Python-сообщество

>>> def is_ascii(s):
    return all(ord(c) < 128 for c in s)
>>> is_ascii('ô')
False
>>> is_ascii('t')
True
>>> is_ascii('в')
False

import string
def isAscii(s):
    if s in string.ascii_letters or s in string.digits or s in string.punctuation:
        return True
    return False
for line in open('Connect.txt' , encoding='utf-16le'):
    st = ''
    for x in line:
        if isAscii(x):
            st += x
    print(st)

import string
def is_ascii(s):
    if (ord(s) > 31 and ord(s)<122 )or(ord(s) > 1039 and ord(s) < 1104):
        return True
    return False
for line in open('test.txt', encoding='utf-16le'):
    st = ''
    for x in line:
        if is_ascii(x):
            st += x
    print(st)

UnicodeDecodeError: 'utf16' codec can't decode bytes in position 1362-1363: illegal UTF-16 surrogate

ffc = open(file,"rb"); data = ffc.read(); ffc.close
text = str()
i = 0
for x in range(int(len(data)/2)):
try:
     text += data[i:i+2].decode('UTF-16LE')
     i += 2
except: i += 2
print(text)

>>> print(str(b'test\xfftest', 'utf-8'))
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xff in position 4: invalid
start byte
 
>>> print(str(b'test\xfftest', 'utf-8', 'ignore'))
testtest

def is_ascii(s):
    if (ord(s) > 31 and ord(s)<122 )or(ord(s) > 1039 and ord(s) < 1104)or(ord(s) in (9,10,13)):
        return True
    return False
file = open('in.some',"rb"); data = file.read(); file.close()
text = str()
texttemp = data.decode('UTF-16LE', 'ignore')
    for i in texttemp:
        if is_ascii(i) == True:
            text += i
file = open('out.txt',"wb"); data = file.write(text.encode()); file.close()