分享一个统计文档中不同key的个数的python脚本

前提：

原统计文档中条目以空格分隔或只有一列（为了方便awk筛选出某一个列）

#!/usr/bin/env python
# -*- coding:utf-8 -*-
import sys
import os

PRINTRED = "33[1;31m"
PRINTGREEN = "33[0;32;47m"   #green color backgroud is white
PRINTGREEN_SIM = "33[1;32m"  #no backgroud green color
PRINTBLUE = "33[1;34m"
PRINTCOLOR_END= "33[0m"

def getAllItemList(fileName):
    try:
        fp = open(fileName, 'r')
        fLines = fp.readlines()
        fp.close()
        perList = []
        for item  in  fLines:
            #perSplit = line.split(';')
            #for item in perSplit:
            if item.isspace() == False:
                # space do nothing
                perList.append(item.strip())

        #print(perList)
        return perList
    except IOError:
        print("error: file not found, please check it !!!")
        sys.exit(0)

def calSameItemCount(itemList):
    sameCountDict={}
    for item in itemList:
        if sameCountDict.has_key(item):
            sameCountDict[item] += 1
        else:
            #print("notfindkey")
            sameCountDict[item] = 1
    print(("不重复key个数:{cstart}%d{cend}").format(cstart=PRINTRED,cend=PRINTCOLOR_END) % (len(sameCountDict)))
    print("不重复的key如下:")
    for key,value in sameCountDict.items():
        print(("%s 有[{cstart}%d{cend}]个!").format(cstart=PRINTRED,cend=PRINTCOLOR_END) % (key, value))
        #print(("{cstart}%s{cend}").format(cstart=PRINTRED,cend=PRINTCOLOR_END) % (key))


def main():
    #想要统计的key的列在第10列，原文档固定名为count.txt
    os.system("awk '{print $10}' count.txt > awkCountitem.txt")

    #fileName = raw_input("please input fileName: 
")
    fileName = "awkCountitem.txt"
    itemList = getAllItemList(fileName)
    itemCount = len(itemList)
    print(("%s:样本数据[{cstart}%d{cend}] 个!!!").format(cstart=PRINTRED,cend=PRINTCOLOR_END) % (fileName, itemCount))
    calSameItemCount(itemList)

if __name__=="__main__":
  main()