144 lines
4.2 KiB
Python
144 lines
4.2 KiB
Python
import argparse
|
|
import pathlib
|
|
import pandas
|
|
import wx
|
|
|
|
parser = argparse.ArgumentParser(description="邮件列表切片脚本")
|
|
parser.add_argument('--column-pays', type=str, nargs='?', default='国家地区')
|
|
parser.add_argument('--column-code', type=str, nargs='?', default='客户编号')
|
|
parser.add_argument('-d', '--outdir', type=str, nargs='?')
|
|
parser.add_argument('-s', '--size', type=int, nargs='?', default=1000)
|
|
|
|
args = parser.parse_args()
|
|
|
|
mappings = [
|
|
{
|
|
"locale": "fr",
|
|
"predicate": lambda it: it in ['法国', 'FR', '比利时', 'BE']
|
|
},
|
|
{
|
|
"locale": "de",
|
|
"predicate": lambda it: it in ['德国', 'DE', '奥地利', 'AT', '瑞士', 'CH']
|
|
},
|
|
{
|
|
"locale": "it",
|
|
"predicate": lambda it: it in ['意大利', 'IT']
|
|
},
|
|
{
|
|
"locale": "es",
|
|
"predicate": lambda it: it in ['西班牙', 'ES']
|
|
},
|
|
{
|
|
"locale": "pt",
|
|
"predicate": lambda it: it in ['葡萄牙', 'PT']
|
|
},
|
|
{
|
|
"locale": "en",
|
|
"predicate": lambda it: bool(it)
|
|
},
|
|
{
|
|
"locale": "un",
|
|
"predicate": lambda it: True
|
|
},
|
|
]
|
|
|
|
def main():
|
|
try:
|
|
print('[信息] 请选择数据源')
|
|
app = wx.App(None)
|
|
dialog = wx.FileDialog(None, 'Open', wildcard='*.xlsx', style=wx.FD_OPEN|wx.FD_FILE_MUST_EXIST)
|
|
|
|
if dialog.ShowModal() == wx.ID_OK:
|
|
filepath = dialog.GetPath()
|
|
else:
|
|
print('[警告] 操作取消')
|
|
return 0
|
|
dialog.Destroy()
|
|
|
|
if args.outdir is None:
|
|
print('[信息] 请选择保存位置')
|
|
dialog = wx.DirDialog(None, 'Save to', style=wx.DD_DIR_MUST_EXIST)
|
|
|
|
if dialog.ShowModal() == wx.ID_OK:
|
|
args.outdir = dialog.GetPath()
|
|
else:
|
|
print('[警告] 操作取消')
|
|
return 0
|
|
dialog.Destroy()
|
|
|
|
print(f'[信息] 正在读取数据：{filepath}')
|
|
sheets = pandas.read_excel(filepath, sheet_name=None)
|
|
names = sheets.keys()
|
|
|
|
parts = pathlib.Path(filepath)
|
|
prefix = parts.stem
|
|
except Exception as e:
|
|
print(f'[警告] 读取数据表失败：{e}')
|
|
return 1
|
|
|
|
if (length := len(sheets)) > 1:
|
|
print(f'[信息] 已读取以下 ({length}) 工作表：', end='\n\n')
|
|
for name in names: print(f'\t{name}')
|
|
|
|
while True:
|
|
if (key := input('\n[????] 请输入工作表名称：')) in names:
|
|
sheet = sheets.get(key)
|
|
break
|
|
else:
|
|
print(f'[警告] 名称无效，请重试')
|
|
else:
|
|
print(f'[信息] 已读取工作表：{names[0]}')
|
|
sheet = sheets.get(names[0])
|
|
|
|
data = sheet.to_dict(orient='records')
|
|
primary = {}
|
|
secondary = {}
|
|
|
|
for record in data:
|
|
pays = record.get(args.column_pays)
|
|
|
|
for rule in mappings:
|
|
locale = rule.get('locale')
|
|
predicate = rule.get('predicate')
|
|
|
|
if predicate(pays):
|
|
group: list = primary.setdefault(locale, [])
|
|
group.append(record)
|
|
break
|
|
|
|
for key, group in primary.items():
|
|
factor = 1
|
|
offset = 0
|
|
cursor = 0
|
|
|
|
while (limit := args.size * factor + offset) and (slice := group[cursor:limit]):
|
|
last: dict = slice[-1:][0]
|
|
next: dict = group[limit] if len(group) > limit else None
|
|
|
|
if next is not None and (c1 := last.get(args.column_code)) and (c2 := next.get(args.column_code)) and c1 == c2:
|
|
offset += 1
|
|
continue
|
|
|
|
name = '.'.join([key, str(factor)])
|
|
secondary.setdefault(name, slice)
|
|
factor += 1
|
|
cursor = limit
|
|
offset = 0
|
|
|
|
for key, group in secondary.items():
|
|
try:
|
|
filepath = f'{args.outdir}/{prefix}.{key}.xlsx'
|
|
df = pandas.DataFrame.from_records(group)
|
|
|
|
print(f'[信息] 正在写入文件：{filepath}')
|
|
df.to_excel(filepath, index=False, sheet_name='Sheet1')
|
|
except Exception as e:
|
|
print(f'[警告] 写入文件时发生了错误：{e}')
|
|
continue
|
|
|
|
return 0
|
|
|
|
try: status = main()
|
|
except KeyboardInterrupt: status = 144
|
|
exit(status)
|