Created
March 30, 2018 17:16
-
-
Save jerrylususu/bb664173ffba2d63bd9af62188980630 to your computer and use it in GitHub Desktop.
UTF-8 Fixer
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
# utf8-fixer | |
import os | |
import chardet | |
s = os.sep | |
dirname = "C:\Projects\Assignment1" | |
# your assignment dir goes here | |
for root, dirs, files in os.walk(dirname): | |
for file in files: | |
if(file=="comments.txt"): | |
print(os.path.join(root, file)) | |
f = open(os.path.join(root, file),'rb') | |
data = f.read() | |
f.close() | |
guess_encoding = chardet.detect(data)['encoding'] | |
print(guess_encoding) | |
isutf8 = (guess_encoding == "utf-8") | |
print(isutf8) | |
if(not isutf8): | |
f = open(os.path.join(root, file),'r',encoding=guess_encoding) | |
content = f.read(); | |
print(content) | |
f.close() | |
f = open(os.path.join(root, file),'w',encoding="utf-8") | |
f.write(content) | |
f.close() | |
print("written") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment