aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/utils.py
blob: 9124c36212481b860b92d4bc35676e4ab3453bd4 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
#!/usr/bin/env python
# -*- coding: utf-8 -*-

import calendar
import codecs
import contextlib
import ctypes
import datetime
import email.utils
import errno
import getpass
import gzip
import itertools
import io
import json
import locale
import math
import os
import pipes
import platform
import re
import ssl
import socket
import struct
import subprocess
import sys
import tempfile
import traceback
import xml.etree.ElementTree
import zlib

try:
    import urllib.request as compat_urllib_request
except ImportError: # Python 2
    import urllib2 as compat_urllib_request

try:
    import urllib.error as compat_urllib_error
except ImportError: # Python 2
    import urllib2 as compat_urllib_error

try:
    import urllib.parse as compat_urllib_parse
except ImportError: # Python 2
    import urllib as compat_urllib_parse

try:
    from urllib.parse import urlparse as compat_urllib_parse_urlparse
except ImportError: # Python 2
    from urlparse import urlparse as compat_urllib_parse_urlparse

try:
    import urllib.parse as compat_urlparse
except ImportError: # Python 2
    import urlparse as compat_urlparse

try:
    import http.cookiejar as compat_cookiejar
except ImportError: # Python 2
    import cookielib as compat_cookiejar

try:
    import html.entities as compat_html_entities
except ImportError: # Python 2
    import htmlentitydefs as compat_html_entities

try:
    import html.parser as compat_html_parser
except ImportError: # Python 2
    import HTMLParser as compat_html_parser

try:
    import http.client as compat_http_client
except ImportError: # Python 2
    import httplib as compat_http_client

try:
    from urllib.error import HTTPError as compat_HTTPError
except ImportError:  # Python 2
    from urllib2 import HTTPError as compat_HTTPError

try:
    from urllib.request import urlretrieve as compat_urlretrieve
except ImportError:  # Python 2
    from urllib import urlretrieve as compat_urlretrieve


try:
    from subprocess import DEVNULL
    compat_subprocess_get_DEVNULL = lambda: DEVNULL
except ImportError:
    compat_subprocess_get_DEVNULL = lambda: open(os.path.devnull, 'w')

try:
    from urllib.parse import unquote as compat_urllib_parse_unquote
except ImportError:
    def compat_urllib_parse_unquote(string, encoding='utf-8', errors='replace'):
        if string == '':
            return string
        res = string.split('%')
        if len(res) == 1:
            return string
        if encoding is None:
            encoding = 'utf-8'
        if errors is None:
            errors = 'replace'
        # pct_sequence: contiguous sequence of percent-encoded bytes, decoded
        pct_sequence = b''
        string = res[0]
        for item in res[1:]:
            try:
                if not item:
                    raise ValueError
                pct_sequence += item[:2].decode('hex')
                rest = item[2:]
                if not rest:
                    # This segment was just a single percent-encoded character.
                    # May be part of a sequence of code units, so delay decoding.
                    # (Stored in pct_sequence).
                    continue
            except ValueError:
                rest = '%' + item
            # Encountered non-percent-encoded characters. Flush the current
            # pct_sequence.
            string += pct_sequence.decode(encoding, errors) + rest
            pct_sequence = b''
        if pct_sequence:
            # Flush the final pct_sequence
            string += pct_sequence.decode(encoding, errors)
        return string


try:
    from urllib.parse import parse_qs as compat_parse_qs
except ImportError: # Python 2
    # HACK: The following is the correct parse_qs implementation from cpython 3's stdlib.
    # Python 2's version is apparently totally broken

    def _parse_qsl(qs, keep_blank_values=False, strict_parsing=False,
                encoding='utf-8', errors='replace'):
        qs, _coerce_result = qs, unicode
        pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
        r = []
        for name_value in pairs:
            if not name_value and not strict_parsing:
                continue
            nv = name_value.split('=', 1)
            if len(nv) != 2:
                if strict_parsing:
                    raise ValueError("bad query field: %r" % (name_value,))
                # Handle case of a control-name with no equal sign
                if keep_blank_values:
                    nv.append('')
                else:
                    continue
            if len(nv[1]) or keep_blank_values:
                name = nv[0].replace('+', ' ')
                name = compat_urllib_parse_unquote(
                    name, encoding=encoding, errors=errors)
                name = _coerce_result(name)
                value = nv[1].replace('+', ' ')
                value = compat_urllib_parse_unquote(
                    value, encoding=encoding, errors=errors)
                value = _coerce_result(value)
                r.append((name, value))
        return r

    def compat_parse_qs(qs, keep_blank_values=False, strict_parsing=False,
                encoding='utf-8', errors='replace'):
        parsed_result = {}
        pairs = _parse_qsl(qs, keep_blank_values, strict_parsing,
                        encoding=encoding, errors=errors)
        for name, value in pairs:
            if name in parsed_result:
                parsed_result[name].append(value)
            else:
                parsed_result[name] = [value]
        return parsed_result

try:
    compat_str = unicode # Python 2
except NameError:
    compat_str = str

try:
    compat_chr = unichr # Python 2
except NameError:
    compat_chr = chr

try:
    from xml.etree.ElementTree import ParseError as compat_xml_parse_error
except ImportError:  # Python 2.6
    from xml.parsers.expat import ExpatError as compat_xml_parse_error

try:
    from shlex import quote as shlex_quote
except ImportError:  # Python < 3.3
    def shlex_quote(s):
        return "'" + s.replace("'", "'\"'\"'") + "'"


def compat_ord(c):
    if type(c) is int: return c
    else: return ord(c)

# This is not clearly defined otherwise
compiled_regex_type = type(re.compile(''))

std_headers = {
    'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20100101 Firefox/10.0 (Chrome)',
    'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
    'Accept-Encoding': 'gzip, deflate',
    'Accept-Language': 'en-us,en;q=0.5',
}

def preferredencoding():
    """Get preferred encoding.

    Returns the best encoding scheme for the system, based on
    locale.getpreferredencoding() and some further tweaks.
    """
    try:
        pref = locale.getpreferredencoding()
        u'TEST'.encode(pref)
    except:
        pref = 'UTF-8'

    return pref

if sys.version_info < (3,0):
    def compat_print(s):
        print(s.encode(preferredencoding(), 'xmlcharrefreplace'))
else:
    def compat_print(s):
        assert type(s) == type(u'')
        print(s)


def write_json_file(obj, fn):
    """ Encode obj as JSON and write it to fn, atomically """

    args = {
        'suffix': '.tmp',
        'prefix': os.path.basename(fn) + '.',
        'dir': os.path.dirname(fn),
        'delete': False,
    }

    # In Python 2.x, json.dump expects a bytestream.
    # In Python 3.x, it writes to a character stream
    if sys.version_info < (3, 0):
        args['mode'] = 'wb'
    else:
        args.update({
            'mode': 'w',
            'encoding': 'utf-8',
        })

    tf = tempfile.NamedTemporaryFile(**args)

    try:
        with tf:
            json.dump(obj, tf)
        os.rename(tf.name, fn)
    except:
        try:
            os.remove(tf.name)
        except OSError:
            pass
        raise


if sys.version_info >= (2, 7):
    def find_xpath_attr(node, xpath, key, val):
        """ Find the xpath xpath[@key=val] """
        assert re.match(r'^[a-zA-Z-]+$', key)
        assert re.match(r'^[a-zA-Z0-9@\s:._-]*$', val)
        expr = xpath + u"[@%s='%s']" % (key, val)
        return node.find(expr)
else:
    def find_xpath_attr(node, xpath, key, val):
        for f in node.findall(xpath):
            if f.attrib.get(key) == val:
                return f
        return None

# On python2.6 the xml.etree.ElementTree.Element methods don't support
# the namespace parameter
def xpath_with_ns(path, ns_map):
    components = [c.split(':') for c in path.split('/')]
    replaced = []
    for c in components:
        if len(c) == 1:
            replaced.append(c[0])
        else:
            ns, tag = c
            replaced.append('{%s}%s' % (ns_map[ns], tag))
    return '/'.join(replaced)


compat_html_parser.locatestarttagend = re.compile(r"""<[a-zA-Z][-.a-zA-Z0-9:_]*(?:\s+(?:(?<=['"\s])[^\s/>][^\s/=>]*(?:\s*=+\s*(?:'[^']*'|"[^"]*"|(?!['"])[^>\s]*))?\s*)*)?\s*""", re.VERBOSE) # backport bugfix
class BaseHTMLParser(compat_html_parser.HTMLParser):
    def __init(self):
        compat_html_parser.HTMLParser.__init__(self)
        self.html = None

    def loads(self, html):
        self.html = html
        self.feed(html)
        self.close()

class AttrParser(BaseHTMLParser):
    """Modified HTMLParser that isolates a tag with the specified attribute"""
    def __init__(self, attribute, value):
        self.attribute = attribute
        self.value = value
        self.result = None
        self.started = False
        self.depth = {}
        self.watch_startpos = False
        self.error_count = 0
        BaseHTMLParser.__init__(self)

    def error(self, message):
        if self.error_count > 10 or self.started:
            raise compat_html_parser.HTMLParseError(message, self.getpos())
        self.rawdata = '\n'.join(self.html.split('\n')[self.getpos()[0]:]) # skip one line
        self.error_count += 1
        self.goahead(1)

    def handle_starttag(self, tag, attrs):
        attrs = dict(attrs)
        if self.started:
            self.find_startpos(None)
        if self.attribute in attrs and attrs[self.attribute] == self.value:
            self.result = [tag]
            self.started = True
            self.watch_startpos = True
        if self.started:
            if not tag in self.depth: self.depth[tag] = 0
            self.depth[tag] += 1

    def handle_endtag(self, tag):
        if self.started:
            if tag in self.depth: self.depth[tag] -= 1
            if self.depth[self.result[0]] == 0:
                self.started = False
                self.result.append(self.getpos())

    def find_startpos(self, x):
        """Needed to put the start position of the result (self.result[1])
        after the opening tag with the requested id"""
        if self.watch_startpos:
            self.watch_startpos = False
            self.result.append(self.getpos())
    handle_entityref = handle_charref = handle_data = handle_comment = \
    handle_decl = handle_pi = unknown_decl = find_startpos

    def get_result(self):
        if self.result is None:
            return None
        if len(self.result) != 3:
            return None
        lines = self.html.split('\n')
        lines = lines[self.result[1][0]-1:self.result[2][0]]
        lines[0] = lines[0][self.result[1][1]:]
        if len(lines) == 1:
            lines[-1] = lines[-1][:self.result[2][1]-self.result[1][1]]
        lines[-1] = lines[-1][:self.result[2][1]]
        return '\n'.join(lines).strip()
# Hack for https://github.com/rg3/youtube-dl/issues/662
if sys.version_info < (2, 7, 3):
    AttrParser.parse_endtag = (lambda self, i:
        i + len("</scr'+'ipt>")
        if self.rawdata[i:].startswith("</scr'+'ipt>")
        else compat_html_parser.HTMLParser.parse_endtag(self, i))

def get_element_by_id(id, html):
    """Return the content of the tag with the specified ID in the passed HTML document"""
    return get_element_by_attribute("id", id, html)

def get_element_by_attribute(attribute, value, html):
    """Return the content of the tag with the specified attribute in the passed HTML document"""
    parser = AttrParser(attribute, value)
    try:
        parser.loads(html)
    except compat_html_parser.HTMLParseError:
        pass
    return parser.get_result()

class MetaParser(BaseHTMLParser):
    """
    Modified HTMLParser that isolates a meta tag with the specified name 
    attribute.
    """
    def __init__(self, name):
        BaseHTMLParser.__init__(self)
        self.name = name
        self.content = None
        self.result = None

    def handle_starttag(self, tag, attrs):
        if tag != 'meta':
            return
        attrs = dict(attrs)
        if attrs.get('name') == self.name:
            self.result = attrs.get('content')

    def get_result(self):
        return self.result

def get_meta_content(name, html):
    """
    Return the content attribute from the meta tag with the given name attribute.
    """
    parser = MetaParser(name)
    try:
        parser.loads(html)
    except compat_html_parser.HTMLParseError:
        pass
    return parser.get_result()


def clean_html(html):
    """Clean an HTML snippet into a readable string"""
    # Newline vs <br />
    html = html.replace('\n', ' ')
    html = re.sub(r'\s*<\s*br\s*/?\s*>\s*', '\n', html)
    html = re.sub(r'<\s*/\s*p\s*>\s*<\s*p[^>]*>', '\n', html)
    # Strip html tags
    html = re.sub('<.*?>', '', html)
    # Replace html entities
    html = unescapeHTML(html)
    return html.strip()


def sanitize_open(filename, open_mode):
    """Try to open the given filename, and slightly tweak it if this fails.

    Attempts to open the given filename. If this fails, it tries to change
    the filename slightly, step by step, until it's either able to open it
    or it fails and raises a final exception, like the standard open()
    function.

    It returns the tuple (stream, definitive_file_name).
    """
    try:
        if filename == u'-':
            if sys.platform == 'win32':
                import msvcrt
                msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
            return (sys.stdout.buffer if hasattr(sys.stdout, 'buffer') else sys.stdout, filename)
        stream = open(encodeFilename(filename), open_mode)
        return (stream, filename)
    except (IOError, OSError) as err:
        if err.errno in (errno.EACCES,):
            raise

        # In case of error, try to remove win32 forbidden chars
        alt_filename = os.path.join(
                        re.sub(u'[/<>:"\\|\\\\?\\*]', u'#', path_part)
                        for path_part in os.path.split(filename)
                       )
        if alt_filename == filename:
            raise
        else:
            # An exception here should be caught in the caller
            stream = open(encodeFilename(filename), open_mode)
            return (stream, alt_filename)


def timeconvert(timestr):
    """Convert RFC 2822 defined time string into system timestamp"""
    timestamp = None
    timetuple = email.utils.parsedate_tz(timestr)
    if timetuple is not None:
        timestamp = email.utils.mktime_tz(timetuple)
    return timestamp

def sanitize_filename(s, restricted=False, is_id=False):
    """Sanitizes a string so it could be used as part of a filename.
    If restricted is set, use a stricter subset of allowed characters.
    Set is_id if this is not an arbitrary string, but an ID that should be kept if possible
    """
    def replace_insane(char):
        if char == '?' or ord(char) < 32 or ord(char) == 127:
            return ''
        elif char == '"':
            return '' if restricted else '\''
        elif char == ':':
            return '_-' if restricted else ' -'
        elif char in '\\/|*<>':
            return '_'
        if restricted and (char in '!&\'()[]{}$;`^,#' or char.isspace()):
            return '_'
        if restricted and ord(char) > 127:
            return '_'
        return char

    result = u''.join(map(replace_insane, s))
    if not is_id:
        while '__' in result:
            result = result.replace('__', '_')
        result = result.strip('_')
        # Common case of "Foreign band name - English song title"
        if restricted and result.startswith('-_'):
            result = result[2:]
        if not result:
            result = '_'
    return result

def orderedSet(iterable):
    """ Remove all duplicates from the input iterable """
    res = []
    for el in iterable:
        if el not in res:
            res.append(el)
    return res


def _htmlentity_transform(entity):
    """Transforms an HTML entity to a character."""
    # Known non-numeric HTML entity
    if entity in compat_html_entities.name2codepoint:
        return compat_chr(compat_html_entities.name2codepoint[entity])

    mobj = re.match(r'#(x?[0-9]+)', entity)
    if mobj is not None:
        numstr = mobj.group(1)
        if numstr.startswith(u'x'):
            base = 16
            numstr = u'0%s' % numstr
        else:
            base = 10
        return compat_chr(int(numstr, base))

    # Unknown entity in name, return its literal representation
    return (u'&%s;' % entity)


def unescapeHTML(s):
    if s is None:
        return None
    assert type(s) == compat_str

    return re.sub(
        r'&([^;]+);', lambda m: _htmlentity_transform(m.group(1)), s)


def encodeFilename(s, for_subprocess=False):
    """
    @param s The name of the file
    """

    assert type(s) == compat_str

    # Python 3 has a Unicode API
    if sys.version_info >= (3, 0):
        return s

    if sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5:
        # Pass u'' directly to use Unicode APIs on Windows 2000 and up
        # (Detecting Windows NT 4 is tricky because 'major >= 4' would
        # match Windows 9x series as well. Besides, NT 4 is obsolete.)
        if not for_subprocess:
            return s
        else:
            # For subprocess calls, encode with locale encoding
            # Refer to http://stackoverflow.com/a/9951851/35070
            encoding = preferredencoding()
    else:
        encoding = sys.getfilesystemencoding()
    if encoding is None:
        encoding = 'utf-8'
    return s.encode(encoding, 'ignore')


def encodeArgument(s):
    if not isinstance(s, compat_str):
        # Legacy code that uses byte strings
        # Uncomment the following line after fixing all post processors
        #assert False, 'Internal error: %r should be of type %r, is %r' % (s, compat_str, type(s))
        s = s.decode('ascii')
    return encodeFilename(s, True)


def decodeOption(optval):
    if optval is None:
        return optval
    if isinstance(optval, bytes):
        optval = optval.decode(preferredencoding())

    assert isinstance(optval, compat_str)
    return optval

def formatSeconds(secs):
    if secs > 3600:
        return '%d:%02d:%02d' % (secs // 3600, (secs % 3600) // 60, secs % 60)
    elif secs > 60:
        return '%d:%02d' % (secs // 60, secs % 60)
    else:
        return '%d' % secs


def make_HTTPS_handler(opts_no_check_certificate, **kwargs):
    if sys.version_info < (3, 2):
        import httplib

        class HTTPSConnectionV3(httplib.HTTPSConnection):
            def __init__(self, *args, **kwargs):
                httplib.HTTPSConnection.__init__(self, *args, **kwargs)

            def connect(self):
                sock = socket.create_connection((self.host, self.port), self.timeout)
                if getattr(self, '_tunnel_host', False):
                    self.sock = sock
                    self._tunnel()
                try:
                    self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file, ssl_version=ssl.PROTOCOL_TLSv1)
                except ssl.SSLError:
                    self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file, ssl_version=ssl.PROTOCOL_SSLv23)

        class HTTPSHandlerV3(compat_urllib_request.HTTPSHandler):
            def https_open(self, req):
                return self.do_open(HTTPSConnectionV3, req)
        return HTTPSHandlerV3(**kwargs)
    elif hasattr(ssl, 'create_default_context'):  # Python >= 3.4
        context = ssl.create_default_context(ssl.Purpose.CLIENT_AUTH)
        context.options &= ~ssl.OP_NO_SSLv3  # Allow older, not-as-secure SSLv3
        if opts_no_check_certificate:
            context.verify_mode = ssl.CERT_NONE
        return compat_urllib_request.HTTPSHandler(context=context, **kwargs)
    else:  # Python < 3.4
        context = ssl.SSLContext(ssl.PROTOCOL_SSLv23)
        context.verify_mode = (ssl.CERT_NONE
                               if opts_no_check_certificate
                               else ssl.CERT_REQUIRED)
        context.set_default_verify_paths()
        try:
            context.load_default_certs()
        except AttributeError:
            pass  # Python < 3.4
        return compat_urllib_request.HTTPSHandler(context=context, **kwargs)

class ExtractorError(Exception):
    """Error during info extraction."""
    def __init__(self, msg, tb=None, expected=False, cause=None, video_id=None):
        """ tb, if given, is the original traceback (so that it can be printed out).
        If expected is set, this is a normal error message and most likely not a bug in youtube-dl.
        """

        if sys.exc_info()[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError):
            expected = True
        if video_id is not None:
            msg = video_id + ': ' + msg
        if not expected:
            msg = msg + u'; please report this issue on https://yt-dl.org/bug . Be sure to call youtube-dl with the --verbose flag and include its complete output. Make sure you are using the latest version; type  youtube-dl -U  to update.'
        super(ExtractorError, self).__init__(msg)

        self.traceback = tb
        self.exc_info = sys.exc_info()  # preserve original exception
        self.cause = cause
        self.video_id = video_id

    def format_traceback(self):
        if self.traceback is None:
            return None
        return u''.join(traceback.format_tb(self.traceback))


class RegexNotFoundError(ExtractorError):
    """Error when a regex didn't match"""
    pass


class DownloadError(Exception):
    """Download Error exception.

    This exception may be thrown by FileDownloader objects if they are not
    configured to continue on errors. They will contain the appropriate
    error message.
    """
    def __init__(self, msg, exc_info=None):
        """ exc_info, if given, is the original exception that caused the trouble (as returned by sys.exc_info()). """
        super(DownloadError, self).__init__(msg)
        self.exc_info = exc_info


class SameFileError(Exception):
    """Same File exception.

    This exception will be thrown by FileDownloader objects if they detect
    multiple files would have to be downloaded to the same file on disk.
    """
    pass


class PostProcessingError(Exception):
    """Post Processing exception.

    This exception may be raised by PostProcessor's .run() method to
    indicate an error in the postprocessing task.
    """
    def __init__(self, msg):
        self.msg = msg

class MaxDownloadsReached(Exception):
    """ --max-downloads limit has been reached. """
    pass


class UnavailableVideoError(Exception):
    """Unavailable Format exception.

    This exception will be thrown when a video is requested
    in a format that is not available for that video.
    """
    pass


class ContentTooShortError(Exception):
    """Content Too Short exception.

    This exception may be raised by FileDownloader objects when a file they
    download is too small for what the server announced first, indicating
    the connection was probably interrupted.
    """
    # Both in bytes
    downloaded = None
    expected = None

    def __init__(self, downloaded, expected):
        self.downloaded = downloaded
        self.expected = expected

class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
    """Handler for HTTP requests and responses.

    This class, when installed with an OpenerDirector, automatically adds
    the standard headers to every HTTP request and handles gzipped and
    deflated responses from web servers. If compression is to be avoided in
    a particular request, the original request in the program code only has
    to include the HTTP header "Youtubedl-No-Compression", which will be
    removed before making the real request.

    Part of this code was copied from:

    http://techknack.net/python-urllib2-handlers/

    Andrew Rowls, the author of that code, agreed to release it to the
    public domain.
    """

    @staticmethod
    def deflate(data):
        try:
            return zlib.decompress(data, -zlib.MAX_WBITS)
        except zlib.error:
            return zlib.decompress(data)

    @staticmethod
    def addinfourl_wrapper(stream, headers, url, code):
        if hasattr(compat_urllib_request.addinfourl, 'getcode'):
            return compat_urllib_request.addinfourl(stream, headers, url, code)
        ret = compat_urllib_request.addinfourl(stream, headers, url)
        ret.code = code
        return ret

    def http_request(self, req):
        for h, v in std_headers.items():
            if h not in req.headers:
                req.add_header(h, v)
        if 'Youtubedl-no-compression' in req.headers:
            if 'Accept-encoding' in req.headers:
                del req.headers['Accept-encoding']
            del req.headers['Youtubedl-no-compression']
        if 'Youtubedl-user-agent' in req.headers:
            if 'User-agent' in req.headers:
                del req.headers['User-agent']
            req.headers['User-agent'] = req.headers['Youtubedl-user-agent']
            del req.headers['Youtubedl-user-agent']
        return req

    def http_response(self, req, resp):
        old_resp = resp
        # gzip
        if resp.headers.get('Content-encoding', '') == 'gzip':
            content = resp.read()
            gz = gzip.GzipFile(fileobj=io.BytesIO(content), mode='rb')
            try:
                uncompressed = io.BytesIO(gz.read())
            except IOError as original_ioerror:
                # There may be junk add the end of the file
                # See http://stackoverflow.com/q/4928560/35070 for details
                for i in range(1, 1024):
                    try:
                        gz = gzip.GzipFile(fileobj=io.BytesIO(content[:-i]), mode='rb')
                        uncompressed = io.BytesIO(gz.read())
                    except IOError:
                        continue
                    break
                else:
                    raise original_ioerror
            resp = self.addinfourl_wrapper(uncompressed, old_resp.headers, old_resp.url, old_resp.code)
            resp.msg = old_resp.msg
        # deflate
        if resp.headers.get('Content-encoding', '') == 'deflate':
            gz = io.BytesIO(self.deflate(resp.read()))
            resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
            resp.msg = old_resp.msg
        return resp

    https_request = http_request
    https_response = http_response


def parse_iso8601(date_str, delimiter='T'):
    """ Return a UNIX timestamp from the given date """

    if date_str is None:
        return None

    m = re.search(
        r'Z$| ?(?P<sign>\+|-)(?P<hours>[0-9]{2}):?(?P<minutes>[0-9]{2})$',
        date_str)
    if not m:
        timezone = datetime.timedelta()
    else:
        date_str = date_str[:-len(m.group(0))]
        if not m.group('sign'):
            timezone = datetime.timedelta()
        else:
            sign = 1 if m.group('sign') == '+' else -1
            timezone = datetime.timedelta(
                hours=sign * int(m.group('hours')),
                minutes=sign * int(m.group('minutes')))
    date_format =  '%Y-%m-%d{0}%H:%M:%S'.format(delimiter)
    dt = datetime.datetime.strptime(date_str, date_format) - timezone
    return calendar.timegm(dt.timetuple())


def unified_strdate(date_str):
    """Return a string with the date in the format YYYYMMDD"""

    if date_str is None:
        return None

    upload_date = None
    #Replace commas
    date_str = date_str.replace(',', ' ')
    # %z (UTC offset) is only supported in python>=3.2
    date_str = re.sub(r' ?(\+|-)[0-9]{2}:?[0-9]{2}$', '', date_str)
    format_expressions = [
        '%d %B %Y',
        '%d %b %Y',
        '%B %d %Y',
        '%b %d %Y',
        '%b %dst %Y %I:%M%p',
        '%b %dnd %Y %I:%M%p',
        '%b %dth %Y %I:%M%p',
        '%Y-%m-%d',
        '%Y/%m/%d',
        '%d.%m.%Y',
        '%d/%m/%Y',
        '%d/%m/%y',
        '%Y/%m/%d %H:%M:%S',
        '%Y-%m-%d %H:%M:%S',
        '%d.%m.%Y %H:%M',
        '%d.%m.%Y %H.%M',
        '%Y-%m-%dT%H:%M:%SZ',
        '%Y-%m-%dT%H:%M:%S.%fZ',
        '%Y-%m-%dT%H:%M:%S.%f0Z',
        '%Y-%m-%dT%H:%M:%S',
        '%Y-%m-%dT%H:%M:%S.%f',
        '%Y-%m-%dT%H:%M',
    ]
    for expression in format_expressions:
        try:
            upload_date = datetime.datetime.strptime(date_str, expression).strftime('%Y%m%d')
        except ValueError:
            pass
    if upload_date is None:
        timetuple = email.utils.parsedate_tz(date_str)
        if timetuple:
            upload_date = datetime.datetime(*timetuple[:6]).strftime('%Y%m%d')
    return upload_date

def determine_ext(url, default_ext=u'unknown_video'):
    if url is None:
        return default_ext
    guess = url.partition(u'?')[0].rpartition(u'.')[2]
    if re.match(r'^[A-Za-z0-9]+$', guess):
        return guess
    else:
        return default_ext

def subtitles_filename(filename, sub_lang, sub_format):
    return filename.rsplit('.', 1)[0] + u'.' + sub_lang + u'.' + sub_format

def date_from_str(date_str):
    """
    Return a datetime object from a string in the format YYYYMMDD or
    (now|today)[+-][0-9](day|week|month|year)(s)?"""
    today = datetime.date.today()
    if date_str == 'now'or date_str == 'today':
        return today
    match = re.match('(now|today)(?P<sign>[+-])(?P<time>\d+)(?P<unit>day|week|month|year)(s)?', date_str)
    if match is not None:
        sign = match.group('sign')
        time = int(match.group('time'))
        if sign == '-':
            time = -time
        unit = match.group('unit')
        #A bad aproximation?
        if unit == 'month':
            unit = 'day'
            time *= 30
        elif unit == 'year':
            unit = 'day'
            time *= 365
        unit += 's'
        delta = datetime.timedelta(**{unit: time})
        return today + delta
    return datetime.datetime.strptime(date_str, "%Y%m%d").date()
    
def hyphenate_date(date_str):
    """
    Convert a date in 'YYYYMMDD' format to 'YYYY-MM-DD' format"""
    match = re.match(r'^(\d\d\d\d)(\d\d)(\d\d)$', date_str)
    if match is not None:
        return '-'.join(match.groups())
    else:
        return date_str

class DateRange(object):
    """Represents a time interval between two dates"""
    def __init__(self, start=None, end=None):
        """start and end must be strings in the format accepted by date"""
        if start is not None:
            self.start = date_from_str(start)
        else:
            self.start = datetime.datetime.min.date()
        if end is not None:
            self.end = date_from_str(end)
        else:
            self.end = datetime.datetime.max.date()
        if self.start > self.end:
            raise ValueError('Date range: "%s" , the start date must be before the end date' % self)
    @classmethod
    def day(cls, day):
        """Returns a range that only contains the given day"""
        return cls(day,day)
    def __contains__(self, date):
        """Check if the date is in the range"""
        if not isinstance(date, datetime.date):
            date = date_from_str(date)
        return self.start <= date <= self.end
    def __str__(self):
        return '%s - %s' % ( self.start.isoformat(), self.end.isoformat())


def platform_name():
    """ Returns the platform name as a compat_str """
    res = platform.platform()
    if isinstance(res, bytes):
        res = res.decode(preferredencoding())

    assert isinstance(res, compat_str)
    return res


def _windows_write_string(s, out):
    """ Returns True if the string was written using special methods,
    False if it has yet to be written out."""
    # Adapted from http://stackoverflow.com/a/3259271/35070

    import ctypes
    import ctypes.wintypes

    WIN_OUTPUT_IDS = {
        1: -11,
        2: -12,
    }

    try:
        fileno = out.fileno()
    except AttributeError:
        # If the output stream doesn't have a fileno, it's virtual
        return False
    if fileno not in WIN_OUTPUT_IDS:
        return False

    GetStdHandle = ctypes.WINFUNCTYPE(
        ctypes.wintypes.HANDLE, ctypes.wintypes.DWORD)(
        ("GetStdHandle", ctypes.windll.kernel32))
    h = GetStdHandle(WIN_OUTPUT_IDS[fileno])

    WriteConsoleW = ctypes.WINFUNCTYPE(
        ctypes.wintypes.BOOL, ctypes.wintypes.HANDLE, ctypes.wintypes.LPWSTR,
        ctypes.wintypes.DWORD, ctypes.POINTER(ctypes.wintypes.DWORD),
        ctypes.wintypes.LPVOID)(("WriteConsoleW", ctypes.windll.kernel32))
    written = ctypes.wintypes.DWORD(0)

    GetFileType = ctypes.WINFUNCTYPE(ctypes.wintypes.DWORD, ctypes.wintypes.DWORD)(("GetFileType", ctypes.windll.kernel32))
    FILE_TYPE_CHAR = 0x0002
    FILE_TYPE_REMOTE = 0x8000
    GetConsoleMode = ctypes.WINFUNCTYPE(
        ctypes.wintypes.BOOL, ctypes.wintypes.HANDLE,
        ctypes.POINTER(ctypes.wintypes.DWORD))(
        ("GetConsoleMode", ctypes.windll.kernel32))
    INVALID_HANDLE_VALUE = ctypes.wintypes.DWORD(-1).value

    def not_a_console(handle):
        if handle == INVALID_HANDLE_VALUE or handle is None:
            return True
        return ((GetFileType(handle) & ~FILE_TYPE_REMOTE) != FILE_TYPE_CHAR
                or GetConsoleMode(handle, ctypes.byref(ctypes.wintypes.DWORD())) == 0)

    if not_a_console(h):
        return False

    def next_nonbmp_pos(s):
        try:
            return next(i for i, c in enumerate(s) if ord(c) > 0xffff)
        except StopIteration:
            return len(s)

    while s:
        count = min(next_nonbmp_pos(s), 1024)

        ret = WriteConsoleW(
            h, s, count if count else 2, ctypes.byref(written), None)
        if ret == 0:
            raise OSError('Failed to write string')
        if not count:  # We just wrote a non-BMP character
            assert written.value == 2
            s = s[1:]
        else:
            assert written.value > 0
            s = s[written.value:]
    return True


def write_string(s, out=None, encoding=None):
    if out is None:
        out = sys.stderr
    assert type(s) == compat_str

    if sys.platform == 'win32' and encoding is None and hasattr(out, 'fileno'):
        if _windows_write_string(s, out):
            return

    if ('b' in getattr(out, 'mode', '') or
            sys.version_info[0] < 3):  # Python 2 lies about mode of sys.stderr
        byt = s.encode(encoding or preferredencoding(), 'ignore')
        out.write(byt)
    elif hasattr(out, 'buffer'):
        enc = encoding or getattr(out, 'encoding', None) or preferredencoding()
        byt = s.encode(enc, 'ignore')
        out.buffer.write(byt)
    else:
        out.write(s)
    out.flush()


def bytes_to_intlist(bs):
    if not bs:
        return []
    if isinstance(bs[0], int):  # Python 3
        return list(bs)
    else:
        return [ord(c) for c in bs]


def intlist_to_bytes(xs):
    if not xs:
        return b''
    if isinstance(chr(0), bytes):  # Python 2
        return ''.join([chr(x) for x in xs])
    else:
        return bytes(xs)


# Cross-platform file locking
if sys.platform == 'win32':
    import ctypes.wintypes
    import msvcrt

    class OVERLAPPED(ctypes.Structure):
        _fields_ = [
            ('Internal', ctypes.wintypes.LPVOID),
            ('InternalHigh', ctypes.wintypes.LPVOID),
            ('Offset', ctypes.wintypes.DWORD),
            ('OffsetHigh', ctypes.wintypes.DWORD),
            ('hEvent', ctypes.wintypes.HANDLE),
        ]

    kernel32 = ctypes.windll.kernel32
    LockFileEx = kernel32.LockFileEx
    LockFileEx.argtypes = [
        ctypes.wintypes.HANDLE,     # hFile
        ctypes.wintypes.DWORD,      # dwFlags
        ctypes.wintypes.DWORD,      # dwReserved
        ctypes.wintypes.DWORD,      # nNumberOfBytesToLockLow
        ctypes.wintypes.DWORD,      # nNumberOfBytesToLockHigh
        ctypes.POINTER(OVERLAPPED)  # Overlapped
    ]
    LockFileEx.restype = ctypes.wintypes.BOOL
    UnlockFileEx = kernel32.UnlockFileEx
    UnlockFileEx.argtypes = [
        ctypes.wintypes.HANDLE,     # hFile
        ctypes.wintypes.DWORD,      # dwReserved
        ctypes.wintypes.DWORD,      # nNumberOfBytesToLockLow
        ctypes.wintypes.DWORD,      # nNumberOfBytesToLockHigh
        ctypes.POINTER(OVERLAPPED)  # Overlapped
    ]
    UnlockFileEx.restype = ctypes.wintypes.BOOL
    whole_low = 0xffffffff
    whole_high = 0x7fffffff

    def _lock_file(f, exclusive):
        overlapped = OVERLAPPED()
        overlapped.Offset = 0
        overlapped.OffsetHigh = 0
        overlapped.hEvent = 0
        f._lock_file_overlapped_p = ctypes.pointer(overlapped)
        handle = msvcrt.get_osfhandle(f.fileno())
        if not LockFileEx(handle, 0x2 if exclusive else 0x0, 0,
                          whole_low, whole_high, f._lock_file_overlapped_p):
            raise OSError('Locking file failed: %r' % ctypes.FormatError())

    def _unlock_file(f):
        assert f._lock_file_overlapped_p
        handle = msvcrt.get_osfhandle(f.fileno())
        if not UnlockFileEx(handle, 0,
                            whole_low, whole_high, f._lock_file_overlapped_p):
            raise OSError('Unlocking file failed: %r' % ctypes.FormatError())

else:
    import fcntl

    def _lock_file(f, exclusive):
        fcntl.flock(f, fcntl.LOCK_EX if exclusive else fcntl.LOCK_SH)

    def _unlock_file(f):
        fcntl.flock(f, fcntl.LOCK_UN)


class locked_file(object):
    def __init__(self, filename, mode, encoding=None):
        assert mode in ['r', 'a', 'w']
        self.f = io.open(filename, mode, encoding=encoding)
        self.mode = mode

    def __enter__(self):
        exclusive = self.mode != 'r'
        try:
            _lock_file(self.f, exclusive)
        except IOError:
            self.f.close()
            raise
        return self

    def __exit__(self, etype, value, traceback):
        try:
            _unlock_file(self.f)
        finally:
            self.f.close()

    def __iter__(self):
        return iter(self.f)

    def write(self, *args):
        return self.f.write(*args)

    def read(self, *args):
        return self.f.read(*args)


def shell_quote(args):
    quoted_args = []
    encoding = sys.getfilesystemencoding()
    if encoding is None:
        encoding = 'utf-8'
    for a in args:
        if isinstance(a, bytes):
            # We may get a filename encoded with 'encodeFilename'
            a = a.decode(encoding)
        quoted_args.append(pipes.quote(a))
    return u' '.join(quoted_args)


def takewhile_inclusive(pred, seq):
    """ Like itertools.takewhile, but include the latest evaluated element
        (the first element so that Not pred(e)) """
    for e in seq:
        yield e
        if not pred(e):
            return


def smuggle_url(url, data):
    """ Pass additional data in a URL for internal use. """

    sdata = compat_urllib_parse.urlencode(
        {u'__youtubedl_smuggle': json.dumps(data)})
    return url + u'#' + sdata


def unsmuggle_url(smug_url, default=None):
    if not '#__youtubedl_smuggle' in smug_url:
        return smug_url, default
    url, _, sdata = smug_url.rpartition(u'#')
    jsond = compat_parse_qs(sdata)[u'__youtubedl_smuggle'][0]
    data = json.loads(jsond)
    return url, data


def format_bytes(bytes):
    if bytes is None:
        return u'N/A'
    if type(bytes) is str:
        bytes = float(bytes)
    if bytes == 0.0:
        exponent = 0
    else:
        exponent = int(math.log(bytes, 1024.0))
    suffix = [u'B', u'KiB', u'MiB', u'GiB', u'TiB', u'PiB', u'EiB', u'ZiB', u'YiB'][exponent]
    converted = float(bytes) / float(1024 ** exponent)
    return u'%.2f%s' % (converted, suffix)


def get_term_width():
    columns = os.environ.get('COLUMNS', None)
    if columns:
        return int(columns)

    try:
        sp = subprocess.Popen(
            ['stty', 'size'],
            stdout=subprocess.PIPE, stderr=subprocess.PIPE)
        out, err = sp.communicate()
        return int(out.split()[1])
    except:
        pass
    return None


def month_by_name(name):
    """ Return the number of a month by (locale-independently) English name """

    ENGLISH_NAMES = [
        u'January', u'February', u'March', u'April', u'May', u'June',
        u'July', u'August', u'September', u'October', u'November', u'December']
    try:
        return ENGLISH_NAMES.index(name) + 1
    except ValueError:
        return None


def fix_xml_ampersands(xml_str):
    """Replace all the '&' by '&amp;' in XML"""
    return re.sub(
        r'&(?!amp;|lt;|gt;|apos;|quot;|#x[0-9a-fA-F]{,4};|#[0-9]{,4};)',
        u'&amp;',
        xml_str)


def setproctitle(title):
    assert isinstance(title, compat_str)
    try:
        libc = ctypes.cdll.LoadLibrary("libc.so.6")
    except OSError:
        return
    title_bytes = title.encode('utf-8')
    buf = ctypes.create_string_buffer(len(title_bytes))
    buf.value = title_bytes
    try:
        libc.prctl(15, buf, 0, 0, 0)
    except AttributeError:
        return  # Strange libc, just skip this


def remove_start(s, start):
    if s.startswith(start):
        return s[len(start):]
    return s


def remove_end(s, end):
    if s.endswith(end):
        return s[:-len(end)]
    return s


def url_basename(url):
    path = compat_urlparse.urlparse(url).path
    return path.strip(u'/').split(u'/')[-1]


class HEADRequest(compat_urllib_request.Request):
    def get_method(self):
        return "HEAD"


def int_or_none(v, scale=1, default=None, get_attr=None, invscale=1):
    if get_attr:
        if v is not None:
            v = getattr(v, get_attr, None)
    if v == '':
        v = None
    return default if v is None else (int(v) * invscale // scale)


def str_or_none(v, default=None):
    return default if v is None else compat_str(v)


def str_to_int(int_str):
    """ A more relaxed version of int_or_none """
    if int_str is None:
        return None
    int_str = re.sub(r'[,\.\+]', u'', int_str)
    return int(int_str)


def float_or_none(v, scale=1, invscale=1, default=None):
    return default if v is None else (float(v) * invscale / scale)


def parse_duration(s):
    if s is None:
        return None

    s = s.strip()

    m = re.match(
        r'(?i)(?:(?:(?P<hours>[0-9]+)\s*(?:[:h]|hours?)\s*)?(?P<mins>[0-9]+)\s*(?:[:m]|mins?|minutes?)\s*)?(?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?\s*(?:s|secs?|seconds?)?$', s)
    if not m:
        return None
    res = int(m.group('secs'))
    if m.group('mins'):
        res += int(m.group('mins')) * 60
        if m.group('hours'):
            res += int(m.group('hours')) * 60 * 60
    if m.group('ms'):
        res += float(m.group('ms'))
    return res


def prepend_extension(filename, ext):
    name, real_ext = os.path.splitext(filename) 
    return u'{0}.{1}{2}'.format(name, ext, real_ext)


def check_executable(exe, args=[]):
    """ Checks if the given binary is installed somewhere in PATH, and returns its name.
    args can be a list of arguments for a short output (like -version) """
    try:
        subprocess.Popen([exe] + args, stdout=subprocess.PIPE, stderr=subprocess.PIPE).communicate()
    except OSError:
        return False
    return exe


class PagedList(object):
    def __init__(self, pagefunc, pagesize):
        self._pagefunc = pagefunc
        self._pagesize = pagesize

    def __len__(self):
        # This is only useful for tests
        return len(self.getslice())

    def getslice(self, start=0, end=None):
        res = []
        for pagenum in itertools.count(start // self._pagesize):
            firstid = pagenum * self._pagesize
            nextfirstid = pagenum * self._pagesize + self._pagesize
            if start >= nextfirstid:
                continue

            page_results = list(self._pagefunc(pagenum))

            startv = (
                start % self._pagesize
                if firstid <= start < nextfirstid
                else 0)

            endv = (
                ((end - 1) % self._pagesize) + 1
                if (end is not None and firstid <= end <= nextfirstid)
                else None)

            if startv != 0 or endv is not None:
                page_results = page_results[startv:endv]
            res.extend(page_results)

            # A little optimization - if current page is not "full", ie. does
            # not contain page_size videos then we can assume that this page
            # is the last one - there are no more ids on further pages -
            # i.e. no need to query again.
            if len(page_results) + startv < self._pagesize:
                break

            # If we got the whole page, but the next page is not interesting,
            # break out early as well
            if end == nextfirstid:
                break
        return res


def uppercase_escape(s):
    unicode_escape = codecs.getdecoder('unicode_escape')
    return re.sub(
        r'\\U[0-9a-fA-F]{8}',
        lambda m: unicode_escape(m.group(0))[0],
        s)


def escape_rfc3986(s):
    """Escape non-ASCII characters as suggested by RFC 3986"""
    if sys.version_info < (3, 0) and isinstance(s, unicode):
        s = s.encode('utf-8')
    return compat_urllib_parse.quote(s, "%/;:@&=+$,!~*'()?#[]") #"%/;:@&=+$,!~*'()?#[]+"   #?#[]+


def escape_url(url):
    """Escape URL as suggested by RFC 3986"""
    url_parsed = compat_urllib_parse_urlparse(url)
    return url_parsed._replace(
        path=escape_rfc3986(url_parsed.path),
        params=escape_rfc3986(url_parsed.params),
        query=escape_rfc3986(url_parsed.query),
        fragment=escape_rfc3986(url_parsed.fragment)
    ).geturl()

try:
    struct.pack(u'!I', 0)
except TypeError:
    # In Python 2.6 (and some 2.7 versions), struct requires a bytes argument
    def struct_pack(spec, *args):
        if isinstance(spec, compat_str):
            spec = spec.encode('ascii')
        return struct.pack(spec, *args)

    def struct_unpack(spec, *args):
        if isinstance(spec, compat_str):
            spec = spec.encode('ascii')
        return struct.unpack(spec, *args)
else:
    struct_pack = struct.pack
    struct_unpack = struct.unpack


def read_batch_urls(batch_fd):
    def fixup(url):
        if not isinstance(url, compat_str):
            url = url.decode('utf-8', 'replace')
        BOM_UTF8 = u'\xef\xbb\xbf'
        if url.startswith(BOM_UTF8):
            url = url[len(BOM_UTF8):]
        url = url.strip()
        if url.startswith(('#', ';', ']')):
            return False
        return url

    with contextlib.closing(batch_fd) as fd:
        return [url for url in map(fixup, fd) if url]


def urlencode_postdata(*args, **kargs):
    return compat_urllib_parse.urlencode(*args, **kargs).encode('ascii')


try:
    etree_iter = xml.etree.ElementTree.Element.iter
except AttributeError:  # Python <=2.6
    etree_iter = lambda n: n.findall('.//*')


def parse_xml(s):
    class TreeBuilder(xml.etree.ElementTree.TreeBuilder):
        def doctype(self, name, pubid, system):
            pass  # Ignore doctypes

    parser = xml.etree.ElementTree.XMLParser(target=TreeBuilder())
    kwargs = {'parser': parser} if sys.version_info >= (2, 7) else {}
    tree = xml.etree.ElementTree.XML(s.encode('utf-8'), **kwargs)
    # Fix up XML parser in Python 2.x
    if sys.version_info < (3, 0):
        for n in etree_iter(tree):
            if n.text is not None:
                if not isinstance(n.text, compat_str):
                    n.text = n.text.decode('utf-8')
    return tree


if sys.version_info < (3, 0) and sys.platform == 'win32':
    def compat_getpass(prompt, *args, **kwargs):
        if isinstance(prompt, compat_str):
            prompt = prompt.encode(preferredencoding())
        return getpass.getpass(prompt, *args, **kwargs)
else:
    compat_getpass = getpass.getpass


US_RATINGS = {
    'G': 0,
    'PG': 10,
    'PG-13': 13,
    'R': 16,
    'NC': 18,
}


def strip_jsonp(code):
    return re.sub(r'(?s)^[a-zA-Z0-9_]+\s*\(\s*(.*)\);?\s*?\s*$', r'\1', code)


def js_to_json(code):
    def fix_kv(m):
        key = m.group(2)
        if key.startswith("'"):
            assert key.endswith("'")
            assert '"' not in key
            key = '"%s"' % key[1:-1]
        elif not key.startswith('"'):
            key = '"%s"' % key

        value = m.group(4)
        if value.startswith("'"):
            assert value.endswith("'")
            assert '"' not in value
            value = '"%s"' % value[1:-1]

        return m.group(1) + key + m.group(3) + value

    res = re.sub(r'''(?x)
            ([{,]\s*)
            ("[^"]*"|\'[^\']*\'|[a-z0-9A-Z]+)
            (:\s*)
            ([0-9.]+|true|false|"[^"]*"|\'[^\']*\'|\[|\{)
        ''', fix_kv, code)
    res = re.sub(r',(\s*\])', lambda m: m.group(1), res)
    return res


def qualities(quality_ids):
    """ Get a numeric quality value out of a list of possible values """
    def q(qid):
        try:
            return quality_ids.index(qid)
        except ValueError:
            return -1
    return q


DEFAULT_OUTTMPL = '%(title)s-%(id)s.%(ext)s'

try:
    subprocess_check_output = subprocess.check_output
except AttributeError:
    def subprocess_check_output(*args, **kwargs):
        assert 'input' not in kwargs
        p = subprocess.Popen(*args, stdout=subprocess.PIPE, **kwargs)
        output, _ = p.communicate()
        ret = p.poll()
        if ret:
            raise subprocess.CalledProcessError(ret, p.args, output=output)
        return output