Last active
August 29, 2015 14:01
-
-
Save ZiTAL/1b011032616a5b3bf7e6 to your computer and use it in GitHub Desktop.
Python: Remove BOM from UTF-8 files
This file contains 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
#!/usr/bin/env python | |
# -*- coding: utf-8 -*- | |
import sys, os, re, binascii | |
if(len(sys.argv)<2): | |
print 'Errorea: Karpeta argumentu bidez sartu' | |
sys.exit() | |
else: | |
dir = sys.argv[1] | |
# fitxategien zerrenda | |
file_list = [] | |
def scandir(dir): | |
if os.path.isdir(dir): | |
dir_list = os.listdir(dir) | |
for f in dir_list: | |
path = os.path.join(dir, f) | |
if os.path.isfile(path): | |
file_list.append(path) | |
elif os.path.isdir(path): | |
scandir(path) | |
# fitxategien zerrenda hartu | |
scandir(dir) | |
print "Fitxategi honeetatik BOM-a kentzen:" | |
for f in file_list: | |
# 1go lerroa bakarrik irakurri eta hexadecimal formatura pasa | |
hex = binascii.hexlify(open(f, 'r').readline()) | |
# bom-a badauka ikusi | |
if(re.match("^efbbbf", hex)): | |
print f | |
file = open(f, 'r') | |
# fitxategi guztia hexadecimal formatura pasa | |
hex = binascii.hexlify(file.read()) | |
# bom-a kendu | |
hex = re.sub("^efbbbf", '', hex) | |
# hex -> testura | |
deco = hex.decode("hex") | |
file = open(f, 'w') | |
file.write(deco) | |
file.close() | |
print "Eginda" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment