forked from yt-dlp/yt-dlp
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathYoutubeDL.py
3316 lines (2967 loc) · 151 KB
/
YoutubeDL.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 python3
# coding: utf-8
from __future__ import absolute_import, unicode_literals
import collections
import contextlib
import copy
import datetime
import errno
import fileinput
import io
import itertools
import json
import locale
import operator
import os
import platform
import re
import shutil
import subprocess
import sys
import tempfile
import time
import tokenize
import traceback
import random
from string import ascii_letters
from zipimport import zipimporter
from .compat import (
compat_basestring,
compat_get_terminal_size,
compat_kwargs,
compat_numeric_types,
compat_os_name,
compat_str,
compat_tokenize_tokenize,
compat_urllib_error,
compat_urllib_request,
compat_urllib_request_DataHandler,
)
from .cookies import load_cookies
from .utils import (
age_restricted,
args_to_str,
ContentTooShortError,
date_from_str,
DateRange,
DEFAULT_OUTTMPL,
determine_ext,
determine_protocol,
DOT_DESKTOP_LINK_TEMPLATE,
DOT_URL_LINK_TEMPLATE,
DOT_WEBLOC_LINK_TEMPLATE,
DownloadError,
encode_compat_str,
encodeFilename,
EntryNotInPlaylist,
error_to_compat_str,
ExistingVideoReached,
expand_path,
ExtractorError,
float_or_none,
format_bytes,
format_field,
STR_FORMAT_RE,
formatSeconds,
GeoRestrictedError,
HEADRequest,
int_or_none,
iri_to_uri,
ISO3166Utils,
LazyList,
locked_file,
make_dir,
make_HTTPS_handler,
MaxDownloadsReached,
network_exceptions,
orderedSet,
OUTTMPL_TYPES,
PagedList,
parse_filesize,
PerRequestProxyHandler,
platform_name,
PostProcessingError,
preferredencoding,
prepend_extension,
process_communicate_or_kill,
register_socks_protocols,
RejectedVideoReached,
render_table,
replace_extension,
SameFileError,
sanitize_filename,
sanitize_path,
sanitize_url,
sanitized_Request,
std_headers,
str_or_none,
strftime_or_none,
subtitles_filename,
ThrottledDownload,
to_high_limit_path,
traverse_obj,
try_get,
UnavailableVideoError,
url_basename,
version_tuple,
write_json_file,
write_string,
YoutubeDLCookieProcessor,
YoutubeDLHandler,
YoutubeDLRedirectHandler,
)
from .cache import Cache
from .extractor import (
gen_extractor_classes,
get_info_extractor,
_LAZY_LOADER,
_PLUGIN_CLASSES
)
from .extractor.openload import PhantomJSwrapper
from .downloader import (
get_suitable_downloader,
shorten_protocol_name
)
from .downloader.rtmp import rtmpdump_version
from .postprocessor import (
get_postprocessor,
FFmpegFixupDurationPP,
FFmpegFixupM3u8PP,
FFmpegFixupM4aPP,
FFmpegFixupStretchedPP,
FFmpegFixupTimestampPP,
FFmpegMergerPP,
FFmpegPostProcessor,
MoveFilesAfterDownloadPP,
)
from .version import __version__
if compat_os_name == 'nt':
import ctypes
class YoutubeDL(object):
"""YoutubeDL class.
YoutubeDL 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, YoutubeDL objects have a method that allows
InfoExtractors to be registered in a given order. When it is passed
a URL, the YoutubeDL object 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
YoutubeDL process the extracted information, possibly using a File
Downloader to download the video.
YoutubeDL objects 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 YoutubeDL 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.
videopassword: Password for accessing a video.
ap_mso: Adobe Pass multiple-system operator identifier.
ap_username: Multiple-system operator account username.
ap_password: Multiple-system operator account password.
usenetrc: Use netrc for authentication instead.
verbose: Print additional info to stdout.
quiet: Do not print messages to stdout.
no_warnings: Do not print out anything for warnings.
forceprint: A list of templates to force print
forceurl: Force printing final URL. (Deprecated)
forcetitle: Force printing title. (Deprecated)
forceid: Force printing ID. (Deprecated)
forcethumbnail: Force printing thumbnail URL. (Deprecated)
forcedescription: Force printing description. (Deprecated)
forcefilename: Force printing final filename. (Deprecated)
forceduration: Force printing duration. (Deprecated)
forcejson: Force printing info_dict as JSON.
dump_single_json: Force printing the info_dict of the whole playlist
(or video) as a single JSON line.
force_write_download_archive: Force writing download archive regardless
of 'skip_download' or 'simulate'.
simulate: Do not download the video files.
format: Video format code. see "FORMAT SELECTION" for more details.
allow_unplayable_formats: Allow unplayable formats to be extracted and downloaded.
ignore_no_formats_error: Ignore "No video formats" error. Usefull for
extracting metadata even if the video is not actually
available for download (experimental)
format_sort: How to sort the video formats. see "Sorting Formats"
for more details.
format_sort_force: Force the given format_sort. see "Sorting Formats"
for more details.
allow_multiple_video_streams: Allow multiple video streams to be merged
into a single file
allow_multiple_audio_streams: Allow multiple audio streams to be merged
into a single file
check_formats Whether to test if the formats are downloadable.
Can be True (check all), False (check none)
or None (check only if requested by extractor)
paths: Dictionary of output paths. The allowed keys are 'home'
'temp' and the keys of OUTTMPL_TYPES (in utils.py)
outtmpl: Dictionary of templates for output names. Allowed keys
are 'default' and the keys of OUTTMPL_TYPES (in utils.py).
A string a also accepted for backward compatibility
outtmpl_na_placeholder: Placeholder for unavailable meta fields.
restrictfilenames: Do not allow "&" and spaces in file names
trim_file_name: Limit length of filename (extension excluded)
windowsfilenames: Force the filenames to be windows compatible
ignoreerrors: Do not stop on download errors
(Default True when running yt-dlp,
but False when directly accessing YoutubeDL class)
skip_playlist_after_errors: Number of allowed failures until the rest of
the playlist is skipped
force_generic_extractor: Force downloader to use the generic extractor
overwrites: Overwrite all video and metadata files if True,
overwrite only non-video files if None
and don't overwrite any file if False
playliststart: Playlist item to start at.
playlistend: Playlist item to end at.
playlist_items: Specific indices of playlist to download.
playlistreverse: Download playlist items in reverse order.
playlistrandom: Download playlist items in random order.
matchtitle: Download only matching titles.
rejecttitle: Reject downloads for matching titles.
logger: Log messages to a logging.Logger instance.
logtostderr: Log messages to stderr instead of stdout.
writedescription: Write the video description to a .description file
writeinfojson: Write the video description to a .info.json file
clean_infojson: Remove private fields from the infojson
writecomments: Extract video comments. This will not be written to disk
unless writeinfojson is also given
writeannotations: Write the video annotations to a .annotations.xml file
writethumbnail: Write the thumbnail image to a file
allow_playlist_files: Whether to write playlists' description, infojson etc
also to disk when using the 'write*' options
write_all_thumbnails: Write all thumbnail formats to files
writelink: Write an internet shortcut file, depending on the
current platform (.url/.webloc/.desktop)
writeurllink: Write a Windows internet shortcut file (.url)
writewebloclink: Write a macOS internet shortcut file (.webloc)
writedesktoplink: Write a Linux internet shortcut file (.desktop)
writesubtitles: Write the video subtitles to a file
writeautomaticsub: Write the automatically generated subtitles to a file
allsubtitles: Deprecated - Use subtitleslangs = ['all']
Downloads all the subtitles of the video
(requires writesubtitles or writeautomaticsub)
listsubtitles: Lists all available subtitles for the video
subtitlesformat: The format code for subtitles
subtitleslangs: List of languages of the subtitles to download (can be regex).
The list may contain "all" to refer to all the available
subtitles. The language can be prefixed with a "-" to
exclude it from the requested languages. Eg: ['all', '-live_chat']
keepvideo: Keep the video file after post-processing
daterange: A DateRange object, download only if the upload_date is in the range.
skip_download: Skip the actual download of the video file
cachedir: Location of the cache files in the filesystem.
False to disable filesystem cache.
noplaylist: Download single video instead of a playlist if in doubt.
age_limit: An integer representing the user's age in years.
Unsuitable videos for the given age are skipped.
min_views: An integer representing the minimum view count the video
must have in order to not be skipped.
Videos without view count information are always
downloaded. None for no limit.
max_views: An integer representing the maximum view count.
Videos that are more popular than that are not
downloaded.
Videos without view count information are always
downloaded. None for no limit.
download_archive: File name of a file where all downloads are recorded.
Videos already present in the file are not downloaded
again.
break_on_existing: Stop the download process after attempting to download a
file that is in the archive.
break_on_reject: Stop the download process when encountering a video that
has been filtered out.
cookiefile: File name where cookies should be read from and dumped to
cookiesfrombrowser: A tuple containing the name of the browser and the profile
name/path from where cookies are loaded.
Eg: ('chrome', ) or (vivaldi, 'default')
nocheckcertificate:Do not verify SSL certificates
prefer_insecure: Use HTTP instead of HTTPS to retrieve information.
At the moment, this is only supported by YouTube.
proxy: URL of the proxy server to use
geo_verification_proxy: URL of the proxy to use for IP address verification
on geo-restricted sites.
socket_timeout: Time to wait for unresponsive hosts, in seconds
bidi_workaround: Work around buggy terminals without bidirectional text
support, using fridibi
debug_printtraffic:Print out sent and received HTTP traffic
include_ads: Download ads as well
default_search: Prepend this string if an input url is not valid.
'auto' for elaborate guessing
encoding: Use this encoding instead of the system-specified.
extract_flat: Do not resolve URLs, return the immediate result.
Pass in 'in_playlist' to only show this behavior for
playlist items.
postprocessors: A list of dictionaries, each with an entry
* key: The name of the postprocessor. See
yt_dlp/postprocessor/__init__.py for a list.
* when: When to run the postprocessor. Can be one of
pre_process|before_dl|post_process|after_move.
Assumed to be 'post_process' if not given
post_hooks: A list of functions that get called as the final step
for each video file, after all postprocessors have been
called. The filename will be passed as the only argument.
progress_hooks: A list of functions that get called on download
progress, with a dictionary with the entries
* status: One of "downloading", "error", or "finished".
Check this first and ignore unknown values.
If status is one of "downloading", or "finished", the
following properties may also be present:
* filename: The final filename (always present)
* tmpfilename: The filename we're currently writing to
* downloaded_bytes: Bytes on disk
* total_bytes: Size of the whole file, None if unknown
* total_bytes_estimate: Guess of the eventual file size,
None if unavailable.
* elapsed: The number of seconds since download started.
* eta: The estimated time in seconds, None if unknown
* speed: The download speed in bytes/second, None if
unknown
* fragment_index: The counter of the currently
downloaded video fragment.
* fragment_count: The number of fragments (= individual
files that will be merged)
Progress hooks are guaranteed to be called at least once
(with status "finished") if the download is successful.
merge_output_format: Extension to use when merging formats.
final_ext: Expected final extension; used to detect when the file was
already downloaded and converted. "merge_output_format" is
replaced by this extension when given
fixup: Automatically correct known faults of the file.
One of:
- "never": do nothing
- "warn": only emit a warning
- "detect_or_warn": check whether we can do anything
about it, warn otherwise (default)
source_address: Client-side IP address to bind to.
call_home: Boolean, true iff we are allowed to contact the
yt-dlp servers for debugging. (BROKEN)
sleep_interval_requests: Number of seconds to sleep between requests
during extraction
sleep_interval: Number of seconds to sleep before each download when
used alone or a lower bound of a range for randomized
sleep before each download (minimum possible number
of seconds to sleep) when used along with
max_sleep_interval.
max_sleep_interval:Upper bound of a range for randomized sleep before each
download (maximum possible number of seconds to sleep).
Must only be used along with sleep_interval.
Actual sleep time will be a random float from range
[sleep_interval; max_sleep_interval].
sleep_interval_subtitles: Number of seconds to sleep before each subtitle download
listformats: Print an overview of available video formats and exit.
list_thumbnails: Print a table of all thumbnails and exit.
match_filter: A function that gets called with the info_dict of
every video.
If it returns a message, the video is ignored.
If it returns None, the video is downloaded.
match_filter_func in utils.py is one example for this.
no_color: Do not emit color codes in output.
geo_bypass: Bypass geographic restriction via faking X-Forwarded-For
HTTP header
geo_bypass_country:
Two-letter ISO 3166-2 country code that will be used for
explicit geographic restriction bypassing via faking
X-Forwarded-For HTTP header
geo_bypass_ip_block:
IP range in CIDR notation that will be used similarly to
geo_bypass_country
The following options determine which downloader is picked:
external_downloader: A dictionary of protocol keys and the executable of the
external downloader to use for it. The allowed protocols
are default|http|ftp|m3u8|dash|rtsp|rtmp|mms.
