1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
|
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# Author: Ricardo Garcia Gonzalez
# Author: Danny Colligan
# Author: Benjamin Johnson
# License: Public domain code
import htmlentitydefs
import httplib
import locale
import math
import netrc
import os
import os.path
import re
import socket
import string
import subprocess
import sys
import time
import urllib
import urllib2
# parse_qs was moved from the cgi module to the urlparse module recently.
try:
from urlparse import parse_qs
except ImportError:
from cgi import parse_qs
std_headers = {
'User-Agent': 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.7) Gecko/20100720 Firefox/3.6.7',
'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-Language': 'en-us,en;q=0.5',
}
simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii')
def preferredencoding():
"""Get preferred encoding.
Returns the best encoding scheme for the system, based on
locale.getpreferredencoding() and some further tweaks.
"""
def yield_preferredencoding():
try:
pref = locale.getpreferredencoding()
u'TEST'.encode(pref)
except:
pref = 'UTF-8'
while True:
yield pref
return yield_preferredencoding().next()
def htmlentity_transform(matchobj):
"""Transforms an HTML entity to a Unicode character.
This function receives a match object and is intended to be used with
the re.sub() function.
"""
entity = matchobj.group(1)
# Known non-numeric HTML entity
if entity in htmlentitydefs.name2codepoint:
return unichr(htmlentitydefs.name2codepoint[entity])
# Unicode character
mobj = re.match(ur'(?u)#(x?\d+)', 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 unichr(long(numstr, base))
# Unknown entity in name, return its literal representation
return (u'&%s;' % entity)
def sanitize_title(utitle):
"""Sanitizes a video title so it could be used as part of a filename."""
utitle = re.sub(ur'(?u)&(.+?);', htmlentity_transform, utitle)
return utitle.replace(unicode(os.sep), u'%')
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'-':
return (sys.stdout, filename)
stream = open(filename, open_mode)
return (stream, filename)
except (IOError, OSError), err:
# In case of error, try to remove win32 forbidden chars
filename = re.sub(ur'[/<>:"\|\?\*]', u'#', filename)
# An exception here should be caught in the caller
stream = open(filename, open_mode)
return (stream, filename)
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.
"""
pass
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.
"""
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 FileDownloader(object):
"""File Downloader class.
File downloader objects are the ones responsible of downloading the
actual video file and writing it to disk if the user has requested
it, among some other tasks. In most cases there should be one per
program. As, given a video URL, the downloader doesn't know how to
extract all the needed information, task that InfoExtractors do, it
has to pass the URL to one of them.
For this, file downloader objects have a method that allows
InfoExtractors to be registered in a given order. When it is passed
a URL, the file downloader handles it to the first InfoExtractor it
finds that reports being able to handle it. The InfoExtractor extracts
all the information about the video or videos the URL refers to, and
asks the FileDownloader to process the video information, possibly
downloading the video.
File downloaders accept a lot of parameters. In order not to saturate
the object constructor with arguments, it receives a dictionary of
options instead. These options are available through the params
attribute for the InfoExtractors to use. The FileDownloader also
registers itself as the downloader in charge for the InfoExtractors
that are added to it, so this is a "mutual registration".
Available options:
username: Username for authentication purposes.
password: Password for authentication purposes.
usenetrc: Use netrc for authentication instead.
quiet: Do not print messages to stdout.
forceurl: Force printing final URL.
forcetitle: Force printing title.
simulate: Do not download the video files.
format: Video format code.
format_limit: Highest quality format to try.
outtmpl: Template for output names.
ignoreerrors: Do not stop on download errors.
ratelimit: Download speed limit, in bytes/sec.
nooverwrites: Prevent overwriting files.
retries: Number of times to retry for HTTP error 503
continuedl: Try to continue downloads if possible.
noprogress: Do not print the progress bar.
"""
params = None
_ies = []
_pps = []
_download_retcode = None
_num_downloads = None
def __init__(self, params):
"""Create a FileDownloader object with the given options."""
self._ies = []
self._pps = []
self._download_retcode = 0
self._num_downloads = 0
self.params = params
@staticmethod
def pmkdir(filename):
"""Create directory components in filename. Similar to Unix "mkdir -p"."""
components = filename.split(os.sep)
aggregate = [os.sep.join(components[0:x]) for x in xrange(1, len(components))]
aggregate = ['%s%s' % (x, os.sep) for x in aggregate] # Finish names with separator
for dir in aggregate:
if not os.path.exists(dir):
os.mkdir(dir)
@staticmethod
def format_bytes(bytes):
if bytes is None:
return 'N/A'
if type(bytes) is str:
bytes = float(bytes)
if bytes == 0.0:
exponent = 0
else:
exponent = long(math.log(bytes, 1024.0))
suffix = 'bkMGTPEZY'[exponent]
converted = float(bytes) / float(1024**exponent)
return '%.2f%s' % (converted, suffix)
@staticmethod
def calc_percent(byte_counter, data_len):
if data_len is None:
return '---.-%'
return '%6s' % ('%3.1f%%' % (float(byte_counter) / float(data_len) * 100.0))
@staticmethod
def calc_eta(start, now, total, current):
if total is None:
return '--:--'
dif = now - start
if current == 0 or dif < 0.001: # One millisecond
return '--:--'
rate = float(current) / dif
eta = long((float(total) - float(current)) / rate)
(eta_mins, eta_secs) = divmod(eta, 60)
if eta_mins > 99:
return '--:--'
return '%02d:%02d' % (eta_mins, eta_secs)
@staticmethod
def calc_speed(start, now, bytes):
dif = now - start
if bytes == 0 or dif < 0.001: # One millisecond
return '%10s' % '---b/s'
return '%10s' % ('%s/s' % FileDownloader.format_bytes(float(bytes) / dif))
@staticmethod
def best_block_size(elapsed_time, bytes):
new_min = max(bytes / 2.0, 1.0)
new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB
if elapsed_time < 0.001:
return long(new_max)
rate = bytes / elapsed_time
if rate > new_max:
return long(new_max)
if rate < new_min:
return long(new_min)
return long(rate)
@staticmethod
def parse_bytes(bytestr):
"""Parse a string indicating a byte quantity into a long integer."""
matchobj = re.match(r'(?i)^(\d+(?:\.\d+)?)([kMGTPEZY]?)$', bytestr)
if matchobj is None:
return None
number = float(matchobj.group(1))
multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
return long(round(number * multiplier))
@staticmethod
def verify_url(url):
"""Verify a URL is valid and data could be downloaded. Return real data URL."""
request = urllib2.Request(url, None, std_headers)
data = urllib2.urlopen(request)
data.read(1)
url = data.geturl()
data.close()
return url
def add_info_extractor(self, ie):
"""Add an InfoExtractor object to the end of the list."""
self._ies.append(ie)
ie.set_downloader(self)
def add_post_processor(self, pp):
"""Add a PostProcessor object to the end of the chain."""
self._pps.append(pp)
pp.set_downloader(self)
def to_stdout(self, message, skip_eol=False, ignore_encoding_errors=False):
"""Print message to stdout if not in quiet mode."""
try:
if not self.params.get('quiet', False):
print (u'%s%s' % (message, [u'\n', u''][skip_eol])).encode(preferredencoding()),
sys.stdout.flush()
except (UnicodeEncodeError), err:
if not ignore_encoding_errors:
raise
def to_stderr(self, message):
"""Print message to stderr."""
print >>sys.stderr, message.encode(preferredencoding())
def fixed_template(self):
"""Checks if the output template is fixed."""
return (re.search(ur'(?u)%\(.+?\)s', self.params['outtmpl']) is None)
def trouble(self, message=None):
"""Determine action to take when a download problem appears.
Depending on if the downloader has been configured to ignore
download errors or not, this method may throw an exception or
not when errors are found, after printing the message.
"""
if message is not None:
self.to_stderr(message)
if not self.params.get('ignoreerrors', False):
raise DownloadError(message)
self._download_retcode = 1
def slow_down(self, start_time, byte_counter):
"""Sleep if the download speed is over the rate limit."""
rate_limit = self.params.get('ratelimit', None)
if rate_limit is None or byte_counter == 0:
return
now = time.time()
elapsed = now - start_time
if elapsed <= 0.0:
return
speed = float(byte_counter) / elapsed
if speed > rate_limit:
time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit)
def report_destination(self, filename):
"""Report destination filename."""
self.to_stdout(u'[download] Destination: %s' % filename, ignore_encoding_errors=True)
def report_progress(self, percent_str, data_len_str, speed_str, eta_str):
"""Report download progress."""
if self.params.get('noprogress', False):
return
self.to_stdout(u'\r[download] %s of %s at %s ETA %s' %
(percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
def report_resuming_byte(self, resume_len):
"""Report attemtp to resume at given byte."""
self.to_stdout(u'[download] Resuming download at byte %s' % resume_len)
def report_retry(self, count, retries):
"""Report retry in case of HTTP error 503"""
self.to_stdout(u'[download] Got HTTP error 503. Retrying (attempt %d of %d)...' % (count, retries))
def report_file_already_downloaded(self, file_name):
"""Report file has already been fully downloaded."""
try:
self.to_stdout(u'[download] %s has already been downloaded' % file_name)
except (UnicodeEncodeError), err:
self.to_stdout(u'[download] The file has already been downloaded')
def report_unable_to_resume(self):
"""Report it was impossible to resume download."""
self.to_stdout(u'[download] Unable to resume')
def report_finish(self):
"""Report download finished."""
if self.params.get('noprogress', False):
self.to_stdout(u'[download] Download completed')
else:
self.to_stdout(u'')
def increment_downloads(self):
"""Increment the ordinal that assigns a number to each file."""
self._num_downloads += 1
def process_info(self, info_dict):
"""Process a single dictionary returned by an InfoExtractor."""
# Do nothing else if in simulate mode
if self.params.get('simulate', False):
# Verify URL if it's an HTTP one
if info_dict['url'].startswith('http'):
try:
self.verify_url(info_dict['url'].encode('utf-8')).decode('utf-8')
except (OSError, IOError, urllib2.URLError, httplib.HTTPException, socket.error), err:
raise UnavailableVideoError
# Forced printings
if self.params.get('forcetitle', False):
print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')
if self.params.get('forceurl', False):
print info_dict['url'].encode(preferredencoding(), 'xmlcharrefreplace')
if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict:
print info_dict['thumbnail'].encode(preferredencoding(), 'xmlcharrefreplace')
if self.params.get('forcedescription', False) and 'description' in info_dict:
print info_dict['description'].encode(preferredencoding(), 'xmlcharrefreplace')
return
try:
template_dict = dict(info_dict)
template_dict['epoch'] = unicode(long(time.time()))
template_dict['ord'] = unicode('%05d' % self._num_downloads)
filename = self.params['outtmpl'] % template_dict
except (ValueError, KeyError), err:
self.trouble('ERROR: invalid output template or system charset: %s' % str(err))
if self.params.get('nooverwrites', False) and os.path.exists(filename):
self.to_stderr(u'WARNING: file exists: %s; skipping' % filename)
return
try:
self.pmkdir(filename)
except (OSError, IOError), err:
self.trouble('ERROR: unable to create directories: %s' % str(err))
return
try:
success = self._do_download(filename, info_dict['url'].encode('utf-8'), info_dict.get('player_url', None))
except (OSError, IOError), err:
raise UnavailableVideoError
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self.trouble('ERROR: unable to download video data: %s' % str(err))
return
except (ContentTooShortError, ), err:
self.trouble('ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
return
if success:
try:
self.post_process(filename, info_dict)
except (PostProcessingError), err:
self.trouble('ERROR: postprocessing: %s' % str(err))
return
def download(self, url_list):
"""Download a given list of URLs."""
if len(url_list) > 1 and self.fixed_template():
raise SameFileError(self.params['outtmpl'])
for url in url_list:
suitable_found = False
for ie in self._ies:
# Go to next InfoExtractor if not suitable
if not ie.suitable(url):
continue
# Suitable InfoExtractor found
suitable_found = True
# Extract information from URL and process it
ie.extract(url)
# Suitable InfoExtractor had been found; go to next URL
break
if not suitable_found:
self.trouble('ERROR: no suitable InfoExtractor: %s' % url)
return self._download_retcode
def post_process(self, filename, ie_info):
"""Run the postprocessing chain on the given file."""
info = dict(ie_info)
info['filepath'] = filename
for pp in self._pps:
info = pp.run(info)
if info is None:
break
def _download_with_rtmpdump(self, filename, url, player_url):
self.report_destination(filename)
# Check for rtmpdump first
try:
subprocess.call(['rtmpdump', '-h'], stdout=(file(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
except (OSError, IOError):
self.trouble(u'ERROR: RTMP download detected but "rtmpdump" could not be run')
return False
# Download using rtmpdump. rtmpdump returns exit code 2 when
# the connection was interrumpted and resuming appears to be
# possible. This is part of rtmpdump's normal usage, AFAIK.
basic_args = ['rtmpdump', '-q'] + [[], ['-W', player_url]][player_url is not None] + ['-r', url, '-o', filename]
retval = subprocess.call(basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)])
while retval == 2 or retval == 1:
prevsize = os.path.getsize(filename)
self.to_stdout(u'\r[rtmpdump] %s bytes' % prevsize, skip_eol=True)
time.sleep(5.0) # This seems to be needed
retval = subprocess.call(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])
cursize = os.path.getsize(filename)
if prevsize == cursize and retval == 1:
break
if retval == 0:
self.to_stdout(u'\r[rtmpdump] %s bytes' % os.path.getsize(filename))
return True
else:
self.trouble('\nERROR: rtmpdump exited with code %d' % retval)
return False
def _do_download(self, filename, url, player_url):
# Attempt to download using rtmpdump
if url.startswith('rtmp'):
return self._download_with_rtmpdump(filename, url, player_url)
stream = None
open_mode = 'wb'
basic_request = urllib2.Request(url, None, std_headers)
request = urllib2.Request(url, None, std_headers)
# Establish possible resume length
if os.path.isfile(filename):
resume_len = os.path.getsize(filename)
else:
resume_len = 0
# Request parameters in case of being able to resume
if self.params.get('continuedl', False) and resume_len != 0:
self.report_resuming_byte(resume_len)
request.add_header('Range','bytes=%d-' % resume_len)
open_mode = 'ab'
count = 0
retries = self.params.get('retries', 0)
while True:
# Establish connection
try:
data = urllib2.urlopen(request)
break
except (urllib2.HTTPError, ), err:
if err.code == 503:
# Retry in case of HTTP error 503
count += 1
if count <= retries:
self.report_retry(count, retries)
continue
if err.code != 416: # 416 is 'Requested range not satisfiable'
raise
# Unable to resume
data = urllib2.urlopen(basic_request)
content_length = data.info()['Content-Length']
if content_length is not None and long(content_length) == resume_len:
# Because the file had already been fully downloaded
self.report_file_already_downloaded(filename)
return True
else:
# Because the server didn't let us
self.report_unable_to_resume()
open_mode = 'wb'
data_len = data.info().get('Content-length', None)
data_len_str = self.format_bytes(data_len)
byte_counter = 0
block_size = 1024
start = time.time()
while True:
# Download and write
before = time.time()
data_block = data.read(block_size)
after = time.time()
data_block_len = len(data_block)
if data_block_len == 0:
break
byte_counter += data_block_len
# Open file just in time
if stream is None:
try:
(stream, filename) = sanitize_open(filename, open_mode)
self.report_destination(filename)
except (OSError, IOError), err:
self.trouble('ERROR: unable to open for writing: %s' % str(err))
return False
try:
stream.write(data_block)
except (IOError, OSError), err:
self.trouble('\nERROR: unable to write data: %s' % str(err))
block_size = self.best_block_size(after - before, data_block_len)
# Progress message
percent_str = self.calc_percent(byte_counter, data_len)
eta_str = self.calc_eta(start, time.time(), data_len, byte_counter)
speed_str = self.calc_speed(start, time.time(), byte_counter)
self.report_progress(percent_str, data_len_str, speed_str, eta_str)
# Apply rate limit
self.slow_down(start, byte_counter)
self.report_finish()
if data_len is not None and str(byte_counter) != data_len:
raise ContentTooShortError(byte_counter, long(data_len))
return True
class InfoExtractor(object):
"""Information Extractor class.
Information extractors are the classes that, given a URL, extract
information from the video (or videos) the URL refers to. This
information includes the real video URL, the video title and simplified
title, author and others. The information is stored in a dictionary
which is then passed to the FileDownloader. The FileDownloader
processes this information possibly downloading the video to the file
system, among other possible outcomes. The dictionaries must include
the following fields:
id: Video identifier.
url: Final video URL.
uploader: Nickname of the video uploader.
title: Literal title.
stitle: Simplified title.
ext: Video filename extension.
format: Video format.
player_url: SWF Player URL (may be None).
The following fields are optional. Their primary purpose is to allow
youtube-dl to serve as the backend for a video search function, such
as the one in youtube2mp3. They are only used when their respective
forced printing functions are called:
thumbnail: Full URL to a video thumbnail image.
description: One-line video description.
Subclasses of this one should re-define the _real_initialize() and
_real_extract() methods, as well as the suitable() static method.
Probably, they should also be instantiated and added to the main
downloader.
"""
_ready = False
_downloader = None
def __init__(self, downloader=None):
"""Constructor. Receives an optional downloader."""
self._ready = False
self.set_downloader(downloader)
@staticmethod
def suitable(url):
"""Receives a URL and returns True if suitable for this IE."""
return False
def initialize(self):
"""Initializes an instance (authentication, etc)."""
if not self._ready:
self._real_initialize()
self._ready = True
def extract(self, url):
"""Extracts URL information and returns it in list of dicts."""
self.initialize()
return self._real_extract(url)
def set_downloader(self, downloader):
"""Sets the downloader for this IE."""
self._downloader = downloader
def _real_initialize(self):
"""Real initialization process. Redefine in subclasses."""
pass
def _real_extract(self, url):
"""Real extraction process. Redefine in subclasses."""
pass
class YoutubeIE(InfoExtractor):
"""Information extractor for youtube.com."""
_VALID_URL = r'^((?:http://)?(?:youtu\.be/|(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:_popup)?(?:\.php)?)?[\?#](?:.+&)?v=))))?([0-9A-Za-z_-]+)(?(1).+)?$'
_LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
_LOGIN_URL = 'http://www.youtube.com/signup?next=/&gl=US&hl=en'
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
_NETRC_MACHINE = 'youtube'
# Listed in order of quality
_available_formats = ['38', '37', '22', '45', '35', '34', '43', '18', '6', '5', '17', '13']
_video_extensions = {
'13': '3gp',
'17': 'mp4',
'18': 'mp4',
'22': 'mp4',
'37': 'mp4',
'38': 'video', # You actually don't know if this will be MOV, AVI or whatever
'43': 'webm',
'45': 'webm',
}
@staticmethod
def suitable(url):
return (re.match(YoutubeIE._VALID_URL, url) is not None)
def report_lang(self):
"""Report attempt to set language."""
self._downloader.to_stdout(u'[youtube] Setting language')
def report_login(self):
"""Report attempt to log in."""
self._downloader.to_stdout(u'[youtube] Logging in')
def report_age_confirmation(self):
"""Report attempt to confirm age."""
self._downloader.to_stdout(u'[youtube] Confirming age')
def report_video_webpage_download(self, video_id):
"""Report attempt to download video webpage."""
self._downloader.to_stdout(u'[youtube] %s: Downloading video webpage' % video_id)
def report_video_info_webpage_download(self, video_id):
"""Report attempt to download video info webpage."""
self._downloader.to_stdout(u'[youtube] %s: Downloading video info webpage' % video_id)
def report_information_extraction(self, video_id):
"""Report attempt to extract video information."""
self._downloader.to_stdout(u'[youtube] %s: Extracting video information' % video_id)
def report_unavailable_format(self, video_id, format):
"""Report extracted video URL."""
self._downloader.to_stdout(u'[youtube] %s: Format %s not available' % (video_id, format))
def report_rtmp_download(self):
"""Indicate the download will use the RTMP protocol."""
self._downloader.to_stdout(u'[youtube] RTMP download detected')
def _real_initialize(self):
if self._downloader is None:
return
username = None
password = None
downloader_params = self._downloader.params
# Attempt to use provided username and password or .netrc data
if downloader_params.get('username', None) is not None:
username = downloader_params['username']
password = downloader_params['password']
elif downloader_params.get('usenetrc', False):
try:
info = netrc.netrc().authenticators(self._NETRC_MACHINE)
if info is not None:
username = info[0]
password = info[2]
else:
raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
except (IOError, netrc.NetrcParseError), err:
self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))
return
# Set language
request = urllib2.Request(self._LANG_URL, None, std_headers)
try:
self.report_lang()
urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.to_stderr(u'WARNING: unable to set language: %s' % str(err))
return
# No authentication to be performed
if username is None:
return
# Log in
login_form = {
'current_form': 'loginForm',
'next': '/',
'action_login': 'Log In',
'username': username,
'password': password,
}
request = urllib2.Request(self._LOGIN_URL, urllib.urlencode(login_form), std_headers)
try:
self.report_login()
login_results = urllib2.urlopen(request).read()
if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None:
self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password')
return
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err))
return
# Confirm age
age_form = {
'next_url': '/',
'action_confirm': 'Confirm',
}
request = urllib2.Request(self._AGE_URL, urllib.urlencode(age_form), std_headers)
try:
self.report_age_confirmation()
age_results = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))
return
def _real_extract(self, url):
# Extract video id from URL
mobj = re.match(self._VALID_URL, url)
if mobj is None:
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return
video_id = mobj.group(2)
# Get video webpage
self.report_video_webpage_download(video_id)
request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id, None, std_headers)
try:
video_webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
return
# Attempt to extract SWF player URL
mobj = re.search(r'swfConfig.*"(http://.*?watch.*?-.*?\.swf)"', video_webpage)
if mobj is not None:
player_url = mobj.group(1)
else:
player_url = None
# Get video info
self.report_video_info_webpage_download(video_id)
for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
% (video_id, el_type))
request = urllib2.Request(video_info_url, None, std_headers)
try:
video_info_webpage = urllib2.urlopen(request).read()
video_info = parse_qs(video_info_webpage)
if 'token' in video_info:
break
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
return
self.report_information_extraction(video_id)
# uploader
if 'author' not in video_info:
self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
return
video_uploader = urllib.unquote_plus(video_info['author'][0])
# title
if 'title' not in video_info:
self._downloader.trouble(u'ERROR: unable to extract video title')
return
video_title = urllib.unquote_plus(video_info['title'][0])
video_title = video_title.decode('utf-8')
video_title = sanitize_title(video_title)
# simplified title
simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
simple_title = simple_title.strip(ur'_')
# thumbnail image
if 'thumbnail_url' not in video_info:
self._downloader.trouble(u'WARNING: unable to extract video thumbnail')
video_thumbnail = ''
else: # don't panic if we can't find it
video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0])
# description
video_description = 'No description available.'
if self._downloader.params.get('forcedescription', False):
mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', video_webpage)
if mobj is not None:
video_description = mobj.group(1)
# Decide which formats to download
if 'fmt_url_map' in video_info:
url_map = dict(tuple(pair.split('|')) for pair in video_info['fmt_url_map'][0].split(','))
format_limit = self._downloader.params.get('format_limit', None)
if format_limit is not None and format_limit in self._available_formats:
format_list = self._available_formats[self._available_formats.index(format_limit):]
else:
format_list = self._available_formats
existing_formats = [x for x in format_list if x in url_map]
if len(existing_formats) == 0:
self._downloader.trouble(u'ERROR: no known formats available for video')
return
requested_format = self._downloader.params.get('format', None)
if requested_format is None:
video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
elif requested_format == '-1':
video_url_list = url_map.items() # All formats
else:
if requested_format not in existing_formats:
self._downloader.trouble(u'ERROR: format not available for video')
return
video_url_list = [(requested_format, url_map[requested_format])] # Specific format
elif 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
self.report_rtmp_download()
video_url_list = [(None, video_info['conn'][0])]
else:
self._downloader.trouble(u'ERROR: no fmt_url_map or conn information found in video info')
return
for format_param, video_real_url in video_url_list:
# At this point we have a new video
self._downloader.increment_downloads()
# Extension
video_extension = self._video_extensions.get(format_param, 'flv')
# Find the video URL in fmt_url_map or conn paramters
try:
# Process video information
self._downloader.process_info({
'id': video_id.decode('utf-8'),
'url': video_real_url.decode('utf-8'),
'uploader': video_uploader.decode('utf-8'),
'title': video_title,
'stitle': simple_title,
'ext': video_extension.decode('utf-8'),
'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
'thumbnail': video_thumbnail.decode('utf-8'),
'description': video_description.decode('utf-8'),
'player_url': player_url,
})
except UnavailableVideoError, err:
self._downloader.trouble(u'ERROR: unable to download video')
class MetacafeIE(InfoExtractor):
"""Information Extractor for metacafe.com."""
_VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
_DISCLAIMER = 'http://www.metacafe.com/family_filter/'
_FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
_youtube_ie = None
def __init__(self, youtube_ie, downloader=None):
InfoExtractor.__init__(self, downloader)
self._youtube_ie = youtube_ie
@staticmethod
def suitable(url):
return (re.match(MetacafeIE._VALID_URL, url) is not None)
def report_disclaimer(self):
"""Report disclaimer retrieval."""
self._downloader.to_stdout(u'[metacafe] Retrieving disclaimer')
def report_age_confirmation(self):
"""Report attempt to confirm age."""
self._downloader.to_stdout(u'[metacafe] Confirming age')
def report_download_webpage(self, video_id):
"""Report webpage download."""
self._downloader.to_stdout(u'[metacafe] %s: Downloading webpage' % video_id)
def report_extraction(self, video_id):
"""Report information extraction."""
self._downloader.to_stdout(u'[metacafe] %s: Extracting information' % video_id)
def _real_initialize(self):
# Retrieve disclaimer
request = urllib2.Request(self._DISCLAIMER, None, std_headers)
try:
self.report_disclaimer()
disclaimer = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % str(err))
return
# Confirm age
disclaimer_form = {
'filters': '0',
'submit': "Continue - I'm over 18",
}
request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form), std_headers)
try:
self.report_age_confirmation()
disclaimer = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to confirm age: %s' % str(err))
return
def _real_extract(self, url):
# Extract id and simplified title from URL
mobj = re.match(self._VALID_URL, url)
if mobj is None:
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return
video_id = mobj.group(1)
# Check if video comes from YouTube
mobj2 = re.match(r'^yt-(.*)$', video_id)
if mobj2 is not None:
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1))
return
# At this point we have a new video
self._downloader.increment_downloads()
simple_title = mobj.group(2).decode('utf-8')
video_extension = 'flv'
# Retrieve video webpage to extract further information
request = urllib2.Request('http://www.metacafe.com/watch/%s/' % video_id)
try:
self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err))
return
# Extract URL, uploader and title from webpage
self.report_extraction(video_id)
mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract media URL')
return
mediaURL = urllib.unquote(mobj.group(1))
#mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
#if mobj is None:
# self._downloader.trouble(u'ERROR: unable to extract gdaKey')
# return
#gdaKey = mobj.group(1)
#
#video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
video_url = mediaURL
mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract title')
return
video_title = mobj.group(1).decode('utf-8')
video_title = sanitize_title(video_title)
mobj = re.search(r'(?ms)By:\s*<a .*?>(.+?)<', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
return
video_uploader = mobj.group(1)
try:
# Process video information
self._downloader.process_info({
'id': video_id.decode('utf-8'),
'url': video_url.decode('utf-8'),
'uploader': video_uploader.decode('utf-8'),
'title': video_title,
'stitle': simple_title,
'ext': video_extension.decode('utf-8'),
'format': u'NA',
'player_url': None,
})
except UnavailableVideoError:
self._downloader.trouble(u'ERROR: unable to download video')
class DailymotionIE(InfoExtractor):
"""Information Extractor for Dailymotion"""
_VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)'
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
@staticmethod
def suitable(url):
return (re.match(DailymotionIE._VALID_URL, url) is not None)
def report_download_webpage(self, video_id):
"""Report webpage download."""
self._downloader.to_stdout(u'[dailymotion] %s: Downloading webpage' % video_id)
def report_extraction(self, video_id):
"""Report information extraction."""
self._downloader.to_stdout(u'[dailymotion] %s: Extracting information' % video_id)
def _real_initialize(self):
return
def _real_extract(self, url):
# Extract id and simplified title from URL
mobj = re.match(self._VALID_URL, url)
if mobj is None:
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return
# At this point we have a new video
self._downloader.increment_downloads()
video_id = mobj.group(1)
simple_title = mobj.group(2).decode('utf-8')
video_extension = 'flv'
# Retrieve video webpage to extract further information
request = urllib2.Request(url)
try:
self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err))
return
# Extract URL, uploader and title from webpage
self.report_extraction(video_id)
mobj = re.search(r'(?i)addVariable\(\"video\"\s*,\s*\"([^\"]*)\"\)', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract media URL')
return
mediaURL = urllib.unquote(mobj.group(1))
# if needed add http://www.dailymotion.com/ if relative URL
video_url = mediaURL
# '<meta\s+name="title"\s+content="Dailymotion\s*[:\-]\s*(.*?)"\s*\/\s*>'
mobj = re.search(r'(?im)<title>Dailymotion\s*[\-:]\s*(.+?)</title>', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract title')
return
video_title = mobj.group(1).decode('utf-8')
video_title = sanitize_title(video_title)
mobj = re.search(r'(?im)<div class="dmco_html owner">.*?<a class="name" href="/.+?">(.+?)</a></div>', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
return
video_uploader = mobj.group(1)
try:
# Process video information
self._downloader.process_info({
'id': video_id.decode('utf-8'),
'url': video_url.decode('utf-8'),
'uploader': video_uploader.decode('utf-8'),
'title': video_title,
'stitle': simple_title,
'ext': video_extension.decode('utf-8'),
'format': u'NA',
'player_url': None,
})
except UnavailableVideoError:
self._downloader.trouble(u'ERROR: unable to download video')
class GoogleIE(InfoExtractor):
"""Information extractor for video.google.com."""
_VALID_URL = r'(?:http://)?video\.google\.(?:com(?:\.au)?|co\.(?:uk|jp|kr|cr)|ca|de|es|fr|it|nl|pl)/videoplay\?docid=([^\&]+).*'
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
@staticmethod
def suitable(url):
return (re.match(GoogleIE._VALID_URL, url) is not None)
def report_download_webpage(self, video_id):
"""Report webpage download."""
self._downloader.to_stdout(u'[video.google] %s: Downloading webpage' % video_id)
def report_extraction(self, video_id):
"""Report information extraction."""
self._downloader.to_stdout(u'[video.google] %s: Extracting information' % video_id)
def _real_initialize(self):
return
def _real_extract(self, url):
# Extract id from URL
mobj = re.match(self._VALID_URL, url)
if mobj is None:
self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
return
# At this point we have a new video
self._downloader.increment_downloads()
video_id = mobj.group(1)
video_extension = 'mp4'
# Retrieve video webpage to extract further information
request = urllib2.Request('http://video.google.com/videoplay?docid=%s&hl=en&oe=utf-8' % video_id)
try:
self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
return
# Extract URL, uploader, and title from webpage
self.report_extraction(video_id)
mobj = re.search(r"download_url:'([^']+)'", webpage)
if mobj is None:
video_extension = 'flv'
mobj = re.search(r"(?i)videoUrl\\x3d(.+?)\\x26", webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract media URL')
return
mediaURL = urllib.unquote(mobj.group(1))
mediaURL = mediaURL.replace('\\x3d', '\x3d')
mediaURL = mediaURL.replace('\\x26', '\x26')
video_url = mediaURL
mobj = re.search(r'<title>(.*)</title>', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract title')
return
video_title = mobj.group(1).decode('utf-8')
video_title = sanitize_title(video_title)
simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
# Extract video description
mobj = re.search(r'<span id=short-desc-content>([^<]*)</span>', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract video description')
return
video_description = mobj.group(1).decode('utf-8')
if not video_description:
video_description = 'No description available.'
# Extract video thumbnail
if self._downloader.params.get('forcethumbnail', False):
request = urllib2.Request('http://video.google.com/videosearch?q=%s+site:video.google.com&hl=en' % abs(int(video_id)))
try:
webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
return
mobj = re.search(r'<img class=thumbnail-img (?:.* )?src=(http.*)>', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
return
video_thumbnail = mobj.group(1)
else: # we need something to pass to process_info
video_thumbnail = ''
try:
# Process video information
self._downloader.process_info({
'id': video_id.decode('utf-8'),
'url': video_url.decode('utf-8'),
'uploader': u'NA',
'title': video_title,
'stitle': simple_title,
'ext': video_extension.decode('utf-8'),
'format': u'NA',
'player_url': None,
})
except UnavailableVideoError:
self._downloader.trouble(u'ERROR: unable to download video')
class PhotobucketIE(InfoExtractor):
"""Information extractor for photobucket.com."""
_VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
@staticmethod
def suitable(url):
return (re.match(PhotobucketIE._VALID_URL, url) is not None)
def report_download_webpage(self, video_id):
"""Report webpage download."""
self._downloader.to_stdout(u'[photobucket] %s: Downloading webpage' % video_id)
def report_extraction(self, video_id):
"""Report information extraction."""
self._downloader.to_stdout(u'[photobucket] %s: Extracting information' % video_id)
def _real_initialize(self):
return
def _real_extract(self, url):
# Extract id from URL
mobj = re.match(self._VALID_URL, url)
if mobj is None:
self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
return
# At this point we have a new video
self._downloader.increment_downloads()
video_id = mobj.group(1)
video_extension = 'flv'
# Retrieve video webpage to extract further information
request = urllib2.Request(url)
try:
self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
return
# Extract URL, uploader, and title from webpage
self.report_extraction(video_id)
mobj = re.search(r'<link rel="video_src" href=".*\?file=([^"]+)" />', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract media URL')
return
mediaURL = urllib.unquote(mobj.group(1))
video_url = mediaURL
mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract title')
return
video_title = mobj.group(1).decode('utf-8')
video_title = sanitize_title(video_title)
simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
video_uploader = mobj.group(2).decode('utf-8')
try:
# Process video information
self._downloader.process_info({
'id': video_id.decode('utf-8'),
'url': video_url.decode('utf-8'),
'uploader': video_uploader,
'title': video_title,
'stitle': simple_title,
'ext': video_extension.decode('utf-8'),
'format': u'NA',
'player_url': None,
})
except UnavailableVideoError:
self._downloader.trouble(u'ERROR: unable to download video')
class YahooIE(InfoExtractor):
"""Information extractor for video.yahoo.com."""
# _VALID_URL matches all Yahoo! Video URLs
# _VPAGE_URL matches only the extractable '/watch/' URLs
_VALID_URL = r'(?:http://)?(?:[a-z]+\.)?video\.yahoo\.com/(?:watch|network)/([0-9]+)(?:/|\?v=)([0-9]+)(?:[#\?].*)?'
_VPAGE_URL = r'(?:http://)?video\.yahoo\.com/watch/([0-9]+)/([0-9]+)(?:[#\?].*)?'
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
@staticmethod
def suitable(url):
return (re.match(YahooIE._VALID_URL, url) is not None)
def report_download_webpage(self, video_id):
"""Report webpage download."""
self._downloader.to_stdout(u'[video.yahoo] %s: Downloading webpage' % video_id)
def report_extraction(self, video_id):
"""Report information extraction."""
self._downloader.to_stdout(u'[video.yahoo] %s: Extracting information' % video_id)
def _real_initialize(self):
return
def _real_extract(self, url, new_video=True):
# Extract ID from URL
mobj = re.match(self._VALID_URL, url)
if mobj is None:
self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
return
# At this point we have a new video
self._downloader.increment_downloads()
video_id = mobj.group(2)
video_extension = 'flv'
# Rewrite valid but non-extractable URLs as
# extractable English language /watch/ URLs
if re.match(self._VPAGE_URL, url) is None:
request = urllib2.Request(url)
try:
webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
return
mobj = re.search(r'\("id", "([0-9]+)"\);', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: Unable to extract id field')
return
yahoo_id = mobj.group(1)
mobj = re.search(r'\("vid", "([0-9]+)"\);', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: Unable to extract vid field')
return
yahoo_vid = mobj.group(1)
url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id)
return self._real_extract(url, new_video=False)
# Retrieve video webpage to extract further information
request = urllib2.Request(url)
try:
self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
return
# Extract uploader and title from webpage
self.report_extraction(video_id)
mobj = re.search(r'<meta name="title" content="(.*)" />', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract video title')
return
video_title = mobj.group(1).decode('utf-8')
simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
mobj = re.search(r'<h2 class="ti-5"><a href="http://video\.yahoo\.com/(people|profile)/[0-9]+" beacon=".*">(.*)</a></h2>', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract video uploader')
return
video_uploader = mobj.group(1).decode('utf-8')
# Extract video thumbnail
mobj = re.search(r'<link rel="image_src" href="(.*)" />', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract video thumbnail')
return
video_thumbnail = mobj.group(1).decode('utf-8')
# Extract video description
mobj = re.search(r'<meta name="description" content="(.*)" />', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract video description')
return
video_description = mobj.group(1).decode('utf-8')
if not video_description: video_description = 'No description available.'
