Python实现的统计文章单词次数功能示例

#coding=utf-8
import collections
import re
import os
useless_words=('the','a','an','and','by','of','in','on','is','to')
def get_important_word(file):
  f=open(file)
  word_counter=collections.Counter()
  for line in f:
    words=re.findall('\w+',line.lower())
    word_counter.update(words)
  f.close()
  most_important_word=word_counter.most_common(1)[0][0]
  count=2
  while(most_important_word in useless_words):
    most_important_word=word_counter.most_common(count)[count-1][0]
    count+=1
  num=word_counter.most_common(count)[count-1][1]
  print 'the most important word in %s is %s,it appears %d times'%(file,most_important_word,num)
if __name__=='__main__':
  filepath='.'
  for dirpath,dirname,dirfiles in os.walk(filepath):
    for file in dirfiles:
      if os.path.splitext(file)[1]=='.txt':
        abspath=os.path.join(dirpath,file)
        if os.path.isfile(abspath):
          get_important_word(abspath)