正则表达式从dataframe中的一列中提取和拆分文本

import re
import pandas as pd

df = pd.DataFrame({'text': ['hello world', 'foo bar', 'spam eggs']})

# 提取单词
df['words'] = df['text'].apply(lambda x: re.findall(r'\w+', x))

# 拆分字符串
df['split'] = df['text'].apply(lambda x: re.split(r'\s', x))

          text          words            split
0  hello world  [hello, world]  [hello, world]
1      foo bar      [foo, bar]      [foo, bar]
2    spam eggs    [spam, eggs]    [spam, eggs]