正则的实验应用

"""
有一个长文本，需要解析成特定的数据格式

解析后的格式为：
{
'name': 'Variopartner SICAV',
'lei': '529900LPCSV88817QH61',
'sub_fund': [{
'title': 'TARENO GLOBAL WATER SOLUTIONS FUND',
'isin': ['LU2001709034', 'LU2057889995', 'LU2001709547']
}, {
'title': 'TARENO FIXED INCOME FUND',
'isin': ['LU1299722972']
}, {
'title': 'TARENO GLOBAL EQUITY FUND',
'isin': ['LU1299721909', 'LU1299722113', 'LU1299722030']
}, {
'title': 'MIV GLOBAL MEDTECH FUND',
'isin': ['LU0329630999', 'LU0329630130']
}]
}
注意sub_fund数组的个数不是固定为4，并且isin个数不固定，需要写成通用逻辑，以适应最多100个sub_fund。
"""

long_text = """
Variopartner SICAV
529900LPCSV88817QH61

1. TARENO GLOBAL WATER SOLUTIONS FUND
   LU2001709034
   LU2057889995
   LU2001709547
2. TARENO FIXED INCOME FUND
   LU1299722972
3. TARENO GLOBAL EQUITY FUND
   LU1299721909
   LU1299722113
   LU1299722030
4. MIV GLOBAL MEDTECH FUND
   LU0329630999
   LU0329630130
5. TARENO GLOBAL EQUITY FUND
   LU0329630999
   LU0329630130
   LU0329630999
   LU0329630130
   """
   dicts = {}
   lists = []
   result = re.split('\d. ',long_text)
   print(result)
   data1 = result[0].split('\n')
   print(data1)
   dicts['name'] = data1[1]
   dicts['lei'] = data1[2]
   print(dicts)

data2 = result[1:]
for i in data2:
ii = i.split('\n')
lists.append({
'title': ii[0],
'isin': ii[1:-1]
})

dicts['sub_fund'] = lists
print(dicts)