无码检测移入number_parser.py并扩充识别能力

ADC_function.py

@@ -566,17 +566,6 @@ f"https://{gsite}/translate_a/single?client=gtx&dt=t&dj=1&ie=UTF-8&sl=auto&tl={t
     return trans_result
 
 
-# ========================================================================是否为无码
-def is_uncensored(number):
-    if re.match('^\d{4,}', number) or re.match('n\d{4}', number) or 'HEYZO' in number.upper():
-        return True
-    configs = config.getInstance().get_uncensored()
-    prefix_list = str(configs).split(',')
-    for pre in prefix_list:
-        if pre.upper() in number.upper():
-            return True
-    return False
-
 # 从浏览器中导出网站登录验证信息的cookies，能够以会员方式打开游客无法访问到的页面
 # 示例: FC2-755670 url https://javdb9.com/v/vO8Mn
 # json 文件格式

config.ini

@@ -65,8 +65,7 @@ switch=0
 
 ; 用来确定是否是无码
 [uncensored]
-uncensored_prefix=S2M,BT,LAF,SMD
+uncensored_prefix=S2M,BT,LAF,SMD,SMBD,SM3D2DBD,SKY-,SKYHD,CWP,CWDV,CWBD,CW3D2DBD,MKD,MKBD,MXBD,MK3D2DBD,MCB3DBD,MCBD,RHJ,RED
-
 
 [media]
 ; 影片后缀

core.py

@@ -12,7 +12,7 @@ from datetime import datetime
 
 from ADC_function import *
 from WebCrawler import get_data_from_json
-
+from number_parser import is_uncensored
 
 def escape_path(path, escape_literals: str):  # Remove escape literals
     backslash = '\\'

number_parser.py

@@ -1,6 +1,7 @@
 import os
 import re
 import sys
+import config
 
 G_spat = re.compile(
     "^22-sht\.me|-fhd|_fhd|^fhd_|^fhd-|-hd|_hd|^hd_|^hd-|-sd|_sd|-1080p|_1080p|-720p|_720p|^hhd800\.com@",
@@ -82,6 +83,37 @@ def get_number_by_dict(filename: str) -> str:
         pass
     return None
 
+class Cache_uncensored_conf:
+    prefix = None
+    def is_empty(self):
+        return bool(self.prefix is None)
+    def set(self, v: list):
+        if not v or not len(v) or not len(v[0]):
+            raise ValueError('input prefix list empty or None')
+        s = v[0]
+        if len(v) > 1:
+            for i in v[1:]:
+                s += f"|{i}.+"
+        self.prefix = re.compile(s, re.I)
+    def check(self, number):
+        if self.prefix is None:
+            raise ValueError('No init re compile')
+        return self.prefix.match(number)
+
+G_cache_uncensored_conf = Cache_uncensored_conf()
+
+# ========================================================================是否为无码
+def is_uncensored(number):
+    if re.match(
+r'[\d-]{4,}|\d{6}_\d{2,3}|(cz|gedo|k|n|red-|se)\d{2,4}|heyzo.+|xxx-av-.+|heydouga-.+|x-art\.\d{2}\.\d{2}\.\d{2}',
+        number,
+        re.I
+    ):
+        return True
+    if G_cache_uncensored_conf.is_empty():
+        G_cache_uncensored_conf.set(config.getInstance().get_uncensored().split(','))
+    return G_cache_uncensored_conf.check(number)
+
 if __name__ == "__main__":
 #     import doctest
 #     doctest.testmod(raise_on_error=True)
@@ -164,7 +196,7 @@ if __name__ == "__main__":
         try:
             n = get_number(True, filename)
             if n:
-                print(f'  [{n}] # {filename}')
+                print('  [{0}] {2}# {1}'.format(n, filename, '#无码' if is_uncensored(n) else ''))
             else:
                 print(f'[-]Number return None. # {filename}')
         except Exception as e: