Python统计文本文件字数与词频的完整实现

# -*- coding: GBK -*-
import string
import sys
reload(sys)
def compareItems((w1,c1), (w2,c2)):
  if c1 > c2:
    return - 1
  elif c1 == c2:
    return cmp(w1, w2)
  else:
    return 1
def main():
  fname = "file.txt"
  try:
    text = open(fname,'r').read()
    text = string.lower(text)
  except:
    print "\nfile.txt is not exist!!! or There is a R/W error! "
    sys.exit()
  for ch in '!"#$%&()*+,-./:;<=>?@[\\]^_`{|}~':
    text = string.replace(text, ch, ' ')
  words = string.split(text)
  counts = {}
  for w in words:
    counts[w] = counts.get(w,0) + 1
  n = input("\n输入要统计的top单词数:")
  items = counts.items()
  items.sort(compareItems)
  max = len(items)
  print "\n单词总计:" + str(len(words))
  print "单词净个数(已去重):" + str(max)
  print "\n"
  if n > max:
    n = max
  for i in range(n):
    print "%-10s%5d" % items[i]
if __name__ == '__main__':
  main()