-
Notifications
You must be signed in to change notification settings - Fork 227
/
fetch.py
1296 lines (1211 loc) · 54.1 KB
/
fetch.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
#!/usr/bin/env python3
# pyright: reportConstantRedefinition = none
# pyright: reportMissingTypeStubs = none
# pyright: reportRedeclaration = none
# pyright: reportMissingParameterType = none
# pyright: reportUnnecessaryIsInstance = none
# pyright: reportUnknownVariableType = none
# pyright: reportUnknownMemberType = none
# pyright: reportUnknownArgumentType = none
# pyright: reportArgumentType = none
# pyright: reportAttributeAccessIssue = none
# pyright: reportGeneralTypeIssues = none
import yaml
import json
import base64
from urllib.parse import quote, unquote, urlparse
import requests
from requests_file import FileAdapter
import datetime
import traceback
import binascii
import threading
import sys
import os
import copy
from types import FunctionType as function
from typing import Set, List, Dict, Tuple, Union, Callable, Any, Optional, no_type_check
try: PROXY = open("local_proxy.conf").read().strip()
except FileNotFoundError: LOCAL = False; PROXY = None
else:
if not PROXY: PROXY = None
LOCAL = not PROXY
def b64encodes(s: str):
return base64.b64encode(s.encode('utf-8')).decode('utf-8')
def b64encodes_safe(s: str):
return base64.urlsafe_b64encode(s.encode('utf-8')).decode('utf-8')
def b64decodes(s: str):
ss = s + '=' * ((4-len(s)%4)%4)
try:
return base64.b64decode(ss.encode('utf-8')).decode('utf-8')
except UnicodeDecodeError: raise
except binascii.Error: raise
def b64decodes_safe(s: str):
ss = s + '=' * ((4-len(s)%4)%4)
try:
return base64.urlsafe_b64decode(ss.encode('utf-8')).decode('utf-8')
except UnicodeDecodeError: raise
except binascii.Error: raise
DEFAULT_UUID = '8'*8+'-8888'*3+'-'+'8'*12
CLASH2VMESS = {'name': 'ps', 'server': 'add', 'port': 'port', 'uuid': 'id',
'alterId': 'aid', 'cipher': 'scy', 'network': 'net', 'servername': 'sni'}
VMESS2CLASH: Dict[str, str] = {}
for k,v in CLASH2VMESS.items(): VMESS2CLASH[v] = k
VMESS_EXAMPLE = {
"v": "2", "ps": "", "add": "0.0.0.0", "port": "0", "aid": "0", "scy": "auto",
"net": "tcp", "type": "none", "tls": "", "id": DEFAULT_UUID
}
CLASH_CIPHER_VMESS = "auto aes-128-gcm chacha20-poly1305 none".split()
CLASH_CIPHER_SS = "aes-128-gcm aes-192-gcm aes-256-gcm aes-128-cfb aes-192-cfb \
aes-256-cfb aes-128-ctr aes-192-ctr aes-256-ctr rc4-md5 chacha20-ietf \
xchacha20 chacha20-ietf-poly1305 xchacha20-ietf-poly1305".split()
CLASH_SSR_OBFS = "plain http_simple http_post random_head tls1.2_ticket_auth tls1.2_ticket_fastauth".split()
CLASH_SSR_PROTOCOL = "origin auth_sha1_v4 auth_aes128_md5 auth_aes128_sha1 auth_chain_a auth_chain_b".split()
ABFURLS = (
"https://raw.githubusercontent.com/AdguardTeam/AdguardFilters/master/ChineseFilter/sections/adservers.txt",
"https://raw.githubusercontent.com/AdguardTeam/AdguardFilters/master/ChineseFilter/sections/adservers_firstparty.txt",
"https://raw.githubusercontent.com/AdguardTeam/FiltersRegistry/master/filters/filter_224_Chinese/filter.txt",
# "https://raw.githubusercontent.com/AdguardTeam/FiltersRegistry/master/filters/filter_15_DnsFilter/filter.txt",
# "https://malware-filter.gitlab.io/malware-filter/urlhaus-filter-ag.txt",
# "https://raw.githubusercontent.com/banbendalao/ADgk/master/ADgk.txt",
# "https://raw.githubusercontent.com/hoshsadiq/adblock-nocoin-list/master/nocoin.txt",
# "https://anti-ad.net/adguard.txt",
"https://raw.githubusercontent.com/TG-Twilight/AWAvenue-Ads-Rule/main/AWAvenue-Ads-Rule.txt",
"https://raw.githubusercontent.com/d3ward/toolz/master/src/d3host.adblock",
# "https://raw.githubusercontent.com/Cats-Team/AdRules/main/dns.txt",
# "https://raw.githubusercontent.com/hagezi/dns-blocklists/main/adblock/light.txt",
# "https://raw.githubusercontent.com/uniartisan/adblock_list/master/adblock_lite.txt",
"https://raw.githubusercontent.com/afwfv/DD-AD/main/rule/DD-AD.txt",
# "https://raw.githubusercontent.com/afwfv/DD-AD/main/rule/domain.txt",
)
ABFWHITE = (
"https://raw.githubusercontent.com/privacy-protection-tools/dead-horse/master/anti-ad-white-list.txt",
"file:///abpwhite.txt",
)
FAKE_IPS = "8.8.8.8; 8.8.4.4; 4.2.2.2; 4.2.2.1; 114.114.114.114; 127.0.0.1; 0.0.0.0".split('; ')
FAKE_DOMAINS = ".google.com .gh.neting.cc".split()
FETCH_TIMEOUT = (6, 5)
BANNED_WORDS = b64decodes('5rOV6L2uIOi9ruWtkCDova4g57uDIOawlCDlip8gb25ndGFpd2Fu').split()
