使用REGEX从Python中的列中剥离一段文本字符串

import pandas as pd
import re

# 创建一个示例DataFrame
data = {
    'text_column': [
        'This is a sample text with extra info (remove this)',
        'Another example text (also remove this part)',
        'No extra info here'
    ]
}

df = pd.DataFrame(data)

# 定义一个函数，使用正则表达式剥离文本
def strip_text(text):
    # 假设你想剥离括号及其内容
    pattern = r'\([^)]*\)'
    return re.sub(pattern, '', text)

# 应用函数到DataFrame的列
df['stripped_text'] = df['text_column'].apply(strip_text)

print(df)

                              text_column            stripped_text
0  This is a sample text with extra info (remove this)  This is a sample text with extra info 
1      Another example text (also remove this part)      Another example text 
2                            No extra info here              No extra info here