如何清理不规则字符串并将它们组织成右列中的数据帧

import re
import json

def clean_and_organize_string(input_string):
    # 正则表达式匹配
    pattern = r'\d+:\s+(\w+)\s+(\w+)\s+(\w+)\s+(\w+)'
    matches = re.findall(pattern, input_string)

    data_frame = []
    for match in matches:
        # 数据清洗和处理
        cleaned_data = [item.strip() for item in match]

        # 数据组织
        data_frame.append({
            'column1': cleaned_data[0],
            'column2': cleaned_data[1],
            'column3': cleaned_data[2],
            'column4': cleaned_data[3]
        })

    # 数据存储
    with open('data_frame.json', 'w') as file:
        json.dump(data_frame, file)

    return data_frame

# 示例输入字符串
input_string = '''
1:  data1  data2  data3  data4
2:  data5  data6  data7  data8
3:  data9  data10 data11 data12
'''

# 清理和组织数据
result = clean_and_organize_string(input_string)
print(result)