Set the value to 'native' to use the native downloader
hls_prefer_native: Deprecated - Use external_downloader = {'m3u8': 'native'}
or {'m3u8': 'ffmpeg'} instead.
Use the native HLS downloader instead of ffmpeg/avconv
if True, otherwise use ffmpeg/avconv if False, otherwise
use downloader suggested by extractor if None.
compat_opts: Compatibility options. See "Differences in default behavior".
The following options do not work when used through the API:
filename, abort-on-error, multistreams, no-live-chat,
no-playlist-metafiles. Refer __init__.py for their implementation
The following parameters are not used by YoutubeDL itself, they are used by
the downloader (see yt_dlp/downloader/common.py):
nopart, updatetime, buffersize, ratelimit, throttledratelimit, min_filesize,
max_filesize, test, noresizebuffer, retries, continuedl, noprogress, consoletitle,
xattr_set_filesize, external_downloader_args, hls_use_mpegts, http_chunk_size.
The following options are used by the post processors:
prefer_ffmpeg: If False, use avconv instead of ffmpeg if both are available,
otherwise prefer ffmpeg. (avconv support is deprecated)
ffmpeg_location: Location of the ffmpeg/avconv binary; either the path
to the binary or its containing directory.
postprocessor_args: A dictionary of postprocessor/executable keys (in lower case)
and a list of additional command-line arguments for the
postprocessor/executable. The dict can also have "PP+EXE" keys
which are used when the given exe is used by the given PP.
Use 'default' as the name for arguments to passed to all PP
The following options are used by the extractors:
extractor_retries: Number of times to retry for known errors
dynamic_mpd: Whether to process dynamic DASH manifests (default: True)
hls_split_discontinuity: Split HLS playlists to different formats at
discontinuities such as ad breaks (default: False)
extractor_args: A dictionary of arguments to be passed to the extractors.
See "EXTRACTOR ARGUMENTS" for details.
Eg: {'youtube': {'skip': ['dash', 'hls']}}
youtube_include_dash_manifest: Deprecated - Use extractor_args instead.
If True (default), DASH manifests and related
data will be downloaded and processed by extractor.
You can reduce network I/O by disabling it if you don't
care about DASH. (only for youtube)
youtube_include_hls_manifest: Deprecated - Use extractor_args instead.
If True (default), HLS manifests and related
data will be downloaded and processed by extractor.
You can reduce network I/O by disabling it if you don't
care about HLS. (only for youtube)
"""
_NUMERIC_FIELDS = set((
'width', 'height', 'tbr', 'abr', 'asr', 'vbr', 'fps', 'filesize', 'filesize_approx',
'timestamp', 'upload_year', 'upload_month', 'upload_day',
'duration', 'view_count', 'like_count', 'dislike_count', 'repost_count',
'average_rating', 'comment_count', 'age_limit',
'start_time', 'end_time',
'chapter_number', 'season_number', 'episode_number',
'track_number', 'disc_number', 'release_year',
'playlist_index',
))
params = None
_ies = []
_pps = {'pre_process': [], 'before_dl': [], 'after_move': [], 'post_process': []}
_printed_messages = set()
_first_webpage_request = True
_download_retcode = None
_num_downloads = None
_playlist_level = 0
_playlist_urls = set()
_screen_file = None
def __init__(self, params=None, auto_init=True):
"""Create a FileDownloader object with the given options."""
if params is None:
params = {}
self._ies = []
self._ies_instances = {}
self._pps = {'pre_process': [], 'before_dl': [], 'after_move': [], 'post_process': []}
self._printed_messages = set()
self._first_webpage_request = True
self._post_hooks = []
self._progress_hooks = []
self._download_retcode = 0
self._num_downloads = 0
self._screen_file = [sys.stdout, sys.stderr][params.get('logtostderr', False)]
self._err_file = sys.stderr
self.params = {
# Default parameters
'nocheckcertificate': False,
}
self.params.update(params)
self.cache = Cache(self)
if sys.version_info < (3, 6):
self.report_warning(
'Python version %d.%d is not supported! Please update to Python 3.6 or above' % sys.version_info[:2])
def check_deprecated(param, option, suggestion):
if self.params.get(param) is not None:
self.report_warning('%s is deprecated. Use %s instead' % (option, suggestion))
return True
return False
if check_deprecated('cn_verification_proxy', '--cn-verification-proxy', '--geo-verification-proxy'):
if self.params.get('geo_verification_proxy') is None:
self.params['geo_verification_proxy'] = self.params['cn_verification_proxy']
check_deprecated('autonumber', '--auto-number', '-o "%(autonumber)s-%(title)s.%(ext)s"')
check_deprecated('usetitle', '--title', '-o "%(title)s-%(id)s.%(ext)s"')
check_deprecated('useid', '--id', '-o "%(id)s.%(ext)s"')
for msg in self.params.get('warnings', []):
self.report_warning(msg)
if self.params.get('final_ext'):
if self.params.get('merge_output_format'):
self.report_warning('--merge-output-format will be ignored since --remux-video or --recode-video is given')
self.params['merge_output_format'] = self.params['final_ext']
if 'overwrites' in self.params and self.params['overwrites'] is None:
del self.params['overwrites']
if params.get('bidi_workaround', False):
try:
import pty
master, slave = pty.openpty()
width = compat_get_terminal_size().columns
if width is None:
width_args = []
else:
width_args = ['-w', str(width)]
sp_kwargs = dict(
stdin=subprocess.PIPE,
stdout=slave,
stderr=self._err_file)
try:
self._output_process = subprocess.Popen(
['bidiv'] + width_args, **sp_kwargs
)
except OSError:
self._output_process = subprocess.Popen(
['fribidi', '-c', 'UTF-8'] + width_args, **sp_kwargs)
self._output_channel = os.fdopen(master, 'rb')
except OSError as ose:
if ose.errno == errno.ENOENT:
self.report_warning('Could not find fribidi executable, ignoring --bidi-workaround . Make sure that fribidi is an executable file in one of the directories in your $PATH.')
else:
raise
if (sys.platform != 'win32'
and sys.getfilesystemencoding() in ['ascii', 'ANSI_X3.4-1968']
and not params.get('restrictfilenames', False)):
# Unicode filesystem API will throw errors (#1474, #13027)
self.report_warning(
'Assuming --restrict-filenames since file system encoding '
'cannot encode all characters. '
'Set the LC_ALL environment variable to fix this.')
self.params['restrictfilenames'] = True
self.outtmpl_dict = self.parse_outtmpl()
# Creating format selector here allows us to catch syntax errors before the extraction
self.format_selector = (
None if self.params.get('format') is None
else self.build_format_selector(self.params['format']))
self._setup_opener()
"""Preload the archive, if any is specified"""
def preload_download_archive(fn):
if fn is None:
return False
self.write_debug('Loading archive file %r\n' % fn)
try:
with locked_file(fn, 'r', encoding='utf-8') as archive_file:
for line in archive_file:
self.archive.add(line.strip())
except IOError as ioe:
if ioe.errno != errno.ENOENT:
raise
return False
return True
self.archive = set()
preload_download_archive(self.params.get('download_archive'))
if auto_init:
self.print_debug_header()
self.add_default_info_extractors()
for pp_def_raw in self.params.get('postprocessors', []):
pp_def = dict(pp_def_raw)
when = pp_def.pop('when', 'post_process')
pp_class = get_postprocessor(pp_def.pop('key'))
pp = pp_class(self, **compat_kwargs(pp_def))
self.add_post_processor(pp, when=when)
for ph in self.params.get('post_hooks', []):
self.add_post_hook(ph)
for ph in self.params.get('progress_hooks', []):
self.add_progress_hook(ph)
register_socks_protocols()
def warn_if_short_id(self, argv):
# short YouTube ID starting with dash?
idxs = [
i for i, a in enumerate(argv)
if re.match(r'^-[0-9A-Za-z_-]{10}$', a)]
if idxs:
correct_argv = (
['yt-dlp']
+ [a for i, a in enumerate(argv) if i not in idxs]
+ ['--'] + [argv[i] for i in idxs]
)
self.report_warning(
'Long argument string detected. '
'Use -- to separate parameters and URLs, like this:\n%s\n' %
args_to_str(correct_argv))
def add_info_extractor(self, ie):
"""Add an InfoExtractor object to the end of the list."""
self._ies.append(ie)
if not isinstance(ie, type):
self._ies_instances[ie.ie_key()] = ie
ie.set_downloader(self)
def get_info_extractor(self, ie_key):
"""
Get an instance of an IE with name ie_key, it will try to get one from
the _ies list, if there's no instance it will create a new one and add
it to the extractor list.
"""
ie = self._ies_instances.get(ie_key)
if ie is None:
ie = get_info_extractor(ie_key)()
self.add_info_extractor(ie)
return ie
def add_default_info_extractors(self):
"""
Add the InfoExtractors returned by gen_extractors to the end of the list
"""
for ie in gen_extractor_classes():
self.add_info_extractor(ie)
def add_post_processor(self, pp, when='post_process'):
"""Add a PostProcessor object to the end of the chain."""
self._pps[when].append(pp)
pp.set_downloader(self)
def add_post_hook(self, ph):
"""Add the post hook"""
self._post_hooks.append(ph)
def add_progress_hook(self, ph):
"""Add the progress hook (currently only for the file downloader)"""
self._progress_hooks.append(ph)
def _bidi_workaround(self, message):
if not hasattr(self, '_output_channel'):
return message
assert hasattr(self, '_output_process')
assert isinstance(message, compat_str)
line_count = message.count('\n') + 1
self._output_process.stdin.write((message + '\n').encode('utf-8'))
self._output_process.stdin.flush()
res = ''.join(self._output_channel.readline().decode('utf-8')
for _ in range(line_count))
return res[:-len('\n')]
def _write_string(self, message, out=None, only_once=False):
if only_once:
if message in self._printed_messages:
return
self._printed_messages.add(message)
write_string(message, out=out, encoding=self.params.get('encoding'))
def to_stdout(self, message, skip_eol=False, quiet=False):
"""Print message to stdout"""
if self.params.get('logger'):
self.params['logger'].debug(message)
elif not quiet or self.params.get('verbose'):
self._write_string(
'%s%s' % (self._bidi_workaround(message), ('' if skip_eol else '\n')),
self._err_file if quiet else self._screen_file)
def to_stderr(self, message, only_once=False):
"""Print message to stderr"""
assert isinstance(message, compat_str)
if self.params.get('logger'):
self.params['logger'].error(message)
else:
self._write_string('%s\n' % self._bidi_workaround(message), self._err_file, only_once=only_once)
def to_console_title(self, message):
if not self.params.get('consoletitle', False):
return
if compat_os_name == 'nt':
if ctypes.windll.kernel32.GetConsoleWindow():
# c_wchar_p() might not be necessary if `message` is
# already of type unicode()
ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message))
elif 'TERM' in os.environ:
self._write_string('\033]0;%s\007' % message, self._screen_file)
def save_console_title(self):
if not self.params.get('consoletitle', False):
return
if self.params.get('simulate', False):
return
if compat_os_name != 'nt' and 'TERM' in os.environ:
# Save the title on stack
self._write_string('\033[22;0t', self._screen_file)
def restore_console_title(self):
if not self.params.get('consoletitle', False):
return
if self.params.get('simulate', False):
return
if compat_os_name != 'nt' and 'TERM' in os.environ:
# Restore the title from stack
self._write_string('\033[23;0t', self._screen_file)
def __enter__(self):
self.save_console_title()
return self
def __exit__(self, *args):
self.restore_console_title()
if self.params.get('cookiefile') is not None:
self.cookiejar.save(ignore_discard=True, ignore_expires=True)
def trouble(self, message=None, tb=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.
tb, if given, is additional traceback information.
"""
if message is not None:
self.to_stderr(message)
if self.params.get('verbose'):
if tb is None:
if sys.exc_info()[0]: # if .trouble has been called from an except block
tb = ''
if hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]:
tb += ''.join(traceback.format_exception(*sys.exc_info()[1].exc_info))
tb += encode_compat_str(traceback.format_exc())
else:
tb_data = traceback.format_list(traceback.extract_stack())
tb = ''.join(tb_data)
if tb:
self.to_stderr(tb)
if not self.params.get('ignoreerrors', False):
if sys.exc_info()[0] and hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]:
exc_info = sys.exc_info()[1].exc_info
else:
exc_info = sys.exc_info()
raise DownloadError(message, exc_info)
self._download_retcode = 1
def to_screen(self, message, skip_eol=False):
"""Print message to stdout if not in quiet mode"""
self.to_stdout(
message, skip_eol, quiet=self.params.get('quiet', False))
def report_warning(self, message, only_once=False):
'''
Print the message to stderr, it will be prefixed with 'WARNING:'
If stderr is a tty file the 'WARNING:' will be colored
'''
if self.params.get('logger') is not None:
self.params['logger'].warning(message)
else:
if self.params.get('no_warnings'):
return
if not self.params.get('no_color') and self._err_file.isatty() and compat_os_name != 'nt':
_msg_header = '\033[0;33mWARNING:\033[0m'
else:
_msg_header = 'WARNING:'
warning_message = '%s %s' % (_msg_header, message)
self.to_stderr(warning_message, only_once)
def report_error(self, message, tb=None):
'''
Do the same as trouble, but prefixes the message with 'ERROR:', colored
in red if stderr is a tty file.
'''
if not self.params.get('no_color') and self._err_file.isatty() and compat_os_name != 'nt':
_msg_header = '\033[0;31mERROR:\033[0m'
else:
_msg_header = 'ERROR:'
error_message = '%s %s' % (_msg_header, message)
self.trouble(error_message, tb)
def write_debug(self, message, only_once=False):
'''Log debug message or Print message to stderr'''
if not self.params.get('verbose', False):
return
message = '[debug] %s' % message
if self.params.get('logger'):
self.params['logger'].debug(message)
else:
self.to_stderr(message, only_once)
def report_file_already_downloaded(self, file_name):
"""Report file has already been fully downloaded."""
try:
self.to_screen('[download] %s has already been downloaded' % file_name)
except UnicodeEncodeError:
self.to_screen('[download] The file has already been downloaded')
def report_file_delete(self, file_name):
"""Report that existing file will be deleted."""
try:
self.to_screen('Deleting existing file %s' % file_name)
except UnicodeEncodeError:
self.to_screen('Deleting existing file')
def parse_outtmpl(self):
outtmpl_dict = self.params.get('outtmpl', {})
if not isinstance(outtmpl_dict, dict):
outtmpl_dict = {'default': outtmpl_dict}
outtmpl_dict.update({
k: v for k, v in DEFAULT_OUTTMPL.items()
if not outtmpl_dict.get(k)})
for key, val in outtmpl_dict.items():
if isinstance(val, bytes):
self.report_warning(
'Parameter outtmpl is bytes, but should be a unicode string. '
'Put from __future__ import unicode_literals at the top of your code file or consider switching to Python 3.x.')
return outtmpl_dict
def get_output_path(self, dir_type='', filename=None):
paths = self.params.get('paths', {})
assert isinstance(paths, dict)
path = os.path.join(
expand_path(paths.get('home', '').strip()),
expand_path(paths.get(dir_type, '').strip()) if dir_type else '',
filename or '')
# Temporary fix for #4787
# 'Treat' all problem characters by passing filename through preferredencoding
# to workaround encoding issues with subprocess on python2 @ Windows
if sys.version_info < (3, 0) and sys.platform == 'win32':
path = encodeFilename(path, True).decode(preferredencoding())
return sanitize_path(path, force=self.params.get('windowsfilenames'))
@staticmethod
def validate_outtmpl(tmpl):
''' @return None or Exception object '''
try:
re.sub(
STR_FORMAT_RE.format(''),
lambda mobj: ('%' if not mobj.group('has_key') else '') + mobj.group(0),
tmpl
) % collections.defaultdict(int)
return None
except ValueError as err:
return err
def prepare_outtmpl(self, outtmpl, info_dict, sanitize=None):
""" Make the template and info_dict suitable for substitution (outtmpl % info_dict)"""
info_dict = dict(info_dict)
na = self.params.get('outtmpl_na_placeholder', 'NA')
info_dict['duration_string'] = ( # %(duration>%H-%M-%S)s is wrong if duration > 24hrs
formatSeconds(info_dict['duration'], '-' if sanitize else ':')
if info_dict.get('duration', None) is not None
else None)
info_dict['epoch'] = int(time.time())
info_dict['autonumber'] = self.params.get('autonumber_start', 1) - 1 + self._num_downloads
if info_dict.get('resolution') is None:
info_dict['resolution'] = self.format_resolution(info_dict, default=None)
# For fields playlist_index and autonumber convert all occurrences
# of %(field)s to %(field)0Nd for backward compatibility
field_size_compat_map = {
'playlist_index': len(str(info_dict.get('_last_playlist_index') or '')),
'autonumber': self.params.get('autonumber_size') or 5,
}
TMPL_DICT = {}
EXTERNAL_FORMAT_RE = re.compile(STR_FORMAT_RE.format('[^)]*'))
MATH_FUNCTIONS = {
'+': float.__add__,
'-': float.__sub__,
}
# Field is of the form key1.key2...
# where keys (except first) can be string, int or slice
FIELD_RE = r'\w+(?:\.(?:\w+|{num}|{num}?(?::{num}?){{1,2}}))*'.format(num=r'(?:-?\d+)')
MATH_FIELD_RE = r'''{field}|{num}'''.format(field=FIELD_RE, num=r'-?\d+(?:.\d+)?')
