forked from mvdctop/Movie_Data_Capture
-
Notifications
You must be signed in to change notification settings - Fork 0
/
core.py
1116 lines (1001 loc) · 47.5 KB
/
core.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
import json
import os.path
import os
import pathlib
import re
import shutil
import sys
import zipfile
from PIL import Image
from io import BytesIO
from pathlib import Path
from datetime import datetime
from lxml import etree
from ADC_function import *
from WebCrawler import get_data_from_json
from number_parser import is_uncensored
from ImageProcessing import cutImage
def escape_path(path, escape_literals: str): # Remove escape literals
backslash = '\\'
for literal in escape_literals:
path = path.replace(backslash + literal, '')
return path
def moveFailedFolder(filepath):
conf = config.getInstance()
failed_folder = conf.failed_folder()
link_mode = conf.link_mode()
# 模式3或软连接，改为维护一个失败列表，启动扫描时加载用于排除该路径，以免反复处理
# 原先的创建软连接到失败目录，并不直观，不方便找到失败文件位置，不如直接记录该文件路径
if conf.main_mode() == 3 or link_mode:
ftxt = os.path.abspath(os.path.join(failed_folder, 'failed_list.txt'))
print("[-]Add to Failed List file, see '%s'" % ftxt)
with open(ftxt, 'a', encoding='utf-8') as flt:
flt.write(f'{filepath}\n')
elif conf.failed_move() and not link_mode:
failed_name = os.path.join(failed_folder, os.path.basename(filepath))
mtxt = os.path.abspath(os.path.join(failed_folder, 'where_was_i_before_being_moved.txt'))
print("'[-]Move to Failed output folder, see '%s'" % mtxt)
with open(mtxt, 'a', encoding='utf-8') as wwibbmt:
tmstr = datetime.now().strftime("%Y-%m-%d %H:%M")
wwibbmt.write(f'{tmstr} FROM[{filepath}]TO[{failed_name}]\n')
try:
if os.path.exists(failed_name):
print('[-]File Exists while moving to FailedFolder')
return
shutil.move(filepath, failed_name)
except:
print('[-]File Moving to FailedFolder unsuccessful!')
def get_info(json_data): # 返回json里的数据
title = json_data.get('title')
studio = json_data.get('studio')
year = json_data.get('year')
outline = json_data.get('outline')
runtime = json_data.get('runtime')
director = json_data.get('director')
actor_photo = json_data.get('actor_photo', {})
release = json_data.get('release')
number = json_data.get('number')
cover = json_data.get('cover')
trailer = json_data.get('trailer')
website = json_data.get('website')
series = json_data.get('series')
label = json_data.get('label', "")
return title, studio, year, outline, runtime, director, actor_photo, release, number, cover, trailer, website, series, label
def small_cover_check(path, filename, cover_small, movie_path, json_data=None):
full_filepath = Path(path) / filename
if config.getInstance().download_only_missing_images() and not file_not_exist_or_empty(str(full_filepath)):
return
download_file_with_filename(cover_small, filename, path, movie_path, json_data)
print('[+]Image Downloaded! ' + full_filepath.name)
def create_folder(json_data): # 创建文件夹
title, studio, year, outline, runtime, director, actor_photo, release, number, cover, trailer, website, series, label = get_info(json_data)
conf = config.getInstance()
success_folder = conf.success_folder()
actor = json_data.get('actor')
location_rule = eval(conf.location_rule(), json_data)
if 'actor' in conf.location_rule() and len(actor) > 100:
print(conf.location_rule())
location_rule = eval(conf.location_rule().replace("actor","'多人作品'"), json_data)
maxlen = conf.max_title_len()
if 'title' in conf.location_rule() and len(title) > maxlen:
shorttitle = title[0:maxlen]
location_rule = location_rule.replace(title, shorttitle)
# 当演员为空时，location_rule被计算为'/number'绝对路径，导致路径连接忽略第一个路径参数，因此添加./使其始终为相对路径
path = os.path.join(success_folder, f'./{location_rule.strip()}')
if not os.path.exists(path):
path = escape_path(path, conf.escape_literals())
try:
os.makedirs(path)
except:
path = success_folder + '/' + location_rule.replace('/[' + number + ')-' + title, "/number")
path = escape_path(path, conf.escape_literals())
try:
os.makedirs(path)
except:
print(f"[-]Fatal error! Can not make folder '{path}'")
os._exit(0)
return os.path.normpath(path)
# =====================资源下载部分===========================
# path = examle:photo , video.in the Project Folder!
def download_file_with_filename(url, filename, path, filepath, json_headers=None):
conf = config.getInstance()
configProxy = conf.proxy()
for i in range(configProxy.retry):
try:
if configProxy.enable:
if not os.path.exists(path):
try:
os.makedirs(path)
except:
print(f"[-]Fatal error! Can not make folder '{path}'")
os._exit(0)
proxies = configProxy.proxies()
headers = {'User-Agent': G_USER_AGENT}
if json_headers != None:
headers.update(json_headers)
r = requests.get(url, headers=headers, timeout=configProxy.timeout, proxies=proxies)
if r == '':
print('[-]Movie Download Data not found!')
