正则将段落分割成句子

这里分割段落不区分中英文标点，你可以根据需求改

分割后标点跟随句子后面

def split_sentences_keep_delimiter(text):
    pattern = r'[^。!！?？:：;；,，]+[。!！?？:：;；，,]'
    sentences = re.findall(pattern, text)
    last_sentence = re.sub(r'[。!！?？:：;；;，,]', '', text)
    if last_sentence and not re.search(pattern, last_sentence):
        sentences.append(last_sentence.strip())
    return sentences[:len(sentences)-1]

分割后去掉标点只保留文本

import re

def split_text_with_punctuation(text):
    split_sentences = re.split(r'[。.！!？?：:；;，,]', text)
    return split_sentences

text = "你好，世界！这是个测试。看看是否有效？当然，它会的。"
print(split_text_with_punctuation(text))

分割后标点和文本分开

import re

def split_text_with_punctuation(text):
    split_sentences = re.split(r'([。.！!？?：:；;，,])', text)
    return split_sentences

text = "你好，世界！这是个测试。看看是否有效？当然，它会的。"
print(split_text_with_punctuation(text))