{"id":1095313,"date":"2025-01-08T14:49:57","date_gmt":"2025-01-08T06:49:57","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1095313.html"},"modified":"2025-01-08T14:49:59","modified_gmt":"2025-01-08T06:49:59","slug":"python%e5%a6%82%e4%bd%95%e5%b0%86%e6%b1%89%e5%ad%97%e8%bd%ac%e6%8d%a2%e4%b8%ba%e5%ad%97%e7%ac%a6-2","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1095313.html","title":{"rendered":"python\u5982\u4f55\u5c06\u6c49\u5b57\u8f6c\u6362\u4e3a\u5b57\u7b26"},"content":{"rendered":"

\"python\u5982\u4f55\u5c06\u6c49\u5b57\u8f6c\u6362\u4e3a\u5b57\u7b26\"<\/p>\n

\u5728Python\u4e2d\uff0c\u5c06\u6c49\u5b57\u8f6c\u6362\u4e3a\u5b57\u7b26\u7684\u65b9\u5f0f\u6709\u591a\u79cd\uff0c\u53ef\u4ee5\u4f7f\u7528\u7f16\u7801\u8f6c\u6362\u3001Unicode\u7801\u3001pypinyin\u5e93<\/strong>\u7b49\u65b9\u6cd5\u3002\u6700\u5e38\u7528\u7684\u65b9\u6cd5\u662f\u5229\u7528Unicode\u7f16\u7801\uff0c\u56e0\u4e3a\u6c49\u5b57\u5728\u8ba1\u7b97\u673a\u5185\u90e8\u662f\u4ee5Unicode\u7f16\u7801\u5f62\u5f0f\u5b58\u50a8\u7684\u3002\u4e0b\u9762\uff0c\u6211\u4eec\u8be6\u7ec6\u4ecb\u7ecd\u5176\u4e2d\u4e00\u79cd\u65b9\u6cd5\uff0c\u5373\u4f7f\u7528pypinyin\u5e93\u8fdb\u884c\u6c49\u5b57\u8f6c\u6362\u4e3a\u62fc\u97f3\u5b57\u7b26\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u4f7f\u7528pypinyin\u5e93<\/h3>\n<\/p>\n

pypinyin\u662f\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684\u5e93\uff0c\u7528\u4e8e\u5c06\u6c49\u5b57\u8f6c\u6362\u4e3a\u62fc\u97f3\u5b57\u7b26\u3002\u5b83\u4e0d\u4ec5\u80fd\u5904\u7406\u5355\u4e2a\u6c49\u5b57\uff0c\u8fd8\u80fd\u5904\u7406\u6574\u4e2a\u53e5\u5b50\u3002\u4f7f\u7528pypinyin\u5e93\u975e\u5e38\u7b80\u5355\uff0c\u53ea\u9700\u8981\u5b89\u88c5\u5e76\u8c03\u7528\u76f8\u5e94\u51fd\u6570\u5373\u53ef\u3002<\/p>\n<\/p>\n

1. \u5b89\u88c5pypinyin\u5e93<\/h4>\n<\/p>\n

\u5728\u4f7f\u7528pypinyin\u5e93\u4e4b\u524d\uff0c\u9700\u8981\u5148\u5b89\u88c5\u5b83\u3002\u53ef\u4ee5\u901a\u8fc7pip\u547d\u4ee4\u8fdb\u884c\u5b89\u88c5\uff1a<\/p>\n<\/p>\n

pip install pypinyin<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u57fa\u672c\u4f7f\u7528\u65b9\u6cd5<\/h4>\n<\/p>\n
\u5b89\u88c5\u5b8c\u6210\u540e\uff0c\u53ef\u4ee5\u4f7f\u7528pypinyin\u5e93\u5c06\u6c49\u5b57\u8f6c\u6362\u4e3a\u62fc\u97f3\u5b57\u7b26\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n
from pypinyin import pinyin, lazy_pinyin<\/p>\n
\u5c06\u6c49\u5b57\u8f6c\u6362\u4e3a\u62fc\u97f3<\/strong><\/h2>\n
text = "\u6c49\u5b57"<\/p>\n
pinyin_result = pinyin(text)<\/p>\n
print(pinyin_result)  # \u8f93\u51fa [['h\u00e0n'], ['z\u00ec']]<\/p>\n
\u5c06\u6c49\u5b57\u8f6c\u6362\u4e3a\u62fc\u97f3\uff08\u7b80\u5316\u663e\u793a\uff09<\/strong><\/h2>\n
lazy_pinyin_result = lazy_pinyin(text)<\/p>\n
print(lazy_pinyin_result)  # \u8f93\u51fa ['han', 'zi']<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u901a\u8fc7\u4ee5\u4e0a\u4ee3\u7801\uff0c\u53ef\u4ee5\u770b\u5230pypinyin\u5e93\u53ef\u4ee5\u8f7b\u677e\u5730\u5c06\u6c49\u5b57\u8f6c\u6362\u4e3a\u62fc\u97f3\u5b57\u7b26\u3002<\/p>\n<\/p>\n
\u4e8c\u3001\u4f7f\u7528Unicode\u7f16\u7801<\/h3>\n<\/p>\n
Unicode\u662f\u4e00\u4e2a\u8ba1\u7b97\u673a\u884c\u4e1a\u6807\u51c6\uff0c\u5b83\u4e3a\u6bcf\u4e2a\u5b57\u7b26\u5206\u914d\u4e86\u4e00\u4e2a\u552f\u4e00\u7684\u7f16\u7801\u3002\u6211\u4eec\u53ef\u4ee5\u5229\u7528Python\u5185\u7f6e\u7684ord()\u548cchr()\u51fd\u6570\u6765\u8fdb\u884c\u6c49\u5b57\u4e0eUnicode\u7f16\u7801\u7684\u8f6c\u6362\u3002<\/p>\n<\/p>\n
1. \u6c49\u5b57\u8f6cUnicode\u7f16\u7801<\/h4>\n<\/p>\n
char = '\u6c49'<\/p>\n
unicode_code = ord(char)<\/p>\n
print(f"\u6c49\u5b57 '{char}' \u7684 Unicode \u7f16\u7801\u662f\uff1a{unicode_code}")<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. Unicode\u7f16\u7801\u8f6c\u6c49\u5b57<\/h4>\n<\/p>\n
unicode_code = 27721<\/p>\n
char = chr(unicode_code)<\/p>\n
print(f"Unicode \u7f16\u7801 {unicode_code} \u5bf9\u5e94\u7684\u6c49\u5b57\u662f\uff1a'{char}'")<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u901a\u8fc7\u4e0a\u8ff0\u65b9\u6cd5\uff0c\u53ef\u4ee5\u5c06\u6c49\u5b57\u8f6c\u6362\u4e3aUnicode\u7f16\u7801\uff0c\u53cd\u4e4b\u4ea6\u7136\u3002<\/p>\n<\/p>\n
\u4e09\u3001\u4f7f\u7528\u7b2c\u4e09\u65b9\u5e93\uff1azhon<\/h3>\n<\/p>\n
zhon\u5e93\u662f\u4e00\u4e2a\u4e13\u95e8\u5904\u7406\u4e2d\u6587\u5b57\u7b26\u7684\u7b2c\u4e09\u65b9\u5e93\uff0c\u5b83\u63d0\u4f9b\u4e86\u4e30\u5bcc\u7684\u5de5\u5177\u7528\u4e8e\u5904\u7406\u4e2d\u6587\u5b57\u7b26\u3002\u53ef\u4ee5\u4f7f\u7528\u5b83\u5c06\u6c49\u5b57\u8f6c\u6362\u4e3a\u62fc\u97f3\u6216\u5176\u4ed6\u5f62\u5f0f\u7684\u5b57\u7b26\u3002<\/p>\n<\/p>\n
1. \u5b89\u88c5zhon\u5e93<\/h4>\n<\/p>\n
pip install zhon<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u4f7f\u7528zhon\u5e93<\/h4>\n<\/p>\n
from zhon.hanzi import characters<\/p>\n
\u5224\u65ad\u5b57\u7b26\u662f\u5426\u4e3a\u6c49\u5b57<\/strong><\/h2>\n
char = '\u6c49'<\/p>\n
if char in characters:<\/p>\n
    print(f"'{char}' \u662f\u6c49\u5b57")<\/p>\n
else:<\/p>\n
    print(f"'{char}' \u4e0d\u662f\u6c49\u5b57")<\/p>\n
<\/code><\/pre>\n<\/p>\n
zhon\u5e93\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u5feb\u901f\u5224\u65ad\u5b57\u7b26\u662f\u5426\u4e3a\u6c49\u5b57\uff0c\u5e76\u8fdb\u884c\u76f8\u5e94\u7684\u5904\u7406\u3002<\/p>\n<\/p>\n
\u56db\u3001\u5904\u7406\u6c49\u5b57\u7684\u5176\u4ed6\u65b9\u6cd5<\/h3>\n<\/p>\n
1. \u4f7f\u7528unicodedata\u5e93<\/h4>\n<\/p>\n
unicodedata\u662fPython\u5185\u7f6e\u7684\u5e93\uff0c\u7528\u4e8e\u5904\u7406Unicode\u5b57\u7b26\u3002\u5b83\u53ef\u4ee5\u83b7\u53d6\u5b57\u7b26\u7684\u540d\u79f0\u3001\u7c7b\u522b\u7b49\u4fe1\u606f\u3002<\/p>\n<\/p>\n
import unicodedata<\/p>\n
char = '\u6c49'<\/p>\n
name = unicodedata.name(char)<\/p>\n
print(f"'{char}' \u7684\u540d\u79f0\u662f\uff1a{name}")<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u4f7f\u7528jieba\u5e93\u8fdb\u884c\u5206\u8bcd\u5904\u7406<\/h4>\n<\/p>\n
jieba\u5e93\u662f\u4e00\u4e2a\u5f3a\u5927\u7684\u4e2d\u6587\u5206\u8bcd\u5de5\u5177\uff0c\u5b83\u53ef\u4ee5\u5c06\u53e5\u5b50\u4e2d\u7684\u6c49\u5b57\u8fdb\u884c\u5206\u8bcd\u5904\u7406\uff0c\u5e76\u8f6c\u6362\u4e3a\u62fc\u97f3\u6216\u5176\u4ed6\u5f62\u5f0f\u7684\u5b57\u7b26\u3002<\/p>\n<\/p>\n
import jieba<\/p>\n
import jieba.posseg as pseg<\/p>\n
sentence = "\u6211\u7231\u7f16\u7a0b"<\/p>\n
words = pseg.cut(sentence)<\/p>\n
for word, flag in words:<\/p>\n
    print(f"{word} {flag}")<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u901a\u8fc7jieba\u5e93\uff0c\u53ef\u4ee5\u5c06\u53e5\u5b50\u4e2d\u7684\u6c49\u5b57\u8fdb\u884c\u5206\u8bcd\u5904\u7406\uff0c\u5e76\u83b7\u53d6\u6bcf\u4e2a\u8bcd\u7684\u8bcd\u6027\u3002<\/p>\n<\/p>\n
\u4e94\u3001\u5c06\u6c49\u5b57\u8f6c\u4e3a\u62fc\u97f3\u65f6\u7684\u6ce8\u610f\u4e8b\u9879<\/h3>\n<\/p>\n
\u5728\u5c06\u6c49\u5b57\u8f6c\u6362\u4e3a\u62fc\u97f3\u5b57\u7b26\u65f6\uff0c\u9700\u8981\u6ce8\u610f\u4ee5\u4e0b\u51e0\u70b9\uff1a<\/p>\n<\/p>\n
1. \u591a\u97f3\u5b57\u7684\u5904\u7406<\/h4>\n<\/p>\n
\u4e2d\u6587\u4e2d\u5b58\u5728\u5927\u91cf\u7684\u591a\u97f3\u5b57\uff0c\u4f8b\u5982\u201c\u884c\u201d\u53ef\u4ee5\u8bfb\u4f5c\u201cx\u00edng\u201d\u6216\u201ch\u00e1ng\u201d\u3002\u5728\u5904\u7406\u591a\u97f3\u5b57\u65f6\uff0c\u9700\u8981\u6839\u636e\u4e0a\u4e0b\u6587\u8bed\u5883\u8fdb\u884c\u6b63\u786e\u7684\u62fc\u97f3\u8f6c\u6362\u3002<\/p>\n<\/p>\n
2. \u7279\u6b8a\u5b57\u7b26\u7684\u5904\u7406<\/h4>\n<\/p>\n
\u6709\u4e9b\u6c49\u5b57\u53ef\u80fd\u5305\u542b\u7279\u6b8a\u5b57\u7b26\u6216\u6807\u70b9\u7b26\u53f7\uff0c\u9700\u8981\u8fdb\u884c\u7279\u6b8a\u5904\u7406\u3002\u4f8b\u5982\u201c\u4f60\u597d\uff01\u201d\u4e2d\u7684\u201c\uff01\u201d\u9700\u8981\u5355\u72ec\u5904\u7406\u3002<\/p>\n<\/p>\n
3. \u62fc\u97f3\u683c\u5f0f\u7684\u9009\u62e9<\/h4>\n<\/p>\n
\u5728\u8f6c\u6362\u6c49\u5b57\u4e3a\u62fc\u97f3\u65f6\uff0c\u53ef\u4ee5\u9009\u62e9\u4e0d\u540c\u7684\u62fc\u97f3\u683c\u5f0f\uff0c\u5982\u5e26\u58f0\u8c03\u7684\u62fc\u97f3\u3001\u53bb\u58f0\u8c03\u7684\u62fc\u97f3\u7b49\u3002\u6839\u636e\u5177\u4f53\u9700\u6c42\u9009\u62e9\u5408\u9002\u7684\u62fc\u97f3\u683c\u5f0f\u3002<\/p>\n<\/p>\n
\u516d\u3001\u603b\u7ed3<\/h3>\n<\/p>\n
\u901a\u8fc7\u4e0a\u8ff0\u65b9\u6cd5\uff0c\u53ef\u4ee5\u8f7b\u677e\u5730\u5c06\u6c49\u5b57\u8f6c\u6362\u4e3a\u5b57\u7b26\u3002\u5e38\u7528\u7684\u65b9\u6cd5\u5305\u62ec\u4f7f\u7528pypinyin\u5e93\u3001Unicode\u7f16\u7801\u3001zhon\u5e93\u3001unicodedata\u5e93\u548cjieba\u5e93\u7b49\u3002\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u6839\u636e\u5177\u4f53\u9700\u6c42\u9009\u62e9\u5408\u9002\u7684\u65b9\u6cd5\u8fdb\u884c\u6c49\u5b57\u7684\u5b57\u7b26\u8f6c\u6362\u3002\u65e0\u8bba\u662f\u5355\u4e2a\u6c49\u5b57\u8fd8\u662f\u6574\u53e5\u6c49\u5b57\uff0c\u90fd\u53ef\u4ee5\u901a\u8fc7\u8fd9\u4e9b\u65b9\u6cd5\u8fdb\u884c\u9ad8\u6548\u7684\u5904\u7406\u3002<\/p>\n<\/p>\n
\u5e0c\u671b\u4ee5\u4e0a\u5185\u5bb9\u80fd\u591f\u5e2e\u52a9\u4f60\u66f4\u597d\u5730\u7406\u89e3\u548c\u638c\u63e1Python\u4e2d\u5c06\u6c49\u5b57\u8f6c\u6362\u4e3a\u5b57\u7b26\u7684\u5404\u79cd\u65b9\u6cd5\u3002\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u53ef\u4ee5\u6839\u636e\u5177\u4f53\u9700\u6c42\u9009\u62e9\u5408\u9002\u7684\u65b9\u6cd5\u8fdb\u884c\u6c49\u5b57\u7684\u5b57\u7b26\u8f6c\u6362\u3002\u65e0\u8bba\u662f\u5355\u4e2a\u6c49\u5b57\u8fd8\u662f\u6574\u53e5\u6c49\u5b57\uff0c\u90fd\u53ef\u4ee5\u901a\u8fc7\u8fd9\u4e9b\u65b9\u6cd5\u8fdb\u884c\u9ad8\u6548\u7684\u5904\u7406\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u5982\u4f55\u4f7f\u7528Python\u5c06\u6c49\u5b57\u8f6c\u6362\u4e3a\u5bf9\u5e94\u7684Unicode\u7f16\u7801\uff1f<\/strong>
\u5728Python\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528\u5185\u7f6e\u7684ord()<\/code>\u51fd\u6570\u5c06\u6c49\u5b57\u8f6c\u6362\u4e3a\u5176\u5bf9\u5e94\u7684Unicode\u7f16\u7801\u3002\u4f8b\u5982\uff0c\u4f7f\u7528ord('\u6c49')<\/code>\u53ef\u4ee5\u83b7\u5f97\u6c49\u5b57\u201c\u6c49\u201d\u7684Unicode\u503c\u3002\u4f60\u53ef\u4ee5\u5c06\u8fd9\u4e2a\u65b9\u6cd5\u5e94\u7528\u4e8e\u4e00\u4e2a\u5b57\u7b26\u4e32\u4e2d\u7684\u6bcf\u4e2a\u6c49\u5b57\uff0c\u5229\u7528\u5217\u8868\u63a8\u5bfc\u5f0f\u8f7b\u677e\u5b9e\u73b0\u6279\u91cf\u8f6c\u6362\u3002<\/p>\n
\u662f\u5426\u53ef\u4ee5\u5c06\u6c49\u5b57\u8f6c\u6362\u4e3aASCII\u5b57\u7b26\uff1f<\/strong>
\u6c49\u5b57\u672c\u8eab\u5e76\u4e0d\u5c5e\u4e8eASCII\u5b57\u7b26\u96c6\uff0c\u56e0\u6b64\u65e0\u6cd5\u76f4\u63a5\u8f6c\u6362\u4e3aASCII\u5b57\u7b26\u3002\u82e5\u5e0c\u671b\u5c06\u6c49\u5b57\u8f6c\u6362\u4e3a\u82f1\u6587\u6216\u5176\u4ed6\u5b57\u7b26\uff0c\u53ef\u4ee5\u8003\u8651\u4f7f\u7528\u7ffb\u8bd1API\u6216\u5e93\uff0c\u5982googletrans<\/code>\uff0c\u5c06\u6c49\u5b57\u7ffb\u8bd1\u6210\u76f8\u5e94\u7684\u82f1\u6587\u8bcd\u6c47\u3002\u8fd9\u79cd\u65b9\u6cd5\u9002\u5408\u9700\u8981\u8bed\u4e49\u8f6c\u6362\u7684\u573a\u666f\u3002<\/p>\n
\u5982\u4f55\u5c06\u6c49\u5b57\u8f6c\u6362\u4e3a\u62fc\u97f3\uff1f<\/strong>
\u5728Python\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528pypinyin<\/code>\u5e93\u6765\u5c06\u6c49\u5b57\u8f6c\u6362\u4e3a\u62fc\u97f3\u3002\u5b89\u88c5\u8be5\u5e93\u540e\uff0c\u901a\u8fc7\u8c03\u7528pypinyin.lazy_pinyin()<\/code>\u51fd\u6570\uff0c\u5c06\u6c49\u5b57\u5b57\u7b26\u4e32\u4f5c\u4e3a\u53c2\u6570\u4f20\u5165\u5373\u53ef\u83b7\u5f97\u5bf9\u5e94\u7684\u62fc\u97f3\u5217\u8868\u3002\u8fd9\u5bf9\u4e8e\u9700\u8981\u5bf9\u6c49\u5b57\u8fdb\u884c\u8bed\u97f3\u5904\u7406\u6216\u62fc\u97f3\u5c55\u793a\u7684\u5e94\u7528\u573a\u666f\u975e\u5e38\u6709\u7528\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5728Python\u4e2d\uff0c\u5c06\u6c49\u5b57\u8f6c\u6362\u4e3a\u5b57\u7b26\u7684\u65b9\u5f0f\u6709\u591a\u79cd\uff0c\u53ef\u4ee5\u4f7f\u7528\u7f16\u7801\u8f6c\u6362\u3001Unicode\u7801\u3001pypinyin\u5e93\u7b49\u65b9\u6cd5\u3002 […]","protected":false},"author":3,"featured_media":1095318,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[37],"tags":[],"acf":[],"_links":{"self":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1095313"}],"collection":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/comments?post=1095313"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1095313\/revisions"}],"predecessor-version":[{"id":1095322,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1095313\/revisions\/1095322"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1095318"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1095313"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1095313"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1095313"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}