-
Notifications
You must be signed in to change notification settings - Fork 0
/
boosty_archiver.py
1336 lines (1124 loc) · 46.5 KB
/
boosty_archiver.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
"""
Boosty downloader
Run with --help argument to see arguments.
"""
from typing import Annotated, Literal, NotRequired, TypedDict
from collections import deque
from collections.abc import Iterator, Sequence
from contextlib import closing, suppress
from dataclasses import dataclass
from functools import partial
from http.cookiejar import MozillaCookieJar
from pathlib import Path
import re
import sqlite3
from time import sleep
# from bs4 import BeautifulSoup # + html5lib
import httpx
import magic # python-magic (Linux) or python-magic-bin (Windows)
import orjson
import rich
from rich.console import Group
from rich.live import Live
from rich.panel import Panel
from rich.progress import BarColumn, DownloadColumn, MofNCompleteColumn, Progress, TaskID, TimeElapsedColumn, TimeRemainingColumn, TransferSpeedColumn
from rich.table import Table
import rich.traceback
import typer
__version__ = "2024.10.01"
# ? API
API_PREFIX = "https://api.boosty.to/v1/"
API_POSTS_PER_PAGE = 100
API_GET_CURRENT_USER = f"{API_PREFIX}user/current"
API_GET_SUBSCRIPTIONS = f"{API_PREFIX}user/subscriptions?limit=30&with_follow=false" # include / exclude followers
API_GET_USER = f"{API_PREFIX}blog/{{user}}"
API_GET_POSTS_FIRST = f"{API_PREFIX}blog/{{user}}/post/?limit={API_POSTS_PER_PAGE}&comments_limit=0&reply_limit=0&is_only_allowed=false"
API_GET_POSTS = f"{API_PREFIX}blog/{{user}}/post/?limit={API_POSTS_PER_PAGE}&offset={{offset}}&comments_limit=0&reply_limit=0&is_only_allowed=false"
# ? Image extension detection with magic
# NOTE: avif and jxl is not supported yet by magic, they detected as "application/octet-stream"
MIME_TO_EXTENSION: dict[str, str] = {
"image/png": "png",
"image/jpeg": "jpg",
"image/x-ms-bmp": "bmp",
"image/webp": "webp",
"image/svg+xml": "svg",
"video/webm": "webm",
"video/mp4": "mp4",
"video/x-matroska": "mkv",
"video/x-msvideo": "avi",
"video/quicktime": "mov",
"audio/mpeg": "mp3",
"audio/x-wav": "wav",
"audio/x-flac": "flac",
"audio/x-m4a": "m4a",
"video/ogg": "ogv",
"audio/ogg": "ogg", # ? .opus also guessed as audio/ogg by magic
"audio/x-hx-aac-adts": "aac",
}
# ? DB
DB_PATH = Path(__file__).parent / "archive.db"
CREATE_TABLE = "CREATE TABLE IF NOT EXISTS archive (entry PRIMARY KEY) WITHOUT ROWID;"
CHECK_ENTRY = "SELECT EXISTS(SELECT true FROM archive WHERE entry = '{entry}');"
INSERT_ENTRY = "INSERT INTO archive (entry) VALUES ('{entry}') ON CONFLICT DO NOTHING;"
USER_CHECK: re.Pattern[str] = re.compile(r"^(?P<domain>https?:\/\/(?:www\.)?boosty\.to\/)?(?P<user>[\w\-]+)", flags=re.IGNORECASE)
FILENAME_REPLACEMENTS: Sequence[tuple[str, str]] = [
("\\", "⧹"),
("/", "⧸"),
(":", "："),
("*", "✩"),
("?", "？"),
('"', "＂"),
("<", "⧼"),
(">", "⧽"),
("|", "｜"),
]
FILENAME_CONTROLS: re.Pattern[str] = re.compile(r"[\000-\031]")
VIDEO_QUALITY_ORDER: Sequence[str] = ("ultra_hd", "quad_hd", "full_hd", "high", "medium", "tiny", "low", "lowest")
# ? Models
class Social(TypedDict):
url: str
type: Literal["facebook", "twitter", "website"]
class Subscription(TypedDict):
custumPrice: int
id: int
isApplePayed: bool
levelId: int
offTime: int # unix timestamp
onTime: int # unix timestamp
period: int
class InitialStateBlogBlogData(TypedDict):
"""
Only nessesary fields are typed, others are omitted
"signedQuery" not present when authentication is not successful
"""
blogUrl: str
coverUrl: str
signedQuery: NotRequired[str]
description: Sequence[dict]
socialLinks: Sequence[Social]
subscription: Subscription
isSubscribed: bool
subscriptionKind: Literal["paid", "free", "none"]
title: str
class InitialStateBlogBlog(TypedDict):
data: InitialStateBlogBlogData
meta: dict
class InitialStateBlog(TypedDict):
"""Only nessesary fields are typed, others are omitted"""
blog: InitialStateBlogBlog
class InitialState(TypedDict):
"""Only nessesary fields are typed, others are omitted"""
blog: InitialStateBlog
class CurrentUser(TypedDict):
"""Only nessesary fields are typed, others are omitted"""
id: int
blogUrl: str # same as id, but str
email: str
name: str
hasAvatar: bool
avatarUrl: str | None
timezone: int # 100 -> UTC+1
defaultCurrency: Literal["USD", "RUB"]
locale: Literal["en", "ru"]
hasSubscriptions: bool
hasFreeSubscriptions: bool
hasPaidSubscriptions: bool
class User(TypedDict):
"""
Only nessesary fields are typed, others are omitted
"signedQuery" not present when authentication is not successful
"""
isSubscribed: bool
subscription: dict | None
subscriptionKind: Literal["paid", "free", "none"]
signedQuery: NotRequired[str]
class PostDataText(TypedDict):
type: Literal["text"]
content: str # dumped json, e.g. "content": "[\"\",\"unstyled\",[]]"
modificator: Literal["", "BLOCK_END"] | str # BLOCK_END aka <br />, has no content # noqa: PYI051
# NOTE: Examples: ["Text", "unstyled", []], ["Bold text", "unstyled", [[0, 0, 6]]]
type PostDataTextParsed = tuple[str, Literal["unstyled"] | str, Sequence[Sequence[int]]] # noqa: PYI051
class PostDataLink(TypedDict):
type: Literal["link"]
content: str # e.g. "[\"https://...\",\"unstyled\",[]]"
explicit: bool
url: str
class PostDataFile(TypedDict):
type: Literal["file"]
complete: bool
id: str # UUID
isMigrated: bool
size: int
title: str
url: str # NOTE: url is https://cdn.boosty.to/file/00000000-0000-0000-0000-0000000000000 need migrate to https://cdn.boosty.to/file/00000000-0000-0000-0000-0000000000000?user_id=0000000&content_id=00000000-0000-0000-0000-0000000000000&expire_time=0000000000&sign=0000000000000000000000000000000000000000000000000000000000000000&is_migrated=true
type PostDataVideoURLsType = Literal[
"live_cmaf",
"live_playback_dash",
"ultra_hd",
"live_playback_hls",
"hls",
"live_ondemand_hls",
"lowest",
"tiny",
"high",
"medium",
"full_hd",
"live_dash",
"dash_uni",
"low",
"live_hls",
"quad_hd",
"dash",
]
class PostDataVideoURLs(TypedDict):
"""
NOTE: seems like when video does not have specified type (quality preset), url = ""
Regular static .mp4 ~720p upload have this types: ["hls", "lowest", "tiny', "medium", "low", "dash"]
URL look like this:
https://vd123.okcdn.ru/video.m3u8?cmd=videoPlayerCdn&expires=0000000000000&srcIp=1.2.3.4&pr=12&srcAg=UNKNOWN&ms=1.2.3.4&type=2&sig=00000000000&ct=8&urls=1.2.3.4&clientType=18&id=0000000000000
https://vd123.okcdn.ru/?expires=0000000000000&srcIp=1.2.3.4&pr=42&srcAg=UNKNOWN&ms=1.2.3.4&type=0&sig=00000000000&ct=0&urls=1.2.3.4&clientType=18&id=0000000000000
Where:
* expires - unix timestamp
* srcIp, ms, urls - 3 different IPs
* pr - seems always = 42
* ct - seems always = 0 for static types and 8 for hls, 6 for dash
* clientType - seems always = 18
* srcAg - seems always = UNKNOWN
* type - is integer representation of text type
* hls = 2
* lowest = 0
* tiny = 4
* medium = 2
* low = 1
* dash = 1
Approximate priority:
ultra_hd > quad_hd > full_hd > high > medium > tiny > low > lowest
hls and dash seems to use highest quality
"""
type: PostDataVideoURLsType
url: str
class PostDataVideo(TypedDict):
"""
Example JSON:
```json
{
"height":480,
"showViewsCounter":true,
"viewsCounter":0,
"timeCode":5,
"complete":true,
"uploadStatus": "ok",
"playerUrls": [
{"type": "live_cmaf", "url": ""},
{"url": "", "type": "live_playback_dash"},
{"type": "ultra_hd", "url": ""},
{"url": "", "type": "live_playback_hls"},
{"type": "hls", "url": "https://vd123.okcdn.ru/video.m3u8?cmd=videoPlayerCdn&expires=0000000000000&srcIp=1.2.3.4&pr=42&srcAg=UNKNOWN&ms=1.2.3.4&type=2&sig=00000000000&ct=8&urls=1.2.3.4&clientType=18&id=0000000000000"},
{"type": "live_ondemand_hls", "url": ""},
{"url": "https://vd123.okcdn.ru/?expires=0000000000000&srcIp=1.2.3.4&pr=42&srcAg=UNKNOWN&ms=1.2.3.4&type=0&sig=00000000000&ct=0&urls=1.2.3.4&clientType=18&id=0000000000000", "type": "lowest"},
{"url": "https://vd123.okcdn.ru/?expires=0000000000000&srcIp=1.2.3.4&pr=42&srcAg=UNKNOWN&ms=1.2.3.4&type=4&sig=00000000000&ct=0&urls=1.2.3.4&clientType=18&id=0000000000000", "type": "tiny"},
{"type": "high", "url": ""},
{"type": "medium", "url": "https://vd123.okcdn.ru/?expires=0000000000000&srcIp=1.2.3.4&pr=42&srcAg=UNKNOWN&ms=1.2.3.4&type=2&sig=00000000000&ct=0&urls=1.2.3.4&clientType=18&id=0000000000000"},
{"url": "", "type": "full_hd"},
{"type": "live_dash", "url": ""},
{"type": "dash_uni", "url": ""},
{"type": "low", "url": "https://vd123.okcdn.ru/?expires=0000000000000&srcIp=1.2.3.4&pr=42&srcAg=UNKNOWN&ms=1.2.3.4&type=1&sig=00000000000&ct=0&urls=1.2.3.4&clientType=18&id=0000000000000"},
{"type": "live_hls", "url": ""},
{"type": "quad_hd", "url": ""},
{"url": "https://vd123.okcdn.ru/?expires=0000000000000&srcIp=1.2.3.4&pr=42&srcAg=UNKNOWN&ms=1.2.3.4&type=1&sig=00000000000&ct=6&urls=1.2.3.4&clientType=18&id=0000000000000", "type": "dash"}
],
"duration":34,
"vid": "0000000000000",
"width": 754,
"failoverHost": "vd234.okcdn.ru",
"preview": "https://i.okcdn.ru/videoPreview?id=0000000000000&type=39&idx=13&tkn=0000000000000000-0000000000",
"defaultPreview": "https://i.okcdn.ru/videoPreview?id=0000000000000&type=39&idx=13&tkn=0000000000000000-0000000000",
"url": "",
"title": "Title",
"type": "ok_video",
"id": "00000000-0000-0000-0000-000000000000"
}
```
""" # noqa: E501
type: Literal["ok_video"]
complete: bool
id: str
height: int
showViewsCounter: bool
viewsCounter: NotRequired[int]
timeCode: int
uploadStatus: Literal["ok"] | str # noqa: PYI051 # TODO: other statuses?
playerUrls: Sequence[PostDataVideoURLs]
duration: NotRequired[int]
vid: str
width: int
failoverHost: NotRequired[str]
preview: str
defaultPreview: str
url: NotRequired[str]
title: str
class PostDataAudio(TypedDict):
"""
Example JSON:
```json
{
"uploadStatus": "",
"timeCode": 0,
"complete": True,
"size": 7526176,
"viewsCounter": 0,
"showViewsCounter": True,
"track": "Day and Night",
"duration": 188,
"url": "https://cdn.boosty.to/audio/b46f05b1-c6d1-4a10-8791-6a65077aa1c2",
"album": "Shiki Original Soundtrack Mini Album ''Rouge''",
"title": "Day and Night.mp3",
"artist": "Yasuharu Takanashi",
"id": "b46f05b1-c6d1-4a10-8791-6a65077aa1c2",
"isMigrated": True,
"fileType": "MP3",
"type": "audio_file"
}
```
"""
type: Literal["audio_file"]
complete: bool
id: str
isMigrated: bool
uploadStatus: str
timeCode: int
size: int
viewsCounter: NotRequired[int]
showViewsCounter: bool
track: NotRequired[str] # ? from file metadata
duration: int
url: str
album: NotRequired[str] # ? from file metadata
title: str # ? filename
artist: NotRequired[str] # ? from file metadata
fileType: Literal["MP3"] | str # noqa: PYI051 # TODO: other types?
class PostDataImage(TypedDict):
"""NOTE: When file deleted from CDN, "width", "height", "size" are not present and any image URL redirect to https://images.boosty.to/stubs/default.png"""
type: Literal["image"]
id: str # UUID
height: NotRequired[int]
rendition: str
size: NotRequired[int]
url: str # e.g. "https://images.boosty.to/image/00000000-0000-0000-0000-000000000000?change_time=0000000000" - unix time
width: NotRequired[int]
class Posts(TypedDict):
"""
Only nessesary fields are typed, others are omitted
"signedQuery" not present when authentication is not successful
"""
id: str # UUID
int_id: int
title: str
hasAccess: bool
data: Sequence[PostDataText | PostDataLink | PostDataFile | PostDataVideo | PostDataAudio | PostDataImage]
signedQuery: NotRequired[str]
poll: NotRequired[dict]
class PostsExtra(TypedDict):
offset: str
isLast: bool
class PostsResponse(TypedDict):
data: Sequence[Posts]
extra: PostsExtra
@dataclass
class ProgressContext:
progress: Progress
posts: TaskID
users: TaskID | None
progress_download: Progress
download: TaskID
total: int
group: Group
# ? Methods
def handle_file(
*,
client: httpx.Client,
headers: dict[str, str],
int_id: int,
title: str,
incremental_id: int,
url: str,
filename: str,
size: int | None = None,
is_migrated: bool,
user: str,
output_dir: Path,
signed_query: str,
ctx: ProgressContext,
force_redownload: bool = False,
db_conn: sqlite3.Connection | None = None,
) -> None:
"""
Handle file downloads
"""
final_url = f"{url}{signed_query}&is_migrated={str(is_migrated).lower()}"
path = output_dir / f"{int_id}_{title}_{incremental_id}_{filename}"
entry = f"boosty_{user}_{int_id}_{incremental_id}"
if size is None:
ctx.progress.print("[yellow]Skipping downloading deleted file from CDN:[/yellow]", final_url)
return
if not force_redownload and db_conn:
with db_conn as cur, suppress(ValueError, sqlite3.Error):
[[check]] = cur.execute(CHECK_ENTRY.format(entry=entry))
if check:
ctx.progress.print(f"[yellow]Skipping downloaded file ({size:_} B):[/yellow]", url, "(DB)")
return
elif not force_redownload and path.exists() and path.stat().st_size == size:
ctx.progress.print(f"[yellow]Skipping downloaded file ({size:_} B):[/yellow]", final_url)
return
try:
with client.stream("GET", final_url, headers=headers, timeout=60.0) as stream:
if stream.is_server_error:
ctx.progress.print("Get server error:", stream.status_code, "Retrying after 5 seconds...")
sleep(5.0)
handle_file(
client=client,
headers=headers,
int_id=int_id,
title=title,
incremental_id=incremental_id,
url=url,
filename=filename,
size=size,
is_migrated=is_migrated,
user=user,
output_dir=output_dir,
signed_query=signed_query,
ctx=ctx,
force_redownload=force_redownload,
db_conn=db_conn,
)
return
if not stream.is_success:
rich.inspect(stream, title="Downloading file error")
# rich.inspect(stream.request)
return
with path.open("wb") as f:
total = int(stream.headers["Content-Length"])
ctx.progress_download.start_task(ctx.download)
ctx.progress_download.update(ctx.download, total=total, visible=True)
ctx.progress.print(f"[green]Downloading ({size:_} B):[/green]", final_url)
for chunk in stream.iter_bytes():
f.write(chunk)
ctx.progress_download.update(ctx.download, completed=stream.num_bytes_downloaded)
ctx.progress_download.update(ctx.download, completed=0, visible=False)
ctx.progress_download.stop_task(ctx.download)
except httpx.TimeoutException:
ctx.progress.print(f"[red italic]Timeout exception: {final_url}[/red italic]")
return
except httpx.NetworkError as e:
rich.inspect(e, title=f"Network error: {final_url}")
return
except httpx.ProtocolError as e:
rich.inspect(e, title=f"Protocol error: {final_url}")
return
except httpx.StreamError as e:
rich.inspect(e, title=f"Streaming file error: {final_url}")
return
if db_conn:
with db_conn as cur, suppress(sqlite3.Error):
cur.execute(INSERT_ENTRY.format(entry=entry))
cur.commit()
def handle_image(
*,
client: httpx.Client,
headers: dict[str, str],
int_id: int,
title: str,
incremental_id: int,
url: str,
filename: str,
user: str,
output_dir: Path,
width: int | None = None,
height: int | None = None,
size: int | None = None,
ctx: ProgressContext,
force_redownload: bool = False,
db_conn: sqlite3.Connection | None = None,
) -> None:
"""
Handle image downloads. Extension is not known, so has to be guessed with magic
"""
if width is None or height is None or size is None:
ctx.progress.print("[yellow]Skipping downloading deleted image from CDN:[/yellow]", url)
return
entry = f"boosty_{user}_{int_id}_{incremental_id}"
if not force_redownload and db_conn:
with db_conn as cur, suppress(ValueError, sqlite3.Error):
[[check]] = cur.execute(CHECK_ENTRY.format(entry=entry))
if check:
ctx.progress.print(f"[yellow]Skipping downloaded image ({size:_} B):[/yellow]", url, "(DB)")
return
try:
with client.stream("GET", url, headers=headers, timeout=60.0) as stream:
if stream.is_server_error:
ctx.progress.print("Get server error:", stream.status_code, "Retrying after 5 seconds...")
sleep(5.0)
handle_image(
client=client,
headers=headers,
int_id=int_id,
title=title,
incremental_id=incremental_id,
url=url,
filename=filename,
user=user,
output_dir=output_dir,
width=width,
height=height,
size=size,
ctx=ctx,
force_redownload=force_redownload,
db_conn=db_conn,
)
return
if not stream.is_success:
rich.inspect(stream, title="Downloading image error")
return
total = int(stream.headers["Content-Length"])
ctx.progress_download.start_task(ctx.download)
ctx.progress_download.update(ctx.download, total=total, visible=True)
iterator: Iterator[bytes] = stream.iter_bytes(chunk_size=16_384)
chunk: bytes = next(iterator)
mime_type: str = magic.from_buffer(chunk, mime=True)
extension: str = MIME_TO_EXTENSION.get(mime_type, "png")
path = output_dir / f"{int_id}_{title}_{incremental_id}_{filename}.{extension}"
if not force_redownload and not db_conn and path.exists() and path.stat().st_size == size:
ctx.progress.print(f"[yellow]Skipping downloaded image ({size:_} B):[/yellow]", url)
return
ctx.progress.print(f"[green]Downloading ({size:_} B):[/green]", url)
with path.open("wb") as f:
f.write(chunk)
for chunk in iterator:
f.write(chunk)
ctx.progress_download.update(ctx.download, completed=stream.num_bytes_downloaded)
ctx.progress_download.update(ctx.download, completed=0, visible=False)
ctx.progress_download.stop_task(ctx.download)
except httpx.TimeoutException:
ctx.progress.print(f"[red italic]Timeout exception: {url}[/red italic]")
return
except httpx.NetworkError as e:
rich.inspect(e, title=f"Network error: {url}")
return
except httpx.ProtocolError as e:
rich.inspect(e, title=f"Protocol error: {url}")
return
except httpx.StreamError as e:
rich.inspect(e, title=f"Streaming image error: {url}")
return
if db_conn:
with db_conn as cur, suppress(sqlite3.Error):
cur.execute(INSERT_ENTRY.format(entry=entry))
cur.commit()
def best_video(urls: dict[PostDataVideoURLsType, str], /) -> tuple[str, str] | tuple[None, None]:
"""Return best video quality"""
for q in VIDEO_QUALITY_ORDER:
if q in urls:
return (q, urls[q])
return (None, None)
def handle_video(
*,
client: httpx.Client,
headers: dict[str, str],
int_id: int,
title: str,
incremental_id: int,
urls: dict[PostDataVideoURLsType, str],
failover_host: str | None = None,
filename: str,
user: str,
output_dir: Path,
width: int | None = None,
height: int | None = None,
duration: int | None = None,
ctx: ProgressContext,
force_redownload: bool = False,
db_conn: sqlite3.Connection | None = None,
retry: int = 0,
) -> None:
"""
Handle video downloads. Extension is not known, so has to be guessed with magic
"""
if width is None or height is None: # or duration is None:
ctx.progress.print("[yellow]Skipping downloading deleted video from CDN:[/yellow]", urls)
return
entry = f"boosty_{user}_{int_id}_{incremental_id}"
if not force_redownload and db_conn:
with db_conn as cur, suppress(ValueError, sqlite3.Error):
[[check]] = cur.execute(CHECK_ENTRY.format(entry=entry))
if check:
ctx.progress.print(f"[yellow]Skipping downloaded video ({width}x{height} {duration or 0}s):[/yellow]", urls, "(DB)")
return
quality, url = best_video(urls)
if not url or not quality:
ctx.progress.print("[red]Not found supported video quality[/red]", urls)
return
# ? retry using failover host
if retry >= 5 and failover_host:
url = re.sub(r"(?<=https:\/\/)[\w.\-]+(?=/)", failover_host, url)
ctx.progress.print("Trying downloading video using failover host:", failover_host)
try:
with client.stream("GET", url, headers=headers, timeout=60.0) as stream:
if stream.is_server_error:
ctx.progress.print("Get server error:", stream.status_code, "Retrying after 5 seconds...")
sleep(5.0)
handle_video(
client=client,
headers=headers,
int_id=int_id,
title=title,
incremental_id=incremental_id,
urls=urls,
failover_host=failover_host,
filename=filename,
user=user,
output_dir=output_dir,
width=width,
height=height,
duration=duration,
ctx=ctx,
force_redownload=force_redownload,
db_conn=db_conn,
retry=retry + 1,
)
return
if not stream.is_success:
rich.inspect(stream, title="Downloading video error")
return
total = int(stream.headers["Content-Length"])
ctx.progress_download.start_task(ctx.download)
ctx.progress_download.update(ctx.download, total=total, visible=True)
iterator: Iterator[bytes] = stream.iter_bytes(chunk_size=16_384)
chunk: bytes = next(iterator)
mime_type: str = magic.from_buffer(chunk, mime=True)
extension: str = MIME_TO_EXTENSION.get(mime_type, "mp4")
path = output_dir / f"{int_id}_{title}_{incremental_id}_{filename}.{quality}.{extension}"
if not force_redownload and not db_conn and path.exists() and path.stat().st_size > 0:
ctx.progress.print(f"[yellow]Skipping downloaded video ({width}x{height} {duration or 0}s):[/yellow]", url)
return
ctx.progress.print(f"[green]Downloading ({width}x{height} {duration or 0}s):[/green]", url)
with path.open("wb") as f:
f.write(chunk)
for chunk in iterator:
f.write(chunk)
ctx.progress_download.update(ctx.download, completed=stream.num_bytes_downloaded)
ctx.progress_download.update(ctx.download, completed=0, visible=False)
ctx.progress_download.stop_task(ctx.download)
except httpx.TimeoutException:
ctx.progress.print(f"[red italic]Timeout exception: {url}[/red italic]")
return
except httpx.NetworkError as e:
rich.inspect(e, title=f"Network error: {url}")
return
except httpx.ProtocolError as e:
rich.inspect(e, title=f"Protocol error: {url}")
return
except httpx.StreamError as e:
rich.inspect(e, title=f"Streaming video error: {url}")
return
if db_conn:
with db_conn as cur, suppress(sqlite3.Error):
cur.execute(INSERT_ENTRY.format(entry=entry))
cur.commit()
def handle_audio(
*,
client: httpx.Client,
headers: dict[str, str],
int_id: int,
title: str,
incremental_id: int,
url: str,
filename: str,
filename_fallback: str,
file_type: str | None = None,
size: int | None = None,
is_migrated: bool,
user: str,
output_dir: Path,
signed_query: str,
ctx: ProgressContext,
force_redownload: bool = False,
db_conn: sqlite3.Connection | None = None,
) -> None:
"""
Handle audio downloads. Extension is within a title, however if not, there is file_type in CAPS from API.
"""
if size is None:
ctx.progress.print("[yellow]Skipping downloading deleted audio from CDN:[/yellow]", url)
return
if not filename:
filename = f"{filename_fallback}.{(file_type or "mp3").lower()}"
final_url = f"{url}{signed_query}&is_migrated={str(is_migrated).lower()}"
path = output_dir / f"{int_id}_{title}_{incremental_id}_{filename}"
entry = f"boosty_{user}_{int_id}_{incremental_id}"
if not force_redownload and db_conn:
with db_conn as cur, suppress(ValueError, sqlite3.Error):
[[check]] = cur.execute(CHECK_ENTRY.format(entry=entry))
if check:
ctx.progress.print(f"[yellow]Skipping downloaded audio ({size:_} B):[/yellow]", url, "(DB)")
return
try:
with client.stream("GET", final_url, headers=headers, timeout=60.0) as stream:
if stream.is_server_error:
ctx.progress.print("Get server error:", stream.status_code, "Retrying after 5 seconds...")
sleep(5.0)
handle_audio(
client=client,
headers=headers,
int_id=int_id,
title=title,
incremental_id=incremental_id,
url=url,
filename=filename,
filename_fallback=filename_fallback,
file_type=file_type,
size=size,
is_migrated=is_migrated,
user=user,
output_dir=output_dir,
signed_query=signed_query,
ctx=ctx,
force_redownload=force_redownload,
db_conn=db_conn,
)
return
if not stream.is_success:
rich.inspect(stream, title="Downloading audio error")
# rich.inspect(stream.request)
return
with path.open("wb") as f:
total = int(stream.headers["Content-Length"])
ctx.progress_download.start_task(ctx.download)
ctx.progress_download.update(ctx.download, total=total, visible=True)
ctx.progress.print(f"[green]Downloading ({size:_} B):[/green]", final_url)
for chunk in stream.iter_bytes():
f.write(chunk)
ctx.progress_download.update(ctx.download, completed=stream.num_bytes_downloaded)
ctx.progress_download.update(ctx.download, completed=0, visible=False)
ctx.progress_download.stop_task(ctx.download)
except httpx.TimeoutException:
ctx.progress.print(f"[red italic]Timeout exception: {final_url}[/red italic]")
return
except httpx.NetworkError as e:
rich.inspect(e, title=f"Network error: {final_url}")
return
except httpx.ProtocolError as e:
rich.inspect(e, title=f"Protocol error: {final_url}")
return
except httpx.StreamError as e:
rich.inspect(e, title=f"Streaming audio error: {final_url}")
return
if db_conn:
with db_conn as cur, suppress(sqlite3.Error):
cur.execute(INSERT_ENTRY.format(entry=entry))
cur.commit()
def parse_text(raw_text: str) -> str:
"""
Get text from stringified JSON
"""
try:
text_obj: PostDataTextParsed = orjson.loads(raw_text or """["", "unstyled", []]""")
return text_obj[0]
except (orjson.JSONDecodeError, IndexError):
rich.inspect(raw_text, title="Error parsing post text JSON")
return ""
def clear_post_text(post_text: Sequence[PostDataText | PostDataLink]) -> str:
"""
Return human-readable post text
NOTE: Links have similar to markdown content where [text](https://url), however hidden links also persist where content == "", they should be stripped
Regular text have content encoded in stringified JSON, like ["Text", "unstyled", []] or ["Bold text", "unstyled", [[0, 0, 6]]]
Modifiers are typically = "BLOCK_END" which is new line, <br />
"""
return "".join(
((d["url"] if parse_text(d["content"]) != "" else "") if d["type"] == "link" else (parse_text(d["content"]) if d["type"] == "text" and d["modificator"] == "" else "\n"))
for d in post_text
)
def clear_filename(filename: str) -> str:
"""
Clear filename from forbidden characters
* Remove spaces around file name
* Remove dot at the end of name (if no extension)
* Remove control characters
* Replace forbidden characters for unicode alternative
"""
filename = filename.strip().strip(".")
for [replacement, replacer] in FILENAME_REPLACEMENTS:
filename = filename.replace(replacement, replacer)
return FILENAME_CONTROLS.sub("", filename)
def handle_posts(
client: httpx.Client,
headers: dict[str, str],
posts: Sequence[Posts],
user: str,
output_dir: Path,
# user_id: int,
*,
force_redownload: bool = False,
all_links: deque[tuple[str, str, str]],
signed_query: str = "?t",
db_conn: sqlite3.Connection | None = None,
ctx: ProgressContext,
) -> None:
"""
Handle posts
"""
for post in posts:
if _sq := post.get("signedQuery"):
signed_query = _sq
post_id: str = post["id"]
int_id: int = post["int_id"]
title: str = clear_filename(post["title"])
has_access = post["hasAccess"]
data = post["data"]
incremental_id = 0
post_text: list[PostDataText | PostDataLink] = []
dl_tasks: list = []
# found_password: bool = False
if not has_access:
ctx.progress.print(f"Skipping post {post['id']} ({post["int_id"]}) - has no access\n")
ctx.total -= 1
ctx.progress.update(ctx.posts, total=ctx.total)
continue
for d in data:
if d["type"] == "file":
dl_tasks.append(
partial(
handle_file,
client=client,
headers=headers,
int_id=int_id,
title=title,
incremental_id=incremental_id,
url=d["url"],
filename=clear_filename(d["title"]),
size=d["size"],
is_migrated=d["isMigrated"],
user=user,
output_dir=output_dir,
ctx=ctx,
signed_query=signed_query,
force_redownload=force_redownload,
db_conn=db_conn,
),
)
incremental_id += 1
elif d["type"] == "image":
dl_tasks.append(
partial(
handle_image,
client=client,
headers=headers,
int_id=int_id,
title=title,
incremental_id=incremental_id,
url=d["url"],
filename=d["id"],
user=user,
output_dir=output_dir,
width=d.get("width"),
height=d.get("height"),
size=d.get("size"),
ctx=ctx,
force_redownload=force_redownload,
db_conn=db_conn,
),
)
incremental_id += 1
elif d["type"] == "link":
post_text.append(d)
all_links.appendleft((str(int_id), f"https://boosty.to/{user}/posts/{post_id}", d["url"]))
# ctx.progress.print(f"Found link in post: https://boosty.to/{user}/posts/{post_id}", d["url"])
elif d["type"] == "text":
post_text.append(d)
# NOTE: v2 removed alering only on passwords, save all text content instead
# if not ((raw_text := d["content"]) and d["modificator"] == ""):
# continue
# if "password" in parse_text(raw_text).lower():
# found_password = True
elif d["type"] == "ok_video":