jieba 分词

尾号为1,2,3的同学做，西游记相关的分词，出现次数最高的20个。

import jieba


#
# wb = openpyxl.load_workbook('学生.xlsx')
# ws = wb.active
# for col in ws['a1':'f2']:
#     for c in col:
#         print(c.value,end='\t')
#     print()

f = open('4447.txt', mode='r',encoding='GB18030')
txt = f.read()
txt = jieba.lcut(txt)
for ch in '，。：；！？“’”【】（）|《》、{}\n':
    if ch in txt:
        for i in range(len(ch)):
            txt.remove(ch)

buyao = ['。','，','：','“','”','？','、','《','》','！','!','\n']

count = {}
for ch in txt:
    if ch not in buyao:
        count[ch] = count.get(ch, 0)+1
items = list(count.items())
items.sort(key=lambda x: x[1], reverse=True)

for i in range(1000):
    rw, gs=items[i]
    print("{0:5} {1:5}".format(rw, gs))