ansi2utf.py - Konvertiert eine Textdatei nach UTF-8
Verfasst: Dienstag 27. Dezember 2005, 11:19
Stichworte: Unicode, Umwandeln
Beispielaufruf:
Beispielaufruf:
Code: Alles auswählen
ansi2utf.py hallowelt.txt
Code: Alles auswählen
#!/usr/bin/python
# -*- coding: utf-8 -*-
import sys
import os
import codecs
FROM_CODINGS = (
"utf-8",
sys.getfilesystemencoding(),
"latin-1",
"ascii",
"cp1252",
)
TO_CODING = "utf-8"
#----------------------------------------------------------------------
def main():
for filename in sys.argv[1:]:
tmp_filename = "%s.tmp" % filename
del_filename = "%s.del" % filename
f_in = file(filename, "rb")
f_out = codecs.open(
tmp_filename,
'wb',
encoding = TO_CODING
)
s_in = f_in.read()
f_in.close()
for coding in FROM_CODINGS:
try:
s_out = s_in.decode(coding)
break
except:
pass
f_out.write(s_out)
f_out.close()
os.rename(filename, del_filename)
os.rename(tmp_filename, filename)
os.remove(del_filename)
#----------------------------------------------------------------------
if __name__ == "__main__":
main()