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

number_parser:add x-art support

Browse Source
This commit is contained in:
lededev
2021-07-16 13:23:29 +08:00
parent 8c5d85298e
commit 1c759e713e
1 changed files with 19 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
number_parser.py
View File

@@ -43,16 +43,9 @@ def get_number(debug,filepath: str) -> str:
lower_check = filename.lower() lower_check = filename.lower()
if 'fc2' in lower_check: if 'fc2' in lower_check:
filename = lower_check.replace('ppv', '').replace('--', '-').replace('_', '-').upper() filename = lower_check.replace('ppv', '').replace('--', '-').replace('_', '-').upper()
file_number = re.search(r'\w+(-|_)\w+', filename, re.A).group() if file_number := get_number_by_dict(lower_check):
if "tokyo" in lower_check and "hot" in lower_check:
file_number = re.search(r'(cz|gedo|k|n|red-|se)\d{2,4}', lower_check, re.A).group()
elif "carib" in lower_check:
file_number = str(re.search(r'\d{6}(-|_)\d{3}', lower_check, re.A).group()).replace('_', '-')
elif "1pon" in lower_check or "paco" in lower_check:
file_number = str(re.search(r'\d{6}(-|_)\d{3}', lower_check, re.A).group()).replace('-', '_')
elif "10mu" in lower_check:
file_number = str(re.search(r'\d{6}(-|_)\d{2}', lower_check, re.A).group()).replace('-', '_')
return file_number return file_number
return str(re.search(r'\w+(-|_)\w+', filename, re.A).group())
else: # 提取不含减号-的番号，FANZA CID else: # 提取不含减号-的番号，FANZA CID
# 欧美番号匹配规则 # 欧美番号匹配规则
oumei = re.search(r'[a-zA-Z]+\.\d{2}\.\d{2}\.\d{2}', filepath) oumei = re.search(r'[a-zA-Z]+\.\d{2}\.\d{2}\.\d{2}', filepath)
@@ -77,16 +70,9 @@ def get_number(debug,filepath: str) -> str:
lower_check = filename.lower() lower_check = filename.lower()
if 'fc2' in lower_check: if 'fc2' in lower_check:
filename = lower_check.replace('ppv', '').replace('--', '-').replace('_', '-').upper() filename = lower_check.replace('ppv', '').replace('--', '-').replace('_', '-').upper()
file_number = re.search(r'\w+(-|_)\w+', filename, re.A).group() if file_number := get_number_by_dict(lower_check):
if "tokyo" in lower_check and "hot" in lower_check:
file_number = re.search(r'(cz|gedo|k|n|red-|se)\d{2,4}', lower_check, re.A).group()
elif "carib" in lower_check:
file_number = str(re.search(r'\d{6}(-|_)\d{3}', lower_check, re.A).group()).replace('_', '-')
elif "1pon" in lower_check or "paco" in lower_check:
file_number = str(re.search(r'\d{6}(-|_)\d{3}', lower_check, re.A).group()).replace('-', '_')
elif "10mu" in lower_check:
file_number = str(re.search(r'\d{6}(-|_)\d{2}', lower_check, re.A).group()).replace('-', '_')
return file_number return file_number
return str(re.search(r'\w+(-|_)\w+', filename, re.A).group())
else: # 提取不含减号-的番号，FANZA CID else: # 提取不含减号-的番号，FANZA CID
# 欧美番号匹配规则 # 欧美番号匹配规则
oumei = re.search(r'[a-zA-Z]+\.\d{2}\.\d{2}\.\d{2}', filepath) oumei = re.search(r'[a-zA-Z]+\.\d{2}\.\d{2}\.\d{2}', filepath)
@@ -101,6 +87,19 @@ def get_number(debug,filepath: str) -> str:
except: except:
return re.search(r'(.+?)\.', filepath)[0] return re.search(r'(.+?)\.', filepath)[0]
G_TAKE_NUM_RULES = {
'tokyo' : lambda x:str(re.search(r'(cz|gedo|k|n|red-|se)\d{2,4}', x, re.A).group()),
'carib' : lambda x:str(re.search(r'\d{6}(-|_)\d{3}', x, re.A).group()).replace('_', '-'),
'1pon' : lambda x:str(re.search(r'\d{6}(-|_)\d{3}', x, re.A).group()).replace('-', '_'),
'10mu' : lambda x:str(re.search(r'\d{6}(-|_)\d{2}', lower_check, re.A).group()).replace('-', '_'),
'x-art' : lambda x:str(re.search(r'x-art\.\d{2}\.\d{2}\.\d{2}', x, re.A).group())
}
def get_number_by_dict(lower_filename: str) -> str:
for k,v in G_TAKE_NUM_RULES.items():
if k in lower_filename:
return v(lower_filename)
return None
# if __name__ == "__main__": # if __name__ == "__main__":
# import doctest # import doctest