# Extract video height and width
mobj = re.search(r'<meta name="video_height" content="([0-9]+)" />', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract video height')
return
yv_video_height = mobj.group(1)
mobj = re.search(r'<meta name="video_width" content="([0-9]+)" />', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract video width')
return
yv_video_width = mobj.group(1)
# Retrieve video playlist to extract media URL
# I'm not completely sure what all these options are, but we
# seem to need most of them, otherwise the server sends a 401.
yv_lg = 'R0xx6idZnW2zlrKP8xxAIR' # not sure what this represents
yv_bitrate = '700' # according to Wikipedia this is hard-coded
request = urllib2.Request('http://cosmos.bcst.yahoo.com/up/yep/process/getPlaylistFOP.php?node_id=' + video_id +
'&tech=flash&mode=playlist&lg=' + yv_lg + '&bitrate=' + yv_bitrate + '&vidH=' + yv_video_height +
'&vidW=' + yv_video_width + '&swf=as3&rd=video.yahoo.com&tk=null&adsupported=v1,v2,&eventid=1301797')
try:
self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
return
# Extract media URL from playlist XML
mobj = re.search(r'<STREAM APP="(http://.*)" FULLPATH="/?(/.*\.flv\?[^"]*)"', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: Unable to extract media URL')
return
video_url = urllib.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8')
video_url = re.sub(r'(?u)&(.+?);', htmlentity_transform, video_url)
try:
# Process video information
self._downloader.process_info({
'id': video_id.decode('utf-8'),
'url': video_url,
'uploader': video_uploader,
'title': video_title,
'stitle': simple_title,
'ext': video_extension.decode('utf-8'),
'thumbnail': video_thumbnail.decode('utf-8'),
'description': video_description,
'thumbnail': video_thumbnail,
'description': video_description,
'player_url': None,
})
except UnavailableVideoError:
self._downloader.trouble(u'ERROR: unable to download video')
class GenericIE(InfoExtractor):
"""Generic last-resort information extractor."""
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
@staticmethod
def suitable(url):
return True
def report_download_webpage(self, video_id):
"""Report webpage download."""
self._downloader.to_stdout(u'WARNING: Falling back on generic information extractor.')
self._downloader.to_stdout(u'[generic] %s: Downloading webpage' % video_id)
def report_extraction(self, video_id):
"""Report information extraction."""
self._downloader.to_stdout(u'[generic] %s: Extracting information' % video_id)
def _real_initialize(self):
return
def _real_extract(self, url):
# At this point we have a new video
self._downloader.increment_downloads()
video_id = url.split('/')[-1]
request = urllib2.Request(url)
try:
self.report_download_webpage(video_id)
webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
return
except ValueError, err:
# since this is the last-resort InfoExtractor, if
# this error is thrown, it'll be thrown here
self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
return
# Start with something easy: JW Player in SWFObject
mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
if mobj is None:
# Broaden the search a little bit
mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
return
# It's possible that one of the regexes
# matched, but returned an empty group:
if mobj.group(1) is None:
self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
return
video_url = urllib.unquote(mobj.group(1))
video_id = os.path.basename(video_url)
# here's a fun little line of code for you:
video_extension = os.path.splitext(video_id)[1][1:]
video_id = os.path.splitext(video_id)[0]
# it's tempting to parse this further, but you would
# have to take into account all the variations like
# Video Title - Site Name
# Site Name | Video Title
# Video Title - Tagline | Site Name
# and so on and so forth; it's just not practical
mobj = re.search(r'<title>(.*)</title>', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract title')
return
video_title = mobj.group(1).decode('utf-8')
video_title = sanitize_title(video_title)
simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
# video uploader is domain name
mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract title')
return
video_uploader = mobj.group(1).decode('utf-8')
try:
# Process video information
self._downloader.process_info({
'id': video_id.decode('utf-8'),
'url': video_url.decode('utf-8'),
'uploader': video_uploader,
'title': video_title,
'stitle': simple_title,
'ext': video_extension.decode('utf-8'),
'format': u'NA',
'player_url': None,
})
except UnavailableVideoError, err:
self._downloader.trouble(u'ERROR: unable to download video')
class YoutubeSearchIE(InfoExtractor):
"""Information Extractor for YouTube search queries."""
_VALID_QUERY = r'ytsearch(\d+|all)?:[\s\S]+'
_TEMPLATE_URL = 'http://www.youtube.com/results?search_query=%s&page=%s&gl=US&hl=en'
_VIDEO_INDICATOR = r'href="/watch\?v=.+?"'
_MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
_youtube_ie = None
_max_youtube_results = 1000
def __init__(self, youtube_ie, downloader=None):
InfoExtractor.__init__(self, downloader)
self._youtube_ie = youtube_ie
@staticmethod
def suitable(url):
return (re.match(YoutubeSearchIE._VALID_QUERY, url) is not None)
def report_download_page(self, query, pagenum):
"""Report attempt to download playlist page with given number."""
query = query.decode(preferredencoding())
self._downloader.to_stdout(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
def _real_initialize(self):
self._youtube_ie.initialize()
def _real_extract(self, query):
mobj = re.match(self._VALID_QUERY, query)
if mobj is None:
self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
return
prefix, query = query.split(':')
prefix = prefix[8:]
query = query.encode('utf-8')
if prefix == '':
self._download_n_results(query, 1)
return
elif prefix == 'all':
self._download_n_results(query, self._max_youtube_results)
return
else:
try:
n = long(prefix)
if n <= 0:
self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
return
elif n > self._max_youtube_results:
self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
n = self._max_youtube_results
self._download_n_results(query, n)
return
except ValueError: # parsing prefix as integer fails
self._download_n_results(query, 1)
return
def _download_n_results(self, query, n):
"""Downloads a specified number of results for a query"""
video_ids = []
already_seen = set()
pagenum = 1
while True:
self.report_download_page(query, pagenum)
result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
request = urllib2.Request(result_url, None, std_headers)
try:
page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
return
# Extract video identifiers
for mobj in re.finditer(self._VIDEO_INDICATOR, page):
video_id = page[mobj.span()[0]:mobj.span()[1]].split('=')[2][:-1]
if video_id not in already_seen:
video_ids.append(video_id)
already_seen.add(video_id)
if len(video_ids) == n:
# Specified n videos reached
for id in video_ids:
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
return
if re.search(self._MORE_PAGES_INDICATOR, page) is None:
for id in video_ids:
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
return
pagenum = pagenum + 1
class GoogleSearchIE(InfoExtractor):
"""Information Extractor for Google Video search queries."""
_VALID_QUERY = r'gvsearch(\d+|all)?:[\s\S]+'
_TEMPLATE_URL = 'http://video.google.com/videosearch?q=%s+site:video.google.com&start=%s&hl=en'
_VIDEO_INDICATOR = r'videoplay\?docid=([^\&>]+)\&'
_MORE_PAGES_INDICATOR = r'<span>Next</span>'
_google_ie = None
_max_google_results = 1000
def __init__(self, google_ie, downloader=None):
InfoExtractor.__init__(self, downloader)
self._google_ie = google_ie
@staticmethod
def suitable(url):
return (re.match(GoogleSearchIE._VALID_QUERY, url) is not None)
def report_download_page(self, query, pagenum):
"""Report attempt to download playlist page with given number."""
query = query.decode(preferredencoding())
self._downloader.to_stdout(u'[video.google] query "%s": Downloading page %s' % (query, pagenum))
def _real_initialize(self):
self._google_ie.initialize()
def _real_extract(self, query):
mobj = re.match(self._VALID_QUERY, query)
if mobj is None:
self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
return
prefix, query = query.split(':')
prefix = prefix[8:]
query = query.encode('utf-8')
if prefix == '':
self._download_n_results(query, 1)
return
elif prefix == 'all':
self._download_n_results(query, self._max_google_results)
return
else:
try:
n = long(prefix)
if n <= 0:
self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
return
elif n > self._max_google_results:
self._downloader.to_stderr(u'WARNING: gvsearch returns max %i results (you requested %i)' % (self._max_google_results, n))
n = self._max_google_results
self._download_n_results(query, n)
return
except ValueError: # parsing prefix as integer fails
self._download_n_results(query, 1)
return
def _download_n_results(self, query, n):
"""Downloads a specified number of results for a query"""
video_ids = []
already_seen = set()
pagenum = 1
while True:
self.report_download_page(query, pagenum)
result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
request = urllib2.Request(result_url, None, std_headers)
try:
page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
return
# Extract video identifiers
for mobj in re.finditer(self._VIDEO_INDICATOR, page):
video_id = mobj.group(1)
if video_id not in already_seen:
video_ids.append(video_id)
already_seen.add(video_id)
if len(video_ids) == n:
# Specified n videos reached
for id in video_ids:
self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id)
return
if re.search(self._MORE_PAGES_INDICATOR, page) is None:
for id in video_ids:
self._google_ie.extract('http://video.google.com/videoplay?docid=%s' % id)
return
pagenum = pagenum + 1
class YahooSearchIE(InfoExtractor):
"""Information Extractor for Yahoo! Video search queries."""
_VALID_QUERY = r'yvsearch(\d+|all)?:[\s\S]+'
_TEMPLATE_URL = 'http://video.yahoo.com/search/?p=%s&o=%s'
_VIDEO_INDICATOR = r'href="http://video\.yahoo\.com/watch/([0-9]+/[0-9]+)"'
_MORE_PAGES_INDICATOR = r'\s*Next'
_yahoo_ie = None
_max_yahoo_results = 1000
def __init__(self, yahoo_ie, downloader=None):
InfoExtractor.__init__(self, downloader)
self._yahoo_ie = yahoo_ie
@staticmethod
def suitable(url):
return (re.match(YahooSearchIE._VALID_QUERY, url) is not None)
def report_download_page(self, query, pagenum):
"""Report attempt to download playlist page with given number."""
query = query.decode(preferredencoding())
self._downloader.to_stdout(u'[video.yahoo] query "%s": Downloading page %s' % (query, pagenum))
def _real_initialize(self):
self._yahoo_ie.initialize()
def _real_extract(self, query):
mobj = re.match(self._VALID_QUERY, query)
if mobj is None:
self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
return
prefix, query = query.split(':')
prefix = prefix[8:]
query = query.encode('utf-8')
if prefix == '':
self._download_n_results(query, 1)
return
elif prefix == 'all':
self._download_n_results(query, self._max_yahoo_results)
return
else:
try:
n = long(prefix)
if n <= 0:
self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
return
elif n > self._max_yahoo_results:
self._downloader.to_stderr(u'WARNING: yvsearch returns max %i results (you requested %i)' % (self._max_yahoo_results, n))
n = self._max_yahoo_results
self._download_n_results(query, n)
return
except ValueError: # parsing prefix as integer fails
self._download_n_results(query, 1)
return
def _download_n_results(self, query, n):
"""Downloads a specified number of results for a query"""
video_ids = []
already_seen = set()
pagenum = 1
while True:
self.report_download_page(query, pagenum)
result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
request = urllib2.Request(result_url, None, std_headers)
try:
page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
return
# Extract video identifiers
for mobj in re.finditer(self._VIDEO_INDICATOR, page):
video_id = mobj.group(1)
if video_id not in already_seen:
video_ids.append(video_id)
already_seen.add(video_id)
if len(video_ids) == n:
# Specified n videos reached
for id in video_ids:
self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id)
return
if re.search(self._MORE_PAGES_INDICATOR, page) is None:
for id in video_ids:
self._yahoo_ie.extract('http://video.yahoo.com/watch/%s' % id)
return
pagenum = pagenum + 1
class YoutubePlaylistIE(InfoExtractor):
"""Information Extractor for YouTube playlists."""
_VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:(?:view_play_list|my_playlists)\?.*?p=|user/.*?/user/)([^&]+).*'
_TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en'
_VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
_MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
_youtube_ie = None
def __init__(self, youtube_ie, downloader=None):
InfoExtractor.__init__(self, downloader)
self._youtube_ie = youtube_ie
@staticmethod
def suitable(url):
return (re.match(YoutubePlaylistIE._VALID_URL, url) is not None)
def report_download_page(self, playlist_id, pagenum):
"""Report attempt to download playlist page with given number."""
self._downloader.to_stdout(u'[youtube] PL %s: Downloading page #%s' % (playlist_id, pagenum))
def _real_initialize(self):
self._youtube_ie.initialize()
def _real_extract(self, url):
# Extract playlist id
mobj = re.match(self._VALID_URL, url)
if mobj is None:
self._downloader.trouble(u'ERROR: invalid url: %s' % url)
return
# Download playlist pages
playlist_id = mobj.group(1)
video_ids = []
pagenum = 1
while True:
self.report_download_page(playlist_id, pagenum)
request = urllib2.Request(self._TEMPLATE_URL % (playlist_id, pagenum), None, std_headers)
try:
page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
return
# Extract video identifiers
ids_in_page = []
for mobj in re.finditer(self._VIDEO_INDICATOR, page):
if mobj.group(1) not in ids_in_page:
ids_in_page.append(mobj.group(1))
video_ids.extend(ids_in_page)
if re.search(self._MORE_PAGES_INDICATOR, page) is None:
break
pagenum = pagenum + 1
for id in video_ids:
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
return
class YoutubeUserIE(InfoExtractor):
"""Information Extractor for YouTube users."""
_VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/user/(.*)'
_TEMPLATE_URL = 'http://gdata.youtube.com/feeds/api/users/%s'
_VIDEO_INDICATOR = r'http://gdata.youtube.com/feeds/api/videos/(.*)' # XXX Fix this.
_youtube_ie = None
def __init__(self, youtube_ie, downloader=None):
InfoExtractor.__init__(self, downloader)
self._youtube_ie = youtube_ie
@staticmethod
def suitable(url):
return (re.match(YoutubeUserIE._VALID_URL, url) is not None)
def report_download_page(self, username):
"""Report attempt to download user page."""
self._downloader.to_stdout(u'[youtube] user %s: Downloading page ' % (username))
def _real_initialize(self):
self._youtube_ie.initialize()
def _real_extract(self, url):
# Extract username
mobj = re.match(self._VALID_URL, url)
if mobj is None:
self._downloader.trouble(u'ERROR: invalid url: %s' % url)
return
# Download user page
username = mobj.group(1)
video_ids = []
pagenum = 1
self.report_download_page(username)
request = urllib2.Request(self._TEMPLATE_URL % (username), None, std_headers)
try:
page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
return
# Extract video identifiers
ids_in_page = []
for mobj in re.finditer(self._VIDEO_INDICATOR, page):
if mobj.group(1) not in ids_in_page:
ids_in_page.append(mobj.group(1))
video_ids.extend(ids_in_page)
for id in video_ids:
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
return
class PostProcessor(object):
"""Post Processor class.
PostProcessor objects can be added to downloaders with their
add_post_processor() method. When the downloader has finished a
successful download, it will take its internal chain of PostProcessors
and start calling the run() method on each one of them, first with
an initial argument and then with the returned value of the previous
PostProcessor.
The chain will be stopped if one of them ever returns None or the end
of the chain is reached.
PostProcessor objects follow a "mutual registration" process similar
to InfoExtractor objects.
"""
_downloader = None
def __init__(self, downloader=None):
self._downloader = downloader
def set_downloader(self, downloader):
"""Sets the downloader for this PP."""
self._downloader = downloader
def run(self, information):
"""Run the PostProcessor.
The "information" argument is a dictionary like the ones
composed by InfoExtractors. The only difference is that this
one has an extra field called "filepath" that points to the
downloaded file.
When this method returns None, the postprocessing chain is
stopped. However, this method may return an information
dictionary that will be passed to the next postprocessing
object in the chain. It can be the one it received after
changing some fields.
In addition, this method may raise a PostProcessingError
exception that will be taken into account by the downloader
it was called from.
"""
return information # by default, do nothing
### MAIN PROGRAM ###
if __name__ == '__main__':
try:
# Modules needed only when running the main program
import getpass
import optparse
# Function to update the program file with the latest version from bitbucket.org
def update_self(downloader, filename):
# Note: downloader only used for options
if not os.access (filename, os.W_OK):
sys.exit('ERROR: no write permissions on %s' % filename)
downloader.to_stdout('Updating to latest stable version...')
latest_url = 'http://bitbucket.org/rg3/youtube-dl/raw/tip/LATEST_VERSION'
latest_version = urllib.urlopen(latest_url).read().strip()
prog_url = 'http://bitbucket.org/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version
newcontent = urllib.urlopen(prog_url).read()
stream = open(filename, 'w')
stream.write(newcontent)
stream.close()
downloader.to_stdout('Updated to version %s' % latest_version)
# General configuration
urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler()))
urllib2.install_opener(urllib2.build_opener(urllib2.HTTPCookieProcessor()))
socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
# Parse command line
parser = optparse.OptionParser(
usage='Usage: %prog [options] url...',
version='2010.07.22',
conflict_handler='resolve',
)
parser.add_option('-h', '--help',
action='help', help='print this help text and exit')
parser.add_option('-v', '--version',
action='version', help='print program version and exit')
parser.add_option('-U', '--update',
action='store_true', dest='update_self', help='update this program to latest stable version')
parser.add_option('-i', '--ignore-errors',
action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
parser.add_option('-r', '--rate-limit',
dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)')
parser.add_option('-R', '--retries',
dest='retries', metavar='RETRIES', help='number of retries (default is 10)', default=10)
authentication = optparse.OptionGroup(parser, 'Authentication Options')
authentication.add_option('-u', '--username',
dest='username', metavar='USERNAME', help='account username')
authentication.add_option('-p', '--password',
dest='password', metavar='PASSWORD', help='account password')
authentication.add_option('-n', '--netrc',
action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
parser.add_option_group(authentication)
video_format = optparse.OptionGroup(parser, 'Video Format Options')
video_format.add_option('-f', '--format',
action='store', dest='format', metavar='FORMAT', help='video format code')
video_format.add_option('-m', '--mobile-version',
action='store_const', dest='format', help='alias for -f 17', const='17')
video_format.add_option('--all-formats',
action='store_const', dest='format', help='download all available video formats', const='-1')
video_format.add_option('--max-quality',
action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
parser.add_option_group(video_format)
verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
verbosity.add_option('-q', '--quiet',
action='store_true', dest='quiet', help='activates quiet mode', default=False)
verbosity.add_option('-s', '--simulate',
action='store_true', dest='simulate', help='do not download video', default=False)
verbosity.add_option('-g', '--get-url',
action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
verbosity.add_option('-e', '--get-title',
action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
verbosity.add_option('--get-thumbnail',
action='store_true', dest='getthumbnail', help='simulate, quiet but print thumbnail URL', default=False)
verbosity.add_option('--get-description',
action='store_true', dest='getdescription', help='simulate, quiet but print video description', default=False)
verbosity.add_option('--no-progress',
action='store_true', dest='noprogress', help='do not print progress bar', default=False)
parser.add_option_group(verbosity)
filesystem = optparse.OptionGroup(parser, 'Filesystem Options')
filesystem.add_option('-t', '--title',
action='store_true', dest='usetitle', help='use title in file name', default=False)
filesystem.add_option('-l', '--literal',
action='store_true', dest='useliteral', help='use literal title in file name', default=False)
filesystem.add_option('-o', '--output',
dest='outtmpl', metavar='TEMPLATE', help='output filename template')
filesystem.add_option('-a', '--batch-file',
dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
filesystem.add_option('-w', '--no-overwrites',
action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
filesystem.add_option('-c', '--continue',
action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False)
parser.add_option_group(filesystem)
(opts, args) = parser.parse_args()
# Batch file verification
batchurls = []
if opts.batchfile is not None:
try:
if opts.batchfile == '-':
batchfd = sys.stdin
else:
batchfd = open(opts.batchfile, 'r')
batchurls = batchfd.readlines()
batchurls = [x.strip() for x in batchurls]
batchurls = [x for x in batchurls if len(x) > 0]
except IOError:
sys.exit(u'ERROR: batch file could not be read')
all_urls = batchurls + args
# Conflicting, missing and erroneous options
if opts.usenetrc and (opts.username is not None or opts.password is not None):
parser.error(u'using .netrc conflicts with giving username/password')
if opts.password is not None and opts.username is None:
parser.error(u'account username missing')
if opts.outtmpl is not None and (opts.useliteral or opts.usetitle):
parser.error(u'using output template conflicts with using title or literal title')
if opts.usetitle and opts.useliteral:
parser.error(u'using title conflicts with using literal title')
if opts.username is not None and opts.password is None:
opts.password = getpass.getpass(u'Type account password and press return:')
if opts.ratelimit is not None:
numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
if numeric_limit is None:
parser.error(u'invalid rate limit specified')
opts.ratelimit = numeric_limit
if opts.retries is not None:
try:
opts.retries = long(opts.retries)
except (TypeError, ValueError), err:
parser.error(u'invalid retry count specified')
# Information extractors
youtube_ie = YoutubeIE()
metacafe_ie = MetacafeIE(youtube_ie)
dailymotion_ie = DailymotionIE()
youtube_pl_ie = YoutubePlaylistIE(youtube_ie)
youtube_user_ie = YoutubeUserIE(youtube_ie)
youtube_search_ie = YoutubeSearchIE(youtube_ie)
google_ie = GoogleIE()
google_search_ie = GoogleSearchIE(google_ie)
photobucket_ie = PhotobucketIE()
yahoo_ie = YahooIE()
yahoo_search_ie = YahooSearchIE(yahoo_ie)
generic_ie = GenericIE()
# File downloader
fd = FileDownloader({
'usenetrc': opts.usenetrc,
'username': opts.username,
'password': opts.password,
'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription),
'forceurl': opts.geturl,
'forcetitle': opts.gettitle,
'forcethumbnail': opts.getthumbnail,
'forcedescription': opts.getdescription,
'simulate': (opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription),
'format': opts.format,
'format_limit': opts.format_limit,
'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding()))
or (opts.format == '-1' and opts.usetitle and u'%(stitle)s-%(id)s-%(format)s.%(ext)s')
or (opts.format == '-1' and opts.useliteral and u'%(title)s-%(id)s-%(format)s.%(ext)s')
or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s')
or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s')
or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s')
or u'%(id)s.%(ext)s'),
'ignoreerrors': opts.ignoreerrors,
'ratelimit': opts.ratelimit,
'nooverwrites': opts.nooverwrites,
'retries': opts.retries,
'continuedl': opts.continue_dl,
'noprogress': opts.noprogress,
})
fd.add_info_extractor(youtube_search_ie)
fd.add_info_extractor(youtube_pl_ie)
fd.add_info_extractor(youtube_user_ie)
fd.add_info_extractor(metacafe_ie)
fd.add_info_extractor(dailymotion_ie)
fd.add_info_extractor(youtube_ie)
fd.add_info_extractor(google_ie)
fd.add_info_extractor(google_search_ie)
fd.add_info_extractor(photobucket_ie)
fd.add_info_extractor(yahoo_ie)
fd.add_info_extractor(yahoo_search_ie)
# This must come last since it's the
# fallback if none of the others work
fd.add_info_extractor(generic_ie)
# Update version
if opts.update_self:
update_self(fd, sys.argv[0])
# Maybe do nothing
if len(all_urls) < 1:
if not opts.update_self:
parser.error(u'you must provide at least one URL')
else:
sys.exit()
retcode = fd.download(all_urls)
sys.exit(retcode)
except DownloadError:
sys.exit(1)
except SameFileError:
sys.exit(u'ERROR: fixed output name but more than one file to download')
except KeyboardInterrupt:
sys.exit(u'\nERROR: Interrupted by user')
|