正则表达式-汉字的匹配方法

unicode　:　　 ([u4e00-u9fa5]+)

unicode　:　　([u2E80-u9FFF]+)

utf-8　　:　　([x80-xff]+)

#encoding:utf-8
import re 



def main():
    
    # ([u4e00-u9fa5]+)
    TEST_STR_1 = u'ab123kk123'
    pattern_str = u'[0-9]+([u4e00-u9fa5]+)[0-9]+'
    pattern = re.compile (pattern_str)
    m = pattern.search(TEST_STR_1)
    print m.group() if m is not None else None
    print m.group(1) if m is not None else None
    print '
'
    
    TEST_STR_2 = u'ab123汉字123'
    m = pattern.search(TEST_STR_2)
    print m.group() if m is not None else None
    print m.group(1) if m is not None else None
    print '
'
    
    # ([x80-xff]+)
    TEST_STR_3 = 'ab123汉字123'
    pattern_str = '[0-9]+([x80-xff]+)[0-9]+'
    pattern = re.compile (pattern_str)
    m = pattern.search(TEST_STR_3)
    print m.group().decode('utf-8') if m is not None else None
    print m.group(1).decode('utf-8') if m is not None else None
    print '
'    
    
    # ([u2E80-u9FFF]+)
    TEST_STR_2 = u'ab123汉字123'
    pattern_str = u'[0-9]+([u2E80-u9FFF]+)[0-9]+'
    pattern = re.compile (pattern_str)
    m = pattern.search(TEST_STR_2)
    print m.group() if m is not None else None
    print m.group(1) if m is not None else None
    print '
'
    
    
    
if __name__ == '__main__':
    main()