1 #-*-coding:utf-8-*-
2 __author__ = 'Deen'
3 '''
4 题目描述：任一个英文的纯文本文件，统计其中的单词出现的个数。
5 参考学习链接：
6 re http://www.cnblogs.com/tina-python/p/5508402.html#undefined
7 collections http://blog.csdn.net/liufang0001/article/details/54618484
8 '''
9 import re,collections
10 with open('english.txt','r') as fp:
11 text=fp.read().strip(',')
12 s=re.compile(r'\w+\b')
13 words=s.findall(text)
14 b=list()
15 dic=collections.defaultdict(lambda :0)
16 for word in words:
17 dic[word.lower()] +=1
18
19 print dic
20
21 '''
22 import collections,re
23 import sys
24 def cal(filename = 'english.txt'):
25 print 'now processing:' + filename + '......'
26 f = open(filename,'r')
27 data = f.read()
28 dic = collections.defaultdict(lambda :0)
29 data = re.sub(r'[\W\d]',' ',data)
30 data = data.lower()
31 datalist = data.split(' ')
32 for item in datalist:
33 dic[item] += 1
34 del dic['']
35 return dic
36 try:
37 print sorted(cal().items())
38 except:
39 print 'no input file'
40 '''
