Jan
Jan
Programming language:Python
2021-07-08 02:29:40
0
Q:

encode decode python â\x80\x99

CrescentSickle
CrescentSickle
Code: Python
2021-07-10 00:52:01 
LATIN_1_CHARS = (
    ('\xe2\x80\x99', "'"),
    ('\xc3\xa9', 'e'),
    ('\xe2\x80\x90', '-'),
    ('\xe2\x80\x91', '-'),
    ('\xe2\x80\x92', '-'),
    ('\xe2\x80\x93', '-'),
    ('\xe2\x80\x94', '-'),
    ('\xe2\x80\x94', '-'),
    ('\xe2\x80\x98', "'"),
    ('\xe2\x80\x9b', "'"),
    ('\xe2\x80\x9c', '"'),
    ('\xe2\x80\x9c', '"'),
    ('\xe2\x80\x9d', '"'),
    ('\xe2\x80\x9e', '"'),
    ('\xe2\x80\x9f', '"'),
    ('\xe2\x80\xa6', '...'),
    ('\xe2\x80\xb2', "'"),
    ('\xe2\x80\xb3', "'"),
    ('\xe2\x80\xb4', "'"),
    ('\xe2\x80\xb5', "'"),
    ('\xe2\x80\xb6', "'"),
    ('\xe2\x80\xb7', "'"),
    ('\xe2\x81\xba', "+"),
    ('\xe2\x81\xbb', "-"),
    ('\xe2\x81\xbc', "="),
    ('\xe2\x81\xbd', "("),
    ('\xe2\x81\xbe', ")")
)


def clean_latin1(data):
    try:
        return data.encode('utf-8')
    except UnicodeDecodeError:
        data = data.decode('iso-8859-1')
        for _hex, _char in LATIN_1_CHARS:
            data = data.replace(_hex, _char)
        return data.encode('utf8')
-1

Tags

Related

New to Communities?

Join the community