521
f48409c7
YCH
5522def pkcs1pad(data, length):
5523 """
5524 Padding input data with PKCS#1 scheme
5525
5526 @param {int[]} data input data
5527 @param {int} length target length
5528 @returns {int[]} padded data
5529 """
5530 if len(data) > length - 11:
5531 raise ValueError('Input data too long for PKCS#1 padding')
5532
5533 pseudo_random = [random.randint(0, 254) for _ in range(length - len(data) - 3)]
5534 return [0, 2] + pseudo_random + [0] + data
5535
5536
5eb6bdce 5537def encode_base_n(num, n, table=None):
59f898b7 5538 FULL_TABLE = '0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ'
59f898b7
YCH
5539 if not table:
5540 table = FULL_TABLE[:n]
5541
5eb6bdce
YCH
5542 if n > len(table):
5543 raise ValueError('base %d exceeds table length %d' % (n, len(table)))
5544
5545 if num == 0:
5546 return table[0]
5547
81bdc8fd
YCH
5548 ret = ''
5549 while num:
5550 ret = table[num % n] + ret
5551 num = num // n
5552 return ret
f52354a8
YCH
5553
5554
5555def decode_packed_codes(code):
06b3fe29 5556 mobj = re.search(PACKED_CODES_RE, code)
a0566bbf 5557 obfuscated_code, base, count, symbols = mobj.groups()
f52354a8
YCH
5558 base = int(base)
5559 count = int(count)
5560 symbols = symbols.split('|')
5561 symbol_table = {}
5562
5563 while count:
5564 count -= 1
5eb6bdce 5565 base_n_count = encode_base_n(count, base)
f52354a8
YCH
5566 symbol_table[base_n_count] = symbols[count] or base_n_count
5567
5568 return re.sub(
5569 r'\b(\w+)\b', lambda mobj: symbol_table[mobj.group(0)],
a0566bbf 5570 obfuscated_code)
e154c651 5571
5572
1ced2221
S
5573def caesar(s, alphabet, shift):
5574 if shift == 0:
5575 return s
5576 l = len(alphabet)
5577 return ''.join(
5578 alphabet[(alphabet.index(c) + shift) % l] if c in alphabet else c
5579 for c in s)
5580
5581
5582def rot47(s):
5583 return caesar(s, r'''!"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~''', 47)
5584
5585
e154c651 5586def parse_m3u8_attributes(attrib):
5587 info = {}
5588 for (key, val) in re.findall(r'(?P<key>[A-Z0-9-]+)=(?P<val>"[^"]+"|[^",]+)(?:,|$)', attrib):
5589 if val.startswith('"'):
5590 val = val[1:-1]
5591 info[key] = val
5592 return info
1143535d
YCH
5593
5594
5595def urshift(val, n):
5596 return val >> n if val >= 0 else (val + 0x100000000) >> n
d3f8e038
YCH
5597
5598
5599# Based on png2str() written by @gdkchan and improved by @yokrysty
067aa17e 5600# Originally posted at https://github.com/ytdl-org/youtube-dl/issues/9706
d3f8e038
YCH
5601def decode_png(png_data):
5602 # Reference: https://www.w3.org/TR/PNG/
5603 header = png_data[8:]
5604
5605 if png_data[:8] != b'\x89PNG\x0d\x0a\x1a\x0a' or header[4:8] != b'IHDR':
5606 raise IOError('Not a valid PNG file.')
5607
5608 int_map = {1: '>B', 2: '>H', 4: '>I'}
5609 unpack_integer = lambda x: compat_struct_unpack(int_map[len(x)], x)[0]
5610
5611 chunks = []
5612
5613 while header:
5614 length = unpack_integer(header[:4])
5615 header = header[4:]
5616
5617 chunk_type = header[:4]
5618 header = header[4:]
5619
5620 chunk_data = header[:length]
5621 header = header[length:]
5622
5623 header = header[4:] # Skip CRC
5624
5625 chunks.append({
5626 'type': chunk_type,
5627 'length': length,
5628 'data': chunk_data
5629 })
5630
5631 ihdr = chunks[0]['data']
5632
5633 width = unpack_integer(ihdr[:4])
5634 height = unpack_integer(ihdr[4:8])
5635
5636 idat = b''
5637
5638 for chunk in chunks:
5639 if chunk['type'] == b'IDAT':
5640 idat += chunk['data']
5641
5642 if not idat:
5643 raise IOError('Unable to read PNG data.')
5644
5645 decompressed_data = bytearray(zlib.decompress(idat))
5646
5647 stride = width * 3
5648 pixels = []
5649
5650 def _get_pixel(idx):
5651 x = idx % stride
5652 y = idx // stride
5653 return pixels[y][x]
5654
5655 for y in range(height):
5656 basePos = y * (1 + stride)
5657 filter_type = decompressed_data[basePos]
5658
5659 current_row = []
5660
5661 pixels.append(current_row)
5662
5663 for x in range(stride):
5664 color = decompressed_data[1 + basePos + x]
5665 basex = y * stride + x
5666 left = 0
5667 up = 0
5668
5669 if x > 2:
5670 left = _get_pixel(basex - 3)
5671 if y > 0:
5672 up = _get_pixel(basex - stride)
5673
5674 if filter_type == 1: # Sub
5675 color = (color + left) & 0xff
5676 elif filter_type == 2: # Up
5677 color = (color + up) & 0xff
5678 elif filter_type == 3: # Average
5679 color = (color + ((left + up) >> 1)) & 0xff
5680 elif filter_type == 4: # Paeth
5681 a = left
5682 b = up
5683 c = 0
5684
5685 if x > 2 and y > 0:
5686 c = _get_pixel(basex - stride - 3)
5687
5688 p = a + b - c
5689
5690 pa = abs(p - a)
5691 pb = abs(p - b)
5692 pc = abs(p - c)
5693
5694 if pa <= pb and pa <= pc:
5695 color = (color + a) & 0xff
5696 elif pb <= pc:
5697 color = (color + b) & 0xff
5698 else:
5699 color = (color + c) & 0xff
5700
5701 current_row.append(color)
5702
5703 return width, height, pixels
efa97bdc
YCH
5704
5705
5706def write_xattr(path, key, value):
5707 # This mess below finds the best xattr tool for the job
5708 try:
5709 # try the pyxattr module...
5710 import xattr
5711
53a7e3d2
YCH
5712 if hasattr(xattr, 'set'): # pyxattr
5713 # Unicode arguments are not supported in python-pyxattr until
5714 # version 0.5.0
067aa17e 5715 # See https://github.com/ytdl-org/youtube-dl/issues/5498
53a7e3d2
YCH
5716 pyxattr_required_version = '0.5.0'
5717 if version_tuple(xattr.__version__) < version_tuple(pyxattr_required_version):
5718 # TODO: fallback to CLI tools
5719 raise XAttrUnavailableError(
5720 'python-pyxattr is detected but is too old. '
cefecac1 5721 'youtube-dlc requires %s or above while your version is %s. '
53a7e3d2
YCH
5722 'Falling back to other xattr implementations' % (
5723 pyxattr_required_version, xattr.__version__))
5724
5725 setxattr = xattr.set
5726 else: # xattr
5727 setxattr = xattr.setxattr
efa97bdc
YCH
5728
5729 try:
53a7e3d2 5730 setxattr(path, key, value)
efa97bdc
YCH
5731 except EnvironmentError as e:
5732 raise XAttrMetadataError(e.errno, e.strerror)
5733
5734 except ImportError:
5735 if compat_os_name == 'nt':
5736 # Write xattrs to NTFS Alternate Data Streams:
5737 # http://en.wikipedia.org/wiki/NTFS#Alternate_data_streams_.28ADS.29
5738 assert ':' not in key
5739 assert os.path.exists(path)
5740
5741 ads_fn = path + ':' + key
5742 try:
5743 with open(ads_fn, 'wb') as f:
5744 f.write(value)
5745 except EnvironmentError as e:
5746 raise XAttrMetadataError(e.errno, e.strerror)
5747 else:
5748 user_has_setfattr = check_executable('setfattr', ['--version'])
5749 user_has_xattr = check_executable('xattr', ['-h'])
5750
5751 if user_has_setfattr or user_has_xattr:
5752
5753 value = value.decode('utf-8')
5754 if user_has_setfattr:
5755 executable = 'setfattr'
5756 opts = ['-n', key, '-v', value]
5757 elif user_has_xattr:
5758 executable = 'xattr'
5759 opts = ['-w', key, value]
5760
3089bc74
S
5761 cmd = ([encodeFilename(executable, True)]
5762 + [encodeArgument(o) for o in opts]
5763 + [encodeFilename(path, True)])
efa97bdc
YCH
5764
5765 try:
5766 p = subprocess.Popen(
5767 cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, stdin=subprocess.PIPE)
5768 except EnvironmentError as e:
5769 raise XAttrMetadataError(e.errno, e.strerror)
f5b1bca9 5770 stdout, stderr = process_communicate_or_kill(p)
efa97bdc
YCH
5771 stderr = stderr.decode('utf-8', 'replace')
5772 if p.returncode != 0:
5773 raise XAttrMetadataError(p.returncode, stderr)
5774
5775 else:
5776 # On Unix, and can't find pyxattr, setfattr, or xattr.
5777 if sys.platform.startswith('linux'):
5778 raise XAttrUnavailableError(
5779 "Couldn't find a tool to set the xattrs. "
5780 "Install either the python 'pyxattr' or 'xattr' "
5781 "modules, or the GNU 'attr' package "
5782 "(which contains the 'setfattr' tool).")
5783 else:
5784 raise XAttrUnavailableError(
5785 "Couldn't find a tool to set the xattrs. "
5786 "Install either the python 'xattr' module, "
5787 "or the 'xattr' binary.")
0c265486
YCH
5788
5789
5790def random_birthday(year_field, month_field, day_field):
aa374bc7
AS
5791 start_date = datetime.date(1950, 1, 1)
5792 end_date = datetime.date(1995, 12, 31)
5793 offset = random.randint(0, (end_date - start_date).days)
5794 random_date = start_date + datetime.timedelta(offset)
0c265486 5795 return {
aa374bc7
AS
5796 year_field: str(random_date.year),
5797 month_field: str(random_date.month),
5798 day_field: str(random_date.day),
0c265486 5799 }
732044af 5800
c76eb41b 5801
732044af 5802# Templates for internet shortcut files, which are plain text files.
5803DOT_URL_LINK_TEMPLATE = '''
5804[InternetShortcut]
5805URL=%(url)s
5806'''.lstrip()
5807
5808DOT_WEBLOC_LINK_TEMPLATE = '''
5809<?xml version="1.0" encoding="UTF-8"?>
5810<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
5811<plist version="1.0">
5812<dict>
5813\t<key>URL</key>
5814\t<string>%(url)s</string>
5815</dict>
5816</plist>
5817'''.lstrip()
5818
5819DOT_DESKTOP_LINK_TEMPLATE = '''
5820[Desktop Entry]
5821Encoding=UTF-8
5822Name=%(filename)s
5823Type=Link
5824URL=%(url)s
5825Icon=text-html
5826'''.lstrip()
5827
5828
5829def iri_to_uri(iri):
5830 """
5831 Converts an IRI (Internationalized Resource Identifier, allowing Unicode characters) to a URI (Uniform Resource Identifier, ASCII-only).
5832
5833 The function doesn't add an additional layer of escaping; e.g., it doesn't escape `%3C` as `%253C`. Instead, it percent-escapes characters with an underlying UTF-8 encoding *besides* those already escaped, leaving the URI intact.
5834 """
5835
5836 iri_parts = compat_urllib_parse_urlparse(iri)
5837
5838 if '[' in iri_parts.netloc:
5839 raise ValueError('IPv6 URIs are not, yet, supported.')
5840 # Querying `.netloc`, when there's only one bracket, also raises a ValueError.
5841
5842 # The `safe` argument values, that the following code uses, contain the characters that should not be percent-encoded. Everything else but letters, digits and '_.-' will be percent-encoded with an underlying UTF-8 encoding. Everything already percent-encoded will be left as is.
5843
5844 net_location = ''
5845 if iri_parts.username:
5846 net_location += compat_urllib_parse_quote(iri_parts.username, safe=r"!$%&'()*+,~")
5847 if iri_parts.password is not None:
5848 net_location += ':' + compat_urllib_parse_quote(iri_parts.password, safe=r"!$%&'()*+,~")
5849 net_location += '@'
5850
5851 net_location += iri_parts.hostname.encode('idna').decode('utf-8') # Punycode for Unicode hostnames.
5852 # The 'idna' encoding produces ASCII text.
5853 if iri_parts.port is not None and iri_parts.port != 80:
5854 net_location += ':' + str(iri_parts.port)
5855
5856 return compat_urllib_parse_urlunparse(
5857 (iri_parts.scheme,
5858 net_location,
5859
5860 compat_urllib_parse_quote_plus(iri_parts.path, safe=r"!$%&'()*+,/:;=@|~"),
5861
5862 # Unsure about the `safe` argument, since this is a legacy way of handling parameters.
5863 compat_urllib_parse_quote_plus(iri_parts.params, safe=r"!$%&'()*+,/:;=@|~"),
5864
5865 # Not totally sure about the `safe` argument, since the source does not explicitly mention the query URI component.
5866 compat_urllib_parse_quote_plus(iri_parts.query, safe=r"!$%&'()*+,/:;=?@{|}~"),
5867
5868 compat_urllib_parse_quote_plus(iri_parts.fragment, safe=r"!#$%&'()*+,/:;=?@{|}~")))
5869
5870 # Source for `safe` arguments: https://url.spec.whatwg.org/#percent-encoded-bytes.
5871
5872
5873def to_high_limit_path(path):
5874 if sys.platform in ['win32', 'cygwin']:
5875 # Work around MAX_PATH limitation on Windows. The maximum allowed length for the individual path segments may still be quite limited.
5876 return r'\\?\ '.rstrip() + os.path.abspath(path)
5877
5878 return path
76d321f6 5879
c76eb41b 5880
76d321f6 5881def format_field(obj, field, template='%s', ignore=(None, ''), default='', func=None):
5882 val = obj.get(field, default)
5883 if func and val not in ignore:
5884 val = func(val)
5885 return template % val if val not in ignore else default
00dd0cd5 5886
5887
5888def clean_podcast_url(url):
5889 return re.sub(r'''(?x)
5890 (?:
5891 (?:
5892 chtbl\.com/track|
5893 media\.blubrry\.com| # https://create.blubrry.com/resources/podcast-media-download-statistics/getting-started/
5894 play\.podtrac\.com
5895 )/[^/]+|
5896 (?:dts|www)\.podtrac\.com/(?:pts/)?redirect\.[0-9a-z]{3,4}| # http://analytics.podtrac.com/how-to-measure
5897 flex\.acast\.com|
5898 pd(?:
5899 cn\.co| # https://podcorn.com/analytics-prefix/
5900 st\.fm # https://podsights.com/docs/
5901 )/e
5902 )/''', '', url)
ffcb8191
THD
5903
5904
5905_HEX_TABLE = '0123456789abcdef'
5906
5907
5908def random_uuidv4():
5909 return re.sub(r'[xy]', lambda x: _HEX_TABLE[random.randint(0, 15)], 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx')
0202b52a 5910
5911
5912def make_dir(path, to_screen=None):
5913 try:
5914 dn = os.path.dirname(path)
5915 if dn and not os.path.exists(dn):
5916 os.makedirs(dn)
5917 return True
5918 except (OSError, IOError) as err:
5919 if callable(to_screen) is not None:
5920 to_screen('unable to create directory ' + error_to_compat_str(err))
5921 return False
f74980cb 5922
5923
5924def get_executable_path():
5925 path = os.path.dirname(sys.argv[0])
5926 if os.path.abspath(sys.argv[0]) != os.path.abspath(sys.executable): # Not packaged
5927 path = os.path.join(path, '..')
5928 return os.path.abspath(path)
5929
5930
5931def load_plugins(name, type, namespace):
5932 plugin_info = [None]
5933 classes = []
5934 try:
5935 plugin_info = imp.find_module(
5936 name, [os.path.join(get_executable_path(), 'ytdlp_plugins')])
5937 plugins = imp.load_module(name, *plugin_info)
5938 for name in dir(plugins):
5939 if not name.endswith(type):
5940 continue
5941 klass = getattr(plugins, name)
5942 classes.append(klass)
5943 namespace[name] = klass
5944 except ImportError:
5945 pass
5946 finally:
5947 if plugin_info[0] is not None:
5948 plugin_info[0].close()
5949 return classes
06167fbb 5950
5951
5952def traverse_dict(dictn, keys, casesense=True):
5953 if not isinstance(dictn, dict):
5954 return None
5955 first_key = keys[0]
5956 if not casesense:
5957 dictn = {key.lower(): val for key, val in dictn.items()}
5958 first_key = first_key.lower()
5959 value = dictn.get(first_key, None)
5960 return value if len(keys) < 2 else traverse_dict(value, keys[1:], casesense)