forked from yt-dlp/yt-dlp
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathcommon.py
3669 lines (3306 loc) · 171 KB
/
common.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
# coding: utf-8
from __future__ import unicode_literals
import base64
import datetime
import hashlib
import itertools
import json
import netrc
import os
import random
import re
import sys
import time
import math
from ..compat import (
compat_cookiejar_Cookie,
compat_cookies_SimpleCookie,
compat_etree_Element,
compat_etree_fromstring,
compat_expanduser,
compat_getpass,
compat_http_client,
compat_os_name,
compat_str,
compat_urllib_error,
compat_urllib_parse_unquote,
compat_urllib_parse_urlencode,
compat_urllib_request,
compat_urlparse,
compat_xml_parse_error,
)
from ..downloader import FileDownloader
from ..downloader.f4m import (
get_base_url,
remove_encrypted_media,
)
from ..utils import (
age_restricted,
base_url,
bug_reports_message,
clean_html,
compiled_regex_type,
determine_ext,
determine_protocol,
dict_get,
error_to_compat_str,
extract_attributes,
ExtractorError,
fix_xml_ampersands,
float_or_none,
format_field,
GeoRestrictedError,
GeoUtils,
int_or_none,
js_to_json,
JSON_LD_RE,
mimetype2ext,
network_exceptions,
NO_DEFAULT,
orderedSet,
parse_bitrate,
parse_codecs,
parse_duration,
parse_iso8601,
parse_m3u8_attributes,
parse_resolution,
RegexNotFoundError,
sanitize_filename,
sanitized_Request,
str_or_none,
str_to_int,
strip_or_none,
traverse_obj,
unescapeHTML,
unified_strdate,
unified_timestamp,
update_Request,
update_url_query,
url_basename,
url_or_none,
urljoin,
variadic,
xpath_element,
xpath_text,
xpath_with_ns,
)
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 YoutubeDL. The YoutubeDL processes this
information possibly downloading the video to the file system, among
other possible outcomes.
The type field determines the type of the result.
By far the most common value (and the default if _type is missing) is
"video", which indicates a single video.
For a video, the dictionaries must include the following fields:
id: Video identifier.
title: Video title, unescaped.
Additionally, it must contain either a formats entry or a url one:
formats: A list of dictionaries for each format available, ordered
from worst to best quality.
Potential fields:
* url The mandatory URL representing the media:
for plain file media - HTTP URL of this file,
for RTMP - RTMP URL,
for HLS - URL of the M3U8 media playlist,
for HDS - URL of the F4M manifest,
for DASH
- HTTP URL to plain file media (in case of
unfragmented media)
- URL of the MPD manifest or base URL
representing the media if MPD manifest
is parsed from a string (in case of
fragmented media)
for MSS - URL of the ISM manifest.
* manifest_url
The URL of the manifest file in case of
fragmented media:
for HLS - URL of the M3U8 master playlist,
for HDS - URL of the F4M manifest,
for DASH - URL of the MPD manifest,
for MSS - URL of the ISM manifest.
* ext Will be calculated from URL if missing
* format A human-readable description of the format
("mp4 container with h264/opus").
Calculated from the format_id, width, height.
and format_note fields if missing.
* format_id A short description of the format
("mp4_h264_opus" or "19").
Technically optional, but strongly recommended.
* format_note Additional info about the format
("3D" or "DASH video")
* width Width of the video, if known
* height Height of the video, if known
* resolution Textual description of width and height
* dynamic_range The dynamic range of the video. One of:
"SDR" (None), "HDR10", "HDR10+, "HDR12", "HLG, "DV"
* tbr Average bitrate of audio and video in KBit/s
* abr Average audio bitrate in KBit/s
* acodec Name of the audio codec in use
* asr Audio sampling rate in Hertz
* vbr Average video bitrate in KBit/s
* fps Frame rate
* vcodec Name of the video codec in use
* container Name of the container format
* filesize The number of bytes, if known in advance
* filesize_approx An estimate for the number of bytes
* player_url SWF Player URL (used for rtmpdump).
* protocol The protocol that will be used for the actual
download, lower-case.
"http", "https", "rtsp", "rtmp", "rtmp_ffmpeg", "rtmpe",
"m3u8", "m3u8_native" or "http_dash_segments".
* fragment_base_url
Base URL for fragments. Each fragment's path
value (if present) will be relative to
this URL.
* fragments A list of fragments of a fragmented media.
Each fragment entry must contain either an url
or a path. If an url is present it should be
considered by a client. Otherwise both path and
fragment_base_url must be present. Here is
the list of all potential fields:
* "url" - fragment's URL
* "path" - fragment's path relative to
fragment_base_url
* "duration" (optional, int or float)
* "filesize" (optional, int)
* preference Order number of this format. If this field is
present and not None, the formats get sorted
by this field, regardless of all other values.
-1 for default (order by other properties),
-2 or smaller for less than default.
< -1000 to hide the format (if there is
another one which is strictly better)
* language Language code, e.g. "de" or "en-US".
* language_preference Is this in the language mentioned in
the URL?
10 if it's what the URL is about,
-1 for default (don't know),
-10 otherwise, other values reserved for now.
* quality Order number of the video quality of this
format, irrespective of the file format.
-1 for default (order by other properties),
-2 or smaller for less than default.
* source_preference Order number for this video source
(quality takes higher priority)
-1 for default (order by other properties),
-2 or smaller for less than default.
* http_headers A dictionary of additional HTTP headers
to add to the request.
* stretched_ratio If given and not 1, indicates that the
video's pixels are not square.
width : height ratio as float.
* no_resume The server does not support resuming the
(HTTP or RTMP) download. Boolean.
* has_drm The format has DRM and cannot be downloaded. Boolean
* downloader_options A dictionary of downloader options as
described in FileDownloader
RTMP formats can also have the additional fields: page_url,
app, play_path, tc_url, flash_version, rtmp_live, rtmp_conn,
rtmp_protocol, rtmp_real_time
url: Final video URL.
ext: Video filename extension.
format: The video format, defaults to ext (used for --get-format)
player_url: SWF Player URL (used for rtmpdump).
The following fields are optional:
alt_title: A secondary title of the video.
display_id An alternative identifier for the video, not necessarily
unique, but available before title. Typically, id is
something like "4234987", title "Dancing naked mole rats",
and display_id "dancing-naked-mole-rats"
thumbnails: A list of dictionaries, with the following entries:
* "id" (optional, string) - Thumbnail format ID
* "url"
* "preference" (optional, int) - quality of the image
* "width" (optional, int)
* "height" (optional, int)
* "resolution" (optional, string "{width}x{height}",
deprecated)
* "filesize" (optional, int)
thumbnail: Full URL to a video thumbnail image.
description: Full video description.
uploader: Full name of the video uploader.
license: License name the video is licensed under.
creator: The creator of the video.
release_timestamp: UNIX timestamp of the moment the video was released.
release_date: The date (YYYYMMDD) when the video was released.
timestamp: UNIX timestamp of the moment the video was uploaded
upload_date: Video upload date (YYYYMMDD).
If not explicitly set, calculated from timestamp.
uploader_id: Nickname or id of the video uploader.
uploader_url: Full URL to a personal webpage of the video uploader.
channel: Full name of the channel the video is uploaded on.
Note that channel fields may or may not repeat uploader
fields. This depends on a particular extractor.
channel_id: Id of the channel.
channel_url: Full URL to a channel webpage.
location: Physical location where the video was filmed.
subtitles: The available subtitles as a dictionary in the format
{tag: subformats}. "tag" is usually a language code, and
"subformats" is a list sorted from lower to higher
preference, each element is a dictionary with the "ext"
entry and one of:
* "data": The subtitles file contents
* "url": A URL pointing to the subtitles file
It can optionally also have:
* "name": Name or description of the subtitles
"ext" will be calculated from URL if missing
automatic_captions: Like 'subtitles'; contains automatically generated
captions instead of normal subtitles
duration: Length of the video in seconds, as an integer or float.
view_count: How many users have watched the video on the platform.
like_count: Number of positive ratings of the video
dislike_count: Number of negative ratings of the video
repost_count: Number of reposts of the video
average_rating: Average rating give by users, the scale used depends on the webpage
comment_count: Number of comments on the video
comments: A list of comments, each with one or more of the following
properties (all but one of text or html optional):
* "author" - human-readable name of the comment author
* "author_id" - user ID of the comment author
* "author_thumbnail" - The thumbnail of the comment author
* "id" - Comment ID
* "html" - Comment as HTML
* "text" - Plain text of the comment
* "timestamp" - UNIX timestamp of comment
* "parent" - ID of the comment this one is replying to.
Set to "root" to indicate that this is a
comment to the original video.
* "like_count" - Number of positive ratings of the comment
* "dislike_count" - Number of negative ratings of the comment
* "is_favorited" - Whether the comment is marked as
favorite by the video uploader
* "author_is_uploader" - Whether the comment is made by
the video uploader
age_limit: Age restriction for the video, as an integer (years)
webpage_url: The URL to the video webpage, if given to yt-dlp it
should allow to get the same result again. (It will be set
by YoutubeDL if it's missing)
categories: A list of categories that the video falls in, for example
["Sports", "Berlin"]
tags: A list of tags assigned to the video, e.g. ["sweden", "pop music"]
cast: A list of the video cast
is_live: True, False, or None (=unknown). Whether this video is a
live stream that goes on instead of a fixed-length video.
was_live: True, False, or None (=unknown). Whether this video was
originally a live stream.
live_status: 'is_live', 'is_upcoming', 'was_live', 'not_live' or None (=unknown)
If absent, automatically set from is_live, was_live
start_time: Time in seconds where the reproduction should start, as
specified in the URL.
end_time: Time in seconds where the reproduction should end, as
specified in the URL.
chapters: A list of dictionaries, with the following entries:
* "start_time" - The start time of the chapter in seconds
* "end_time" - The end time of the chapter in seconds
* "title" (optional, string)
playable_in_embed: Whether this video is allowed to play in embedded
players on other sites. Can be True (=always allowed),
False (=never allowed), None (=unknown), or a string
specifying the criteria for embedability (Eg: 'whitelist')
availability: Under what condition the video is available. One of
'private', 'premium_only', 'subscriber_only', 'needs_auth',
'unlisted' or 'public'. Use 'InfoExtractor._availability'
to set it
__post_extractor: A function to be called just before the metadata is
written to either disk, logger or console. The function
must return a dict which will be added to the info_dict.
This is usefull for additional information that is
time-consuming to extract. Note that the fields thus
extracted will not be available to output template and
match_filter. So, only "comments" and "comment_count" are
currently allowed to be extracted via this method.
The following fields should only be used when the video belongs to some logical
chapter or section:
chapter: Name or title of the chapter the video belongs to.
chapter_number: Number of the chapter the video belongs to, as an integer.
chapter_id: Id of the chapter the video belongs to, as a unicode string.
The following fields should only be used when the video is an episode of some
series, programme or podcast:
series: Title of the series or programme the video episode belongs to.
season: Title of the season the video episode belongs to.
season_number: Number of the season the video episode belongs to, as an integer.
season_id: Id of the season the video episode belongs to, as a unicode string.
episode: Title of the video episode. Unlike mandatory video title field,
this field should denote the exact title of the video episode
without any kind of decoration.
episode_number: Number of the video episode within a season, as an integer.
episode_id: Id of the video episode, as a unicode string.
The following fields should only be used when the media is a track or a part of
a music album:
track: Title of the track.
track_number: Number of the track within an album or a disc, as an integer.
track_id: Id of the track (useful in case of custom indexing, e.g. 6.iii),
as a unicode string.
artist: Artist(s) of the track.
genre: Genre(s) of the track.
album: Title of the album the track belongs to.
album_type: Type of the album (e.g. "Demo", "Full-length", "Split", "Compilation", etc).
album_artist: List of all artists appeared on the album (e.g.
"Ash Borer / Fell Voices" or "Various Artists", useful for splits
and compilations).
disc_number: Number of the disc or other physical medium the track belongs to,
as an integer.
release_year: Year (YYYY) when the album was released.
Unless mentioned otherwise, the fields should be Unicode strings.
Unless mentioned otherwise, None is equivalent to absence of information.
_type "playlist" indicates multiple videos.
There must be a key "entries", which is a list, an iterable, or a PagedList
object, each element of which is a valid dictionary by this specification.
Additionally, playlists can have "id", "title", and any other relevent
attributes with the same semantics as videos (see above).
_type "multi_video" indicates that there are multiple videos that
form a single show, for examples multiple acts of an opera or TV episode.
It must have an entries key like a playlist and contain all the keys
required for a video at the same time.
_type "url" indicates that the video must be extracted from another
location, possibly by a different extractor. Its only required key is:
"url" - the next URL to extract.
The key "ie_key" can be set to the class name (minus the trailing "IE",
e.g. "Youtube") if the extractor class is known in advance.
Additionally, the dictionary may have any properties of the resolved entity
known in advance, for example "title" if the title of the referred video is
known ahead of time.
_type "url_transparent" entities have the same specification as "url", but
indicate that the given additional information is more precise than the one
associated with the resolved URL.
This is useful when a site employs a video service that hosts the video and
its technical metadata, but that video service does not embed a useful
title, description etc.
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.
Subclasses may also override suitable() if necessary, but ensure the function
signature is preserved and that this function imports everything it needs
(except other extractors), so that lazy_extractors works correctly
_GEO_BYPASS attribute may be set to False in order to disable
geo restriction bypass mechanisms for a particular extractor.
Though it won't disable explicit geo restriction bypass based on
country code provided with geo_bypass_country.
_GEO_COUNTRIES attribute may contain a list of presumably geo unrestricted
countries for this extractor. One of these countries will be used by
geo restriction bypass mechanism right away in order to bypass
geo restriction, of course, if the mechanism is not disabled.
_GEO_IP_BLOCKS attribute may contain a list of presumably geo unrestricted
IP blocks in CIDR notation for this extractor. One of these IP blocks
will be used by geo restriction bypass mechanism similarly
to _GEO_COUNTRIES.
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
_x_forwarded_for_ip = None
_GEO_BYPASS = True
_GEO_COUNTRIES = None
_GEO_IP_BLOCKS = None
_WORKING = True
_LOGIN_HINTS = {
'any': 'Use --cookies, --username and --password or --netrc to provide account credentials',
'cookies': (
'Use --cookies-from-browser or --cookies for the authentication. '
'See https://github.com/ytdl-org/youtube-dl#how-do-i-pass-cookies-to-youtube-dl for how to manually pass cookies'),
'password': 'Use --username and --password or --netrc to provide account credentials',
}
def __init__(self, downloader=None):
"""Constructor. Receives an optional downloader (a YoutubeDL instance).
If a downloader is not passed during initialization,
it must be set using "set_downloader()" before "extract()" is called"""
self._ready = False
self._x_forwarded_for_ip = None
self._printed_messages = set()
self.set_downloader(downloader)
@classmethod
def _match_valid_url(cls, url):
# This does not use has/getattr intentionally - we want to know whether
# we have cached the regexp for *this* class, whereas getattr would also
# match the superclass
if '_VALID_URL_RE' not in cls.__dict__:
cls._VALID_URL_RE = re.compile(cls._VALID_URL)
return cls._VALID_URL_RE.match(url)
@classmethod
def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE."""
# This function must import everything it needs (except other extractors),
# so that lazy_extractors works correctly
return cls._match_valid_url(url) is not None
@classmethod
def _match_id(cls, url):
return cls._match_valid_url(url).group('id')
@classmethod
def get_temp_id(cls, url):
try:
return cls._match_id(url)
except (IndexError, AttributeError):
return None
@classmethod
def working(cls):
"""Getter method for _WORKING."""
return cls._WORKING
def initialize(self):
"""Initializes an instance (authentication, etc)."""
self._printed_messages = set()
self._initialize_geo_bypass({
'countries': self._GEO_COUNTRIES,
'ip_blocks': self._GEO_IP_BLOCKS,
})
if not self._ready:
self._real_initialize()
self._ready = True
def _initialize_geo_bypass(self, geo_bypass_context):
"""
Initialize geo restriction bypass mechanism.
This method is used to initialize geo bypass mechanism based on faking
X-Forwarded-For HTTP header. A random country from provided country list
is selected and a random IP belonging to this country is generated. This
IP will be passed as X-Forwarded-For HTTP header in all subsequent
HTTP requests.
This method will be used for initial geo bypass mechanism initialization
during the instance initialization with _GEO_COUNTRIES and
_GEO_IP_BLOCKS.
You may also manually call it from extractor's code if geo bypass
information is not available beforehand (e.g. obtained during
extraction) or due to some other reason. In this case you should pass
this information in geo bypass context passed as first argument. It may
contain following fields:
countries: List of geo unrestricted countries (similar
to _GEO_COUNTRIES)
ip_blocks: List of geo unrestricted IP blocks in CIDR notation
(similar to _GEO_IP_BLOCKS)
"""
if not self._x_forwarded_for_ip:
# Geo bypass mechanism is explicitly disabled by user
if not self.get_param('geo_bypass', True):
return
if not geo_bypass_context:
geo_bypass_context = {}
# Backward compatibility: previously _initialize_geo_bypass
# expected a list of countries, some 3rd party code may still use
# it this way
if isinstance(geo_bypass_context, (list, tuple)):
geo_bypass_context = {
'countries': geo_bypass_context,
}
# The whole point of geo bypass mechanism is to fake IP
# as X-Forwarded-For HTTP header based on some IP block or
# country code.
# Path 1: bypassing based on IP block in CIDR notation
# Explicit IP block specified by user, use it right away
# regardless of whether extractor is geo bypassable or not
ip_block = self.get_param('geo_bypass_ip_block', None)
# Otherwise use random IP block from geo bypass context but only
# if extractor is known as geo bypassable
if not ip_block:
ip_blocks = geo_bypass_context.get('ip_blocks')
if self._GEO_BYPASS and ip_blocks:
ip_block = random.choice(ip_blocks)
if ip_block:
self._x_forwarded_for_ip = GeoUtils.random_ipv4(ip_block)
self._downloader.write_debug(
'[debug] Using fake IP %s as X-Forwarded-For' % self._x_forwarded_for_ip)
return
# Path 2: bypassing based on country code
# Explicit country code specified by user, use it right away
# regardless of whether extractor is geo bypassable or not
country = self.get_param('geo_bypass_country', None)
# Otherwise use random country code from geo bypass context but
# only if extractor is known as geo bypassable
if not country:
countries = geo_bypass_context.get('countries')
if self._GEO_BYPASS and countries:
country = random.choice(countries)
if country:
self._x_forwarded_for_ip = GeoUtils.random_ipv4(country)
self._downloader.write_debug(
'Using fake IP %s (%s) as X-Forwarded-For' % (self._x_forwarded_for_ip, country.upper()))
def extract(self, url):
"""Extracts URL information and returns it in list of dicts."""
try:
for _ in range(2):
try:
self.initialize()
self.write_debug('Extracting URL: %s' % url)
ie_result = self._real_extract(url)
if ie_result is None:
return None
if self._x_forwarded_for_ip:
ie_result['__x_forwarded_for_ip'] = self._x_forwarded_for_ip
subtitles = ie_result.get('subtitles')
if (subtitles and 'live_chat' in subtitles
and 'no-live-chat' in self.get_param('compat_opts', [])):
del subtitles['live_chat']
return ie_result
except GeoRestrictedError as e:
if self.__maybe_fake_ip_and_retry(e.countries):
continue
raise
except ExtractorError as e:
video_id = e.video_id or self.get_temp_id(url)
raise ExtractorError(
e.msg, video_id=video_id, ie=self.IE_NAME, tb=e.traceback, expected=e.expected, cause=e.cause)
except compat_http_client.IncompleteRead as e:
raise ExtractorError('A network error has occurred.', cause=e, expected=True, video_id=self.get_temp_id(url))
except (KeyError, StopIteration) as e:
raise ExtractorError('An extractor error has occurred.', cause=e, video_id=self.get_temp_id(url))
def __maybe_fake_ip_and_retry(self, countries):
if (not self.get_param('geo_bypass_country', None)
and self._GEO_BYPASS
and self.get_param('geo_bypass', True)
and not self._x_forwarded_for_ip
and countries):
country_code = random.choice(countries)
self._x_forwarded_for_ip = GeoUtils.random_ipv4(country_code)
if self._x_forwarded_for_ip:
self.report_warning(
'Video is geo restricted. Retrying extraction with fake IP %s (%s) as X-Forwarded-For.'
% (self._x_forwarded_for_ip, country_code.upper()))
return True
return False
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
@classmethod
def ie_key(cls):
"""A string for getting the InfoExtractor with get_info_extractor"""
return cls.__name__[:-2]
@property
def IE_NAME(self):
return compat_str(type(self).__name__[:-2])
@staticmethod
def __can_accept_status_code(err, expected_status):
assert isinstance(err, compat_urllib_error.HTTPError)
if expected_status is None:
return False
elif callable(expected_status):
return expected_status(err.code) is True
else:
return err.code in variadic(expected_status)
def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, data=None, headers={}, query={}, expected_status=None):
"""
Return the response handle.
See _download_webpage docstring for arguments specification.
"""
if not self._downloader._first_webpage_request:
sleep_interval = self.get_param('sleep_interval_requests') or 0
if sleep_interval > 0:
self.to_screen('Sleeping %s seconds ...' % sleep_interval)
time.sleep(sleep_interval)
else:
self._downloader._first_webpage_request = False
if note is None:
self.report_download_webpage(video_id)
elif note is not False:
if video_id is None:
self.to_screen('%s' % (note,))
else:
self.to_screen('%s: %s' % (video_id, note))
# Some sites check X-Forwarded-For HTTP header in order to figure out
# the origin of the client behind proxy. This allows bypassing geo
# restriction by faking this header's value to IP that belongs to some
# geo unrestricted country. We will do so once we encounter any
# geo restriction error.
if self._x_forwarded_for_ip:
if 'X-Forwarded-For' not in headers:
headers['X-Forwarded-For'] = self._x_forwarded_for_ip
if isinstance(url_or_request, compat_urllib_request.Request):
url_or_request = update_Request(
url_or_request, data=data, headers=headers, query=query)
else:
if query:
url_or_request = update_url_query(url_or_request, query)
if data is not None or headers:
url_or_request = sanitized_Request(url_or_request, data, headers)
try:
return self._downloader.urlopen(url_or_request)
except network_exceptions as err:
if isinstance(err, compat_urllib_error.HTTPError):
if self.__can_accept_status_code(err, expected_status):
# Retain reference to error to prevent file object from
# being closed before it can be read. Works around the
# effects of <https://bugs.python.org/issue15002>
# introduced in Python 3.4.1.
err.fp._error = err
return err.fp
if errnote is False:
return False
if errnote is None:
errnote = 'Unable to download webpage'
errmsg = '%s: %s' % (errnote, error_to_compat_str(err))
if fatal:
raise ExtractorError(errmsg, sys.exc_info()[2], cause=err)
else:
self.report_warning(errmsg)
return False
def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None, data=None, headers={}, query={}, expected_status=None):
"""
Return a tuple (page content as string, URL handle).
See _download_webpage docstring for arguments specification.
"""
# Strip hashes from the URL (#1038)
if isinstance(url_or_request, (compat_str, str)):
url_or_request = url_or_request.partition('#')[0]
urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal, data=data, headers=headers, query=query, expected_status=expected_status)
if urlh is False:
assert not fatal
return False
content = self._webpage_read_content(urlh, url_or_request, video_id, note, errnote, fatal, encoding=encoding)
return (content, urlh)
@staticmethod
def _guess_encoding_from_content(content_type, webpage_bytes):
m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
if m:
encoding = m.group(1)
else:
m = re.search(br'<meta[^>]+charset=[\'"]?([^\'")]+)[ /\'">]',
webpage_bytes[:1024])
if m:
encoding = m.group(1).decode('ascii')
elif webpage_bytes.startswith(b'\xff\xfe'):
encoding = 'utf-16'
else:
encoding = 'utf-8'
return encoding
def __check_blocked(self, content):
first_block = content[:512]
if ('<title>Access to this site is blocked</title>' in content
and 'Websense' in first_block):
msg = 'Access to this webpage has been blocked by Websense filtering software in your network.'
blocked_iframe = self._html_search_regex(
r'<iframe src="([^"]+)"', content,
'Websense information URL', default=None)
if blocked_iframe:
msg += ' Visit %s for more details' % blocked_iframe
raise ExtractorError(msg, expected=True)
if '<title>The URL you requested has been blocked</title>' in first_block:
msg = (
'Access to this webpage has been blocked by Indian censorship. '
'Use a VPN or proxy server (with --proxy) to route around it.')
block_msg = self._html_search_regex(
r'</h1><p>(.*?)</p>',
content, 'block message', default=None)
if block_msg:
msg += ' (Message: "%s")' % block_msg.replace('\n', ' ')
raise ExtractorError(msg, expected=True)
if ('<title>TTK :: Доступ к ресурсу ограничен</title>' in content
and 'blocklist.rkn.gov.ru' in content):
raise ExtractorError(
'Access to this webpage has been blocked by decision of the Russian government. '
'Visit http://blocklist.rkn.gov.ru/ for a block reason.',
expected=True)
def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True, prefix=None, encoding=None):
content_type = urlh.headers.get('Content-Type', '')
webpage_bytes = urlh.read()
if prefix is not None:
webpage_bytes = prefix + webpage_bytes
if not encoding:
encoding = self._guess_encoding_from_content(content_type, webpage_bytes)
if self.get_param('dump_intermediate_pages', False):
self.to_screen('Dumping request to ' + urlh.geturl())
dump = base64.b64encode(webpage_bytes).decode('ascii')
self._downloader.to_screen(dump)
if self.get_param('write_pages', False):
basen = '%s_%s' % (video_id, urlh.geturl())
trim_length = self.get_param('trim_file_name') or 240
if len(basen) > trim_length:
h = '___' + hashlib.md5(basen.encode('utf-8')).hexdigest()
basen = basen[:trim_length - len(h)] + h
raw_filename = basen + '.dump'
filename = sanitize_filename(raw_filename, restricted=True)
self.to_screen('Saving request to ' + filename)
# Working around MAX_PATH limitation on Windows (see
# http://msdn.microsoft.com/en-us/library/windows/desktop/aa365247(v=vs.85).aspx)
if compat_os_name == 'nt':
absfilepath = os.path.abspath(filename)
if len(absfilepath) > 259:
filename = '\\\\?\\' + absfilepath
with open(filename, 'wb') as outf:
outf.write(webpage_bytes)
try:
content = webpage_bytes.decode(encoding, 'replace')
except LookupError:
content = webpage_bytes.decode('utf-8', 'replace')
self.__check_blocked(content)
return content
def _download_webpage(
self, url_or_request, video_id, note=None, errnote=None,
fatal=True, tries=1, timeout=5, encoding=None, data=None,
headers={}, query={}, expected_status=None):
"""
Return the data of the page as a string.
Arguments:
url_or_request -- plain text URL as a string or
a compat_urllib_request.Requestobject
video_id -- Video/playlist/item identifier (string)
Keyword arguments:
note -- note printed before downloading (string)
errnote -- note printed in case of an error (string)
fatal -- flag denoting whether error should be considered fatal,
i.e. whether it should cause ExtractionError to be raised,
otherwise a warning will be reported and extraction continued
tries -- number of tries
timeout -- sleep interval between tries
encoding -- encoding for a page content decoding, guessed automatically
when not explicitly specified
data -- POST data (bytes)
headers -- HTTP headers (dict)
query -- URL query (dict)
expected_status -- allows to accept failed HTTP requests (non 2xx
status code) by explicitly specifying a set of accepted status
codes. Can be any of the following entities:
- an integer type specifying an exact failed status code to
accept
- a list or a tuple of integer types specifying a list of
failed status codes to accept
- a callable accepting an actual failed status code and
returning True if it should be accepted
Note that this argument does not affect success status codes (2xx)
which are always accepted.
"""
success = False
try_count = 0
while success is False:
try:
res = self._download_webpage_handle(
url_or_request, video_id, note, errnote, fatal,
encoding=encoding, data=data, headers=headers, query=query,
expected_status=expected_status)
success = True
except compat_http_client.IncompleteRead as e:
try_count += 1
if try_count >= tries:
raise e
self._sleep(timeout, video_id)
if res is False:
return res
else:
content, _ = res
return content
def _download_xml_handle(
self, url_or_request, video_id, note='Downloading XML',
errnote='Unable to download XML', transform_source=None,
fatal=True, encoding=None, data=None, headers={}, query={},
expected_status=None):
"""
Return a tuple (xml as an compat_etree_Element, URL handle).
See _download_webpage docstring for arguments specification.
"""
res = self._download_webpage_handle(
url_or_request, video_id, note, errnote, fatal=fatal,
encoding=encoding, data=data, headers=headers, query=query,
expected_status=expected_status)
if res is False:
return res
xml_string, urlh = res
return self._parse_xml(
xml_string, video_id, transform_source=transform_source,
fatal=fatal), urlh
def _download_xml(
self, url_or_request, video_id,
note='Downloading XML', errnote='Unable to download XML',
transform_source=None, fatal=True, encoding=None,
data=None, headers={}, query={}, expected_status=None):
"""
Return the xml as an compat_etree_Element.
See _download_webpage docstring for arguments specification.
"""
res = self._download_xml_handle(
url_or_request, video_id, note=note, errnote=errnote,
transform_source=transform_source, fatal=fatal, encoding=encoding,
data=data, headers=headers, query=query,
expected_status=expected_status)
return res if res is False else res[0]
def _parse_xml(self, xml_string, video_id, transform_source=None, fatal=True):
if transform_source:
xml_string = transform_source(xml_string)
try:
return compat_etree_fromstring(xml_string.encode('utf-8'))
except compat_xml_parse_error as ve:
errmsg = '%s: Failed to parse XML ' % video_id
if fatal:
raise ExtractorError(errmsg, cause=ve)
else:
self.report_warning(errmsg + str(ve))
def _download_json_handle(
self, url_or_request, video_id, note='Downloading JSON metadata',
errnote='Unable to download JSON metadata', transform_source=None,
fatal=True, encoding=None, data=None, headers={}, query={},
expected_status=None):
"""
Return a tuple (JSON object, URL handle).
See _download_webpage docstring for arguments specification.
"""
res = self._download_webpage_handle(
url_or_request, video_id, note, errnote, fatal=fatal,
encoding=encoding, data=data, headers=headers, query=query,
expected_status=expected_status)
if res is False:
return res
json_string, urlh = res
return self._parse_json(
json_string, video_id, transform_source=transform_source,
fatal=fatal), urlh
def _download_json(
self, url_or_request, video_id, note='Downloading JSON metadata',
errnote='Unable to download JSON metadata', transform_source=None,
fatal=True, encoding=None, data=None, headers={}, query={},
expected_status=None):
"""
Return the JSON object as a dict.
See _download_webpage docstring for arguments specification.
"""
res = self._download_json_handle(
url_or_request, video_id, note=note, errnote=errnote,
transform_source=transform_source, fatal=fatal, encoding=encoding,
data=data, headers=headers, query=query,
expected_status=expected_status)
return res if res is False else res[0]
def _parse_json(self, json_string, video_id, transform_source=None, fatal=True):
if transform_source:
json_string = transform_source(json_string)
try:
return json.loads(json_string)
except ValueError as ve:
errmsg = '%s: Failed to parse JSON ' % video_id
if fatal:
raise ExtractorError(errmsg, cause=ve)
else:
self.report_warning(errmsg + str(ve))
def _parse_socket_response_as_json(self, data, video_id, transform_source=None, fatal=True):
return self._parse_json(
data[data.find('{'):data.rfind('}') + 1],
video_id, transform_source, fatal)
def _download_socket_json_handle(
self, url_or_request, video_id, note='Polling socket',
errnote='Unable to poll socket', transform_source=None,
fatal=True, encoding=None, data=None, headers={}, query={},
expected_status=None):
"""
Return a tuple (JSON object, URL handle).
See _download_webpage docstring for arguments specification.
"""
res = self._download_webpage_handle(
url_or_request, video_id, note, errnote, fatal=fatal,
encoding=encoding, data=data, headers=headers, query=query,