参考:https://github.com/cleverdeng/pinyin.py
上述代码适合python2.7的代码,但是对于python3.5的环境却不是很友好,所以将代码改成python3.5环境下可以运行的代码,代码如下:
# -*- coding:utf-8 -*-
"""
Author:cleverdeng
E-mail:clverdeng@gmail.com
"""
__version__ = '0.9'
__all__ = ["PinYin"]
import os.path
class PinYin(object):
def __init__(self, dict_file='word.data'):
self.word_dict = {}
self.dict_file = dict_file
def load_word(self):
if not os.path.exists(self.dict_file):
raise IOError("NotFoundFile")
with open(self.dict_file) as f_obj:
for f_line in f_obj.readlines():
try:
line = f_line.split(' ')
self.word_dict[line[0]] = line[1]
except:
line = f_line.split(' ')
self.word_dict[line[0]] = line[1]
def hanzi2pinyin(self, string=""):
result = []
for char in string:
key = '%X' % ord(char)
result.append(self.word_dict.get(key, char).split()[0][:-1].lower())
return result
def hanzi2pinyin_split(self, string="", split=""):
result = self.hanzi2pinyin(string=string)
if split == "":
return result
else:
return split.join(result)
if __name__ == "__main__":
test = PinYin()
test.load_word()
string = "钓鱼岛是中国的"
print( "in: %s" % string)
print( "out: %s" % str(test.hanzi2pinyin(string=string)))
print( "out: %s" % test.hanzi2pinyin_split(string=string, split="-"))