#!/usr/bin/python
# -*- coding: utf-8 -*-
#
#author: rex
#
blog: http://iregex.
org #filen
ame counter.py
#created: Mon Sep 20 21:00:52 2010
#desc: convert .py file to ht
ML w
ITh VIM.
import
Sys import re
From operator import itemgetter
def rea
DFile(f):
with file(f,"r") as pFile:
return pFile.read()
def divide(c, regex):
#the regex below is only valid for utf8 coding
return regex.findall(c)
def update_dict(di,li):
for i in li:
if di.has_key(i):
di[i]+=1
else:
di[i]=1
return di
def m
ain():
#rec
eive files f
rom bash
files=sys.
argv[1:]
#regex compile only once
regex=re
.COMpile("(?x) (?: [\w-]+ | [\x80-\xff]{3} )")
dict={}
#get all wo
rds from files
for f in files:
words=divide(readfile(f), regex)
dict=update_dict(dict, words)
#sort dictionary by value
#dict is now a list.
dict=sorted(dict.items(), key=itemgetter(1),
reverse=True)
#output to standard-output
for i in dict:
PRint i[0], i[1]
if __name__
=='__main__':
main()
(r"<[^>]+","",content),这样的结果对于某些文档更精确。