python获得中文的首字母

最新推荐文章于 2025-08-13 16:32:59 发布

原创最新推荐文章于 2025-08-13 16:32:59 发布 · 788 阅读

1 ·

CC 4.0 BY-SA版权

本文为while10博主原创文章，未经博主允许不得转载。

python 专栏收录该内容

15 篇文章

订阅专栏

该代码实现将汉字转换为对应的拼音首字母，主要应用于简单的汉字到拼音的映射处理，例如姓名的拼音缩写。通过GBK编码处理汉字，并根据ASCII码范围映射到相应字母。

def single_get_first(unicode1):
    str1 = unicode1.encode('gbk')
    try:
        ord(str1)
        return str1.decode('gbk')
    except:
        asc = str1[0] * 256 + str1[1] - 65536
        if asc >= -20319 and asc <= -20284:
            return 'a'
        if asc >= -20283 and asc <= -19776:
            return 'b'
        if asc >= -19775 and asc <= -19219:
            return 'c'
        if asc >= -19218 and asc <= -18711:
            return 'd'
        if asc >= -18710 and asc <= -18527:
            return 'e'
        if asc >= -18526 and asc <= -18240:
            return 'f'
        if asc >= -18239 and asc <= -17923:
            return 'g'
        if asc >= -17922 and asc <= -17418:
            return 'h'
        if asc >= -17417 and asc <= -16475:
            return 'j'
        if asc >= -16474 and asc <= -16213:
            return 'k'
        if asc >= -16212 and asc <= -15641:
            return 'l'
        if asc >= -15640 and asc <= -15166:
            return 'm'
        if asc >= -15165 and asc <= -14923:
            return 'n'
        if asc >= -14922 and asc <= -14915:
            return 'o'
        if asc >= -14914 and asc <= -14631:
            return 'p'
        if asc >= -14630 and asc <= -14150:
            return 'q'
        if asc >= -14149 and asc <= -14091:
            return 'r'
        if asc >= -14090 and asc <= -13119:
            return 's'
        if asc >= -13118 and asc <= -12839:
            return 't'
        if asc >= -12838 and asc <= -12557:
            return 'w'
        if asc >= -12556 and asc <= -11848:
            return 'x'
        if asc >= -11847 and asc <= -11056:
            return 'y'
        if asc >= -11055 and asc <= -10247:
            return 'z'
        return ''


def single_get_first(unicode1):
    str1 = unicode1.encode('gbk')
    try:
        ord(str1)
        return str1.decode('gbk')
    except:
        asc = str1[0] * 256 + str1[1] - 65536
        if asc >= -20319 and asc <= -20284:
            return 'a'
        if asc >= -20283 and asc <= -19776:
            return 'b'
        if asc >= -19775 and asc <= -19219:
            return 'c'
        if asc >= -19218 and asc <= -18711:
            return 'd'
        if asc >= -18710 and asc <= -18527:
            return 'e'
        if asc >= -18526 and asc <= -18240:
            return 'f'
        if asc >= -18239 and asc <= -17923:
            return 'g'
        if asc >= -17922 and asc <= -17418:
            return 'h'
        if asc >= -17417 and asc <= -16475:
            return 'j'
        if asc >= -16474 and asc <= -16213:
            return 'k'
        if asc >= -16212 and asc <= -15641:
            return 'l'
        if asc >= -15640 and asc <= -15166:
            return 'm'
        if asc >= -15165 and asc <= -14923:
            return 'n'
        if asc >= -14922 and asc <= -14915:
            return 'o'
        if asc >= -14914 and asc <= -14631:
            return 'p'
        if asc >= -14630 and asc <= -14150:
            return 'q'
        if asc >= -14149 and asc <= -14091:
            return 'r'
        if asc >= -14090 and asc <= -13119:
            return 's'
        if asc >= -13118 and asc <= -12839:
            return 't'
        if asc >= -12838 and asc <= -12557:
            return 'w'
        if asc >= -12556 and asc <= -11848:
            return 'x'
        if asc >= -11847 and asc <= -11056:
            return 'y'
        if asc >= -11055 and asc <= -10247:
            return 'z'
        return ''


def get_pinyin_init(string):
    if string == None:
        return None
    lst = list(string)
    charLst = []
    for l in lst:
        charLst.append(single_get_first(l))
    return ''.join(charLst)


if __name__ == '__main__':
    print(get_pinyin_init('赵志浩'))