43523 发表于 2016-6-21 09:50:25

python 统计单词个数---从文件读取版本---不去重

#/usr//bin/envpytnon
#coding:utf-8

import re

'''
words = 'hello worda@r3143#####   ##$dfabpple# apple##%#$3423421apple \
       apple323423 432422324##apple@@#@@@@@$$!!#!#'
'''

#编译生成正则表达式对象
regexp = re.compile(r'{2,}')

#with open('./aa.txt')as f:
f = open('./aa.txt')
line = f.readlines()
print len(line)

j = 0
sum = 0
for i in range(len(line)):
   j = len(regexp.findall(line))
   sum = sum + j
print sum


页: [1]
查看完整版本: python 统计单词个数---从文件读取版本---不去重