場景說明

把中文漢字啦桌、轉成漢語拼音甜滨，包括：

• 純漢字轉拼音
• 漢字里面加有字母轉拼音
• 轉加聲調的拼音
• 轉用數(shù)字表示聲調的拼音

install

$ pip install pinyin

python.png

引用

GitHub-pinyin

代碼

pinyinutil.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import pinyin


def to_pinyin(var_str):
    """
    漢字[釣魚島是中國的]=>拼音[diaoyudaoshizhongguode]\n
    漢字[我是shui]=>拼音[woshishui]\n
    漢字[AreYou好]=>拼音[AreYouhao]\n
    漢字[None]=>拼音[]\n
    漢字[]=>拼音[]\n
    :param var_str:  str 類型的字符串
    :return: 漢字轉小寫拼音
    """
    if isinstance(var_str, str):
        if var_str == 'None':
            return ""
        else:
            return pinyin.get(var_str, format='strip', delimiter="")
    else:
        return '類型不對'

測試代碼：

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import unittest
from util.pinyinutil import *
from pinyin._compat import u

class TestPinYin(unittest.TestCase):
    def test_to_pinyin(self):
        list = ['釣魚島是中國的', '我是shui', 'AreYou好', None, '']
        for i in list:
            print('漢字[%s]=>拼音[%s]' % (i, to_pinyin(str(i))))

    def test_get(self):
        self.assertEqual(pinyin.get('你好'),
                         pinyin.get('你好', format="diacritical"))
        self.assertEqual(pinyin.get(u('你好'), format="strip"), u('nihao'))
        self.assertEqual(pinyin.get(u('你好'), format="numerical"), u('ni3hao3'))
        self.assertEqual(pinyin.get(u('你好'), format="diacritical"), u('nǐhǎo'))
        self.assertEqual(pinyin.get('你好嗎?'), u('nǐhǎoma?'))
        self.assertEqual(pinyin.get('你好嗎雳殊？'), u('nǐhǎoma赘风？'))

        self.assertEqual(pinyin.get('你好'), u('nǐhǎo'))
        self.assertEqual(pinyin.get('葉'), u('yè'))
        self.assertEqual(pinyin.get('少女'), u('shǎonv?'))

    def test_get_with_delimiter(self):
        self.assertEqual(pinyin.get('你好', " "), u('nǐ hǎo'))
        self.assertEqual(pinyin.get('你好嗎?', " "), u('nǐ hǎo ma ?'))
        self.assertEqual(pinyin.get('你好嗎影暴？', " "), u('nǐ hǎo ma 续语？'))

    def test_get_initial_with_delimiter(self):
        self.assertEqual(pinyin.get_initial('你好', "-"), u('n-h'))
        self.assertEqual(pinyin.get_initial('你好嗎?', "-"), u('n-h-m-?'))
        self.assertEqual(pinyin.get_initial('你好嗎？', "-"), u('n-h-m-肝箱？'))

    def test_get_initial(self):
        self.assertEqual(pinyin.get_initial('你好'), u('n h'))
        self.assertEqual(pinyin.get_initial('你好嗎?'), u('n h m ?'))
        self.assertEqual(pinyin.get_initial('你好嗎哄褒？'), u('n h m ？'))

        self.assertEqual(pinyin.get_initial('你好'), 'n h')

    def test_mixed_chinese_english_input(self):
        self.assertEqual(pinyin.get('hi你好'), u('hinǐhǎo'))

    def test_correct_diacritical(self):
        self.assertEqual(pinyin.get("操"), u("cāo"))
        self.assertEqual(pinyin.get("小"), u("xiǎo"))
        self.assertEqual(pinyin.get("絕"), u("jué"))
        self.assertEqual(pinyin.get("被"), u("bèi"))
        self.assertEqual(pinyin.get("略"), u("lvè"))

    if __name__ == '__main__':
        unittest.main()