Das deutsche Python-Forum

Code: Alles auswählen

# -*- coding: utf-8 -*-
from __future__ import print_function
x1 = chr(0xC3)
x2 = chr(0xBC)
print(x1, x2)
a = x1 + x2
print(a)

Code: Alles auswählen

>>> c = 'c3bc'
>>> s = chr(int('0x%s' % c[:2], 16)) + chr(int('0x%s' % c[2:], 16))
>>> print s.decode("utf8")
ü

Code: Alles auswählen

>>> [s.decode("utf8")]
[u'\xfc']

Code: Alles auswählen

import re


def replace_hex(string):
    def byte_sub(match):
        hex_digits_it = iter(match.group(0)[1:-1])
        return ''.join(chr(int(a + b, 16))
                       for a, b in zip(hex_digits_it, hex_digits_it))
    
    return re.sub(r'\(([0-9a-f]{2})+\)', byte_sub, string)


def main():
    old = 'M(c3bc)ll'
    new = replace_hex(old)
    print new


if __name__ == '__main__':
    main()

Code: Alles auswählen

#!/usr/bin/env python

import re

def replace_hex(string):
    def byte_sub(match):
        return ''.join(chr(int(a, 16)) for a in match.groups())
   
    return re.sub(r'\(([0-9a-f]{2})([0-9a-f]{2})\)', byte_sub, string)


def main():
    old = 'M(c3bc)ll'
    new = replace_hex(old)
    print new


if __name__ == '__main__':
    main()

Code: Alles auswählen

from itertools import izip

def split_in_two(string):
    for a, b in izip(string[::2], string[1::2]):
        yield a+b

Code: Alles auswählen

In [464]: list(string[i:i + 2] for i in xrange(0, len(string), 2))
Out[464]: ['c3', 'bc']

Code: Alles auswählen

import re

def decode(s):
    return re.sub(r"\(([0-9A-Fa-f]+)\)", lambda m:bytes.fromhex(m.group(1)).decode("utf-8"), s)

print(decode('M(C3BC)ll (C384)rger'))

Code: Alles auswählen

lambda m:m.group(1).decode("hex").decode("utf-8")