Используя Python3, вы надеетесь os.walk каталог файлов, считывать их в двоичный объект (строку?) И производить с ними некоторую дальнейшую обработку. Однако первый шаг: как читать результаты файла (ов) os.walk?
# NOTE: Execute with python3.2.2
import os
import sys
path = "/home/user/my-files"
count = 0
successcount = 0
errorcount = 0
i = 0
#for directory in dirs
for (root, dirs, files) in os.walk(path):
# print (path)
print (dirs)
#print (files)
for file in files:
base, ext = os.path.splitext(file)
fullpath = os.path.join(root, file)
# Read the file into binary? --------
input = open(fullpath, "r")
content = input.read()
length = len(content)
count += 1
print (" file: ---->",base," / ",ext," [count:",count,"]", "[length:",length,"]")
print ("fullpath: ---->",fullpath)
ОШИБКА:
Traceback (most recent call last):
File "myFileReader.py", line 41, in <module>
content = input.read()
File "/usr/lib/python3.2/codecs.py", line 300, in decode
(result, consumed) = self._buffer_decode(data, self.errors, final)
UnicodeDecodeError: 'utf8' codec can't decode byte 0xe2 in position 11: invalid continuation byte
