-
-
Save luzfcb/7032203 to your computer and use it in GitHub Desktop.
This file contains hidden or 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
import io, chardet | |
from chardet.universaldetector import UniversalDetector | |
f = open('file.txt') | |
# Jeito mais simples e menos preciso. | |
encoding = chardet.detect(f.read())['encoding'] | |
# Maneira mais precisa de se detectar o encoding. | |
# Servirá de fallback, caso a primeira tentativa não dê resultados. | |
if encoding is None: | |
# Voltando pro início do arquivo | |
f.seek(0) | |
u = UniversalDetector() | |
for linha in f: | |
u.feed(linha) | |
u.close() | |
encoding = u.result['encoding'] | |
f.close() | |
f = io.open('file.txt', encoding=encoding) | |
# A partir daqui, manipulamos o arquivo da maneira que quisermos. | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment