自定义函数集合

#分词
rls = ['？','！','“','”','：','…','（','）',
      '—','《','》','、','‘','’','"','\n','.',
       '；','#','【','】','\'',':','(','」','∠','+',',',
       '!','|',
      ]
def cut_words(x):
    x = str(x).strip()
    for c in rls:
        x = x.replace(c,' ')
    x = ' '.join(x.split())
    s = ' '.join(jieba.cut(x,cut_all=True))
    s = ' '.join(s.split())
    return s

#分字
def cut_chars(x):
    x = str(x).replace(' ','')
    y = [i for i in x]
    y = ' '.join(y)
    return y

转载于:https://www.cnblogs.com/ylHe/p/10109630.html