Python 遍历文件夹，统计所有不同后缀的文件数量与比例

Question

在Github上经常看到项目里不同语言的占比，突然想写一个试试。

自己写完一个残缺的，感觉肯定不是最优解，所以来请教大家的写法。谢谢。

!/usr/bin/env python

coding:utf-8

import os

if name == '__main__':

work_space = os.getcwd()
pycount = 0
javacount = 0
jscount = 0
wecount = 0
othercount = 0
total = 0
print work_space
print '正在计算比例，请稍候.....'.decode('utf-8')
for path, dir, file_arr in os.walk('./'):
    for file_name in file_arr:
        javasuffix = file_name[-5:]
        pysuffix = file_name[-3:]
        if cmp(pysuffix, '.py') == 0:
            pycount += 1
        elif cmp(pysuffix, '.js') == 0:
            jscount += 1
        elif cmp(javasuffix, '.java') == 0:
            javacount += 1
        elif cmp(pysuffix, '.we') == 0:
            wecount += 1
        else:
            othercount += 1

total = pycount + jscount + javacount + wecount + othercount
total = float(total)
print '计算完成： 总文件数 : %d '.decode('utf-8') % total
print '文件数   Java: %d  js: %d  py: %d  we: %d  others: %d '.decode('utf-8') % (
    javacount, jscount, pycount, wecount, othercount)
print '所占比例   Java: %.2f%%  js:%.2f%%  py:%.2f%%  we:%.2f%%   others:%.2f%%'.decode('utf-8') % (
    javacount / total * 100, jscount / total * 100, pycount / total * 100, wecount / total * 100,
    othercount / total * 100)

Answer 1

#coding: utf-8

import os
from itertools import groupby

file_lst = []
for path, dir, files in os.walk('./'):
    file_lst += files

file_count = len(file_lst) * 1.0

for key, lst in groupby(file_lst, key=lambda x: os.path.splitext(x)[1]):
    print key, round(len(list(lst))/file_count, 2)

看第二种：

#coding: utf-8

import os
from collections import defaultdict

file_count = 1.0
res = defaultdict()
for path, dir, files in os.walk('./'):
    file_count += len(files)
    for file in files:
        suf = os.path.splitext(file)[1]
        res[suf] = res.setdefault(suf, 0) + 1

for k, v in res.iteritems():
    print k, round(v/file_count, 4) * 100

Answer 2

改进后的

# coding: utf-8

import os
from itertools import groupby


def getpercent(num):
    return str(round(num / file_count * 100, 2))


def getresult():
    for key in language_dict:
        print '%s count:%d  percent:%s%%' % (key, language_dict.get(key), getpercent(language_dict[key]))


if __name__ == '__main__':
    file_lst = []
    language_dict = {}
    for path, dirs, files in os.walk('./'):
        file_lst += files

    file_count = len(file_lst) * 1.0

    for key, lst in groupby(file_lst, key=lambda x: os.path.splitext(x)[1]):
        if key not in language_dict.keys():
            language_dict[key] = len(list(lst))
        else:
            language_dict[key] = language_dict.get(key) + len(list(lst))

    getresult()