Python:如何从文本中获取首选潜文本？

import re
from collections import Counter

def get_preferred_subtext(text):
    # 使用正则表达式匹配所有子串
    subtexts = re.findall(r'\b\w+\b', text.lower())
    
    # 使用Counter统计每个子串的出现次数
    counter = Counter(subtexts)
    
    # 获取出现次数最高的子串
    preferred_subtext = counter.most_common(1)[0][0]
    
    return preferred_subtext

# 示例文本
text = "Python is a popular programming language. It is widely used for web development, data analysis, and machine learning."

preferred_subtext = get_preferred_subtext(text)
print("首选潜文本:", preferred_subtext)

首选潜文本: python