# !!! JUST FOR DEBUGING !!!
DEBUG_NO_NODES = os.path.exists("local_NO_NODES")
DEBUG_NO_DYNAMIC = os.path.exists("local_NO_DYNAMIC")
DEBUG_NO_ADBLOCK = os.path.exists("local_NO_ADBLOCK")
STOP = False
STOP_FAKE_NODES = """vmess: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
vmess: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
vmess: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
"""
class UnsupportedType(Exception): pass
class NotANode(Exception): pass
session = requests.Session()
session.trust_env = False
if PROXY: session.proxies = {'http': PROXY, 'https': PROXY}
session.headers["User-Agent"] = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36 Edg/114.0.1823.58'
session.mount('file://', FileAdapter())
exc_queue: List[str] = []
d = datetime.datetime.now()
if STOP or (d.month, d.day) in ((6, 4), (7, 1), (10, 1)):
DEBUG_NO_NODES = DEBUG_NO_DYNAMIC = STOP = True
class Node:
names: Set[str] = set()
DATA_TYPE = Dict[str, Any]
def __init__(self, data: Union[DATA_TYPE, str]) -> None:
if isinstance(data, dict):
self.data: __class__.DATA_TYPE = data
self.type = data['type']
elif isinstance(data, str):
self.load_url(data)
else: raise TypeError(f"Got {type(data)}")
if not self.data['name']:
self.data['name'] = "未命名"
if 'password' in self.data:
self.data['password'] = str(self.data['password'])
self.data['type'] = self.type
self.name: str = self.data['name']
def __str__(self):
return self.url
def __hash__(self):
data = self.data
try:
path = ""
if self.type == 'vmess':
net: str = data.get('network', '')
path = net+':'
if not net: pass
elif net == 'ws':
opts: Dict[str, Any] = data.get('ws-opts', {})
path += opts.get('headers', {}).get('Host', '')
path += '/'+opts.get('path', '')
elif net == 'h2':
opts: Dict[str, Any] = data.get('h2-opts', {})
path += ','.join(opts.get('host', []))
path += '/'+opts.get('path', '')
elif net == 'grpc':
path += data.get('grpc-opts', {}).get('grpc-service-name','')
elif self.type == 'ss':
opts: Dict[str, Any] = data.get('plugin-opts', {})
path = opts.get('host', '')
path += '/'+opts.get('path', '')
elif self.type == 'ssr':
path = data.get('obfs-param', '')
elif self.type == 'trojan':
path = data.get('sni', '')+':'
net: str = data.get('network', '')
if not net: pass
elif net == 'ws':
opts: Dict[str, Any] = data.get('ws-opts', {})
path += opts.get('headers', {}).get('Host', '')
path += '/'+opts.get('path', '')
elif net == 'grpc':
path += data.get('grpc-opts', {}).get('grpc-service-name','')
elif self.type == 'vless':
path = data.get('sni', '')+':'
net: str = data.get('network', '')
if not net: pass
elif net == 'ws':
opts: Dict[str, Any] = data.get('ws-opts', {})
path += opts.get('headers', {}).get('Host', '')
path += '/'+opts.get('path', '')
elif net == 'grpc':
path += data.get('grpc-opts', {}).get('grpc-service-name','')
elif self.type == 'hysteria2':
path = data.get('sni', '')+':'
path += data.get('obfs-password', '')+':'
# print(self.url)
# return hash(self.url)
path += '@'+','.join(data.get('alpn', []))+'@'+data.get('password', '')+data.get('uuid', '')
hashstr = f"{self.type}:{data['server']}:{data['port']}:{path}"
return hash(hashstr)
except Exception:
print("节点 Hash 计算失败!", file=sys.stderr)
traceback.print_exc(file=sys.stderr)
return hash('__ERROR__')
def __eq__(self, other: Union['Node', Any]):
if isinstance(other, self.__class__):
return hash(self) == hash(other)
else:
return False
def load_url(self, url: str) -> None:
try: self.type, dt = url.split("://")
except ValueError: raise NotANode(url)
# === Fix begin ===
if not self.type.isascii():
self.type = ''.join([_ for _ in self.type if _.isascii()])
url = self.type+'://'+url.split("://")[1]
if self.type == 'hy2': self.type = 'hysteria2'
# === Fix end ===
if self.type == 'vmess':
v = VMESS_EXAMPLE.copy()
try: v.update(json.loads(b64decodes(dt)))
except Exception:
raise UnsupportedType('vmess', 'SP')
self.data = {}
for key, val in v.items():
if key in VMESS2CLASH:
self.data[VMESS2CLASH[key]] = val
self.data['tls'] = (v['tls'] == 'tls')
self.data['alterId'] = int(self.data['alterId'])
if v['net'] == 'ws':
opts = {}
if 'path' in v:
opts['path'] = v['path']
if 'host' in v:
opts['headers'] = {'Host': v['host']}
self.data['ws-opts'] = opts
elif v['net'] == 'h2':
opts = {}
if 'path' in v:
opts['path'] = v['path']
if 'host' in v:
opts['host'] = v['host'].split(',')
self.data['h2-opts'] = opts
elif v['net'] == 'grpc' and 'path' in v:
self.data['grpc-opts'] = {'grpc-service-name': v['path']}
elif self.type == 'ss':
info = url.split('@')
srvname = info.pop()
if '#' in srvname:
srv, name = srvname.split('#')
else:
srv = srvname
name = ''
server, port = srv.split(':')
try:
port = int(port)
except ValueError:
raise UnsupportedType('ss', 'SP')
info = '@'.join(info)
if not ':' in info:
info = b64decodes_safe(info)
if ':' in info:
cipher, passwd = info.split(':')
else:
cipher = info
passwd = ''
self.data = {'name': unquote(name), 'server': server,
'port': port, 'type': 'ss', 'password': passwd, 'cipher': cipher}
elif self.type == 'ssr':
if '?' in url:
parts = dt.split(':')
else:
parts = b64decodes_safe(dt).split(':')
try:
passwd, info = parts[-1].split('/?')
except: raise
passwd = b64decodes_safe(passwd)
self.data = {'type': 'ssr', 'server': parts[0], 'port': parts[1],
'protocol': parts[2], 'cipher': parts[3], 'obfs': parts[4],
'password': passwd, 'name': ''}
for kv in info.split('&'):
k_v = kv.split('=')
if len(k_v) != 2:
k = k_v[0]
v = ''
else: k,v = k_v
if k == 'remarks':
self.data['name'] = v
elif k == 'group':
self.data['group'] = v
elif k == 'obfsparam':
self.data['obfs-param'] = v
elif k == 'protoparam':
self.data['protocol-param'] = v
elif self.type == 'trojan':
parsed = urlparse(url)
self.data = {'name': unquote(parsed.fragment), 'server': parsed.hostname,
'port': parsed.port, 'type': 'trojan', 'password': unquote(parsed.username)} # type: ignore
if parsed.query:
for kv in parsed.query.split('&'):
k,v = kv.split('=')
if k in ('allowInsecure', 'insecure'):
self.data['skip-cert-verify'] = (v != '0')
elif k == 'sni': self.data['sni'] = v
elif k == 'alpn':
self.data['alpn'] = unquote(v).split(',')
elif k == 'type':
self.data['network'] = v
elif k == 'serviceName':
if 'grpc-opts' not in self.data:
self.data['grpc-opts'] = {}
self.data['grpc-opts']['grpc-service-name'] = v
elif k == 'host':
if 'ws-opts' not in self.data:
self.data['ws-opts'] = {}
if 'headers' not in self.data['ws-opts']:
self.data['ws-opts']['headers'] = {}
self.data['ws-opts']['headers']['Host'] = v
elif k == 'path':
if 'ws-opts' not in self.data:
self.data['ws-opts'] = {}
self.data['ws-opts']['path'] = v
elif self.type == 'vless':
parsed = urlparse(url)
self.data = {'name': unquote(parsed.fragment), 'server': parsed.hostname,
'port': parsed.port, 'type': 'vless', 'uuid': unquote(parsed.username)} # type: ignore
self.data['tls'] = False
if parsed.query:
for kv in parsed.query.split('&'):
k,v = kv.split('=')
if k in ('allowInsecure', 'insecure'):
self.data['skip-cert-verify'] = (v != '0')
elif k == 'sni': self.data['servername'] = v
elif k == 'alpn':
self.data['alpn'] = unquote(v).split(',')
elif k == 'type':
self.data['network'] = v
elif k == 'serviceName':
if 'grpc-opts' not in self.data:
self.data['grpc-opts'] = {}
self.data['grpc-opts']['grpc-service-name'] = v
elif k == 'host':
if 'ws-opts' not in self.data:
self.data['ws-opts'] = {}
if 'headers' not in self.data['ws-opts']:
self.data['ws-opts']['headers'] = {}
self.data['ws-opts']['headers']['Host'] = v
elif k == 'path':
if 'ws-opts' not in self.data:
self.data['ws-opts'] = {}
self.data['ws-opts']['path'] = v
elif k == 'flow':
if v.endswith('-udp443'):
self.data['flow'] = v
else: self.data['flow'] = v+'!'
