python 获取字符串首字母缩写

最新推荐文章于 2023-08-13 00:15:00 发布

道空

最新推荐文章于 2023-08-13 00:15:00 发布

阅读量2.2k

点赞数 1

分类专栏： Python

本文链接：https://blog.csdn.net/DK18397606232/article/details/116296377

版权

python

Python 专栏收录该内容

14 篇文章 1 订阅

订阅专栏

首先声明：感谢提供帮助的博主，原文地址：https://www.cnblogs.com/qsxbc/p/13833827.html 在此基础上稍作封装改为一个方法方便调用而已。如有侵权，请联系我删除

from pytz import unicode


# 获取汉字首字母
def get_chinese_first_word(str_input):
    """
    数据中文字符串，可以获取首字母缩写；例如：你好世界   通过此方法得到    nhsj
    :param str_input:中文字符串
    :return:字符串首字母缩写
    """

    def single_get_first(unicode1):
        str1 = unicode1.encode('gbk')
        try:
            ord(str1)
            return str1
        except:
            asc = str1[0] * 256 + str1[1] - 65536
            # print(asc)
            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 multi_get_letter(str_input):
        if isinstance(str_input, unicode):
            unicode_str = str_input
        else:
            try:
                unicode_str = str_input.decode('utf8')
            except:
                try:
                    unicode_str = str_input.decode('gbk')
                except:
                    print('unknown coding')
                    return
        return_list = []
        for one_unicode in unicode_str:
            return_list.append(single_get_first(one_unicode))
        return return_list

    list1 = multi_get_letter(str_input)
    res = ''
    for i in list1:
        if type(i).__name__ == 'bytes':
            i = i.decode()
        res = res + i
    return res