查找文本列表中的第 n 个字符

Question

    import re

    text = "~SR1*abcde*1234*~end~SR*abcdef*123*~end~SR11*abc*12345*~end"

I have a text that is repetitive in nature. It starts with '~SR' and ends with 'end'. i want to find the index of the 1st, 2nd, and 3rd ' * ' (asterisk) from each repetition.

    def start_point(p1):
        segment_start_array = []
        for match in re.finditer(p1, text):
            index = match.start()
            segment_start_array.append(index)
        return segment_start_array


    def point_a(p1):
        a = start_point(p1)
        return a


    def point_b(p2):
        b = start_point(p2)
        return b


    def get_var_section(p1, p2):
        var_list = []
        for each in range(len(start_point(p1))):
            list = text[point_a(p1)[each]:point_b(p2)[each]]
            var_list.append(list)
        return var_list


    print(get_var_section('~SR', '~end'))

==> Result: ['~SR1*finda*1234*', '~SR*Findab*123*', '~SR11*findabc*12345*']

What i did first is put the repetitions into a list, which resulted into three elements. By doing this I thought it would make it easier to find the position of each asterisk, but when i tried to find the index of the 1st and 2nd asterisk the result were the same.

    def test(p1, p2, occurrence):
        var_list4 = []
        for i in get_var_section(p1, p2):
            x = i.find('*', occurrence)
            var_list4.append(x)
        return var_list4


    print(test('~SR', '~end', 1))
    print(test('~SR', '~end', 2))

==> Result: [4, 3, 5]
==> Result: [4, 3, 5]
I don't understand why the result didn't change after i changed to find the position of the 2nd occurrence.

Answer 1

As you mentioned that the string starts and ends with (~SR1, ~end) , I split the string with ~end and then used item to loop through the list to find indexes in the item .

import re

text = "~SR1*abcde*1234*~end~SR*abcdef*123*~end~SR11*abc*12345*~end"
text_list = text.split('~end')
index = []
for item in text_list:
    #print(item)
    if len(item) > 0:
        ind = [i for i, val in enumerate(item) if val == '*']
        #print(ind)
        index.append(ind)
index_new = np.array(index).T.tolist() #transpose of list of lists

Result

print("index") 

[[4, 10, 15], [3, 10, 14], [5, 9, 15]]

print("index_new") 

[[4, 3, 5], [10, 10, 9], [15, 14, 15]]