elif k == 'fp': self.data['client-fingerprint'] = v
elif k == 'security' and v == 'tls':
self.data['tls'] = True
elif k == 'pbk':
if 'reality-opts' not in self.data:
self.data['reality-opts'] = {}
self.data['reality-opts']['public-key'] = v
elif k == 'sid':
if 'reality-opts' not in self.data:
self.data['reality-opts'] = {}
self.data['reality-opts']['short-id'] = v
# TODO: Unused key encryption
elif self.type == 'hysteria2':
parsed = urlparse(url)
self.data = {'name': unquote(parsed.fragment), 'server': parsed.hostname,
'type': 'hysteria2', 'password': unquote(parsed.username)} # type: ignore
if ':' in parsed.netloc:
ports = parsed.netloc.split(':')[1]
if ',' in ports:
self.data['port'], self.data['ports'] = ports.split(',',1)
else:
self.data['port'] = ports
try: self.data['port'] = int(self.data['port'])
except ValueError: self.data['port'] = 443
else:
self.data['port'] = 443
self.data['tls'] = False
if parsed.query:
for kv in parsed.query.split('&'):
k,v = kv.split('=')
if k == 'insecure':
self.data['skip-cert-verify'] = (v != '0')
elif k == 'alpn':
self.data['alpn'] = unquote(v).split(',')
elif k in ('sni', 'obfs', 'obfs-password'):
self.data[k] = v
elif k == 'fp': self.data['fingerprint'] = v
else: raise UnsupportedType(self.type)
def format_name(self, max_len=30) -> None:
self.data['name'] = self.name
for word in BANNED_WORDS:
self.data['name'] = self.data['name'].replace(word, '*'*len(word))
if len(self.data['name']) > max_len:
self.data['name'] = self.data['name'][:max_len]+'...'
if self.data['name'] in Node.names:
i = 0
new: str = self.data['name']
while new in Node.names:
i += 1
new = f"{self.data['name']} #{i}"
self.data['name'] = new
@property
def isfake(self) -> bool:
try:
if 'server' not in self.data: return True
if '.' not in self.data['server']: return True
if self.data['server'] in FAKE_IPS: return True
if int(str(self.data['port'])) < 20: return True
for domain in FAKE_DOMAINS:
if self.data['server'] == domain.lstrip('.'): return True
if self.data['server'].endswith(domain): return True
# TODO: Fake UUID
# if self.type == 'vmess' and len(self.data['uuid']) != len(DEFAULT_UUID):
# return True
except Exception:
print("无法验证的节点!", file=sys.stderr)
traceback.print_exc(file=sys.stderr)
return False
@property
def url(self) -> str:
data = self.data
if self.type == 'vmess':
v = VMESS_EXAMPLE.copy()
for key,val in data.items():
if key in CLASH2VMESS:
v[CLASH2VMESS[key]] = val
if v['net'] == 'ws':
if 'ws-opts' in data:
try:
v['host'] = data['ws-opts']['headers']['Host']
except KeyError: pass
if 'path' in data['ws-opts']:
v['path'] = data['ws-opts']['path']
elif v['net'] == 'h2':
if 'h2-opts' in data:
if 'host' in data['h2-opts']:
v['host'] = ','.join(data['h2-opts']['host'])
if 'path' in data['h2-opts']:
v['path'] = data['h2-opts']['path']
elif v['net'] == 'grpc':
if 'grpc-opts' in data:
if 'grpc-service-name' in data['grpc-opts']:
v['path'] = data['grpc-opts']['grpc-service-name']
if ('tls' in data) and data['tls']:
v['tls'] = 'tls'
return 'vmess://'+b64encodes(json.dumps(v, ensure_ascii=False))
if self.type == 'ss':
passwd = b64encodes_safe(data['cipher']+':'+data['password'])
return f"ss://{passwd}@{data['server']}:{data['port']}#{quote(data['name'])}"
if self.type == 'ssr':
ret = (':'.join([str(self.data[_]) for _ in ('server','port',
'protocol','cipher','obfs')]) +
b64encodes_safe(self.data['password']) +
f"remarks={b64encodes_safe(self.data['name'])}")
for k, urlk in (('obfs-param','obfsparam'), ('protocol-param','protoparam'), ('group','group')):
if k in self.data:
ret += '&'+urlk+'='+b64encodes_safe(self.data[k])
return "ssr://"+ret
if self.type == 'trojan':
passwd = quote(data['password'])
name = quote(data['name'])
ret = f"trojan://{passwd}@{data['server']}:{data['port']}?"
