Last active
August 29, 2015 14:27
-
-
Save xbee/35ce7e2f52f88cae6356 to your computer and use it in GitHub Desktop.
A small Python script that converts a file encoded in Code Page 936 (aka GBK) to UTF-8.
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 python3.4 | |
# Code Page 936 (GBK) to UTF-8 Transcoder | |
# Author: Kristian Tang (@Krisiouz) | |
# A small script that converts a file encoded in Code Page 936 (GBK) to UTF-8. | |
def gbk_to_utf8(input_file, output_file): | |
# Load Files | |
input_file_opened = open(input_file, 'r', encoding='cp936') | |
input_file_read = input_file_opened.read() | |
output_file_opened = open(output_file, 'x', encoding='utf-8', newline='\n') | |
# Transcode | |
print('Transcoding…') | |
output_file_opened.write(input_file_read) | |
input_file_opened.close() | |
output_file_opened.close() | |
print('Done.\n') | |
def main(): | |
print('Code Page 936 (GBK) to UTF-8 Transcoder\n') | |
# Ask the User Which File to Transcode | |
while 0 == 0: | |
input_file = input('Full file path of GBK file:\n') | |
output_file = input_file + '.utf-8' | |
gbk_to_utf8(input_file, output_file) | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment