1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
|
# coding: utf-8
from __future__ import unicode_literals
import itertools
import json
import os.path
import re
import time
import traceback
from .common import InfoExtractor, SearchInfoExtractor
from ..jsinterp import JSInterpreter
from ..swfinterp import SWFInterpreter
from ..compat import (
compat_chr,
compat_parse_qs,
compat_urllib_parse,
compat_urllib_request,
compat_urlparse,
compat_str,
)
from ..utils import (
clean_html,
ExtractorError,
float_or_none,
get_element_by_attribute,
get_element_by_id,
int_or_none,
OnDemandPagedList,
orderedSet,
unescapeHTML,
unified_strdate,
uppercase_escape,
)
class YoutubeBaseInfoExtractor(InfoExtractor):
"""Provide base functions for Youtube extractors"""
_LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
_TWOFACTOR_URL = 'https://accounts.google.com/SecondFactor'
_NETRC_MACHINE = 'youtube'
# If True it will raise an error if no login info is provided
_LOGIN_REQUIRED = False
def _set_language(self):
self._set_cookie(
'.youtube.com', 'PREF', 'f1=50000000&hl=en',
# YouTube sets the expire time to about two months
expire_time=time.time() + 2 * 30 * 24 * 3600)
def _login(self):
"""
Attempt to log in to YouTube.
True is returned if successful or skipped.
False is returned if login failed.
If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
"""
(username, password) = self._get_login_info()
# No authentication to be performed
if username is None:
if self._LOGIN_REQUIRED:
raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
return True
login_page = self._download_webpage(
self._LOGIN_URL, None,
note='Downloading login page',
errnote='unable to fetch login page', fatal=False)
if login_page is False:
return
galx = self._search_regex(r'(?s)<input.+?name="GALX".+?value="(.+?)"',
login_page, 'Login GALX parameter')
# Log in
login_form_strs = {
'continue': 'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1',
'Email': username,
'GALX': galx,
'Passwd': password,
'PersistentCookie': 'yes',
'_utf8': '霱',
'bgresponse': 'js_disabled',
'checkConnection': '',
'checkedDomains': 'youtube',
'dnConn': '',
'pstMsg': '0',
'rmShown': '1',
'secTok': '',
'signIn': 'Sign in',
'timeStmp': '',
'service': 'youtube',
'uilel': '3',
'hl': 'en_US',
}
# Convert to UTF-8 *before* urlencode because Python 2.x's urlencode
# chokes on unicode
login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in login_form_strs.items())
login_data = compat_urllib_parse.urlencode(login_form).encode('ascii')
req = compat_urllib_request.Request(self._LOGIN_URL, login_data)
login_results = self._download_webpage(
req, None,
note='Logging in', errnote='unable to log in', fatal=False)
if login_results is False:
return False
if re.search(r'id="errormsg_0_Passwd"', login_results) is not None:
raise ExtractorError('Please use your account password and a two-factor code instead of an application-specific password.', expected=True)
# Two-Factor
# TODO add SMS and phone call support - these require making a request and then prompting the user
if re.search(r'(?i)<form[^>]* id="gaia_secondfactorform"', login_results) is not None:
tfa_code = self._get_tfa_info()
if tfa_code is None:
self._downloader.report_warning('Two-factor authentication required. Provide it with --twofactor <code>')
self._downloader.report_warning('(Note that only TOTP (Google Authenticator App) codes work at this time.)')
return False
# Unlike the first login form, secTok and timeStmp are both required for the TFA form
match = re.search(r'id="secTok"\n\s+value=\'(.+)\'/>', login_results, re.M | re.U)
if match is None:
self._downloader.report_warning('Failed to get secTok - did the page structure change?')
secTok = match.group(1)
match = re.search(r'id="timeStmp"\n\s+value=\'(.+)\'/>', login_results, re.M | re.U)
if match is None:
self._downloader.report_warning('Failed to get timeStmp - did the page structure change?')
timeStmp = match.group(1)
tfa_form_strs = {
'continue': 'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1',
'smsToken': '',
'smsUserPin': tfa_code,
'smsVerifyPin': 'Verify',
'PersistentCookie': 'yes',
'checkConnection': '',
'checkedDomains': 'youtube',
'pstMsg': '1',
'secTok': secTok,
'timeStmp': timeStmp,
'service': 'youtube',
'hl': 'en_US',
}
tfa_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in tfa_form_strs.items())
tfa_data = compat_urllib_parse.urlencode(tfa_form).encode('ascii')
tfa_req = compat_urllib_request.Request(self._TWOFACTOR_URL, tfa_data)
tfa_results = self._download_webpage(
tfa_req, None,
note='Submitting TFA code', errnote='unable to submit tfa', fatal=False)
if tfa_results is False:
return False
if re.search(r'(?i)<form[^>]* id="gaia_secondfactorform"', tfa_results) is not None:
self._downloader.report_warning('Two-factor code expired. Please try again, or use a one-use backup code instead.')
return False
if re.search(r'(?i)<form[^>]* id="gaia_loginform"', tfa_results) is not None:
self._downloader.report_warning('unable to log in - did the page structure change?')
return False
if re.search(r'smsauth-interstitial-reviewsettings', tfa_results) is not None:
self._downloader.report_warning('Your Google account has a security notice. Please log in on your web browser, resolve the notice, and try again.')
return False
if re.search(r'(?i)<form[^>]* id="gaia_loginform"', login_results) is not None:
self._downloader.report_warning('unable to log in: bad username or password')
return False
return True
def _real_initialize(self):
if self._downloader is None:
return
self._set_language()
if not self._login():
return
class YoutubeIE(YoutubeBaseInfoExtractor):
IE_DESC = 'YouTube.com'
_VALID_URL = r"""(?x)^
(
(?:https?://|//) # http(s):// or protocol-independent URL
(?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
(?:www\.)?deturl\.com/www\.youtube\.com/|
(?:www\.)?pwnyoutube\.com/|
(?:www\.)?yourepeat\.com/|
tube\.majestyc\.net/|
youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
(?:.*?\#/)? # handle anchor (#/) redirect urls
(?: # the various things that can precede the ID:
(?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
|(?: # or the v= param in all its forms
(?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
(?:\?|\#!?) # the params delimiter ? or # or #!
(?:.*?&)? # any other preceding param (like /?s=tuff&v=xxxx)
v=
)
))
|youtu\.be/ # just youtu.be/xxxx
|(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
)
)? # all until now is optional -> you can pass the naked ID
([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
(?!.*?&list=) # combined list/video URLs are handled by the playlist IE
(?(1).+)? # if we found the ID, everything can follow
$"""
_NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
_formats = {
'5': {'ext': 'flv', 'width': 400, 'height': 240},
'6': {'ext': 'flv', 'width': 450, 'height': 270},
'13': {'ext': '3gp'},
'17': {'ext': '3gp', 'width': 176, 'height': 144},
'18': {'ext': 'mp4', 'width': 640, 'height': 360},
'22': {'ext': 'mp4', 'width': 1280, 'height': 720},
'34': {'ext': 'flv', 'width': 640, 'height': 360},
'35': {'ext': 'flv', 'width': 854, 'height': 480},
'36': {'ext': '3gp', 'width': 320, 'height': 240},
'37': {'ext': 'mp4', 'width': 1920, 'height': 1080},
'38': {'ext': 'mp4', 'width': 4096, 'height': 3072},
'43': {'ext': 'webm', 'width': 640, 'height': 360},
'44': {'ext': 'webm', 'width': 854, 'height': 480},
'45': {'ext': 'webm', 'width': 1280, 'height': 720},
'46': {'ext': 'webm', 'width': 1920, 'height': 1080},
# 3d videos
'82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'preference': -20},
'83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'preference': -20},
'84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'preference': -20},
'85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'preference': -20},
'100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'preference': -20},
'101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'preference': -20},
'102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'preference': -20},
# Apple HTTP Live Streaming
'92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'preference': -10},
'93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'preference': -10},
'94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'preference': -10},
'95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'preference': -10},
'96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'preference': -10},
'132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'preference': -10},
'151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'preference': -10},
# DASH mp4 video
'133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
'134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
'135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
'136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
'137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
'138': {'ext': 'mp4', 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, # Height can vary (https://github.com/rg3/youtube-dl/issues/4559)
'160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
'264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
'298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'h264'},
'299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'h264'},
'266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'vcodec': 'h264'},
# Dash mp4 audio
'139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 48, 'preference': -50, 'container': 'm4a_dash'},
'140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 128, 'preference': -50, 'container': 'm4a_dash'},
'141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 256, 'preference': -50, 'container': 'm4a_dash'},
# Dash webm
'167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40},
'168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40},
'169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40},
'170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40},
'218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40},
'219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40},
'278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'container': 'webm', 'vcodec': 'VP9'},
'242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
'243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
'244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
'245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
'246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
'247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
'248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
'271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
'272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
'302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'},
'303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'},
'308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'},
'313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'vcodec': 'VP9'},
'315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'},
# Dash webm audio
'171': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 128, 'preference': -50},
'172': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 256, 'preference': -50},
# Dash webm audio with opus inside
'249': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50, 'preference': -50},
'250': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70, 'preference': -50},
'251': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160, 'preference': -50},
# RTMP (unnamed)
'_rtmp': {'protocol': 'rtmp'},
}
IE_NAME = 'youtube'
_TESTS = [
{
'url': 'http://www.youtube.com/watch?v=BaW_jenozKc',
'info_dict': {
'id': 'BaW_jenozKc',
'ext': 'mp4',
'title': 'youtube-dl test video "\'/\\ä↭𝕐',
'uploader': 'Philipp Hagemeister',
'uploader_id': 'phihag',
'upload_date': '20121002',
'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .',
'categories': ['Science & Technology'],
'like_count': int,
'dislike_count': int,
}
},
{
'url': 'http://www.youtube.com/watch?v=UxxajLWwzqY',
'note': 'Test generic use_cipher_signature video (#897)',
'info_dict': {
'id': 'UxxajLWwzqY',
'ext': 'mp4',
'upload_date': '20120506',
'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
'description': 'md5:fea86fda2d5a5784273df5c7cc994d9f',
'uploader': 'Icona Pop',
'uploader_id': 'IconaPop',
}
},
{
'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ',
'note': 'Test VEVO video with age protection (#956)',
'info_dict': {
'id': '07FYdnEawAQ',
'ext': 'mp4',
'upload_date': '20130703',
'title': 'Justin Timberlake - Tunnel Vision (Explicit)',
'description': 'md5:64249768eec3bc4276236606ea996373',
'uploader': 'justintimberlakeVEVO',
'uploader_id': 'justintimberlakeVEVO',
}
},
{
'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
'note': 'Embed-only video (#1746)',
'info_dict': {
'id': 'yZIXLfi8CZQ',
'ext': 'mp4',
'upload_date': '20120608',
'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
'uploader': 'SET India',
'uploader_id': 'setindia'
}
},
{
'url': 'http://www.youtube.com/watch?v=a9LDPn-MO4I',
'note': '256k DASH audio (format 141) via DASH manifest',
'info_dict': {
'id': 'a9LDPn-MO4I',
'ext': 'm4a',
'upload_date': '20121002',
'uploader_id': '8KVIDEO',
'description': '',
'uploader': '8KVIDEO',
'title': 'UHDTV TEST 8K VIDEO.mp4'
},
'params': {
'youtube_include_dash_manifest': True,
'format': '141',
},
},
# DASH manifest with encrypted signature
{
'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
'info_dict': {
'id': 'IB3lcPjvWLA',
'ext': 'm4a',
'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson',
'description': 'md5:12e7067fa6735a77bdcbb58cb1187d2d',
'uploader': 'AfrojackVEVO',
'uploader_id': 'AfrojackVEVO',
'upload_date': '20131011',
},
'params': {
'youtube_include_dash_manifest': True,
'format': '141',
},
},
# JS player signature function name containing $
{
'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM',
'info_dict': {
'id': 'nfWlot6h_JM',
'ext': 'm4a',
'title': 'Taylor Swift - Shake It Off',
'description': 'md5:2acfda1b285bdd478ccec22f9918199d',
'uploader': 'TaylorSwiftVEVO',
'uploader_id': 'TaylorSwiftVEVO',
'upload_date': '20140818',
},
'params': {
'youtube_include_dash_manifest': True,
'format': '141',
},
},
# Controversy video
{
'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
'info_dict': {
'id': 'T4XJQO3qol8',
'ext': 'mp4',
'upload_date': '20100909',
'uploader': 'The Amazing Atheist',
'uploader_id': 'TheAmazingAtheist',
'title': 'Burning Everyone\'s Koran',
'description': 'SUBSCRIBE: http://www.youtube.com/saturninefilms\n\nEven Obama has taken a stand against freedom on this issue: http://www.huffingtonpost.com/2010/09/09/obama-gma-interview-quran_n_710282.html',
}
},
# Normal age-gate video (No vevo, embed allowed)
{
'url': 'http://youtube.com/watch?v=HtVdAasjOgU',
'info_dict': {
'id': 'HtVdAasjOgU',
'ext': 'mp4',
'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
'description': 're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
'uploader': 'The Witcher',
'uploader_id': 'WitcherGame',
'upload_date': '20140605',
},
},
# Age-gate video with encrypted signature
{
'url': 'http://www.youtube.com/watch?v=6kLq3WMV1nU',
'info_dict': {
'id': '6kLq3WMV1nU',
'ext': 'mp4',
'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
'uploader': 'LloydVEVO',
'uploader_id': 'LloydVEVO',
'upload_date': '20110629',
},
},
# video_info is None (https://github.com/rg3/youtube-dl/issues/4421)
{
'url': '__2ABJjxzNo',
'info_dict': {
'id': '__2ABJjxzNo',
'ext': 'mp4',
'upload_date': '20100430',
'uploader_id': 'deadmau5',
'description': 'md5:12c56784b8032162bb936a5f76d55360',
'uploader': 'deadmau5',
'title': 'Deadmau5 - Some Chords (HD)',
},
'expected_warnings': [
'DASH manifest missing',
]
},
# Olympics (https://github.com/rg3/youtube-dl/issues/4431)
{
'url': 'lqQg6PlCWgI',
'info_dict': {
'id': 'lqQg6PlCWgI',
'ext': 'mp4',
'upload_date': '20120731',
'uploader_id': 'olympic',
'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
'uploader': 'Olympics',
'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
},
'params': {
'skip_download': 'requires avconv',
}
},
# Non-square pixels
{
'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
'info_dict': {
'id': '_b-2C3KPAM0',
'ext': 'mp4',
'stretched_ratio': 16 / 9.,
'upload_date': '20110310',
'uploader_id': 'AllenMeow',
'description': 'made by Wacom from Korea | 字幕&加油添醋 by TY\'s Allen | 感謝heylisa00cavey1001同學熱情提供梗及翻譯',
'uploader': '孫艾倫',
'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
},
},
# url_encoded_fmt_stream_map is empty string
{
'url': 'qEJwOuvDf7I',
'info_dict': {
'id': 'qEJwOuvDf7I',
'ext': 'mp4',
'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
'description': '',
'upload_date': '20150404',
'uploader_id': 'spbelect',
'uploader': 'Наблюдатели Петербурга',
},
'params': {
'skip_download': 'requires avconv',
}
},
]
def __init__(self, *args, **kwargs):
super(YoutubeIE, self).__init__(*args, **kwargs)
self._player_cache = {}
def report_video_info_webpage_download(self, video_id):
"""Report attempt to download video info webpage."""
self.to_screen('%s: Downloading video info webpage' % video_id)
def report_information_extraction(self, video_id):
"""Report attempt to extract video information."""
self.to_screen('%s: Extracting video information' % video_id)
def report_unavailable_format(self, video_id, format):
"""Report extracted video URL."""
self.to_screen('%s: Format %s not available' % (video_id, format))
def report_rtmp_download(self):
"""Indicate the download will use the RTMP protocol."""
self.to_screen('RTMP download detected')
def _signature_cache_id(self, example_sig):
""" Return a string representation of a signature """
return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
def _extract_signature_function(self, video_id, player_url, example_sig):
id_m = re.match(
r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player)?\.(?P<ext>[a-z]+)$',
player_url)
if not id_m:
raise ExtractorError('Cannot identify player %r' % player_url)
player_type = id_m.group('ext')
player_id = id_m.group('id')
# Read from filesystem cache
func_id = '%s_%s_%s' % (
player_type, player_id, self._signature_cache_id(example_sig))
assert os.path.basename(func_id) == func_id
cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
if cache_spec is not None:
return lambda s: ''.join(s[i] for i in cache_spec)
download_note = (
'Downloading player %s' % player_url
if self._downloader.params.get('verbose') else
'Downloading %s player %s' % (player_type, player_id)
)
if player_type == 'js':
code = self._download_webpage(
player_url, video_id,
note=download_note,
errnote='Download of %s failed' % player_url)
res = self._parse_sig_js(code)
elif player_type == 'swf':
urlh = self._request_webpage(
player_url, video_id,
note=download_note,
errnote='Download of %s failed' % player_url)
code = urlh.read()
res = self._parse_sig_swf(code)
else:
assert False, 'Invalid player type %r' % player_type
test_string = ''.join(map(compat_chr, range(len(example_sig))))
cache_res = res(test_string)
cache_spec = [ord(c) for c in cache_res]
self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
return res
def _print_sig_code(self, func, example_sig):
def gen_sig_code(idxs):
def _genslice(start, end, step):
starts = '' if start == 0 else str(start)
ends = (':%d' % (end + step)) if end + step >= 0 else ':'
steps = '' if step == 1 else (':%d' % step)
return 's[%s%s%s]' % (starts, ends, steps)
step = None
# Quelch pyflakes warnings - start will be set when step is set
start = '(Never used)'
for i, prev in zip(idxs[1:], idxs[:-1]):
if step is not None:
if i - prev == step:
continue
yield _genslice(start, prev, step)
step = None
continue
if i - prev in [-1, 1]:
step = i - prev
start = prev
continue
else:
yield 's[%d]' % prev
if step is None:
yield 's[%d]' % i
else:
yield _genslice(start, i, step)
test_string = ''.join(map(compat_chr, range(len(example_sig))))
cache_res = func(test_string)
cache_spec = [ord(c) for c in cache_res]
expr_code = ' + '.join(gen_sig_code(cache_spec))
signature_id_tuple = '(%s)' % (
', '.join(compat_str(len(p)) for p in example_sig.split('.')))
code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
' return %s\n') % (signature_id_tuple, expr_code)
self.to_screen('Extracted signature function:\n' + code)
def _parse_sig_js(self, jscode):
funcname = self._search_regex(
r'\.sig\|\|([a-zA-Z0-9$]+)\(', jscode,
'Initial JS player signature function name')
jsi = JSInterpreter(jscode)
initial_function = jsi.extract_function(funcname)
return lambda s: initial_function([s])
def _parse_sig_swf(self, file_contents):
swfi = SWFInterpreter(file_contents)
TARGET_CLASSNAME = 'SignatureDecipher'
searched_class = swfi.extract_class(TARGET_CLASSNAME)
initial_function = swfi.extract_function(searched_class, 'decipher')
return lambda s: initial_function([s])
def _decrypt_signature(self, s, video_id, player_url, age_gate=False):
"""Turn the encrypted s field into a working signature"""
if player_url is None:
raise ExtractorError('Cannot decrypt signature without player_url')
if player_url.startswith('//'):
player_url = 'https:' + player_url
try:
player_id = (player_url, self._signature_cache_id(s))
if player_id not in self._player_cache:
func = self._extract_signature_function(
video_id, player_url, s
)
self._player_cache[player_id] = func
func = self._player_cache[player_id]
if self._downloader.params.get('youtube_print_sig_code'):
self._print_sig_code(func, s)
return func(s)
except Exception as e:
tb = traceback.format_exc()
raise ExtractorError(
'Signature extraction failed: ' + tb, cause=e)
def _get_subtitles(self, video_id, webpage):
try:
subs_doc = self._download_xml(
'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id,
video_id, note=False)
except ExtractorError as err:
self._downloader.report_warning('unable to download video subtitles: %s' % compat_str(err))
return {}
sub_lang_list = {}
for track in subs_doc.findall('track'):
lang = track.attrib['lang_code']
if lang in sub_lang_list:
continue
sub_formats = []
for ext in ['sbv', 'vtt', 'srt']:
params = compat_urllib_parse.urlencode({
'lang': lang,
'v': video_id,
'fmt': ext,
'name': track.attrib['name'].encode('utf-8'),
})
sub_formats.append({
'url': 'https://www.youtube.com/api/timedtext?' + params,
'ext': ext,
})
sub_lang_list[lang] = sub_formats
if not sub_lang_list:
self._downloader.report_warning('video doesn\'t have subtitles')
return {}
return sub_lang_list
def _get_automatic_captions(self, video_id, webpage):
"""We need the webpage for getting the captions url, pass it as an
argument to speed up the process."""
self.to_screen('%s: Looking for automatic captions' % video_id)
mobj = re.search(r';ytplayer.config = ({.*?});', webpage)
err_msg = 'Couldn\'t find automatic captions for %s' % video_id
if mobj is None:
self._downloader.report_warning(err_msg)
return {}
player_config = json.loads(mobj.group(1))
try:
args = player_config['args']
caption_url = args['ttsurl']
timestamp = args['timestamp']
# We get the available subtitles
list_params = compat_urllib_parse.urlencode({
'type': 'list',
'tlangs': 1,
'asrs': 1,
})
list_url = caption_url + '&' + list_params
caption_list = self._download_xml(list_url, video_id)
original_lang_node = caption_list.find('track')
if original_lang_node is None:
self._downloader.report_warning('Video doesn\'t have automatic captions')
return {}
original_lang = original_lang_node.attrib['lang_code']
caption_kind = original_lang_node.attrib.get('kind', '')
sub_lang_list = {}
for lang_node in caption_list.findall('target'):
sub_lang = lang_node.attrib['lang_code']
sub_formats = []
for ext in ['sbv', 'vtt', 'srt']:
params = compat_urllib_parse.urlencode({
'lang': original_lang,
'tlang': sub_lang,
'fmt': ext,
'ts': timestamp,
'kind': caption_kind,
})
sub_formats.append({
'url': caption_url + '&' + params,
'ext': ext,
})
sub_lang_list[sub_lang] = sub_formats
return sub_lang_list
# An extractor error can be raise by the download process if there are
# no automatic captions but there are subtitles
except (KeyError, ExtractorError):
self._downloader.report_warning(err_msg)
return {}
@classmethod
def extract_id(cls, url):
mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
if mobj is None:
raise ExtractorError('Invalid URL: %s' % url)
video_id = mobj.group(2)
return video_id
def _extract_from_m3u8(self, manifest_url, video_id):
url_map = {}
def _get_urls(_manifest):
lines = _manifest.split('\n')
urls = filter(lambda l: l and not l.startswith('#'),
lines)
return urls
manifest = self._download_webpage(manifest_url, video_id, 'Downloading formats manifest')
formats_urls = _get_urls(manifest)
for format_url in formats_urls:
itag = self._search_regex(r'itag/(\d+?)/', format_url, 'itag')
url_map[itag] = format_url
return url_map
def _extract_annotations(self, video_id):
url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.')
def _parse_dash_manifest(
self, video_id, dash_manifest_url, player_url, age_gate):
def decrypt_sig(mobj):
s = mobj.group(1)
dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
return '/signature/%s' % dec_s
dash_manifest_url = re.sub(r'/s/([\w\.]+)', decrypt_sig, dash_manifest_url)
dash_doc = self._download_xml(
dash_manifest_url, video_id,
note='Downloading DASH manifest',
errnote='Could not download DASH manifest')
formats = []
for a in dash_doc.findall('.//{urn:mpeg:DASH:schema:MPD:2011}AdaptationSet'):
mime_type = a.attrib.get('mimeType')
for r in a.findall('{urn:mpeg:DASH:schema:MPD:2011}Representation'):
url_el = r.find('{urn:mpeg:DASH:schema:MPD:2011}BaseURL')
if url_el is None:
continue
if mime_type == 'text/vtt':
# TODO implement WebVTT downloading
pass
elif mime_type.startswith('audio/') or mime_type.startswith('video/'):
format_id = r.attrib['id']
video_url = url_el.text
filesize = int_or_none(url_el.attrib.get('{http://youtube.com/yt/2012/10/10}contentLength'))
f = {
'format_id': format_id,
'url': video_url,
'width': int_or_none(r.attrib.get('width')),
'height': int_or_none(r.attrib.get('height')),
'tbr': int_or_none(r.attrib.get('bandwidth'), 1000),
'asr': int_or_none(r.attrib.get('audioSamplingRate')),
'filesize': filesize,
'fps': int_or_none(r.attrib.get('frameRate')),
}
try:
existing_format = next(
fo for fo in formats
if fo['format_id'] == format_id)
except StopIteration:
full_info = self._formats.get(format_id, {}).copy()
full_info.update(f)
formats.append(full_info)
else:
existing_format.update(f)
else:
self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type)
return formats
def _real_extract(self, url):
proto = (
'http' if self._downloader.params.get('prefer_insecure', False)
else 'https')
# Extract original video URL from URL with redirection, like age verification, using next_url parameter
mobj = re.search(self._NEXT_URL_RE, url)
if mobj:
url = proto + '://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/')
video_id = self.extract_id(url)
# Get video webpage
url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id
video_webpage = self._download_webpage(url, video_id)
# Attempt to extract SWF player URL
mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
if mobj is not None:
player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
else:
player_url = None
# Get video info
embed_webpage = None
if re.search(r'player-age-gate-content">', video_webpage) is not None:
age_gate = True
# We simulate the access to the video from www.youtube.com/v/{video_id}
# this can be viewed without login into Youtube
url = proto + '://www.youtube.com/embed/%s' % video_id
embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage')
data = compat_urllib_parse.urlencode({
'video_id': video_id,
'eurl': 'https://youtube.googleapis.com/v/' + video_id,
'sts': self._search_regex(
r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''),
})
video_info_url = proto + '://www.youtube.com/get_video_info?' + data
video_info_webpage = self._download_webpage(
video_info_url, video_id,
note='Refetching age-gated info webpage',
errnote='unable to download video info webpage')
video_info = compat_parse_qs(video_info_webpage)
else:
age_gate = False
try:
# Try looking directly into the video webpage
mobj = re.search(r';ytplayer\.config\s*=\s*({.*?});', video_webpage)
if not mobj:
raise ValueError('Could not find ytplayer.config') # caught below
json_code = uppercase_escape(mobj.group(1))
ytplayer_config = json.loads(json_code)
args = ytplayer_config['args']
# Convert to the same format returned by compat_parse_qs
video_info = dict((k, [v]) for k, v in args.items())
if not args.get('url_encoded_fmt_stream_map'):
raise ValueError('No stream_map present') # caught below
except ValueError:
# We fallback to the get_video_info pages (used by the embed page)
self.report_video_info_webpage_download(video_id)
for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
video_info_url = (
'%s://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
% (proto, video_id, el_type))
video_info_webpage = self._download_webpage(
video_info_url,
video_id, note=False,
errnote='unable to download video info webpage')
video_info = compat_parse_qs(video_info_webpage)
if 'token' in video_info:
break
if 'token' not in video_info:
if 'reason' in video_info:
raise ExtractorError(
'YouTube said: %s' % video_info['reason'][0],
expected=True, video_id=video_id)
else:
raise ExtractorError(
'"token" parameter not in video info for unknown reason',
video_id=video_id)
if 'view_count' in video_info:
view_count = int(video_info['view_count'][0])
else:
view_count = None
# Check for "rental" videos
if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
raise ExtractorError('"rental" videos not supported')
# Start extracting information
self.report_information_extraction(video_id)
# uploader
if 'author' not in video_info:
raise ExtractorError('Unable to extract uploader name')
video_uploader = compat_urllib_parse.unquote_plus(video_info['author'][0])
# uploader_id
video_uploader_id = None
mobj = re.search(r'<link itemprop="url" href="http://www.youtube.com/(?:user|channel)/([^"]+)">', video_webpage)
if mobj is not None:
video_uploader_id = mobj.group(1)
else:
self._downloader.report_warning('unable to extract uploader nickname')
# title
if 'title' in video_info:
video_title = video_info['title'][0]
else:
self._downloader.report_warning('Unable to extract video title')
video_title = '_'
# thumbnail image
# We try first to get a high quality image:
m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
video_webpage, re.DOTALL)
if m_thumb is not None:
video_thumbnail = m_thumb.group(1)
elif 'thumbnail_url' not in video_info:
self._downloader.report_warning('unable to extract video thumbnail')
video_thumbnail = None
else: # don't panic if we can't find it
video_thumbnail = compat_urllib_parse.unquote_plus(video_info['thumbnail_url'][0])
# upload date
upload_date = None
mobj = re.search(r'(?s)id="eow-date.*?>(.*?)</span>', video_webpage)
if mobj is None:
mobj = re.search(
r'(?s)id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live) on (.*?)</strong>',
video_webpage)
if mobj is not None:
upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
upload_date = unified_strdate(upload_date)
m_cat_container = self._search_regex(
r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
video_webpage, 'categories', default=None)
if m_cat_container:
category = self._html_search_regex(
r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
default=None)
video_categories = None if category is None else [category]
else:
video_categories = None
# description
video_description = get_element_by_id("eow-description", video_webpage)
if video_description:
video_description = re.sub(r'''(?x)
<a\s+
(?:[a-zA-Z-]+="[^"]+"\s+)*?
title="([^"]+)"\s+
(?:[a-zA-Z-]+="[^"]+"\s+)*?
class="yt-uix-redirect-link"\s*>
[^<]+
</a>
''', r'\1', video_description)
video_description = clean_html(video_description)
else:
fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)
if fd_mobj:
video_description = unescapeHTML(fd_mobj.group(1))
else:
video_description = ''
def _extract_count(count_name):
count = self._search_regex(
r'id="watch-%s"[^>]*>.*?([\d,]+)\s*</span>' % re.escape(count_name),
video_webpage, count_name, default=None)
if count is not None:
return int(count.replace(',', ''))
return None
like_count = _extract_count('like')
dislike_count = _extract_count('dislike')
# subtitles
video_subtitles = self.extract_subtitles(video_id, video_webpage)
automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
if 'length_seconds' not in video_info:
self._downloader.report_warning('unable to extract video duration')
video_duration = None
else:
video_duration = int(compat_urllib_parse.unquote_plus(video_info['length_seconds'][0]))
# annotations
video_annotations = None
if self._downloader.params.get('writeannotations', False):
video_annotations = self._extract_annotations(video_id)
def _map_to_format_list(urlmap):
formats = []
for itag, video_real_url in urlmap.items():
dct = {
'format_id': itag,
'url': video_real_url,
'player_url': player_url,
}
if itag in self._formats:
dct.update(self._formats[itag])
formats.append(dct)
return formats
if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
self.report_rtmp_download()
formats = [{
'format_id': '_rtmp',
'protocol': 'rtmp',
'url': video_info['conn'][0],
'player_url': player_url,
}]
elif len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1:
encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0]
if 'rtmpe%3Dyes' in encoded_url_map:
raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True)
url_map = {}
for url_data_str in encoded_url_map.split(','):
url_data = compat_parse_qs(url_data_str)
if 'itag' not in url_data or 'url' not in url_data:
continue
format_id = url_data['itag'][0]
url = url_data['url'][0]
if 'sig' in url_data:
url += '&signature=' + url_data['sig'][0]
elif 's' in url_data:
encrypted_sig = url_data['s'][0]
ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")'
jsplayer_url_json = self._search_regex(
ASSETS_RE,
embed_webpage if age_gate else video_webpage,
'JS player URL (1)', default=None)
if not jsplayer_url_json and not age_gate:
# We need the embed website after all
if embed_webpage is None:
embed_url = proto + '://www.youtube.com/embed/%s' % video_id
embed_webpage = self._download_webpage(
embed_url, video_id, 'Downloading embed webpage')
jsplayer_url_json = self._search_regex(
ASSETS_RE, embed_webpage, 'JS player URL')
player_url = json.loads(jsplayer_url_json)
if player_url is None:
player_url_json = self._search_regex(
r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
video_webpage, 'age gate player URL')
player_url = json.loads(player_url_json)
if self._downloader.params.get('verbose'):
if player_url is None:
player_version = 'unknown'
player_desc = 'unknown'
else:
if player_url.endswith('swf'):
player_version = self._search_regex(
r'-(.+?)(?:/watch_as3)?\.swf$', player_url,
'flash player', fatal=False)
player_desc = 'flash player %s' % player_version
else:
player_version = self._search_regex(
r'html5player-([^/]+?)(?:/html5player)?\.js',
player_url,
'html5 player', fatal=False)
player_desc = 'html5 player %s' % player_version
parts_sizes = self._signature_cache_id(encrypted_sig)
self.to_screen('{%s} signature length %s, %s' %
(format_id, parts_sizes, player_desc))
signature = self._decrypt_signature(
encrypted_sig, video_id, player_url, age_gate)
url += '&signature=' + signature
if 'ratebypass' not in url:
url += '&ratebypass=yes'
url_map[format_id] = url
formats = _map_to_format_list(url_map)
elif video_info.get('hlsvp'):
manifest_url = video_info['hlsvp'][0]
url_map = self._extract_from_m3u8(manifest_url, video_id)
formats = _map_to_format_list(url_map)
else:
raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info')
# Look for the DASH manifest
if self._downloader.params.get('youtube_include_dash_manifest', True):
dash_mpd = video_info.get('dashmpd')
if dash_mpd:
dash_manifest_url = dash_mpd[0]
try:
dash_formats = self._parse_dash_manifest(
video_id, dash_manifest_url, player_url, age_gate)
except (ExtractorError, KeyError) as e:
self.report_warning(
'Skipping DASH manifest: %r' % e, video_id)
else:
# Hide the formats we found through non-DASH
dash_keys = set(df['format_id'] for df in dash_formats)
for f in formats:
if f['format_id'] in dash_keys:
f['format_id'] = 'nondash-%s' % f['format_id']
f['preference'] = f.get('preference', 0) - 10000
formats.extend(dash_formats)
# Check for malformed aspect ratio
stretched_m = re.search(
r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
video_webpage)
if stretched_m:
ratio = float(stretched_m.group('w')) / float(stretched_m.group('h'))
for f in formats:
if f.get('vcodec') != 'none':
f['stretched_ratio'] = ratio
self._sort_formats(formats)
return {
'id': video_id,
'uploader': video_uploader,
'uploader_id': video_uploader_id,
'upload_date': upload_date,
'title': video_title,
'thumbnail': video_thumbnail,
'description': video_description,
'categories': video_categories,
'subtitles': video_subtitles,
'automatic_captions': automatic_captions,
'duration': video_duration,
'age_limit': 18 if age_gate else 0,
'annotations': video_annotations,
'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id,
'view_count': view_count,
'like_count': like_count,
'dislike_count': dislike_count,
'average_rating': float_or_none(video_info.get('avg_rating', [None])[0]),
'formats': formats,
}
class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
IE_DESC = 'YouTube.com playlists'
_VALID_URL = r"""(?x)(?:
(?:https?://)?
(?:\w+\.)?
youtube\.com/
(?:
(?:course|view_play_list|my_playlists|artist|playlist|watch|embed/videoseries)
\? (?:.*?&)*? (?:p|a|list)=
| p/
)
(
(?:PL|LL|EC|UU|FL|RD|UL)?[0-9A-Za-z-_]{10,}
# Top tracks, they can also include dots
|(?:MC)[\w\.]*
)
.*
|
((?:PL|LL|EC|UU|FL|RD|UL)[0-9A-Za-z-_]{10,})
)"""
_TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
_VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)'
IE_NAME = 'youtube:playlist'
_TESTS = [{
'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
'info_dict': {
'title': 'ytdl test PL',
'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
},
'playlist_count': 3,
}, {
'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
'info_dict': {
'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
'title': 'YDL_Empty_List',
},
'playlist_count': 0,
}, {
'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
'info_dict': {
'title': '29C3: Not my department',
'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
},
'playlist_count': 95,
}, {
'note': 'issue #673',
'url': 'PLBB231211A4F62143',
'info_dict': {
'title': '[OLD]Team Fortress 2 (Class-based LP)',
'id': 'PLBB231211A4F62143',
},
'playlist_mincount': 26,
}, {
'note': 'Large playlist',
'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
'info_dict': {
'title': 'Uploads from Cauchemar',
'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
},
'playlist_mincount': 799,
}, {
'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
'info_dict': {
'title': 'YDL_safe_search',
'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
},
'playlist_count': 2,
}, {
'note': 'embedded',
'url': 'http://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
'playlist_count': 4,
'info_dict': {
'title': 'JODA15',
'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
}
}, {
'note': 'Embedded SWF player',
'url': 'http://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
'playlist_count': 4,
'info_dict': {
'title': 'JODA7',
'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
}
}, {
'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
'info_dict': {
'title': 'Uploads from Interstellar Movie',
'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
},
'playlist_mincout': 21,
}]
def _real_initialize(self):
self._login()
def _ids_to_results(self, ids):
return [
self.url_result(vid_id, 'Youtube', video_id=vid_id)
for vid_id in ids]
def _extract_mix(self, playlist_id):
# The mixes are generated from a single video
# the id of the playlist is just 'RD' + video_id
url = 'https://youtube.com/watch?v=%s&list=%s' % (playlist_id[-11:], playlist_id)
webpage = self._download_webpage(
url, playlist_id, 'Downloading Youtube mix')
search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
title_span = (
search_title('playlist-title') or
search_title('title long-title') or
search_title('title'))
title = clean_html(title_span)
ids = orderedSet(re.findall(
r'''(?xs)data-video-username=".*?".*?
href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id),
webpage))
url_results = self._ids_to_results(ids)
return self.playlist_result(url_results, playlist_id, title)
def _extract_playlist(self, playlist_id):
url = self._TEMPLATE_URL % playlist_id
page = self._download_webpage(url, playlist_id)
more_widget_html = content_html = page
# Check if the playlist exists or is private
if re.search(r'<div class="yt-alert-message">[^<]*?(The|This) playlist (does not exist|is private)[^<]*?</div>', page) is not None:
raise ExtractorError(
'The playlist doesn\'t exist or is private, use --username or '
'--netrc to access it.',
expected=True)
# Extract the video ids from the playlist pages
ids = []
for page_num in itertools.count(1):
matches = re.finditer(self._VIDEO_RE, content_html)
# We remove the duplicates and the link with index 0
# (it's not the first video of the playlist)
new_ids = orderedSet(m.group('id') for m in matches if m.group('index') != '0')
ids.extend(new_ids)
mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
if not mobj:
break
more = self._download_json(
'https://youtube.com/%s' % mobj.group('more'), playlist_id,
'Downloading page #%s' % page_num,
transform_source=uppercase_escape)
content_html = more['content_html']
if not content_html.strip():
# Some webpages show a "Load more" button but they don't
# have more videos
break
more_widget_html = more['load_more_widget_html']
playlist_title = self._html_search_regex(
r'(?s)<h1 class="pl-header-title[^"]*">\s*(.*?)\s*</h1>',
page, 'title')
url_results = self._ids_to_results(ids)
return self.playlist_result(url_results, playlist_id, playlist_title)
def _real_extract(self, url):
# Extract playlist id
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError('Invalid URL: %s' % url)
playlist_id = mobj.group(1) or mobj.group(2)
# Check if it's a video-specific URL
query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
if 'v' in query_dict:
video_id = query_dict['v'][0]
if self._downloader.params.get('noplaylist'):
self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
return self.url_result(video_id, 'Youtube', video_id=video_id)
else:
self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
if playlist_id.startswith('RD') or playlist_id.startswith('UL'):
# Mixes require a custom extraction process
return self._extract_mix(playlist_id)
return self._extract_playlist(playlist_id)
class YoutubeChannelIE(InfoExtractor):
IE_DESC = 'YouTube.com channels'
_VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)'
_TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos'
IE_NAME = 'youtube:channel'
_TESTS = [{
'note': 'paginated channel',
'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
'playlist_mincount': 91,
'info_dict': {
'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
}
}]
@staticmethod
def extract_videos_from_page(page):
ids_in_page = []
titles_in_page = []
for mobj in re.finditer(r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?', page):
video_id = mobj.group('id')
video_title = unescapeHTML(mobj.group('title'))
try:
idx = ids_in_page.index(video_id)
if video_title and not titles_in_page[idx]:
titles_in_page[idx] = video_title
except ValueError:
ids_in_page.append(video_id)
titles_in_page.append(video_title)
return zip(ids_in_page, titles_in_page)
def _real_extract(self, url):
channel_id = self._match_id(url)
url = self._TEMPLATE_URL % channel_id
channel_page = self._download_webpage(url, channel_id, 'Downloading page #1')
autogenerated = re.search(r'''(?x)
class="[^"]*?(?:
channel-header-autogenerated-label|
yt-channel-title-autogenerated
)[^"]*"''', channel_page) is not None
if autogenerated:
# The videos are contained in a single page
# the ajax pages can't be used, they are empty
entries = [
self.url_result(
video_id, 'Youtube', video_id=video_id,
video_title=video_title)
for video_id, video_title in self.extract_videos_from_page(channel_page)]
return self.playlist_result(entries, channel_id)
def _entries():
more_widget_html = content_html = channel_page
for pagenum in itertools.count(1):
for video_id, video_title in self.extract_videos_from_page(content_html):
yield self.url_result(
video_id, 'Youtube', video_id=video_id,
video_title=video_title)
mobj = re.search(
r'data-uix-load-more-href="/?(?P<more>[^"]+)"',
more_widget_html)
if not mobj:
break
more = self._download_json(
'https://youtube.com/%s' % mobj.group('more'), channel_id,
'Downloading page #%s' % (pagenum + 1),
transform_source=uppercase_escape)
content_html = more['content_html']
more_widget_html = more['load_more_widget_html']
return self.playlist_result(_entries(), channel_id)
class YoutubeUserIE(YoutubeChannelIE):
IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)'
_VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:user/)?(?!(?:attribution_link|watch|results)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_-]+)'
_TEMPLATE_URL = 'https://www.youtube.com/user/%s/videos'
IE_NAME = 'youtube:user'
_TESTS = [{
'url': 'https://www.youtube.com/user/TheLinuxFoundation',
'playlist_mincount': 320,
'info_dict': {
'title': 'TheLinuxFoundation',
}
}, {
'url': 'ytuser:phihag',
'only_matching': True,
}]
@classmethod
def suitable(cls, url):
# Don't return True if the url can be extracted with other youtube
# extractor, the regex would is too permissive and it would match.
other_ies = iter(klass for (name, klass) in globals().items() if name.endswith('IE') and klass is not cls)
if any(ie.suitable(url) for ie in other_ies):
return False
else:
return super(YoutubeUserIE, cls).suitable(url)
class YoutubeSearchIE(SearchInfoExtractor):
IE_DESC = 'YouTube.com searches'
_API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc'
_MAX_RESULTS = 1000
IE_NAME = 'youtube:search'
_SEARCH_KEY = 'ytsearch'
def _get_n_results(self, query, n):
"""Get a specified number of results for a query"""
video_ids = []
pagenum = 0
limit = n
PAGE_SIZE = 50
while (PAGE_SIZE * pagenum) < limit:
result_url = self._API_URL % (
compat_urllib_parse.quote_plus(query.encode('utf-8')),
max((PAGE_SIZE * pagenum) + 1), 2)
data_json = self._download_webpage(
result_url, video_id='query "%s"' % query,
note='Downloading page %s' % (pagenum + 1),
errnote='Unable to download API page')
data = json.loads(data_json)
api_response = data['data']
if 'items' not in api_response:
raise ExtractorError(
'[youtube] No video results', expected=True)
new_ids = list(video['id'] for video in api_response['items'])
video_ids += new_ids
limit = min(n, api_response['totalItems'])
pagenum += 1
if len(video_ids) > n:
video_ids = video_ids[:n]
videos = [self.url_result(video_id, 'Youtube', video_id=video_id)
for video_id in video_ids]
return self.playlist_result(videos, query)
class YoutubeSearchDateIE(YoutubeSearchIE):
IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
_API_URL = 'https://gdata.youtube.com/feeds/api/videos?q=%s&start-index=%i&max-results=50&v=2&alt=jsonc&orderby=published'
_SEARCH_KEY = 'ytsearchdate'
IE_DESC = 'YouTube.com searches, newest videos first'
class YoutubeSearchURLIE(InfoExtractor):
IE_DESC = 'YouTube.com search URLs'
IE_NAME = 'youtube:search_url'
_VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?search_query=(?P<query>[^&]+)(?:[&]|$)'
_TESTS = [{
'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
'playlist_mincount': 5,
'info_dict': {
'title': 'youtube-dl test video',
}
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
query = compat_urllib_parse.unquote_plus(mobj.group('query'))
webpage = self._download_webpage(url, query)
result_code = self._search_regex(
r'(?s)<ol[^>]+class="item-section"(.*?)</ol>', webpage, 'result HTML')
part_codes = re.findall(
r'(?s)<h3 class="yt-lockup-title">(.*?)</h3>', result_code)
entries = []
for part_code in part_codes:
part_title = self._html_search_regex(
[r'(?s)title="([^"]+)"', r'>([^<]+)</a>'], part_code, 'item title', fatal=False)
part_url_snippet = self._html_search_regex(
r'(?s)href="([^"]+)"', part_code, 'item URL')
part_url = compat_urlparse.urljoin(
'https://www.youtube.com/', part_url_snippet)
entries.append({
'_type': 'url',
'url': part_url,
'title': part_title,
})
return {
'_type': 'playlist',
'entries': entries,
'title': query,
}
class YoutubeShowIE(InfoExtractor):
IE_DESC = 'YouTube.com (multi-season) shows'
_VALID_URL = r'https?://www\.youtube\.com/show/(?P<id>[^?#]*)'
IE_NAME = 'youtube:show'
_TESTS = [{
'url': 'http://www.youtube.com/show/airdisasters',
'playlist_mincount': 3,
'info_dict': {
'id': 'airdisasters',
'title': 'Air Disasters',
}
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
playlist_id = mobj.group('id')
webpage = self._download_webpage(
url, playlist_id, 'Downloading show webpage')
# There's one playlist for each season of the show
m_seasons = list(re.finditer(r'href="(/playlist\?list=.*?)"', webpage))
self.to_screen('%s: Found %s seasons' % (playlist_id, len(m_seasons)))
entries = [
self.url_result(
'https://www.youtube.com' + season.group(1), 'YoutubePlaylist')
for season in m_seasons
]
title = self._og_search_title(webpage, fatal=False)
return {
'_type': 'playlist',
'id': playlist_id,
'title': title,
'entries': entries,
}
class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
"""
Base class for extractors that fetch info from
http://www.youtube.com/feed_ajax
Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
"""
_LOGIN_REQUIRED = True
# use action_load_personal_feed instead of action_load_system_feed
_PERSONAL_FEED = False
@property
def _FEED_TEMPLATE(self):
action = 'action_load_system_feed'
if self._PERSONAL_FEED:
action = 'action_load_personal_feed'
return 'https://www.youtube.com/feed_ajax?%s=1&feed_name=%s&paging=%%s' % (action, self._FEED_NAME)
@property
def IE_NAME(self):
return 'youtube:%s' % self._FEED_NAME
def _real_initialize(self):
self._login()
def _real_extract(self, url):
feed_entries = []
paging = 0
for i in itertools.count(1):
info = self._download_json(
self._FEED_TEMPLATE % paging,
'%s feed' % self._FEED_NAME,
'Downloading page %s' % i,
transform_source=uppercase_escape)
feed_html = info.get('feed_html') or info.get('content_html')
load_more_widget_html = info.get('load_more_widget_html') or feed_html
m_ids = re.finditer(r'"/watch\?v=(.*?)["&]', feed_html)
ids = orderedSet(m.group(1) for m in m_ids)
feed_entries.extend(
self.url_result(video_id, 'Youtube', video_id=video_id)
for video_id in ids)
mobj = re.search(
r'data-uix-load-more-href="/?[^"]+paging=(?P<paging>\d+)',
load_more_widget_html)
if mobj is None:
break
paging = mobj.group('paging')
return self.playlist_result(feed_entries, playlist_title=self._PLAYLIST_TITLE)
class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
IE_NAME = 'youtube:recommended'
IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
_VALID_URL = r'https?://www\.youtube\.com/feed/recommended|:ytrec(?:ommended)?'
_FEED_NAME = 'recommended'
_PLAYLIST_TITLE = 'Youtube Recommended videos'
class YoutubeWatchLaterIE(YoutubePlaylistIE):
IE_NAME = 'youtube:watchlater'
IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
_VALID_URL = r'https?://www\.youtube\.com/(?:feed/watch_later|playlist\?list=WL)|:ytwatchlater'
_TESTS = [] # override PlaylistIE tests
def _real_extract(self, url):
return self._extract_playlist('WL')
class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
IE_NAME = 'youtube:history'
IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
_VALID_URL = 'https?://www\.youtube\.com/feed/history|:ythistory'
_FEED_NAME = 'history'
_PERSONAL_FEED = True
_PLAYLIST_TITLE = 'Youtube Watch History'
class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
IE_NAME = 'youtube:favorites'
IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
_VALID_URL = r'https?://www\.youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
_LOGIN_REQUIRED = True
def _real_extract(self, url):
webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id')
return self.url_result(playlist_id, 'YoutubePlaylist')
class YoutubeSubscriptionsIE(YoutubePlaylistIE):
IE_NAME = 'youtube:subscriptions'
IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
_VALID_URL = r'https?://www\.youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
_TESTS = []
def _real_extract(self, url):
title = 'Youtube Subscriptions'
page = self._download_webpage('https://www.youtube.com/feed/subscriptions', title)
# The extraction process is the same as for playlists, but the regex
# for the video ids doesn't contain an index
ids = []
more_widget_html = content_html = page
for page_num in itertools.count(1):
matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html)
new_ids = orderedSet(matches)
ids.extend(new_ids)
mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
if not mobj:
break
more = self._download_json(
'https://youtube.com/%s' % mobj.group('more'), title,
'Downloading page #%s' % page_num,
transform_source=uppercase_escape)
content_html = more['content_html']
more_widget_html = more['load_more_widget_html']
return {
'_type': 'playlist',
'title': title,
'entries': self._ids_to_results(ids),
}
class YoutubeTruncatedURLIE(InfoExtractor):
IE_NAME = 'youtube:truncated_url'
IE_DESC = False # Do not list
_VALID_URL = r'''(?x)
(?:https?://)?
(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
(?:watch\?(?:
feature=[a-z_]+|
annotation_id=annotation_[^&]+|
x-yt-cl=[0-9]+|
hl=[^&]*|
)?
|
attribution_link\?a=[^&]+
)
$
'''
_TESTS = [{
'url': 'http://www.youtube.com/watch?annotation_id=annotation_3951667041',
'only_matching': True,
}, {
'url': 'http://www.youtube.com/watch?',
'only_matching': True,
}, {
'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
'only_matching': True,
}, {
'url': 'https://www.youtube.com/watch?feature=foo',
'only_matching': True,
}, {
'url': 'https://www.youtube.com/watch?hl=en-GB',
'only_matching': True,
}]
def _real_extract(self, url):
raise ExtractorError(
'Did you forget to quote the URL? Remember that & is a meta '
'character in most shells, so you want to put the URL in quotes, '
'like youtube-dl '
'"http://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
' or simply youtube-dl BaW_jenozKc .',
expected=True)
class YoutubeTruncatedIDIE(InfoExtractor):
IE_NAME = 'youtube:truncated_id'
IE_DESC = False # Do not list
_VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
_TESTS = [{
'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
raise ExtractorError(
'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),
expected=True)
|