s1 = u'ÀÁÂÃÈÉÊÌÍÒÓÔÕÙÚÝàáâãèéêìíòóôõùúýĂăĐđĨĩŨũƠơƯưẠạẢảẤấẦầẨẩẪẫẬậẮắẰằẲẳẴẵẶặẸẹẺẻẼẽẾếỀềỂểỄễỆệỈỉỊịỌọỎỏỐốỒồỔổỖỗỘộỚớỜờỞởỠỡỢợỤụỦủỨứỪừỬửỮữỰựỲỳỴỵỶỷỸỹ'
s0 = u'AAAAEEEIIOOOOUUYaaaaeeeiioooouuyAaDdIiUuOoUuAaAaAaAaAaAaAaAaAaAaAaAaEeEeEeEeEeEeEeEeIiIiOoOoOoOoOoOoOoOoOoOoOoOoUuUuUuUuUuUuUuYyYyYyYy'
def remove_accents(input_str):
s = ''
print input_str.encode('utf-8')
for c in input_str:
if c in s1:
s += s0[s1.index(c)]
else:
s += c
return s
Nguồn: https://gist.githubusercontent.com/J2TEAM/9992744f15187ba51d46aecab21fd469/raw/85942b0406f565f4b02b3d899a1478dbbdccb575/remove_accents.py
Không có nhận xét nào:
Đăng nhận xét