Last active
May 23, 2017 08:40
-
-
Save LooEv/5251cd3eb454d32cbcad3231caca48d9 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# -*- coding: utf-8 -*- | |
# Author: LooEv | |
# 2017-05-22 | |
import re | |
PROVINCE_MAPPING = { | |
u'北京': 'beijing', | |
u'上海': 'shanghai', | |
u'天津': 'tianjin', | |
u'重庆': 'chongqing', | |
u'香港': 'xianggang', | |
u'澳门': 'aomen', | |
u'安徽': 'anhui', | |
u'福建': 'fujian', | |
u'广东': 'guangdong', | |
u'广西': 'guangxi', | |
u'贵州': 'guizhou', | |
u'甘肃': 'gansu', | |
u'海南': 'hainan', | |
u'河北': 'hebei', | |
u'河南': 'henan', | |
u'黑龙江': 'heilongjiang', | |
u'湖北': 'hubei', | |
u'湖南': 'hunan', | |
u'吉林': 'jilin', | |
u'江苏': 'jiangsu', | |
u'江西': 'jiangxi', | |
u'辽宁': 'liaoning', | |
u'内蒙古': 'neimenggu', | |
u'宁夏': 'ningxia', | |
u'青海': 'qinghai', | |
u'陕西': 'shanxixian', | |
u'山西': 'shanxitaiyuan', | |
u'山东': 'shandong', | |
u'四川': 'sichuan', | |
u'台湾': 'taiwan', | |
u'西藏': 'xizang', | |
u'新疆': 'xinjiang', | |
u'云南': 'yunnan', | |
u'浙江': 'zhejiang', | |
} | |
def get_pinyin(province_str, sperator=None): | |
if not sperator: | |
sperator = ur' | |,|,|,|-|、' | |
province_list = re.split(sperator, province_str) | |
try: | |
return [PROVINCE_MAPPING[province] for province in province_list if province.strip()] | |
except: | |
raise Exception(u'please check the spelling of provinces') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment