当前位置:   article > 正文

python工具——pypinyin 汉字转换拼音_python 中文转slug

python 中文转slug

把汉字转成拼音后可以进行深度学习分类,做内容识别

1.安装

pip install pypinyin

将汉字转换为拼音并生成 slug 字符串

  1. import pypinyin
  2. from pypinyin import Style
  3. content = pypinyin.slug('汉语拼音')
  4. print(content)
  5. # E:\python\>python pinyin.py
  6. # han-yu-pin-yin

修改分隔字符串

  1. import pypinyin
  2. from pypinyin import Style
  3. content = pypinyin.slug('汉语拼音',separator=' ')
  4. print(content)
  5. # E:\python>python pinyin.py
  6. # han yu pin yin

启用多音字模式

  1. import pypinyin
  2. content = pypinyin.pinyin(u'单个', heteronym=True) # heteronym=False 不启用多音字
  3. print(content)
  4. # [['dān', 'chán', 'shàn'], ['gè', 'gàn', 'gě']]

 生成多音名字所有拼音列表

  1. import pypinyin
  2. from icecream import ic
  3. from itertools import product
  4. def load_pinyins(name):
  5. """通过名字加载拼音列表"""
  6. pinyins = []
  7. for char in name:
  8. pinyins = pinyins + pypinyin.pinyin(char, style=pypinyin.NORMAL, heteronym=True)
  9. # 通过笛卡尔积找到所有姓和名字的组合 product(*pinyins)
  10. return set(["".join(pinyins) for pinyins in product(*pinyins)])

 style设置拼音音调风格

  1. from pypinyin import pinyin, Style
  2. # (1)Style.TONE3音调显示在末尾
  3. print(pinyin('单个',style=Style.TONE3))
  4. # [['dan1'], ['ge4']]#数字为音调
  5. print(pinyin('单个',style=Style.TONE3,heteronym=True))
  6. # [['dan1', 'chan2', 'shan4'], ['ge4', 'gan4', 'ge3']]#数字为音调
  7. # (2) Style.TONE2音调显示在韵母
  8. print(pinyin('单个',style=Style.TONE2,heteronym=True))
  9. # [['da1n', 'cha2n', 'sha4n'], ['ge4', 'ga4n', 'ge3']]#数字为音调
  10. # (3)Style.TONE音调为手写格式
  11. print(pinyin('单个',style=Style.TONE))
  12. # [['dān'], ['gè']]
  13. print(pinyin('单个',style=Style.TONE,heteronym=True))
  14. # [['dān', 'chán', 'shàn'], ['gè', 'gàn', 'gě']]
  15. # (4)pypinyin.NORMAL不显示音调
  16. print(pinyin(u'单个', heteronym=True,style=pypinyin.NORMAL))
  17. # [['dan', 'chan', 'shan'], ['ge', 'gan']]
  18. print(pinyin(u'单个', style=pypinyin.NORMAL))
  19. # [['dan'], ['ge']]
声明:本文内容由网友自发贡献,不代表【wpsshop博客】立场,版权归原作者所有,本站不承担相应法律责任。如您发现有侵权的内容,请联系我们。转载请注明出处:https://www.wpsshop.cn/w/我家自动化/article/detail/203968
推荐阅读
相关标签
  

闽ICP备14008679号