Created
November 26, 2014 11:53
-
-
Save gustavofonseca/c04e6110a88ee4a56af1 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#coding: utf-8 | |
import os | |
from os.path import join, getsize | |
import re | |
IMG_PATTERN = re.compile(r'^\w{4}-\w{4}-') | |
def lista_tifs(top): | |
for dirpath, dirnames, filenames in os.walk(top): | |
for filename in filenames: | |
if filename.endswith('.tif') and re.match(IMG_PATTERN, filename): | |
yield filename, getsize(os.path.normpath(join(dirpath, filename))) | |
def agrega_tifs(tifs): | |
artigos = {} | |
for filename, nbytes in tifs: | |
try: | |
artname, seq = filename.rsplit('-', 1) | |
except ValueError: | |
continue | |
artigo = artigos.setdefault(artname, {'total_img': 0, 'total_bytes': 0}) | |
artigo['total_img'] += 1 | |
artigo['total_bytes'] += nbytes | |
return artigos | |
if __name__ == '__main__': | |
total_artigos = total_imagens = total_bytes = 0 | |
print u'-' * 80 | |
# Artigo,Total de imagens,Total em bytes,Tamanho médio | |
for artigo, info in agrega_tifs(lista_tifs('.')).items(): | |
print u','.join([artigo, unicode(info['total_img']), unicode(info['total_bytes']), | |
unicode(info['total_bytes'] / info['total_img'])]) | |
total_artigos += 1 | |
total_imagens += info['total_img'] | |
total_bytes += info['total_bytes'] | |
print u'-' * 80 | |
print u'Média de imagens por artigo:', total_imagens / total_artigos | |
print u'Média de tamanho das imagens (bytes):', total_bytes / total_imagens | |
print u'-' * 80 | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment