python jieba中文文本切割成句子

# -*- coding: utf-8 -*-
# @Time    : 2024/6/18 10:26
# @Author  : Cocktail_py
import jieba.posseg as pseg


def cut_sentences(text):
    """中文句子分割"""
    # 使用jieba的分句模块
    sentences = pseg.cut(text)
    result = []
    tmp = []
    for word, flag in sentences:
        if word in ['。','!','?'] and flag == 'x':  # 'x'表示单独一个句子
            tmp.append(word)
            if tmp:
                result.append(''.join(tmp))
                tmp = []
        else:
            tmp.append(word)
    if tmp:
        result.append(''.join(tmp))
    return result


text = "你好，我是小明。我今年18岁了。"
print(cut_sentences(text))

当遇到以下异常时降低jieba版本，改为jieba==0.40即可

TypeError: __repr__ returned non-string (type bytes)