forked from Jamie-Landeg-Jones/youtube-dl
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathInfoExtractors.py
executable file
·3950 lines (3290 loc) · 157 KB
/
InfoExtractors.py
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
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from __future__ import absolute_import
import base64
import datetime
import itertools
import netrc
import os
import re
import socket
import time
import email.utils
import xml.etree.ElementTree
import random
import math
from .utils import *
class InfoExtractor(object):
"""Information Extractor class.
Information extractors are the classes that, given a URL, extract
information about the video (or videos) the URL refers to. This
information includes the real video URL, the video 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.
title: Video title, unescaped.
ext: Video filename extension.
The following fields are optional:
format: The video format, defaults to ext (used for --get-format)
thumbnail: Full URL to a video thumbnail image.
description: One-line video description.
uploader: Full name of the video uploader.
upload_date: Video upload date (YYYYMMDD).
uploader_id: Nickname or id of the video uploader.
location: Physical location of the video.
player_url: SWF Player URL (used for rtmpdump).
subtitles: The .srt file contents.
urlhandle: [internal] The urlHandle to be used to download the file,
like returned by urllib.request.urlopen
The fields should all be Unicode strings.
Subclasses of this one should re-define the _real_initialize() and
_real_extract() methods and define a _VALID_URL regexp.
Probably, they should also be added to the list of extractors.
_real_extract() must return a *list* of information dictionaries as
described above.
Finally, the _WORKING attribute should be set to False for broken IEs
in order to warn the users and skip the tests.
"""
_ready = False
_downloader = None
_WORKING = True
def __init__(self, downloader=None):
"""Constructor. Receives an optional downloader."""
self._ready = False
self.set_downloader(downloader)
def suitable(self, url):
"""Receives a URL and returns True if suitable for this IE."""
return re.match(self._VALID_URL, url) is not None
def working(self):
"""Getter method for _WORKING."""
return self._WORKING
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
@property
def IE_NAME(self):
return type(self).__name__[:-2]
def _request_webpage(self, url_or_request, video_id, note=None, errnote=None):
""" Returns the response handle """
if note is None:
note = u'Downloading video webpage'
self._downloader.to_screen(u'[%s] %s: %s' % (self.IE_NAME, video_id, note))
try:
return compat_urllib_request.urlopen(url_or_request)
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
if errnote is None:
errnote = u'Unable to download webpage'
raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2])
def _download_webpage(self, url_or_request, video_id, note=None, errnote=None):
""" Returns the data of the page as a string """
urlh = self._request_webpage(url_or_request, video_id, note, errnote)
webpage_bytes = urlh.read()
return webpage_bytes.decode('utf-8', 'replace')
class YoutubeIE(InfoExtractor):
"""Information extractor for youtube.com."""
_VALID_URL = r"""^
(
(?:https?://)? # http(s):// (optional)
(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|
tube\.majestyc\.net/) # the various hostnames, with wildcard subdomains
(?:.*?\#/)? # handle anchor (#/) redirect urls
(?!view_play_list|my_playlists|artist|playlist) # ignore playlist URLs
(?: # the various things that can precede the ID:
(?:(?:v|embed|e)/) # v/ or embed/ or e/
|(?: # or the v= param in all its forms
(?:watch(?:_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=
)
)? # optional -> youtube.com/xxxx is OK
)? # all until now is optional -> you can pass the naked ID
([0-9A-Za-z_-]+) # here is it! the YouTube video ID
(?(1).+)? # if we found the ID, everything can follow
$"""
_LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
_LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en'
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
_NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
_NETRC_MACHINE = 'youtube'
# Listed in order of quality
_available_formats = ['38', '37', '46', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13']
_available_formats_prefer_free = ['38', '46', '37', '45', '22', '44', '35', '43', '34', '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',
'44': 'webm',
'45': 'webm',
'46': 'webm',
}
_video_dimensions = {
'5': '240x400',
'6': '???',
'13': '???',
'17': '144x176',
'18': '360x640',
'22': '720x1280',
'34': '360x640',
'35': '480x854',
'37': '1080x1920',
'38': '3072x4096',
'43': '360x640',
'44': '480x854',
'45': '720x1280',
'46': '1080x1920',
}
IE_NAME = u'youtube'
def suitable(self, url):
"""Receives a URL and returns True if suitable for this IE."""
return re.match(self._VALID_URL, url, re.VERBOSE) is not None
def report_lang(self):
"""Report attempt to set language."""
self._downloader.to_screen(u'[youtube] Setting language')
def report_login(self):
"""Report attempt to log in."""
self._downloader.to_screen(u'[youtube] Logging in')
def report_age_confirmation(self):
"""Report attempt to confirm age."""
self._downloader.to_screen(u'[youtube] Confirming age')
def report_video_webpage_download(self, video_id):
"""Report attempt to download video webpage."""
self._downloader.to_screen(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_screen(u'[youtube] %s: Downloading video info webpage' % video_id)
def report_video_subtitles_download(self, video_id):
"""Report attempt to download video info webpage."""
self._downloader.to_screen(u'[youtube] %s: Downloading video subtitles' % video_id)
def report_information_extraction(self, video_id):
"""Report attempt to extract video information."""
self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id)
def report_unavailable_format(self, video_id, format):
"""Report extracted video URL."""
self._downloader.to_screen(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_screen(u'[youtube] RTMP download detected')
def _closed_captions_xml_to_srt(self, xml_string):
srt = ''
texts = re.findall(r'<text start="([\d\.]+)"( dur="([\d\.]+)")?>([^<]+)</text>', xml_string, re.MULTILINE)
# TODO parse xml instead of regex
for n, (start, dur_tag, dur, caption) in enumerate(texts):
if not dur: dur = '4'
start = float(start)
end = start + float(dur)
start = "%02i:%02i:%02i,%03i" %(start/(60*60), start/60%60, start%60, start%1*1000)
end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000)
caption = unescapeHTML(caption)
caption = unescapeHTML(caption) # double cycle, intentional
srt += str(n+1) + '\n'
srt += start + ' --> ' + end + '\n'
srt += caption + '\n\n'
return srt
def _extract_subtitles(self, video_id):
self.report_video_subtitles_download(video_id)
request = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id)
try:
srt_list = compat_urllib_request.urlopen(request).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
return (u'WARNING: unable to download video subtitles: %s' % compat_str(err), None)
srt_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', srt_list)
srt_lang_list = dict((l[1], l[0]) for l in srt_lang_list)
if not srt_lang_list:
return (u'WARNING: video has no closed captions', None)
if self._downloader.params.get('subtitleslang', False):
srt_lang = self._downloader.params.get('subtitleslang')
elif 'en' in srt_lang_list:
srt_lang = 'en'
else:
srt_lang = list(srt_lang_list.keys())[0]
if not srt_lang in srt_lang_list:
return (u'WARNING: no closed captions found in the specified language', None)
request = compat_urllib_request.Request('http://www.youtube.com/api/timedtext?lang=%s&name=%s&v=%s' % (srt_lang, srt_lang_list[srt_lang], video_id))
try:
srt_xml = compat_urllib_request.urlopen(request).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
return (u'WARNING: unable to download video subtitles: %s' % compat_str(err), None)
if not srt_xml:
return (u'WARNING: unable to download video subtitles', None)
return (None, self._closed_captions_xml_to_srt(srt_xml))
def _print_formats(self, formats):
print('Available formats:')
for x in formats:
print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'flv'), self._video_dimensions.get(x, '???')))
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) as err:
self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % compat_str(err))
return
# Set language
request = compat_urllib_request.Request(self._LANG_URL)
try:
self.report_lang()
compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self._downloader.to_stderr(u'WARNING: unable to set language: %s' % compat_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 = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form))
try:
self.report_login()
login_results = compat_urllib_request.urlopen(request).read().decode('utf-8')
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 (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self._downloader.to_stderr(u'WARNING: unable to log in: %s' % compat_str(err))
return
# Confirm age
age_form = {
'next_url': '/',
'action_confirm': 'Confirm',
}
request = compat_urllib_request.Request(self._AGE_URL, compat_urllib_parse.urlencode(age_form))
try:
self.report_age_confirmation()
age_results = compat_urllib_request.urlopen(request).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_str(err))
return
def _extract_id(self, url):
mobj = re.match(self._VALID_URL, url, re.VERBOSE)
if mobj is None:
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return
video_id = mobj.group(2)
return video_id
def _real_extract(self, url):
# 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 = 'http://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/')
video_id = self._extract_id(url)
# Get video webpage
self.report_video_webpage_download(video_id)
url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id
request = compat_urllib_request.Request(url)
try:
video_webpage_bytes = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % compat_str(err))
return
video_webpage = video_webpage_bytes.decode('utf-8', 'ignore')
# Attempt to extract SWF player URL
mobj = re.search(r'swfConfig.*?"(http:\\/\\/.*?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
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 = compat_urllib_request.Request(video_info_url)
try:
video_info_webpage_bytes = compat_urllib_request.urlopen(request).read()
video_info_webpage = video_info_webpage_bytes.decode('utf-8', 'ignore')
video_info = compat_parse_qs(video_info_webpage)
if 'token' in video_info:
break
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % compat_str(err))
return
if 'token' not in video_info:
if 'reason' in video_info:
self._downloader.trouble(u'ERROR: YouTube said: %s' % video_info['reason'][0])
else:
self._downloader.trouble(u'ERROR: "token" parameter not in video info for unknown reason')
return
# Check for "rental" videos
if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
self._downloader.trouble(u'ERROR: "rental" videos not supported')
return
# Start extracting information
self.report_information_extraction(video_id)
# uploader
if 'author' not in video_info:
self._downloader.trouble(u'ERROR: unable to extract uploader name')
return
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.trouble(u'WARNING: unable to extract uploader nickname')
# title
if 'title' not in video_info:
self._downloader.trouble(u'ERROR: unable to extract video title')
return
video_title = compat_urllib_parse.unquote_plus(video_info['title'][0])
# 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 = compat_urllib_parse.unquote_plus(video_info['thumbnail_url'][0])
# upload date
upload_date = None
mobj = re.search(r'id="eow-date.*?>(.*?)</span>', video_webpage, re.DOTALL)
if mobj is not None:
upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y']
for expression in format_expressions:
try:
upload_date = datetime.datetime.strptime(upload_date, expression).strftime('%Y%m%d')
except:
pass
# description
video_description = get_element_by_id("eow-description", video_webpage)
if video_description:
video_description = clean_html(video_description)
else:
video_description = ''
# closed captions
video_subtitles = None
if self._downloader.params.get('writesubtitles', False):
(srt_error, video_subtitles) = self._extract_subtitles(video_id)
if srt_error:
self._downloader.trouble(srt_error)
if 'length_seconds' not in video_info:
self._downloader.trouble(u'WARNING: unable to extract video duration')
video_duration = ''
else:
video_duration = compat_urllib_parse.unquote_plus(video_info['length_seconds'][0])
# token
video_token = compat_urllib_parse.unquote_plus(video_info['token'][0])
# Decide which formats to download
req_format = self._downloader.params.get('format', None)
if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
self.report_rtmp_download()
video_url_list = [(None, video_info['conn'][0])]
elif 'url_encoded_fmt_stream_map' in video_info and len(video_info['url_encoded_fmt_stream_map']) >= 1:
url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',')
url_data = [compat_parse_qs(uds) for uds in url_data_strs]
url_data = [ud for ud in url_data if 'itag' in ud and 'url' in ud]
url_map = dict((ud['itag'][0], ud['url'][0] + '&signature=' + ud['sig'][0]) for ud in url_data)
format_limit = self._downloader.params.get('format_limit', None)
available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats
if format_limit is not None and format_limit in available_formats:
format_list = available_formats[available_formats.index(format_limit):]
else:
format_list = 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
if self._downloader.params.get('listformats', None):
self._print_formats(existing_formats)
return
if req_format is None or req_format == 'best':
video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
elif req_format == 'worst':
video_url_list = [(existing_formats[len(existing_formats)-1], url_map[existing_formats[len(existing_formats)-1]])] # worst quality
elif req_format in ('-1', 'all'):
video_url_list = [(f, url_map[f]) for f in existing_formats] # All formats
else:
# Specific formats. We pick the first in a slash-delimeted sequence.
# For example, if '1/2/3/4' is requested and '2' and '4' are available, we pick '2'.
req_formats = req_format.split('/')
video_url_list = None
for rf in req_formats:
if rf in url_map:
video_url_list = [(rf, url_map[rf])]
break
if video_url_list is None:
self._downloader.trouble(u'ERROR: requested format not available')
return
else:
self._downloader.trouble(u'ERROR: no conn or url_encoded_fmt_stream_map information found in video info')
return
results = []
for format_param, video_real_url in video_url_list:
# Extension
video_extension = self._video_extensions.get(format_param, 'flv')
video_format = '{0} - {1}'.format(format_param if format_param else video_extension,
self._video_dimensions.get(format_param, '???'))
results.append({
'id': video_id,
'url': video_real_url,
'uploader': video_uploader,
'uploader_id': video_uploader_id,
'upload_date': upload_date,
'title': video_title,
'ext': video_extension,
'format': video_format,
'thumbnail': video_thumbnail,
'description': video_description,
'player_url': player_url,
'subtitles': video_subtitles,
'duration': video_duration
})
return results
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'
IE_NAME = u'metacafe'
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
def report_disclaimer(self):
"""Report disclaimer retrieval."""
self._downloader.to_screen(u'[metacafe] Retrieving disclaimer')
def report_age_confirmation(self):
"""Report attempt to confirm age."""
self._downloader.to_screen(u'[metacafe] Confirming age')
def report_download_webpage(self, video_id):
"""Report webpage download."""
self._downloader.to_screen(u'[metacafe] %s: Downloading webpage' % video_id)
def report_extraction(self, video_id):
"""Report information extraction."""
self._downloader.to_screen(u'[metacafe] %s: Extracting information' % video_id)
def _real_initialize(self):
# Retrieve disclaimer
request = compat_urllib_request.Request(self._DISCLAIMER)
try:
self.report_disclaimer()
disclaimer = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self._downloader.trouble(u'ERROR: unable to retrieve disclaimer: %s' % compat_str(err))
return
# Confirm age
disclaimer_form = {
'filters': '0',
'submit': "Continue - I'm over 18",
}
request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form))
try:
self.report_age_confirmation()
disclaimer = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self._downloader.trouble(u'ERROR: unable to confirm age: %s' % compat_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._downloader.download(['http://www.youtube.com/watch?v=%s' % mobj2.group(1)])
return
# Retrieve video webpage to extract further information
request = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id)
try:
self.report_download_webpage(video_id)
webpage = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % compat_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 not None:
mediaURL = compat_urllib_parse.unquote(mobj.group(1))
video_extension = mediaURL[-3:]
# Extract gdaKey if available
mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
if mobj is None:
video_url = mediaURL
else:
gdaKey = mobj.group(1)
video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
else:
mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract media URL')
return
vardict = compat_parse_qs(mobj.group(1))
if 'mediaData' not in vardict:
self._downloader.trouble(u'ERROR: unable to extract media URL')
return
mobj = re.search(r'"mediaURL":"(http.*?)","key":"(.*?)"', vardict['mediaData'][0])
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract media URL')
return
mediaURL = mobj.group(1).replace('\\/', '/')
video_extension = mediaURL[-3:]
video_url = '%s?__gda__=%s' % (mediaURL, mobj.group(2))
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')
mobj = re.search(r'submitter=(.*?);', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
return
video_uploader = mobj.group(1)
return [{
'id': video_id.decode('utf-8'),
'url': video_url.decode('utf-8'),
'uploader': video_uploader.decode('utf-8'),
'upload_date': None,
'title': video_title,
'ext': video_extension.decode('utf-8'),
}]
class DailymotionIE(InfoExtractor):
"""Information Extractor for Dailymotion"""
_VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)'
IE_NAME = u'dailymotion'
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
def report_extraction(self, video_id):
"""Report information extraction."""
