今天想获取中文首字母,网上一搜基本都是python2的脚本,试了几个不行,只得在原有脚本基础上改改。
python2的如下脚本在python3上运行是不能通过的
asc = ord(str1[0]) * 256 + ord(str1[1]) - 65536
经过反复思考查证,最终解决了这个问题,现附上思考过程:
就是酱紫。所以下边附上python3支持的获取中文首字母的方法
def single_get_first(unicode1):
str1 = unicode1.encode('gbk')
try:
ord(str1)
return str1
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 getPinyin(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(getPinyin('非场'))