MATH_OPERATORS_RE = r'(?:%s)' % '|'.join(map(re.escape, MATH_FUNCTIONS.keys()))
INTERNAL_FORMAT_RE = re.compile(r'''(?x)
(?P<negate>-)?
(?P<fields>{field})
(?P<maths>(?:{math_op}{math_field})*)
(?:>(?P<strf_format>.+?))?
(?:\|(?P<default>.*?))?
$'''.format(field=FIELD_RE, math_op=MATH_OPERATORS_RE, math_field=MATH_FIELD_RE))
get_key = lambda k: traverse_obj(
info_dict, k.split('.'), is_user_input=True, traverse_string=True)
def get_value(mdict):
# Object traversal
value = get_key(mdict['fields'])
# Negative
if mdict['negate']:
value = float_or_none(value)
if value is not None:
value *= -1
# Do maths
offset_key = mdict['maths']
if offset_key:
value = float_or_none(value)
operator = None
while offset_key:
item = re.match(
MATH_FIELD_RE if operator else MATH_OPERATORS_RE,
offset_key).group(0)
offset_key = offset_key[len(item):]
if operator is None:
operator = MATH_FUNCTIONS[item]
continue
item, multiplier = (item[1:], -1) if item[0] == '-' else (item, 1)
offset = float_or_none(item)
if offset is None:
offset = float_or_none(get_key(item))
try:
value = operator(value, multiplier * offset)
except (TypeError, ZeroDivisionError):
return None
operator = None
# Datetime formatting
if mdict['strf_format']:
value = strftime_or_none(value, mdict['strf_format'])
return value
def create_key(outer_mobj):
if not outer_mobj.group('has_key'):
return '%{}'.format(outer_mobj.group(0))
key = outer_mobj.group('key')
fmt = outer_mobj.group('format')
mobj = re.match(INTERNAL_FORMAT_RE, key)
if mobj is None:
value, default, mobj = None, na, {'fields': ''}
else:
mobj = mobj.groupdict()
default = mobj['default'] if mobj['default'] is not None else na
value = get_value(mobj)
if fmt == 's' and value is not None and key in field_size_compat_map.keys():
fmt = '0{:d}d'.format(field_size_compat_map[key])
value = default if value is None else value
if fmt == 'c':
value = compat_str(value)
if value is None:
value, fmt = default, 's'
else:
value = value[0]
elif fmt[-1] not in 'rs': # numeric
value = float_or_none(value)
if value is None:
value, fmt = default, 's'
if sanitize:
if fmt[-1] == 'r':
# If value is an object, sanitize might convert it to a string
# So we convert it to repr first
value, fmt = repr(value), '%ss' % fmt[:-1]
if fmt[-1] in 'csr':
value = sanitize(mobj['fields'].split('.')[-1], value)
key += '\0%s' % fmt
TMPL_DICT[key] = value
return '%({key}){fmt}'.format(key=key, fmt=fmt)
return EXTERNAL_FORMAT_RE.sub(create_key, outtmpl), TMPL_DICT
def _prepare_filename(self, info_dict, tmpl_type='default'):
try:
sanitize = lambda k, v: sanitize_filename(
compat_str(v),
restricted=self.params.get('restrictfilenames'),
is_id=(k == 'id' or k.endswith('_id')))
outtmpl = self.outtmpl_dict.get(tmpl_type, self.outtmpl_dict['default'])
outtmpl, template_dict = self.prepare_outtmpl(outtmpl, info_dict, sanitize)
# expand_path translates '%%' into '%' and '$$' into '$'
# correspondingly that is not what we want since we need to keep
# '%%' intact for template dict substitution step. Working around
# with boundary-alike separator hack.
sep = ''.join([random.choice(ascii_letters) for _ in range(32)])
outtmpl = outtmpl.replace('%%', '%{0}%'.format(sep)).replace('$$', '${0}$'.format(sep))
# outtmpl should be expand_path'ed before template dict substitution
# because meta fields may contain env variables we don't want to
# be expanded. For example, for outtmpl "%(title)s.%(ext)s" and
# title "Hello $PATH", we don't want `$PATH` to be expanded.
filename = expand_path(outtmpl).replace(sep, '') % template_dict