不同行中变量名称的提取

Question

我正在从文本中提取一些具有自己的函数的变量名。下面你可以看到代码和文本。

   import re
    
    text = '''
    
    def function_cal_new1 (revenues_stories_new1, surplus_margin_new1, meadian_profit):
         median_profit= revenues_stories_new1* surplus_margin_new1
         return median_profit   
    
    def cal_tti_c_a(e_BusinessPropertyRightsSuccessor_c,e_Premium_c,e_Interests_c,e_OtherIncome_c,e_PassivelIncome_c,e_SubSubLease_c,estimation_base_BusinessPropertyRights_c,estimation_base_SubLease_c,estimation_base_SubLeaseBusiness_c,estimation_base_SolidWaste_c,estimation_base_Premium_c,estimation_base_PassiveGainsSaleSharePassive_c,estimation_base_PassiveGainsRealEstateThreeYear_c,estimation_base_PassiveGainssaleOtherMovableAssets_c,estimation_base_PassiveGainsSellsRealEstateFiveYear_c,tti_b_a):
        tti_b_a=e_BusinessPropertyRightsSuccessor_c+e_Premium_c+e_Interests_c+e_OtherIncome_c+e_PassivelIncome_c+e_SubSubLease_c+estimation_base_BusinessPropertyRights_c+estimation_base_SubLease_c+estimation_base_SubLeaseBusiness_c+estimation_base_SolidWaste_c+estimation_base_Premium_c+estimation_base_PassiveGainsSaleSharePassive_c+estimation_base_PassiveGainsRealEstateThreeYear_c+estimation_base_PassiveGainssaleOtherMovableAssets_c+estimation_base_PassiveGainsSellsRealEstateFiveYear_c   
        return(tti_b_a)
    
    '''
    
    # Extracting text
    def extraction_variables(text):
        splited_table1, splited_table2 = dict(), dict()
        lines = text.split('\n')
        for line in lines:
            x = re.search(r"^def.*:$", line)
            if x is not None:
                values = x[0].split('def ')[1].split('(')
                splited_table1 = values[0]
                splited_table2 = values[1][:-2].split(', ') # <--- Probably error is here
                yield splited_table1, splited_table2
    
    # Merging extracted text 
    splited_table1, splited_table2 = zip(*extraction_variables(text))
    table = []
    for elem in splited_table1:
        table.append(elem)
    for sub_array in splited_table2:
        for elem in sub_array:
            table.append(elem)
    
    # Converting in list
    final_table = list(table)
    final_table

在执行这些代码行之后，您可以看到下面的结果

['function_cal_new1 ',
 'cal_tti_c_a',
 'revenues_stories_new1',
 'surplus_margin_new1',
 'meadian_profit',
'e_BusinessPropertyRightsSuccessor_c,e_Premium_c,e_Interests_c,e_OtherIncome_c,e_PassivelIncome_c,e_SubSubLease_c,estimation_base_BusinessPropertyRights_c,estimation_base_SubLease_c,estimation_base_SubLeaseBusiness_c,estimation_base_SolidWaste_c,estimation_base_Premium_c,estimation_base_PassiveGainsSaleSharePassive_c,estimation_base_PassiveGainsRealEstateThreeYear_c,estimation_base_PassiveGainssaleOtherMovableAssets_c,estimation_base_PassiveGainsSellsRealEstateFiveYear_c,tti_b_a']

也就是说，从function_cal_new1提取文本中的meadian_profit单词是正确的，但是在这一行之后，单词不会在单独的行中提取。

那么，谁能帮我解决这个问题，并在不同的行中提取这些单词呢？最后，我需要有这个输出

'function_cal_new1 ',
'cal_tti_c_a',
'revenues_stories_new1',
'surplus_margin_new1',
'meadian_profit',
'e_BusinessPropertyRightsSuccessor_c,
'e_Premium_c',
'e_Interests_c',
'e_OtherIncome_c',
'e_PassivelIncome_c',
'e_SubSubLease_c',
'estimation_base_BusinessPropertyRights_c'.
'estimation_base_SubLease_c'.
'estimation_base_SubLeaseBusiness_c',
'estimation_base_SolidWaste_c',
'estimation_base_Premium_c',
'estimation_base_PassiveGainsSaleSharePassive_c',
'estimation_base_PassiveGainsRealEstateThreeYear_c',
'estimation_base_PassiveGainssaleOtherMovableAssets_c',
'estimation_base_PassiveGainsSellsRealEstateFiveYear_c',
'tti_b_a'

Answer 1

您可以使用ast模块遍历代码并提取您想要的部分。这可能比使用正则表达式更健壮。代码必须是有效的，包括缩进。字符串中的代码将需要删除额外的缩进。在这种情况下，这里有一些代码可以遍历树并产生不同的位。

text = '''
    
def function_cal_new1 (revenues_stories_new1, surplus_margin_new1, meadian_profit):
     median_profit= revenues_stories_new1* surplus_margin_new1
     return median_profit   

def cal_tti_c_a(e_BusinessPropertyRightsSuccessor_c,e_Premium_c,e_Interests_c,e_OtherIncome_c,e_PassivelIncome_c,e_SubSubLease_c,estimation_base_BusinessPropertyRights_c,estimation_base_SubLease_c,estimation_base_SubLeaseBusiness_c,estimation_base_SolidWaste_c,estimation_base_Premium_c,estimation_base_PassiveGainsSaleSharePassive_c,estimation_base_PassiveGainsRealEstateThreeYear_c,estimation_base_PassiveGainssaleOtherMovableAssets_c,estimation_base_PassiveGainsSellsRealEstateFiveYear_c,tti_b_a):
    tti_b_a=e_BusinessPropertyRightsSuccessor_c+e_Premium_c+e_Interests_c+e_OtherIncome_c+e_PassivelIncome_c+e_SubSubLease_c+estimation_base_BusinessPropertyRights_c+estimation_base_SubLease_c+estimation_base_SubLeaseBusiness_c+estimation_base_SolidWaste_c+estimation_base_Premium_c+estimation_base_PassiveGainsSaleSharePassive_c+estimation_base_PassiveGainsRealEstateThreeYear_c+estimation_base_PassiveGainssaleOtherMovableAssets_c+estimation_base_PassiveGainsSellsRealEstateFiveYear_c   
    return(tti_b_a)
    
    '''

import ast

def get_names_and_functions(text):
    root = ast.parse(text)
    for node in ast.walk(root):
        if isinstance(node, ast.FunctionDef):
            yield node.name
            for arg in node.args.args:
                yield arg.arg
        elif isinstance(node, ast.Name):
            yield node.id

found = set(get_names_and_functions(text))

这将给你：

{'cal_tti_c_a',
 'e_BusinessPropertyRightsSuccessor_c',
 'e_Interests_c',
 'e_OtherIncome_c',
 'e_PassivelIncome_c',
 'e_Premium_c',
 'e_SubSubLease_c',
 'estimation_base_BusinessPropertyRights_c',
 'estimation_base_PassiveGainsRealEstateThreeYear_c',
 'estimation_base_PassiveGainsSaleSharePassive_c',
 'estimation_base_PassiveGainsSellsRealEstateFiveYear_c',
 'estimation_base_PassiveGainssaleOtherMovableAssets_c',
 'estimation_base_Premium_c',
 'estimation_base_SolidWaste_c',
 'estimation_base_SubLeaseBusiness_c',
 'estimation_base_SubLease_c',
 'function_cal_new1',
 'meadian_profit',
 'median_profit',
 'revenues_stories_new1',
 'surplus_margin_new1',
 'tti_b_a'}

当考虑函数体中的参数和变量时，它使用一个集合来消除dupes。当然，如果您不想考虑参数，可以删除带有args的elif。