string = 'i am a chinese boy,but she is a japanese girl,she is russia girl.please tell me that how do i choice?' \
'and can we happyniess?can we happyniess?'
# 1.直接替换不需要的符号,在使用精灵函数切割
print(string.replace(',', ' ').replace('?', ' ').replace('.', ' ').split())
# 2.依次查找函数中不需要的符号,与列表对比后替换,在使用精灵函数切割
def st(text, list):
for i in list:
text = text.replace(i, '')
print(text.split())
st(string, [',', '?', '.'])
结果:
['i', 'am', 'a', 'chinese', 'boybut', 'she', 'is', 'a', 'japanese', 'girlshe', 'is', 'russia', 'girlplease', 'tell', 'me', 'that', 'how', 'do', 'i', 'choiceand', 'can', 'we', 'happyniesscan', 'we', 'happyniess']