Python 汉字转拼音

Posted 2020-11-17 quietwalk

 本文参考：

Python中文转拼音代码(支持全拼和首字母缩写)

中文中不可以有“()”

# -*- coding: utf-8 -*-
__version__ = \'0.9\'
__all__ = ["PinYin"]
import os.path


class PinYin(object):
    def __init__(self):
        self.word_dict = {}

    def load_word(self, dict_file):
        self.dict_file = dict_file
        if not os.path.exists(self.dict_file):
            raise IOError("NotFoundFile")

        with file(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="", firstcode=False):
        result = []
        if not isinstance(string, unicode):
            string = string.decode("utf-8")

        for char in string:
            key = \'%X\' % ord(char)
            value = self.word_dict.get(key, char)
            # print("===================")+value
            # print ("str(value).split()===")
            # for i in str(value).split():
            #     print i
            if value is not None and len(value)>0:

                s1=str(value).split()
                # print(type(s1))
                # print(str(len(s1)))
                if s1 is not None and len(s1)>0:
                    outpinyin = str(value).split()[0][:-1].lower()

                    if not outpinyin:
                        outpinyin = char
                    if firstcode:
                        result.append(outpinyin[0])
                    else:
                        result.append(outpinyin)
        return result

    def hanzi2pinyin_split(self, string="", split="", firstcode=False):
        """提取中文的拼音
        @param string:要提取的中文
        @param split:分隔符
        @param firstcode: 提取的是全拼还是首字母？如果为true表示提取首字母，默认为False提取全拼
        """
        result = self.hanzi2pinyin(string=string, firstcode=firstcode)
        return split.join(result)


if __name__ == "__main__":
    test = PinYin()
    test.load_word(\'word.data\')
    string = "Java程序性能优化-让你的Java程序更快更稳定"
    print "in: %s" % string
    print "out: %s" % str(test.hanzi2pinyin(string=string))
    print "out: %s" % test.hanzi2pinyin_split(string=string, split="", firstcode=True)
    print "out: %s" % test.hanzi2pinyin_split(string=string, split="", firstcode=False)

使用：

import app.model.explore.util.pinyin as pinyin

pyCvtor = pinyin.PinYin()

path=os.path.dirname(os.getcwd())+\'\\\\util\\\\word.data\'
print(path)
pyCvtor.load_word(path)

目录结构

 

具体使用：

转换效果：

肉眼及镜下血尿==========ryjjxxn
尿毒症
==========ndz
智力发育迟缓==========zlfych
氮质血症
==========dzxz
空腹血糖及糖耐量试验均正常==========kfxtjtnlsyjzc
血尿==========xn
大量蛋白尿==========dldbn
多尿==========dn
少尿==========sn
贫血氮质血症==========pxdzxz