bacow/AV_Data_Capture
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

PEP8 PREFIX, AND SOME TYPING ANNOTATION

Browse Source
This commit is contained in:
FatalFurY
2022-02-18 00:01:21 +08:00
parent 123a2a0c73
commit c1568cd64a
2 changed files with 156 additions and 118 deletions
Download Patch File Download Diff File Expand all files Collapse all files

121
number_parser.py
View File

@@ -2,36 +2,37 @@ import os
import re
import sys
import config
import typing
G_spat = re.compile(
"^22-sht\.me|-fhd|_fhd|^fhd_|^fhd-|-hd|_hd|^hd_|^hd-|-sd|_sd|-1080p|_1080p|-720p|_720p|^hhd800\.com@|-uncensored|_uncensored|-leak|_leak",
re.IGNORECASE)
def get_number(debug,file_path: str) -> str:
# """
# >>> from number_parser import get_number
# >>> get_number("/Users/Guest/AV_Data_Capture/snis-829.mp4")
# 'snis-829'
# >>> get_number("/Users/Guest/AV_Data_Capture/snis-829-C.mp4")
# 'snis-829'
# >>> get_number("C:¥Users¥Guest¥snis-829.mp4")
# 'snis-829'
# >>> get_number("C:¥Users¥Guest¥snis-829-C.mp4")
# 'snis-829'
# >>> get_number("./snis-829.mp4")
# 'snis-829'
# >>> get_number("./snis-829-C.mp4")
# 'snis-829'
# >>> get_number(".¥snis-829.mp4")
# 'snis-829'
# >>> get_number(".¥snis-829-C.mp4")
# 'snis-829'
# >>> get_number("snis-829.mp4")
# 'snis-829'
# >>> get_number("snis-829-C.mp4")
# 'snis-829'
# """
def get_number(debug: bool, file_path: str) -> str:
"""
从文件路径中提取番号 from number_parser import get_number
>>> get_number(False, "/Users/Guest/AV_Data_Capture/snis-829.mp4")
'snis-829'
>>> get_number(False, "/Users/Guest/AV_Data_Capture/snis-829-C.mp4")
'snis-829'
>>> get_number(False, "C:¥Users¥Guest¥snis-829.mp4")
'snis-829'
>>> get_number(False, "C:¥Users¥Guest¥snis-829-C.mp4")
'snis-829'
>>> get_number(False, "./snis-829.mp4")
'snis-829'
>>> get_number(False, "./snis-829-C.mp4")
'snis-829'
>>> get_number(False, ".¥snis-829.mp4")
'snis-829'
>>> get_number(False, ".¥snis-829-C.mp4")
'snis-829'
>>> get_number(False, "snis-829.mp4")
'snis-829'
>>> get_number(False, "snis-829-C.mp4")
'snis-829'
"""
filepath = os.path.basename(file_path)
# debug True 和 False 两块代码块合并，原因是此模块及函数只涉及字符串计算，没有IO操作，debug on时输出导致异常信息即可
try:
@@ -56,7 +57,7 @@ def get_number(debug,file_path: str) -> str:
try:
return str(
re.findall(r'(.+?)\.',
str(re.search('([^<>/\\\\|:""\\*\\?]+)\\.\\w+$', filepath).group()))).strip(
str(re.search('([^<>/\\\\|:""\\*\\?]+)\\.\\w+$', filepath).group()))).strip(
"['']").replace('_', '-')
except:
return str(re.search(r'(.+?)\.', filepath)[0])
@@ -68,29 +69,33 @@ def get_number(debug,file_path: str) -> str:
# 按javdb数据源的命名规范提取number
G_TAKE_NUM_RULES = {
'tokyo.*hot' : lambda x:str(re.search(r'(cz|gedo|k|n|red-|se)\d{2,4}', x, re.I).group()),
'carib' : lambda x:str(re.search(r'\d{6}(-|_)\d{3}', x, re.I).group()).replace('_', '-'),
'1pon|mura|paco' : lambda x:str(re.search(r'\d{6}(-|_)\d{3}', x, re.I).group()).replace('-', '_'),
'10mu' : lambda x:str(re.search(r'\d{6}(-|_)\d{2}', x, re.I).group()).replace('-', '_'),
'x-art' : lambda x:str(re.search(r'x-art\.\d{2}\.\d{2}\.\d{2}', x, re.I).group()),
'xxx-av': lambda x:''.join(['xxx-av-', re.findall(r'xxx-av[^\d]*(\d{3,5})[^\d]*', x, re.I)[0]]),
'heydouga': lambda x:'heydouga-' + '-'.join(re.findall(r'(\d{4})[\-_](\d{3,4})[^\d]*', x, re.I)[0]),
'heyzo' : lambda x: 'HEYZO-' + re.findall(r'heyzo[^\d]*(\d{4})', x, re.I)[0]
'tokyo.*hot': lambda x: str(re.search(r'(cz|gedo|k|n|red-|se)\d{2,4}', x, re.I).group()),
'carib': lambda x: str(re.search(r'\d{6}(-|_)\d{3}', x, re.I).group()).replace('_', '-'),
'1pon|mura|paco': lambda x: str(re.search(r'\d{6}(-|_)\d{3}', x, re.I).group()).replace('-', '_'),
'10mu': lambda x: str(re.search(r'\d{6}(-|_)\d{2}', x, re.I).group()).replace('-', '_'),
'x-art': lambda x: str(re.search(r'x-art\.\d{2}\.\d{2}\.\d{2}', x, re.I).group()),
'xxx-av': lambda x: ''.join(['xxx-av-', re.findall(r'xxx-av[^\d]*(\d{3,5})[^\d]*', x, re.I)[0]]),
'heydouga': lambda x: 'heydouga-' + '-'.join(re.findall(r'(\d{4})[\-_](\d{3,4})[^\d]*', x, re.I)[0]),
'heyzo': lambda x: 'HEYZO-' + re.findall(r'heyzo[^\d]*(\d{4})', x, re.I)[0]
}
def get_number_by_dict(filename: str) -> str:
def get_number_by_dict(filename: str) -> typing.Optional[str]:
try:
for k,v in G_TAKE_NUM_RULES.items():
for k, v in G_TAKE_NUM_RULES.items():
if re.search(k, filename, re.I):
return v(filename)
except:
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')
@@ -99,28 +104,32 @@ class Cache_uncensored_conf:
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
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)
# import doctest
# doctest.testmod(raise_on_error=True)
test_use_cases = (
"MEYD-594-C.mp4",
"SSIS-001_C.mp4",
@@ -131,26 +140,30 @@ if __name__ == "__main__":
"SDDE-625_uncensored_C.mp4",
"SDDE-625_uncensored_leak_C.mp4",
"SDDE-625_uncensored_leak_C_cd1.mp4",
"Tokyo Hot n9001 FHD.mp4", # 无-号，以前无法正确提取
"Tokyo Hot n9001 FHD.mp4", # 无-号，以前无法正确提取
"TokyoHot-n1287-HD SP2006 .mp4",
"caribean-020317_001.nfo", # -号误命名为_号的
"caribean-020317_001.nfo", # -号误命名为_号的
"257138_3xplanet_1Pondo_080521_001.mp4",
"ADV-R0624-CD3.wmv", # 多碟影片
"XXX-AV 22061-CD5.iso", # 新支持片商格式 xxx-av-22061 命名规则来自javdb数据源
"ADV-R0624-CD3.wmv", # 多碟影片
"XXX-AV 22061-CD5.iso", # 新支持片商格式 xxx-av-22061 命名规则来自javdb数据源
"xxx-av 20589.mp4",
"Muramura-102114_145-HD.wmv", # 新支持片商格式 102114_145 命名规则来自javdb数据源
"heydouga-4102-023-CD2.iso", # 新支持片商格式 heydouga-4102-023 命名规则来自javdb数据源
"HeyDOuGa4236-1048 Ai Qiu - .mp4", # heydouga-4236-1048 命名规则来自javdb数据源
"pacopacomama-093021_539-FHD.mkv", # 新支持片商格式 093021_539 命名规则来自javdb数据源
"heydouga-4102-023-CD2.iso", # 新支持片商格式 heydouga-4102-023 命名规则来自javdb数据源
"HeyDOuGa4236-1048 Ai Qiu - .mp4", # heydouga-4236-1048 命名规则来自javdb数据源
"pacopacomama-093021_539-FHD.mkv", # 新支持片商格式 093021_539 命名规则来自javdb数据源
"sbw99.cc@heyzo_hd_2636_full.mp4"
)
def evprint(evstr):
code = compile(evstr, "<string>", "eval")
print("{1:>20} # '{0}'".format(evstr[18:-2], eval(code)))
for t in test_use_cases:
evprint(f'get_number(True, "{t}")')
if len(sys.argv)<=1 or not re.search('^[A-Z]:?', sys.argv[1], re.IGNORECASE):
if len(sys.argv) <= 1 or not re.search('^[A-Z]:?', sys.argv[1], re.IGNORECASE):
sys.exit(0)
# 使用Everything的ES命令行工具搜集全盘视频文件名作为用例测试number数据，参数为盘符 A .. Z 或带盘符路径
@@ -169,6 +182,7 @@ if __name__ == "__main__":
# 示例：
# python3 ./number_parser.py ALL
import subprocess
ES_search_path = "ALL disks"
if sys.argv[1] == "ALL":
if sys.platform == "win32":
@@ -176,18 +190,19 @@ if __name__ == "__main__":
ES_prog_path = 'es.exe' # es.exe需要放在PATH环境变量的路径之内
ES_cmdline = f'{ES_prog_path} -name size:gigantic ext:mp4;avi;rmvb;wmv;mov;mkv;flv;ts;webm;iso;mpg;m4v'
out_bytes = subprocess.check_output(ES_cmdline.split(' '))
out_text = out_bytes.decode('gb18030') # 中文版windows 10 x64默认输出GB18030，此编码为UNICODE方言与UTF-8系全射关系无转码损失
out_text = out_bytes.decode('gb18030') # 中文版windows 10 x64默认输出GB18030，此编码为UNICODE方言与UTF-8系全射关系无转码损失
out_list = out_text.splitlines()
elif sys.platform in ("linux", "darwin"):
ES_prog_path = 'locate' if sys.platform == 'linux' else 'glocate'
ES_cmdline = r"{} -b -i --regex '\.mp4$|\.avi$|\.rmvb$|\.wmv$|\.mov$|\.mkv$|\.webm$|\.iso$|\.mpg$|\.m4v$'".format(ES_prog_path)
ES_cmdline = r"{} -b -i --regex '\.mp4$|\.avi$|\.rmvb$|\.wmv$|\.mov$|\.mkv$|\.webm$|\.iso$|\.mpg$|\.m4v$'".format(
ES_prog_path)
out_bytes = subprocess.check_output(ES_cmdline.split(' '))
out_text = out_bytes.decode('utf-8')
out_list = [ os.path.basename(line) for line in out_text.splitlines()]
out_list = [os.path.basename(line) for line in out_text.splitlines()]
else:
print('[-]Unsupported platform! Please run on OS Windows/Linux/MacOSX. Exit.')
sys.exit(1)
else: # Windows single disk
else: # Windows single disk
if sys.platform != "win32":
print('[!]Usage: python3 ./number_parser.py ALL')
sys.exit(0)
@@ -202,7 +217,7 @@ if __name__ == "__main__":
ES_search_path = os.path.normcase(ES_search_path)
ES_cmdline = f'{ES_prog_path} -path {ES_search_path} -name size:gigantic ext:mp4;avi;rmvb;wmv;mov;mkv;webm;iso;mpg;m4v'
out_bytes = subprocess.check_output(ES_cmdline.split(' '))
out_text = out_bytes.decode('gb18030') # 中文版windows 10 x64默认输出GB18030，此编码为UNICODE方言与UTF-8系全射关系无转码损失
out_text = out_bytes.decode('gb18030') # 中文版windows 10 x64默认输出GB18030，此编码为UNICODE方言与UTF-8系全射关系无转码损失
out_list = out_text.splitlines()
print(f'\n[!]{ES_prog_path} is searching {ES_search_path} for movies as number parser test cases...')
print(f'[+]Find {len(out_list)} Movies.')