if 'skip-cert-verify' in data:
ret += f"allowInsecure={int(data['skip-cert-verify'])}&"
if 'sni' in data:
ret += f"sni={data['sni']}&"
if 'alpn' in data:
ret += f"alpn={quote(','.join(data['alpn']))}&"
if 'network' in data:
if data['network'] == 'grpc':
ret += f"type=grpc&serviceName={data['grpc-opts']['grpc-service-name']}"
elif data['network'] == 'ws':
ret += f"type=ws&"
if 'ws-opts' in data:
try:
ret += f"host={data['ws-opts']['headers']['Host']}&"
except KeyError: pass
if 'path' in data['ws-opts']:
ret += f"path={data['ws-opts']['path']}"
ret = ret.rstrip('&')+'#'+name
return ret
if self.type == 'vless':
passwd = quote(data['uuid'])
name = quote(data['name'])
ret = f"vless://{passwd}@{data['server']}:{data['port']}?"
if 'skip-cert-verify' in data:
ret += f"allowInsecure={int(data['skip-cert-verify'])}&"
if 'servername' in data:
ret += f"sni={data['servername']}&"
if 'alpn' in data:
ret += f"alpn={quote(','.join(data['alpn']))}&"
if 'network' in data:
if data['network'] == 'grpc':
ret += f"type=grpc&serviceName={data['grpc-opts']['grpc-service-name']}"
elif data['network'] == 'ws':
ret += f"type=ws&"
if 'ws-opts' in data:
try:
ret += f"host={data['ws-opts']['headers']['Host']}&"
except KeyError: pass
if 'path' in data['ws-opts']:
ret += f"path={data['ws-opts']['path']}"
if 'flow' in data:
flow: str = data['flow']
if flow.endswith('!'):
ret += f"flow={flow[:-1]}&"
else: ret += f"flow={flow}-udp443&"
if 'client-fingerprint' in data:
ret += f"fp={data['client-fingerprint']}&"
if 'tls' in data and data['tls']:
ret += f"security=tls&"
elif 'reality-opts' in data:
opts: Dict[str, str] = data['reality-opts']
ret += f"security=reality&pbk={opts.get('public-key','')}&sid={opts.get('short-id','')}&"
ret = ret.rstrip('&')+'#'+name
return ret
if self.type == 'hysteria2':
passwd = quote(data['password'])
name = quote(data['name'])
ret = f"hysteria2://{passwd}@{data['server']}:{data['port']}"
if 'ports' in data:
ret += ','+data['ports']
ret += '?'