self._downloader.to_screen(u'[dailymotion] %s: Extracting information' % video_id)
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).split('_')[0].split('?')[0]
video_extension = 'mp4'
# Retrieve video webpage to extract further information
request = compat_urllib_request.Request(url)
request.add_header('Cookie', 'family_filter=off')
webpage = self._download_webpage(request, video_id)
# Extract URL, uploader and title from webpage
self.report_extraction(video_id)
mobj = re.search(r'\s*var flashvars = (.*)', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract media URL')
return
flashvars = compat_urllib_parse.unquote(mobj.group(1))
for key in ['hd1080URL', 'hd720URL', 'hqURL', 'sdURL', 'ldURL', 'video_url']:
if key in flashvars:
max_quality = key
self._downloader.to_screen(u'[dailymotion] Using %s' % key)
break
else:
self._downloader.trouble(u'ERROR: unable to extract video URL')
return
mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract video URL')
return
video_url = compat_urllib_parse.unquote(mobj.group(1)).replace('\\/', '/')
# TODO: support choosing qualities
mobj = re.search(r'<meta property="og:title" content="(?P<title>[^"]*)" />', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract title')
return
video_title = unescapeHTML(mobj.group('title'))
video_uploader = None
mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>', webpage)
if mobj is None:
# lookin for official user
mobj_official = re.search(r'<span rel="author"[^>]+?>([^<]+?)</span>', webpage)
if mobj_official is None:
self._downloader.trouble(u'WARNING: unable to extract uploader nickname')
else:
video_uploader = mobj_official.group(1)
else:
video_uploader = mobj.group(1)
video_upload_date = None
mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', webpage)
if mobj is not None:
video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1)
return [{
'id': video_id,
'url': video_url,
'uploader': video_uploader,
'upload_date': video_upload_date,
'title': video_title,
'ext': video_extension,
}]
class PhotobucketIE(InfoExtractor):
"""Information extractor for photobucket.com."""
_VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
IE_NAME = u'photobucket'
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
def report_download_webpage(self, video_id):
"""Report webpage download."""
self._downloader.to_screen(u'[photobucket] %s: Downloading webpage' % video_id)
def report_extraction(self, video_id):
"""Report information extraction."""
self._downloader.to_screen(u'[photobucket] %s: Extracting information' % video_id)
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
video_id = mobj.group(1)
video_extension = 'flv'
# Retrieve video webpage to extract further information
request = compat_urllib_request.Request(url)
try:
self.report_download_webpage(video_id)
webpage = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_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 = compat_urllib_parse.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_uploader = mobj.group(2).decode('utf-8')
return [{
'id': video_id.decode('utf-8'),
'url': video_url.decode('utf-8'),
'uploader': video_uploader,
'upload_date': None,
'title': video_title,
'ext': video_extension.decode('utf-8'),
}]
class YahooIE(InfoExtractor):
"""Information extractor for video.yahoo.com."""
_WORKING = False
# _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]+)(?:[#\?].*)?'
IE_NAME = u'video.yahoo'
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
def report_download_webpage(self, video_id):
"""Report webpage download."""
self._downloader.to_screen(u'[video.yahoo] %s: Downloading webpage' % video_id)
def report_extraction(self, video_id):
"""Report information extraction."""
self._downloader.to_screen(u'[video.yahoo] %s: Extracting information' % video_id)
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
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 = compat_urllib_request.Request(url)
try:
webpage = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_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 = compat_urllib_request.Request(url)
try:
self.report_download_webpage(video_id)
webpage = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_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')
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 = compat_urllib_request.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 = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % compat_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 = compat_urllib_parse.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8')
video_url = unescapeHTML(video_url)
return [{
'id': video_id.decode('utf-8'),
'url': video_url,
'uploader': video_uploader,
'upload_date': None,
'title': video_title,
'ext': video_extension.decode('utf-8'),
'thumbnail': video_thumbnail.decode('utf-8'),
'description': video_description,
}]
class VimeoIE(InfoExtractor):
"""Information extractor for vimeo.com."""
# _VALID_URL matches Vimeo URLs
_VALID_URL = r'(?:https?://)?(?:(?:www|player).)?vimeo\.com/(?:(?:groups|album)/[^/]+/)?(?:videos?/)?([0-9]+)'
IE_NAME = u'vimeo'
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
def report_download_webpage(self, video_id):
"""Report webpage download."""
self._downloader.to_screen(u'[vimeo] %s: Downloading webpage' % video_id)
def report_extraction(self, video_id):
"""Report information extraction."""
self._downloader.to_screen(u'[vimeo] %s: Extracting information' % video_id)
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
video_id = mobj.group(1)
# Retrieve video webpage to extract further information
request = compat_urllib_request.Request(url, None, std_headers)