return
with open(os.path.join(path, filename), "wb") as code:
code.write(r.content)
return
else:
if not os.path.exists(path):
try:
os.makedirs(path)
except:
print(f"[-]Fatal error! Can not make folder '{path}'")
os._exit(0)
headers = {'User-Agent': G_USER_AGENT}
if json_headers != None:
headers.update(json_headers)
r = requests.get(url, timeout=configProxy.timeout, headers=headers)
if r == '':
print('[-]Movie Download Data not found!')
return
with open(os.path.join(path, filename), "wb") as code:
code.write(r.content)
return
except requests.exceptions.RequestException:
i += 1
print('[-]Image Download : Connect retry ' + str(i) + '/' + str(configProxy.retry))
except requests.exceptions.ConnectionError:
i += 1
print('[-]Image Download : Connect retry ' + str(i) + '/' + str(configProxy.retry))
except requests.exceptions.ProxyError:
i += 1
print('[-]Image Download : Connect retry ' + str(i) + '/' + str(configProxy.retry))
except requests.exceptions.ConnectTimeout:
i += 1
print('[-]Image Download : Connect retry ' + str(i) + '/' + str(configProxy.retry))
except IOError:
print(f"[-]Create Directory '{path}' failed!")
moveFailedFolder(filepath)
return
print('[-]Connect Failed! Please check your Proxy or Network!')
moveFailedFolder(filepath)
return
def trailer_download(trailer, leak_word, c_word, hack_word, number, path, filepath):
if download_file_with_filename(trailer, number + leak_word + c_word + hack_word + '-trailer.mp4', path, filepath) == 'failed':
return
configProxy = config.getInstance().proxy()
for i in range(configProxy.retry):
if file_not_exist_or_empty(path+'/' + number + leak_word + c_word + hack_word + '-trailer.mp4'):
print('[!]Video Download Failed! Trying again. [{}/3]', i + 1)
download_file_with_filename(trailer, number + leak_word + c_word + hack_word + '-trailer.mp4', path, filepath)
continue
else:
break
if file_not_exist_or_empty(path + '/' + number + leak_word + c_word + hack_word + '-trailer.mp4'):
return
print('[+]Video Downloaded!', path + '/' + number + leak_word + c_word + hack_word + '-trailer.mp4')
class ActorCache:
def is_empty(self) -> bool:
return not bool(hasattr(self, "cache"))
def init(self):
if hasattr(self, "cache") and isinstance(self.cache, dict):
return
self.cache = dict()
def set(self, actor_name, pic_fullpath):
if not self.is_empty() and all(len(str(v)) for v in (actor_name, pic_fullpath)):
self.cache[actor_name] = str(pic_fullpath)
def get(self, actor_name):
if not self.is_empty():
return self.cache.get(actor_name, '')
return ''
G_actor_cache = ActorCache()
class GFriends:
def lib_exists(self) -> bool:
if not hasattr(self, "is_init"):
self.is_init = True
gf = config.getInstance().actor_photo_gfriends_path()
gfpath = Path(gf) if len(gf) else None
if not(gfpath and gfpath.is_dir()):
return False
filetree_path = gfpath / "Filetree.json"
if not filetree_path.is_file():
return False
filetree = json.loads(filetree_path.read_text(encoding='utf-8'))
if not(filetree is not None and len(filetree.get("Content", []))):
return False
self.content = filetree["Content"]
self.path = gfpath
return all(hasattr(self, v) for v in ("content", "path"))
def get(self, actor_name) -> str:
if not self.lib_exists():
return ''
actor_jpg_name = actor_name + '.jpg'
for studio in self.content:
if actor_jpg_name in self.content[studio]:
actor_photo_path = self.path / "Content" / studio / self.content[studio][actor_jpg_name]
return str(actor_photo_path)
return ''
G_gfriends = GFriends()
def cached_link_actor_photo(actor_name, actor_photo, pic_fullpath) -> bool:
debug = config.getInstance().debug()
if G_actor_cache.is_empty():
G_actor_cache.init()
pic_fullpath.parent.mkdir(parents=True, exist_ok=True)
actor_cached_path = G_actor_cache.get(actor_name)
if len(actor_cached_path) and Path(actor_cached_path).is_file():
if pic_fullpath.is_file():
if pic_fullpath.samefile(actor_cached_path):
return True # 处理完-CD1再处理-CD2的情况，来源与目标相同，不用复制，即便download_only_missing_images=0
pic_fullpath.unlink(missing_ok=True)
try:
os.link(actor_cached_path, str(pic_fullpath), follow_symlinks=False)
except:
shutil.copyfile(actor_cached_path, str(pic_fullpath))
target_ok = pic_fullpath.is_file()
if target_ok and debug:
print(f'[+]Cached link or copy actor photo {str(pic_fullpath)}')
return target_ok
# 不判断is_file()直接尝试unlink()，这样可以清理一些坏的软链接，因为坏软链接的is_file()会返回假值。故意创建同名目录的情况copyfile()则会向外层抛异常。
pic_fullpath.unlink(missing_ok=True)
try:
os.link(actor_photo, str(pic_fullpath), follow_symlinks=False)
except:
shutil.copyfile(actor_photo, str(pic_fullpath))
target_ok = pic_fullpath.is_file()
if target_ok:
G_actor_cache.set(actor_name, pic_fullpath)
if debug:
print(f'[+]Link or copy actor photo {str(pic_fullpath)}')
return target_ok
def copy_from_local_gfriends(actor_name, pic_fullpath) -> bool:
if not G_gfriends.lib_exists():
return False
actor_photo = G_gfriends.get(actor_name)
if not(isinstance(actor_photo, str) and os.path.isfile(actor_photo)):
return False
try:
return cached_link_actor_photo(actor_name, actor_photo, pic_fullpath)
except:
return False
def actor_photo_download(actors, save_dir, number):
if not isinstance(actors, dict) or not len(actors) or not len(save_dir):
return
save_dir = Path(save_dir)
if not save_dir.is_dir():
return
conf = config.getInstance()
actors_dir = save_dir / '.actors'
download_only_missing_images = conf.download_only_missing_images()
local_cnt = 0
dn_list = []
for actor_name, url in actors.items():
res = re.match(r'^http.*(\.\w+)$', url, re.A)
if not res:
continue
ext = res.group(1)
pic_fullpath = actors_dir / f'{actor_name}{ext}'
if download_only_missing_images and not file_not_exist_or_empty(pic_fullpath):
continue
# 本地gfriends库优先，没有的才从远程下载
if not copy_from_local_gfriends(actor_name, pic_fullpath):
dn_list.append((url, pic_fullpath))
else:
local_cnt += 1
if local_cnt:
print(f"[+]Successfully link or copy {local_cnt} actor photo from local gfriends git repository")
if not len(dn_list):
return
parallel = min(len(dn_list), conf.extrafanart_thread_pool_download())
if parallel > 100:
print('[!]Warrning: Parallel download thread too large may cause website ban IP!')
result = parallel_download_files(dn_list, parallel)
failed = 0
for i, r in enumerate(result):
if not r:
failed += 1
print(f"[-]Actor photo '{dn_list[i][0]}' to '{dn_list[i][1]}' download failed!")
if failed: # 非致命错误，电影不移入失败文件夹，将来可以用模式3补齐
print(f"[-]Failed downloaded {failed}/{len(result)} actor photo for [{number}] to '{actors_dir}', you may retry run mode 3 later.")
else:
print(f"[+]Successfully downloaded {len(result)} actor photo.")
# 剧照下载成功，否则移动到failed
def extrafanart_download(data, path, number, filepath, json_data=None):
if config.getInstance().extrafanart_thread_pool_download():
return extrafanart_download_threadpool(data, path, number, json_data)
extrafanart_download_one_by_one(data, path, filepath, json_data)
def extrafanart_download_one_by_one(data, path, filepath, json_data=None):
tm_start = time.perf_counter()
j = 1
conf = config.getInstance()
path = os.path.join(path, conf.get_extrafanart())
configProxy = conf.proxy()
download_only_missing_images = conf.download_only_missing_images()
for url in data:
jpg_filename = f'extrafanart-{j}.jpg'
jpg_fullpath = os.path.join(path, jpg_filename)
if download_only_missing_images and not file_not_exist_or_empty(jpg_fullpath):
continue
if download_file_with_filename(url, jpg_filename, path, filepath, json_data) == 'failed':
moveFailedFolder(filepath)
return
for i in range(configProxy.retry):
if file_not_exist_or_empty(jpg_fullpath):
print('[!]Image Download Failed! Trying again. [{}/3]', i + 1)
download_file_with_filename(url, jpg_filename, path, filepath, json_data)
continue
else:
break
if file_not_exist_or_empty(jpg_fullpath):
return
print('[+]Image Downloaded!', Path(jpg_fullpath).name)
j += 1
if conf.debug():
print(f'[!]Extrafanart download one by one mode runtime {time.perf_counter() - tm_start:.3f}s')
def extrafanart_download_threadpool(url_list, save_dir, number,json_data=None):
tm_start = time.perf_counter()
conf = config.getInstance()
extrafanart_dir = Path(save_dir) / conf.get_extrafanart()
download_only_missing_images = conf.download_only_missing_images()
dn_list = []
for i, url in enumerate(url_list, start=1):
jpg_fullpath = extrafanart_dir / f'extrafanart-{i}.jpg'
if download_only_missing_images and not file_not_exist_or_empty(jpg_fullpath):
continue
dn_list.append((url, jpg_fullpath))
if not len(dn_list):
return
parallel = min(len(dn_list), conf.extrafanart_thread_pool_download())
if parallel > 100:
print('[!]Warrning: Parallel download thread too large may cause website ban IP!')
result = parallel_download_files(dn_list, parallel, json_data)
failed = 0
for i, r in enumerate(result, start=1):
if not r:
failed += 1
print(f'[-]Extrafanart {i} for [{number}] download failed!')
if failed: # 非致命错误，电影不移入失败文件夹，将来可以用模式3补齐
print(f"[-]Failed downloaded {failed}/{len(result)} extrafanart images for [{number}] to '{extrafanart_dir}', you may retry run mode 3 later.")
else:
print(f"[+]Successfully downloaded {len(result)} extrafanarts.")
if conf.debug():
print(f'[!]Extrafanart download ThreadPool mode runtime {time.perf_counter() - tm_start:.3f}s')
def unzip_local_gallery(path):
conf = config.getInstance()
if not conf.extrafanart_unzip_gallery():
return
extrafanart = conf.get_extrafanart()
if not len(extrafanart):
return
targetdir = Path(path)
gfolder = targetdir / extrafanart
gfolder.mkdir(parents=True, exist_ok=True)
uzcnt = 0
for z in targetdir.glob('*.zip'):
if not re.match('gallery.*\.zip', z.name, re.I):
continue
with zipfile.ZipFile(str(z),"r") as zobj:
zobj.extractall(str(gfolder))
uzcnt += len(zobj.namelist())
if uzcnt:
print(f"[+]Unzipped {uzcnt} gallery photos to folder '{extrafanart}'")
# 封面是否下载成功，否则移动到failed
def image_download(cover, fanart_path, thumb_path, path, filepath, json_data):
full_filepath = os.path.join(path, fanart_path)
if config.getInstance().download_only_missing_images() and not file_not_exist_or_empty(full_filepath):
return
if "headers" in json_data:
if download_file_with_filename(cover, fanart_path, path, filepath, json_data['headers']) == 'failed':
moveFailedFolder(filepath)
return
else:
if download_file_with_filename(cover, fanart_path, path, filepath) == 'failed':
moveFailedFolder(filepath)
return
configProxy = config.getInstance().proxy()
for i in range(configProxy.retry):
if file_not_exist_or_empty(full_filepath):
print('[!]Image Download Failed! Trying again. [{}/3]', i + 1)
if "headers" in json_data:
download_file_with_filename(cover, fanart_path, path, filepath, json_data['headers'])
else:
download_file_with_filename(cover, fanart_path, path, filepath)
continue
else:
break
if file_not_exist_or_empty(full_filepath):
return
print('[+]Image Downloaded!', Path(full_filepath).name)
shutil.copyfile(full_filepath, os.path.join(path, thumb_path))
def print_files(path, leak_word, c_word, naming_rule, part, cn_sub, json_data, filepath, tag, actor_list, liuchu, uncensored, hack_word,fanart_path,poster_path,thumb_path):
title, studio, year, outline, runtime, director, actor_photo, release, number, cover, trailer, website, series, label = get_info(json_data)
if config.getInstance().main_mode() == 3: # 模式3下，由于视频文件不做任何改变，.nfo文件必须和视频文件名称除后缀外完全一致，KODI等软件方可支持
nfo_path = Path(filepath).with_suffix('.nfo')
else:
nfo_path = Path(path) / f"{number}{part}{leak_word}{c_word}{hack_word}.nfo"
try:
if not os.path.exists(path):
try:
os.makedirs(path)
except:
print(f"[-]Fatal error! can not make folder '{path}'")
os._exit(0)
old_nfo = None
try:
if nfo_path.is_file():
old_nfo = etree.parse(nfo_path)
except:
pass
# KODI内查看影片信息时找不到number，配置naming_rule=number+'#'+title虽可解决
# 但使得标题太长，放入时常为空的outline内会更适合，软件给outline留出的显示版面也较大
outline = f"{number}#{outline}"
with nfo_path.open("wt", encoding='UTF-8') as nfo:
print('<?xml version="1.0" encoding="UTF-8" ?>', file=nfo)
print("<movie>", file=nfo)
print(" <title><![CDATA[" + naming_rule + "]]></title>", file=nfo)
print(" <originaltitle><![CDATA[" + naming_rule + "]]></originaltitle>", file=nfo)
print(" <sorttitle><![CDATA[" + naming_rule + "]]></sorttitle>", file=nfo)
print(" <customrating>JP-18+</customrating>", file=nfo)
print(" <mpaa>JP-18+</mpaa>", file=nfo)
print(" <set>", file=nfo)
print(" </set>", file=nfo)
print(" <studio>" + studio + "</studio>", file=nfo)
print(" <year>" + year + "</year>", file=nfo)
print(" <outline><![CDATA[" + outline + "]]></outline>", file=nfo)
print(" <plot><![CDATA[" + outline + "]]></plot>", file=nfo)
print(" <runtime>" + str(runtime).replace(" ", "") + "</runtime>", file=nfo)
print(" <director>" + director + "</director>", file=nfo)
print(" <poster>" + poster_path + "</poster>", file=nfo)
print(" <thumb>" + thumb_path + "</thumb>", file=nfo)
print(" <fanart>" + fanart_path + "</fanart>", file=nfo)
try:
for key in actor_list:
acturl = actor_photo.get(str(key))
print(" <actor>", file=nfo)
print(" <name>" + key + "</name>", file=nfo)
if isinstance(acturl, str) and len(acturl):
print(f" <thumb>{acturl}</thumb>", file=nfo)
print(" </actor>", file=nfo)
except:
aaaa = ''
print(" <maker>" + studio + "</maker>", file=nfo)
print(" <label>" + label + "</label>", file=nfo)
if cn_sub == '1':
print(" <tag>中文字幕</tag>", file=nfo)
if liuchu == '流出':
print(" <tag>流出</tag>", file=nfo)
if uncensored == 1:
print(" <tag>无码</tag>", file=nfo)
if hack_word != '':
print(" <tag>破解</tag>", file=nfo)
try:
for i in tag:
print(" <tag>" + i + "</tag>", file=nfo)
print(" <tag>" + series + "</tag>", file=nfo)
except:
aaaaa = ''
if cn_sub == '1':
print(" <genre>中文字幕</genre>", file=nfo)
if liuchu == '流出':
print(" <genre>流出</genre>", file=nfo)
if uncensored == 1:
print(" <genre>无码</genre>", file=nfo)
if hack_word != '':
print(" <genre>破解</genre>", file=nfo)
try:
for i in tag:
print(" <genre>" + i + "</genre>", file=nfo)
print(" <genre>" + series + "</genre>", file=nfo)
except:
aaaaaaaa = ''
print(" <num>" + number + "</num>", file=nfo)
print(" <premiered>" + release + "</premiered>", file=nfo)
print(" <releasedate>" + release + "</releasedate>", file=nfo)
print(" <release>" + release + "</release>", file=nfo)
if old_nfo:
try:
xur = old_nfo.xpath('//userrating/text()')[0]
if isinstance(xur, str) and re.match('\d+\.\d+|\d+', xur.strip()):
print(f" <userrating>{xur.strip()}</userrating>", file=nfo)
except:
pass
try:
f_rating = json_data['用户评分']
uc = json_data['评分人数']
print(f""" <rating>{round(f_rating * 2.0, 1)}</rating>
<criticrating>{round(f_rating * 20.0, 1)}</criticrating>
<ratings>
<rating name="javdb" max="5" default="true">
<value>{f_rating}</value>
<votes>{uc}</votes>
</rating>
</ratings>""", file=nfo)
except:
if old_nfo:
try:
for rtag in ('rating', 'criticrating'):
xur = old_nfo.xpath(f'//{rtag}/text()')[0]
if isinstance(xur, str) and re.match('\d+\.\d+|\d+', xur.strip()):
print(f" <{rtag}>{xur.strip()}</{rtag}>", file=nfo)
f_rating = old_nfo.xpath(f"//ratings/rating[@name='javdb']/value/text()")[0]
uc = old_nfo.xpath(f"//ratings/rating[@name='javdb']/votes/text()")[0]
print(f""" <ratings>
<rating name="javdb" max="5" default="true">
<value>{f_rating}</value>
<votes>{uc}</votes>
</rating>
</ratings>""", file=nfo)
except:
pass
print(" <cover>" + cover + "</cover>", file=nfo)
if config.getInstance().is_trailer():
print(" <trailer>" + trailer + "</trailer>", file=nfo)
print(" <website>" + website + "</website>", file=nfo)
print("</movie>", file=nfo)
print(f"[+]Wrote! {nfo_path.resolve(strict=True)}")
except IOError as e:
print("[-]Write Failed!")
print("[-]", e)
moveFailedFolder(filepath)
return
except Exception as e1:
print("[-]Write Failed!")
print("[-]", e1)
moveFailedFolder(filepath)
return
def add_mark(poster_path, thumb_path, cn_sub, leak, uncensored, hack) -> None:
"""
add watermark on poster or thumb for describe extra properties 给海报和缩略图加属性水印
此函数从gui版copy过来用用
:poster_path 海报位置
:thumb_path 缩略图位置
:cn_sub: 中文字幕 可选值：1,"1" 或其他值
:uncensored 无码 可选值：1,"1" 或其他值
:hack 破解 可选值：1,"1" 或其他值
"""
mark_type = ''
if cn_sub:
mark_type += ',字幕'
if leak:
mark_type += ',流出'
if uncensored:
mark_type += ',无码'
if hack:
mark_type += ',破解'
if mark_type == '':
return
add_mark_thread(thumb_path, cn_sub, leak, uncensored, hack)
print('[+]Thumb Add Mark: ' + mark_type.strip(','))
add_mark_thread(poster_path, cn_sub, leak, uncensored, hack)
print('[+]Poster Add Mark: ' + mark_type.strip(','))
def add_mark_thread(pic_path, cn_sub, leak, uncensored, hack):
size = 9
img_pic = Image.open(pic_path)
# 获取自定义位置，取余配合pos达到顺时针添加的效果
# 左上 0, 右上 1, 右下 2， 左下 3
count = config.getInstance().watermark_type()
if cn_sub == 1 or cn_sub == '1':
add_to_pic(pic_path, img_pic, size, count, 1) # 添加
count = (count + 1) % 4
if leak == 1 or leak == '1':
add_to_pic(pic_path, img_pic, size, count, 2)
count = (count + 1) % 4
if uncensored == 1 or uncensored == '1':
add_to_pic(pic_path, img_pic, size, count, 3)
if hack == 1 or hack == '1':
add_to_pic(pic_path, img_pic, size, count, 4)
img_pic.close()
def add_to_pic(pic_path, img_pic, size, count, mode):
mark_pic_path = ''
pngpath = ''
if mode == 1:
pngpath = "Img/SUB.png"
elif mode == 2:
pngpath = "Img/LEAK.png"
elif mode == 3:
pngpath = "Img/UNCENSORED.png"
elif mode == 4:
pngpath = "Img/HACK.png"
else:
print('[-]Error: watermark image param mode invalid!')
return
# 先找pyinstaller打包的图片
if hasattr(sys, '_MEIPASS') and os.path.isfile(os.path.join(getattr(sys, '_MEIPASS'), pngpath)):
mark_pic_path = os.path.join(getattr(sys, '_MEIPASS'), pngpath)
# 再找py脚本所在路径的图片
elif os.path.isfile(os.path.join(os.path.dirname(os.path.realpath(__file__)), pngpath)):
mark_pic_path = os.path.join(os.path.dirname(os.path.realpath(__file__)), pngpath)
# 如果没有本地图片才通过网络下载
else:
mark_pic_path = BytesIO(
get_html("https://raw.githubusercontent.com/yoshiko2/AV_Data_Capture/master/" + pngpath,
return_type="content"))
img_subt = Image.open(mark_pic_path)
scroll_high = int(img_pic.height / size)
scroll_wide = int(scroll_high * img_subt.width / img_subt.height)
img_subt = img_subt.resize((scroll_wide, scroll_high), Image.ANTIALIAS)
r, g, b, a = img_subt.split() # 获取颜色通道，保持png的透明性
# 封面四个角的位置
pos = [
{'x': 0, 'y': 0},
{'x': img_pic.width - scroll_wide, 'y': 0},
{'x': img_pic.width - scroll_wide, 'y': img_pic.height - scroll_high},
{'x': 0, 'y': img_pic.height - scroll_high},
]
img_pic.paste(img_subt, (pos[count]['x'], pos[count]['y']), mask=a)
img_pic.save(pic_path, quality=95)
# ========================结束=================================
def paste_file_to_folder(filepath, path, multi_part, number, part, leak_word, c_word, hack_word): # 文件路径，番号，后缀，要移动至的位置
filepath_obj = pathlib.Path(filepath)
houzhui = filepath_obj.suffix
try:
targetpath = os.path.join(path, f"{number}{leak_word}{c_word}{hack_word}{houzhui}")
# 任何情况下都不要覆盖，以免遭遇数据源或者引擎错误导致所有文件得到同一个number，逐一
# 同名覆盖致使全部文件损失且不可追回的最坏情况
if os.path.exists(targetpath):
raise FileExistsError('File Exists on destination path, we will never overwriting.')
link_mode = config.getInstance().link_mode()
# 如果link_mode 1: 建立软链接 2: 硬链接优先、无法建立硬链接再尝试软链接。
# 移除原先soft_link=2的功能代码，因默认记录日志，已经可追溯文件来源
create_softlink = False
if link_mode not in (1, 2):
shutil.move(filepath, targetpath)
elif link_mode == 2:
# 跨卷或跨盘符无法建立硬链接导致异常，回落到建立软链接
try:
os.link(filepath, targetpath, follow_symlinks=False)
except:
create_softlink = True
if link_mode == 1 or create_softlink:
# 先尝试采用相对路径，以便网络访问时能正确打开视频，失败则可能是因为跨盘符等原因无法支持
# 相对路径径，改用绝对路径方式尝试建立软链接
try:
filerelpath = os.path.relpath(filepath, path)
os.symlink(filerelpath, targetpath)
except:
os.symlink(str(filepath_obj.resolve()), targetpath)
sub_res = config.getInstance().sub_rule()
for onefile in filepath_obj.parent.glob('**/*'):
if not onefile.is_file():
continue
if onefile.suffix.lower() in sub_res:
if multi_part and part.lower() not in onefile.name.lower():
continue
if filepath_obj.stem.split('.')[0].lower() != onefile.stem.split('.')[0].lower():
continue
sub_targetpath = Path(path) / f"{number}{leak_word}{c_word}{hack_word}{''.join(onefile.suffixes)}"
if link_mode not in (1, 2):
shutil.move(str(onefile), str(sub_targetpath))
print(f"[+]Sub Moved! {sub_targetpath.name}")
else:
shutil.copyfile(str(onefile), str(sub_targetpath))
print(f"[+]Sub Copied! {sub_targetpath.name}")
elif re.match(r'gallery.*\.zip', onefile.name, re.I): # 下载目录中存在剧照压缩包
gallery_targetpath = Path(path) / onefile.name
if link_mode not in (1, 2):
shutil.move(str(onefile), str(gallery_targetpath))
print(f"[+]Gallery Moved! {onefile.name}")
else:
shutil.copyfile(str(onefile), str(gallery_targetpath))
print(f"[+]Gallery Copied! {onefile.name}")
return
except FileExistsError as fee:
print(f'[-]FileExistsError: {fee}')
moveFailedFolder(filepath)
return
except PermissionError:
print('[-]Error! Please run as administrator!')
return
except OSError as oserr:
print(f'[-]OS Error errno {oserr.errno}')
return
def paste_file_to_folder_mode2(filepath, path, multi_part, number, part, leak_word, c_word, hack_word): # 文件路径，番号，后缀，要移动至的位置
if multi_part == 1:
number += part # 这时number会被附加上CD1后缀
filepath_obj = pathlib.Path(filepath)
houzhui = filepath_obj.suffix
targetpath = os.path.join(path, f"{number}{part}{leak_word}{c_word}{hack_word}{houzhui}")
if os.path.exists(targetpath):
raise FileExistsError('File Exists on destination path, we will never overwriting.')
try:
link_mode = config.getInstance().link_mode()
create_softlink = False
if link_mode not in (1, 2):
shutil.move(filepath, targetpath)
elif link_mode == 2:
try:
os.link(filepath, targetpath, follow_symlinks=False)
except:
create_softlink = True
if link_mode == 1 or create_softlink:
try:
filerelpath = os.path.relpath(filepath, path)
os.symlink(filerelpath, targetpath)
except:
os.symlink(str(filepath_obj.resolve()), targetpath)
sub_res = config.getInstance().sub_rule()
for onefile in filepath_obj.parent.glob('**/*'):
if not onefile.is_file():
continue
if onefile.suffix.lower() in sub_res:
if multi_part and part.lower() not in onefile.name.lower():
continue
sub_targetpath = Path(path) / f"{number}{leak_word}{c_word}{hack_word}{''.join(onefile.suffixes)}"
if link_mode not in (1, 2):
shutil.move(str(onefile), str(sub_targetpath))
print(f"[+]Sub Moved! {sub_targetpath.name}")
else:
shutil.copyfile(str(onefile), str(sub_targetpath))
print(f"[+]Sub Copied! {sub_targetpath.name}")
elif re.match(r'gallery.*\.zip', onefile.name, re.I): # 下载目录中存在剧照压缩包
gallery_targetpath = Path(path) / onefile.name
if link_mode not in (1, 2):
shutil.move(str(onefile), str(gallery_targetpath))
print(f"[+]Gallery Moved! {onefile.name}")
else:
shutil.copyfile(str(onefile), str(gallery_targetpath))
print(f"[+]Gallery Copied! {onefile.name}")
return
except FileExistsError as fee:
print(f'[-]FileExistsError: {fee}')
return
except PermissionError:
print('[-]Error! Please run as administrator!')
return
except OSError as oserr:
print(f'[-]OS Error errno {oserr.errno}')
return
def linkImage(path, number, part, leak_word, c_word, hack_word, ext):
"""
首先尝试为图片建立符合Jellyfin封面图文件名规则的硬连接以节省磁盘空间
如果目标目录无法建立硬链接则将图片复制一份成为常规文件
常规文件日期已经存在时，若修改日期比源文件更旧，则将被新的覆盖，否则忽略
"""
if not all(len(v) for v in (path, number, part, ext)):
return
covers = ("-fanart", "-poster", "-thumb")
normal_prefix = f"{number}{leak_word}{c_word}{hack_word}"
multi_prefix = f"{number}{part}{leak_word}{c_word}{hack_word}"
normal_pathes = (Path(path) / f"{normal_prefix}{c}{ext}" for c in covers)
multi_pathes = (Path(path) / f"{multi_prefix}{c}{ext}" for c in covers)
for normal_path, multi_path in zip(normal_pathes, multi_pathes):
if not normal_path.is_file():
continue
mkLink = False
if not multi_path.exists():
mkLink = True
elif multi_path.is_file():
if multi_path.stat().st_nlink > 1:
continue
elif normal_path.stat().st_mtime <= multi_path.stat().st_mtime:
continue
mkLink = True
multi_path.unlink(missing_ok=True)
if not mkLink:
continue
try:
os.link(str(normal_path), str(multi_path), follow_symlinks=False)
except:
shutil.copyfile(str(normal_path), str(multi_path))
def debug_print(data: json):
try:
print("[+] ------- DEBUG INFO -------")
for i, v in data.items():
if i == 'outline':
print('[+] -', "%-19s" % i, ':', len(v), 'characters')
continue
if i == 'actor_photo' or i == 'year':
continue
if i == 'extrafanart':
print('[+] -', "%-19s" % i, ':', len(v), 'links')
continue
print(f'[+] - {i:<{cnspace(i,19)}} : {v}')
print("[+] ------- DEBUG INFO -------")
except:
pass
def core_main_no_net_op(movie_path, number):
conf = config.getInstance()
part = ''
leak_word = ''
leak = 0
c_word = ''
cn_sub = ''
hack = ''
hack_word = ''
imagecut = 1
multi = False
part = ''
path = str(Path(movie_path).parent)
if re.search('-CD\d+', movie_path, re.IGNORECASE):
part = re.findall('-CD\d+', movie_path, re.IGNORECASE)[0].upper()
multi = True
if re.search(r'[-_]C(\.\w+$|-\w+)|\d+ch(\.\w+$|-\w+)', movie_path,
re.I) or '中文' in movie_path or '字幕' in movie_path or ".chs" in movie_path or '.cht' in movie_path:
cn_sub = '1'
c_word = '-C' # 中文字幕影片后缀
uncensored = 1 if is_uncensored(number) else 0
if '流出' in movie_path or 'uncensored' in movie_path.lower():
leak_word = '-流出' # 流出影片后缀
leak = 1
if 'hack'.upper() in str(movie_path).upper() or '破解' in movie_path:
hack = 1
hack_word = "-hack"
prestr = f"{number}{leak_word}{c_word}{hack_word}"
full_nfo = Path(path) / f"{prestr}{part}.nfo"
if full_nfo.is_file():
if full_nfo.read_text(encoding='utf-8').find(r'<tag>无码</tag>') >= 0:
uncensored = 1
try:
nfo_xml = etree.parse(full_nfo)
nfo_fanart_path = nfo_xml.xpath('//fanart/text()')[0]
ext = Path(nfo_fanart_path).suffix
if conf.download_actor_photo_for_kodi():
actors_fullpath = full_nfo.with_name('.actors')
actors_name = nfo_xml.xpath('//actor/name/text()')
local_cnt = 0
for actor_name in actors_name:
pic_fullpath = actors_fullpath / f'{actor_name}.jpg'
if conf.download_only_missing_images() and not file_not_exist_or_empty(pic_fullpath):
continue
if copy_from_local_gfriends(actor_name, pic_fullpath):
local_cnt += 1
if local_cnt:
print(f"[+]Successfully link or copy {local_cnt} actor photo from local gfriends git repository")
except:
return
else:
return
fanart_path = f"{prestr}-fanart{ext}"
poster_path = f"{prestr}-poster{ext}"
thumb_path = f"{prestr}-thumb{ext}"
full_fanart_path = os.path.join(path, fanart_path)
full_poster_path = os.path.join(path, poster_path)
full_thumb_path = os.path.join(path, thumb_path)
if not all(os.path.isfile(f) for f in (full_fanart_path, full_thumb_path)):
return
cutImage(imagecut, path, fanart_path, poster_path, bool(conf.face_uncensored_only() and not uncensored))
if conf.is_watermark():
add_mark(full_poster_path, full_thumb_path, cn_sub, leak, uncensored, hack)
if multi and conf.jellyfin_multi_part_fanart():
linkImage(path, number, part, leak_word, c_word, hack_word, ext)
if conf.is_extrafanart():
unzip_local_gallery(path)
def core_main(movie_path, number_th, oCC):
conf = config.getInstance()
# =======================================================================初始化所需变量
multi_part = 0
part = ''
leak_word = ''
c_word = ''
cn_sub = ''
liuchu = ''
hack = ''
hack_word = ''
# 下面被注释的变量不需要
#rootpath= os.getcwd
number = number_th
json_data = get_data_from_json(number, oCC) # 定义番号
# Return if blank dict returned (data not found)
if not json_data:
moveFailedFolder(movie_path)
return
if json_data["number"] != number:
# fix issue #119
# the root cause is we normalize the search id
# print_files() will use the normalized id from website,
# but paste_file_to_folder() still use the input raw search id
# so the solution is: use the normalized search id
number = json_data["number"]
imagecut = json_data.get('imagecut')
tag = json_data.get('tag')
# =======================================================================判断-C,-CD后缀
if re.search('-CD\d+', movie_path, re.IGNORECASE):
multi_part = 1
part = re.findall('-CD\d+', movie_path, re.IGNORECASE)[0].upper()
if re.search(r'[-_]C(\.\w+$|-\w+)|\d+ch(\.\w+$|-\w+)', movie_path,
re.I) or '中文' in movie_path or '字幕' in movie_path:
cn_sub = '1'
c_word = '-C' # 中文字幕影片后缀
# 判断是否无码
unce = json_data.get('无码')
uncensored = int(unce) if isinstance(unce, bool) else int(is_uncensored(number))
if '流出' in movie_path or 'uncensored' in movie_path.lower():
liuchu = '流出'
leak = 1
leak_word = '-流出' # 流出影片后缀
else:
leak = 0
if 'hack'.upper() in str(movie_path).upper() or '破解' in movie_path:
hack = 1
hack_word = "-hack"
# 调试模式检测
if conf.debug():
debug_print(json_data)
# 创建文件夹
#path = create_folder(rootpath + '/' + conf.success_folder(), json_data.get('location_rule'), json_data)