if 'skip-cert-verify' in data:
ret += f"insecure={int(data['skip-cert-verify'])}&"
if 'alpn' in data:
ret += f"alpn={quote(','.join(data['alpn']))}&"
if 'fingerprint' in data:
ret += f"fp={data['fingerprint']}&"
for k in ('sni', 'obfs', 'obfs-password'):
if k in data:
ret += f"{k}={data[k]}&"
ret = ret.rstrip('&')+'#'+name
return ret
raise UnsupportedType(self.type)
@property
def clash_data(self) -> DATA_TYPE:
ret = self.data.copy()
if 'password' in ret and ret['password'].isdigit():
ret['password'] = '!!str '+ret['password']
if 'uuid' in ret and len(ret['uuid']) != len(DEFAULT_UUID):
ret['uuid'] = DEFAULT_UUID
if 'group' in ret: del ret['group']
if 'cipher' in ret and not ret['cipher']:
ret['cipher'] = 'auto'
if self.type == 'vless' and 'flow' in ret:
if ret['flow'].endswith('-udp443'):
ret['flow'] = ret['flow'][:-7]
elif ret['flow'].endswith('!'):
ret['flow'] = ret['flow'][:-1]
if 'alpn' in ret and isinstance(ret['alpn'], str):
# 'alpn' is not a slice
ret['alpn'] = ret['alpn'].replace(' ','').split(',')
return ret
def supports_meta(self, noMeta=False) -> bool:
if self.isfake: return False
if self.type == 'vmess':
supported = CLASH_CIPHER_VMESS
elif self.type == 'ss' or self.type == 'ssr':
supported = CLASH_CIPHER_SS
elif self.type == 'trojan': return True
elif noMeta: return False
else: return True
if 'network' in self.data and self.data['network'] in ('h2','grpc'):
# A quick fix for #2
self.data['tls'] = True
if 'cipher' not in self.data: return True
if not self.data['cipher']: return True
if self.data['cipher'] not in supported: return False
try:
if self.type == 'ssr':
if 'obfs' in self.data and self.data['obfs'] not in CLASH_SSR_OBFS:
return False
if 'protocol' in self.data and self.data['protocol'] not in CLASH_SSR_PROTOCOL:
return False
if 'plugin-opts' in self.data and 'mode' in self.data['plugin-opts'] \
and not self.data['plugin-opts']['mode']: return False
except Exception:
print("无法验证的 Clash 节点!", file=sys.stderr)
traceback.print_exc(file=sys.stderr)
return False
return True
def supports_clash(self, meta=False) -> bool:
if meta: return self.supports_meta()
if self.type == 'vless': return False
if self.data['type'] == 'vless': return False
return self.supports_meta(noMeta=True)
def supports_ray(self) -> bool:
if self.isfake: return False
# if self.type == 'ss':
# if 'plugin' in self.data and self.data['plugin']: return False
# elif self.type == 'ssr':
# return False
return True
class Source():
@no_type_check
def __init__(self, url: Union[str, function]) -> None:
if isinstance(url, function):
self.url: str = "dynamic://"+url.__name__
self.url_source: function = url
elif url.startswith('+'):
self.url_source: str = url
self.date = datetime.datetime.now()# + datetime.timedelta(days=1)
self.gen_url()
else:
self.url: str = url
self.url_source: None = None
self.content: Union[str, List[str], int] = None
self.sub: Union[List[str], List[Dict[str, str]]] = None
self.cfg: Dict[str, Any] = {}
def gen_url(self) -> None:
self.url_source: str
tags = self.url_source.split()
url = tags.pop()
while tags:
tag = tags.pop(0)
if tag[0] != '+': break
if tag == '+date':
url = self.date.strftime(url)
self.date -= datetime.timedelta(days=1)
self.url = url
@no_type_check
def get(self, depth=2) -> None:
global exc_queue
if self.content: return
try:
if self.url.startswith("dynamic:"):
self.content: Union[str, List[str]] = self.url_source()
else:
global session
if '#' in self.url:
segs = self.url.split('#')
self.cfg = dict([_.split('=',1) for _ in segs[-1].split('&')])
if 'max' in self.cfg:
try:
self.cfg['max'] = int(self.cfg['max'])
except ValueError:
exc_queue.append("最大节点数限制不是整数!")
del self.cfg['max']
if 'ignore' in self.cfg:
self.cfg['ignore'] = [_ for _ in self.cfg['ignore'].split(',') if _.strip()]
self.url = '#'.join(segs[:-1])
with session.get(self.url, stream=True) as r:
if r.status_code != 200:
if depth > 0 and isinstance(self.url_source, str):
exc = f"'{self.url}' 抓取时 {r.status_code}"
self.gen_url()
exc += ",重新生成链接:\n\t"+self.url
exc_queue.append(exc)
self.get(depth-1)
else:
self.content = r.status_code
return
self.content = self._download(r)
except KeyboardInterrupt: raise
except requests.exceptions.RequestException:
self.content = -1
except:
self.content = -2
exc = "在抓取 '"+self.url+"' 时发生错误:\n"+traceback.format_exc()
exc_queue.append(exc)
else:
self.parse()
def _download(self, r: requests.Response) -> str:
content: str = ""
tp = None
pending = None
early_stop = False
for chunk in r.iter_content():
if early_stop: pending = None; break
chunk: bytes
if pending is not None:
chunk = pending + chunk
