Handling Accented Characters with Python Regular Expressions
[A-z] just isn't good enough!
import re string = 'riché' print string riché richre = re.compile('([A-z]+)') match = richre.match(string) print match.groups() ('rich',) richre = re.compile('(\w+)',re.LOCALE) match = richre.match(string) print match.groups() ('rich',) richre = re.compile('([é\w]+)') match = richre.match(string) print match.groups() ('rich\xe9',) richre = re.compile('([\xe9\w]+)') match = richre.match(string) print match.groups() ('rich\xe9',) richre = re.compile('([\xe9-\xf8\w]+)') match = richre.match(string) print match.groups() ('rich\xe9',) string = 'richéñ' match = richre.match(string) print match.groups() ('rich\xe9\xf1',) richre = re.compile('([\u00E9-\u00F8\w]+)') print match.groups() ('rich\xe9\xf1',) matched = match.group(1) print matched richéñ