pending = None
if tp == 'sub':
content += chunk.decode(errors='ignore')
continue
lines: List[bytes] = chunk.splitlines()
if lines and lines[-1] and chunk and lines[-1][-1] == chunk[-1]:
pending = lines.pop()
while lines:
line = lines.pop(0).rstrip().decode(errors='ignore').replace('\\r','')
if not line: continue
if not tp:
if ': ' in line:
kv = line.split(': ')
if len(kv) == 2 and kv[0].isalpha():
tp = 'yaml'
elif line[0] == '#': pass
else: tp = 'sub'
if tp == 'yaml':
if content:
if line in ("proxy-groups:", "rules:", "script:"):
early_stop=True; break
content += line+'\n'
elif line == "proxies:":
content = line+'\n'
elif tp == 'sub':
content = chunk.decode(errors='ignore')
if pending is not None: content += pending.decode(errors='ignore')
return content
def parse(self) -> None:
global exc_queue
try:
text = self.content
if isinstance(text, str):
if "proxies:" in text:
# Clash config
config = yaml.full_load(text.replace("!<str>","!!str"))
sub = config['proxies']
elif '://' in text:
# V2Ray raw list
sub = text.strip().splitlines()
else:
# V2Ray Sub
sub = b64decodes(text.strip()).strip().splitlines()
else: sub = text # 动态节点抓取后直接传入列表
if 'max' in self.cfg and len(sub) > self.cfg['max']:
exc_queue.append(f"此订阅有 {len(sub)} 个节点,最大限制为 {self.cfg['max']} 个,忽略此订阅。")
self.sub = []
elif sub and 'ignore' in self.cfg:
if isinstance(sub[0], str):
self.sub = [_ for _ in sub if _.split('://', 1)[0] not in self.cfg['ignore']]
elif isinstance(sub[0], dict):
self.sub = [_ for _ in sub if _.get('type', '') not in self.cfg['ignore']] #type:ignore
else: self.sub = sub
else: self.sub = sub
except KeyboardInterrupt: raise
except: exc_queue.append(
"在解析 '"+self.url+"' 时发生错误:\n"+traceback.format_exc())
class DomainTree:
def __init__(self) -> None:
self.children: Dict[str, __class__] = {}
self.here: bool = False
def insert(self, domain: str) -> None:
segs = domain.split('.')
segs.reverse()
self._insert(segs)
def _insert(self, segs: List[str]) -> None:
if not segs:
self.here = True
return
if segs[0] not in self.children:
self.children[segs[0]] = __class__()
child = self.children[segs[0]]
del segs[0]
child._insert(segs)
def remove(self, domain: str) -> None:
segs = domain.split('.')
segs.reverse()
self._remove(segs)
def _remove(self, segs: List[str]) -> None:
self.here = False
if not segs:
self.children.clear()
return
if segs[0] in self.children:
child = self.children[segs[0]]
del segs[0]
child._remove(segs)
def get(self) -> List[str]:
ret: List[str] = []
for name, child in self.children.items():
if child.here: ret.append(name)
else: ret.extend([_+'.'+name for _ in child.get()])
return ret
def extract(url: str) -> Union[Set[str], int]:
global session
res = session.get(url)
if res.status_code != 200: return res.status_code
urls: Set[str] = set()
for line in res.text:
if line.startswith("http"):
urls.add(line)
return urls
merged: Dict[int, Node] = {}
unknown: Set[str] = set()
used: Dict[int, Dict[int, str]] = {}
def merge(source_obj: Source, sourceId=-1) -> None:
global merged, unknown
sub = source_obj.sub
if not sub: print("空订阅,跳过!", end='', flush=True); return
for p in sub:
if isinstance(p, str):
if '://' not in p: continue
ok = True
for ch in '!|`()[]{} ':
if ch in p:
ok = False; break
if not ok: continue
try: n = Node(p)
except KeyboardInterrupt: raise
except UnsupportedType as e:
if len(e.args) == 1:
print(f"不支持的类型:{e}")
unknown.add(p) # type: ignore
except: traceback.print_exc()
else:
n.format_name()
Node.names.add(n.data['name'])
hashn = hash(n)
if hashn not in merged:
merged[hashn] = n
else:
merged[hashn].data.update(n.data)
if hashn not in used:
used[hashn] = {}
used[hashn][sourceId] = n.name
def raw2fastly(url: str) -> str:
# 由于 Fastly CDN 不好用,因此换成 ghproxy.net,见 README。
# 2023/06/27: ghproxy.com 比 ghproxy.net 稳定性更好,为避免日后代码失效,进行修改
# 2023/06/28: ghproxy.com 似乎有速率或并发限制,改回原来的镜像
# 2023/10/01: ghproxy.net tcping 有大量丢包,且之前出现过证书未续期的问题,改掉
# 2023/12/23: 全都废了
if not LOCAL: return url
url: Union[str, List[str]]
if url.startswith("https://raw.githubusercontent.com/"):
# url = url[34:].split('/')
# url[1] += '@'+url[2]
# del url[2]
# url = "https://fastly.jsdelivr.net/gh/"+('/'.join(url))
# return url
return "https://mirror.ghproxy.com/"+url
return url
def merge_adblock(adblock_name: str, rules: Dict[str, str]) -> None:
print("正在解析 Adblock 列表... ", end='', flush=True)
blocked: Set[str] = set()
unblock: Set[str] = set()
for url in ABFURLS:
url = raw2fastly(url)
try:
res = session.get(url)
except requests.exceptions.RequestException as e:
try:
print(f"{url} 下载失败:{e.args[0].reason}")
except Exception:
print(f"{url} 下载失败:无法解析的错误!")
traceback.print_exc()
continue
if res.status_code != 200:
print(url, res.status_code)
continue
for line in res.text.strip().splitlines():
line = line.strip()
if not line or line[0] in '!#': continue
elif line[:2] == '@@':
unblock.add(line.split('^')[0].strip('@|^'))
elif line[:2] == '||' and ('/' not in line) and ('?' not in line) and \
(line[-1] == '^' or line.endswith("$all")):
blocked.add(line.strip('al').strip('|^$'))
for url in ABFWHITE:
url = raw2fastly(url)
try:
res = session.get(url)
except requests.exceptions.RequestException as e:
try:
print(f"{url} 下载失败:{e.args[0].reason}")
except Exception:
print(f"{url} 下载失败:无法解析的错误!")
traceback.print_exc()
continue
if res.status_code != 200:
print(url, res.status_code)
continue
for line in res.text.strip().splitlines():
line = line.strip()
if not line or line[0] == '!': continue
else: unblock.add(line.split('^')[0].strip('|^'))
domain_root = DomainTree()
domain_keys: Set[str] = set()
for domain in blocked:
if '/' in domain: continue
if '*' in domain:
domain = domain.strip('*')
if '*' not in domain:
domain_keys.add(domain)
continue
segs = domain.split('.')
if len(segs) == 4 and domain.replace('.','').isdigit(): # IP
for seg in segs: # '223.73.212.020' is not valid
if not seg: break
if seg[0] == '0' and seg != '0': break
else:
rules[f'IP-CIDR,{domain}/32'] = adblock_name
else:
domain_root.insert(domain)
for domain in unblock:
domain_root.remove(domain)
for domain in domain_keys:
rules[f'DOMAIN-KEYWORD,{domain}'] = adblock_name
for domain in domain_root.get():
for key in domain_keys:
if key in domain: break
else: rules[f'DOMAIN-SUFFIX,{domain}'] = adblock_name
print(f"共有 {len(rules)} 条规则")
def main():
global exc_queue, merged, FETCH_TIMEOUT, ABFURLS, AUTOURLS, AUTOFETCH
sources = open("sources.list", encoding="utf-8").read().strip().splitlines()
if DEBUG_NO_NODES:
# !!! JUST FOR DEBUGING !!!
print("!!! 警告:您已启用无节点调试,程序产生的配置不能被直接使用 !!!")
sources = []
if DEBUG_NO_DYNAMIC:
# !!! JUST FOR DEBUGING !!!
print("!!! 警告:您已选择不抓取动态节点 !!!")
AUTOURLS = AUTOFETCH = []
print("正在生成动态链接...")
for auto_fun in AUTOURLS:
print("正在生成 '"+auto_fun.__name__+"'... ", end='', flush=True)
try: url = auto_fun()
except requests.exceptions.RequestException: print("失败!")
except: print("错误:");traceback.print_exc()
else:
if url:
if isinstance(url, str):
sources.append(url)
elif isinstance(url, (list, tuple, set)):
sources.extend(url)
print("成功!")
else: print("跳过!")
print("正在整理链接...")
sources_final: Union[Set[str], List[str]] = set()
airports: Set[str] = set()
for source in sources:
if source == 'EOF': break
if not source: continue
if source[0] == '#': continue
sub = source
if sub[0] == '!':
if LOCAL: continue
sub = sub[1:]
if sub[0] == '*':
isairport = True
sub = sub[1:]
else: isairport = False
if sub[0] == '+':
tags = sub.split()
sub = tags.pop()
sub = ' '.join(tags) + ' ' +raw2fastly(sub)
else:
sub = raw2fastly(sub)
if isairport: airports.add(sub)
else: sources_final.add(sub)
if airports:
print("正在抓取机场列表...")
for sub in airports:
print("合并 '"+sub+"'... ", end='', flush=True)
try:
res = extract(sub)
except KeyboardInterrupt: