{"id":1031553,"date":"2024-12-31T11:26:21","date_gmt":"2024-12-31T03:26:21","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1031553.html"},"modified":"2024-12-31T11:26:23","modified_gmt":"2024-12-31T03:26:23","slug":"python%e5%a6%82%e4%bd%95%e5%af%b9%e4%b8%ad%e6%96%87%e5%8f%a5%e5%ad%90%e8%bf%9b%e8%a1%8c%e5%88%87%e7%89%87","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1031553.html","title":{"rendered":"python\u5982\u4f55\u5bf9\u4e2d\u6587\u53e5\u5b50\u8fdb\u884c\u5207\u7247"},"content":{"rendered":"

\"python\u5982\u4f55\u5bf9\u4e2d\u6587\u53e5\u5b50\u8fdb\u884c\u5207\u7247\"<\/p>\n

Python\u5bf9\u4e2d\u6587\u53e5\u5b50\u8fdb\u884c\u5207\u7247\uff0c\u53ef\u4ee5\u4f7f\u7528\u5b57\u7b26\u4e32\u5207\u7247\u3001\u6b63\u5219\u8868\u8fbe\u5f0f\u3001jieba\u5e93<\/strong>\u3002\u5b57\u7b26\u4e32\u5207\u7247\u662f\u6700\u57fa\u7840\u7684\u65b9\u6cd5\uff0c\u6b63\u5219\u8868\u8fbe\u5f0f\u63d0\u4f9b\u4e86\u66f4\u5f3a\u5927\u7684\u5339\u914d\u529f\u80fd\uff0cjieba\u5e93\u5219\u662f\u4e13\u95e8\u4e3a\u4e2d\u6587\u6587\u672c\u5904\u7406\u8bbe\u8ba1\u7684\u5de5\u5177\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u8be6\u7ec6\u4ecb\u7ecd\u5176\u4e2d\u4e00\u79cd\u65b9\u6cd5\uff0c\u5373jieba\u5e93<\/strong>\u7684\u4f7f\u7528\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u5b57\u7b26\u4e32\u5207\u7247<\/h3>\n<\/p>\n

\u5b57\u7b26\u4e32\u5207\u7247\u662fPython\u4e2d\u6700\u57fa\u672c\u7684\u64cd\u4f5c\u4e4b\u4e00\u3002\u6211\u4eec\u53ef\u4ee5\u901a\u8fc7\u6307\u5b9a\u8d77\u59cb\u548c\u7ed3\u675f\u7d22\u5f15\u6765\u83b7\u53d6\u5b57\u7b26\u4e32\u7684\u5b50\u4e32\u3002<\/p>\n<\/p>\n

# \u793a\u4f8b<\/p>\n
sentence = "\u8fd9\u662f\u4e00\u4e2a\u4e2d\u6587\u53e5\u5b50\u3002"<\/p>\n
sub_sentence = sentence[2:5]<\/p>\n
print(sub_sentence)  # \u8f93\u51fa\uff1a\u4e00\u4e2a\u4e2d<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0csentence[2:5]<\/code>\u8868\u793a\u4ece\u7d22\u5f152\u5f00\u59cb\uff08\u5305\u62ec\u7d22\u5f152\uff09\uff0c\u5230\u7d22\u5f155\u7ed3\u675f\uff08\u4e0d\u5305\u62ec\u7d22\u5f155\uff09\u7684\u5b50\u4e32\u3002<\/p>\n<\/p>\n
\u4e8c\u3001\u6b63\u5219\u8868\u8fbe\u5f0f<\/h3>\n<\/p>\n
\u6b63\u5219\u8868\u8fbe\u5f0f\uff08Regular Expression\uff09\u662f\u4e00\u79cd\u5f3a\u5927\u7684\u6587\u672c\u5339\u914d\u5de5\u5177\uff0c\u53ef\u4ee5\u7528\u4e8e\u590d\u6742\u7684\u6587\u672c\u5207\u5206\u548c\u5339\u914d\u3002<\/p>\n<\/p>\n
import re<\/p>\n
\u793a\u4f8b<\/strong><\/h2>\n
sentence = "\u8fd9\u662f\u4e00\u4e2a\u4e2d\u6587\u53e5\u5b50\u3002"<\/p>\n
pattern = r'[\\u4e00-\\u9fa5]+'  # \u5339\u914d\u4e2d\u6587\u5b57\u7b26<\/p>\n
matches = re.findall(pattern, sentence)<\/p>\n
print(matches)  # \u8f93\u51fa\uff1a['\u8fd9\u662f\u4e00\u4e2a\u4e2d\u6587\u53e5\u5b50']<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c[\\u4e00-\\u9fa5]+<\/code>\u662f\u4e00\u4e2a\u5339\u914d\u4e2d\u6587\u5b57\u7b26\u7684\u6b63\u5219\u8868\u8fbe\u5f0f\u6a21\u5f0f\uff0cre.findall<\/code>\u51fd\u6570\u7528\u4e8e\u67e5\u627e\u6240\u6709\u5339\u914d\u9879\u3002<\/p>\n<\/p>\n
\u4e09\u3001jieba\u5e93<\/h3>\n<\/p>\n
jieba\u5e93\u662f\u4e13\u95e8\u4e3a\u4e2d\u6587\u6587\u672c\u5904\u7406\u8bbe\u8ba1\u7684\u5de5\u5177\uff0c\u652f\u6301\u7cbe\u786e\u6a21\u5f0f\u3001\u5168\u6a21\u5f0f\u548c\u641c\u7d22\u5f15\u64ce\u6a21\u5f0f\u4e09\u79cd\u5206\u8bcd\u65b9\u5f0f\u3002<\/p>\n<\/p>\n
1. \u5b89\u88c5jieba\u5e93<\/h4>\n<\/p>\n
\u9996\u5148\uff0c\u9700\u8981\u901a\u8fc7pip\u5b89\u88c5jieba\u5e93\uff1a<\/p>\n<\/p>\n
pip install jieba<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u4f7f\u7528jieba\u8fdb\u884c\u5206\u8bcd<\/h4>\n<\/p>\n
jieba\u5e93\u63d0\u4f9b\u4e86\u7b80\u5355\u6613\u7528\u7684\u63a5\u53e3\u6765\u8fdb\u884c\u4e2d\u6587\u5206\u8bcd\u3002<\/p>\n<\/p>\n
import jieba<\/p>\n
\u793a\u4f8b<\/strong><\/h2>\n
sentence = "\u8fd9\u662f\u4e00\u4e2a\u4e2d\u6587\u53e5\u5b50\u3002"<\/p>\n
words = jieba.cut(sentence, cut_all=False)  # \u7cbe\u786e\u6a21\u5f0f<\/p>\n
print("\/".join(words))  # \u8f93\u51fa\uff1a\u8fd9\u662f\/\u4e00\u4e2a\/\u4e2d\u6587\/\u53e5\u5b50\/\u3002<\/p>\n
<\/code><\/pre>\n<\/p>\n
3. jieba\u7684\u5176\u4ed6\u529f\u80fd<\/h4>\n<\/p>\n
jieba\u5e93\u8fd8\u63d0\u4f9b\u4e86\u5173\u952e\u8bcd\u63d0\u53d6\u3001\u8bcd\u6027\u6807\u6ce8\u7b49\u529f\u80fd\u3002<\/p>\n<\/p>\n
import jieba.analyse<\/p>\n
\u793a\u4f8b\uff1a\u5173\u952e\u8bcd\u63d0\u53d6<\/strong><\/h2>\n
sentence = "\u8fd9\u662f\u4e00\u4e2a\u4e2d\u6587\u53e5\u5b50\uff0c\u5305\u542b\u4e86\u8bb8\u591a\u6709\u8da3\u7684\u5185\u5bb9\u3002"<\/p>\n
keywords = jieba.analyse.extract_tags(sentence, topK=5)<\/p>\n
print(keywords)  # \u8f93\u51fa\uff1a['\u6709\u8da3', '\u5305\u542b', '\u5185\u5bb9', '\u53e5\u5b50', '\u4e2d\u6587']<\/p>\n
\u793a\u4f8b\uff1a\u8bcd\u6027\u6807\u6ce8<\/strong><\/h2>\n
import jieba.posseg as pseg<\/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
\u56db\u3001\u7ed3\u5408\u6240\u6709\u65b9\u6cd5\u7684\u5b8c\u6574\u793a\u4f8b<\/h3>\n<\/p>\n
\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u53ef\u4ee5\u7ed3\u5408\u4f7f\u7528\u4e0a\u8ff0\u65b9\u6cd5\u6765\u5bf9\u4e2d\u6587\u53e5\u5b50\u8fdb\u884c\u5207\u7247\u548c\u5904\u7406\u3002<\/p>\n<\/p>\n
import jieba<\/p>\n
import re<\/p>\n
def cut_sentence(sentence):<\/p>\n
    # \u4f7f\u7528jieba\u8fdb\u884c\u5206\u8bcd<\/p>\n
    words = jieba.cut(sentence, cut_all=False)<\/p>\n
    return list(words)<\/p>\n
def extract_chinese_substring(sentence, start, end):<\/p>\n
    # \u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u63d0\u53d6\u4e2d\u6587\u5b50\u4e32<\/p>\n
    pattern = r'[\\u4e00-\\u9fa5]+'<\/p>\n
    matches = re.findall(pattern, sentence)<\/p>\n
    sub_sentence = "".join(matches)[start:end]<\/p>\n
    return sub_sentence<\/p>\n
\u793a\u4f8b<\/strong><\/h2>\n
sentence = "\u8fd9\u662f\u4e00\u4e2a\u4e2d\u6587\u53e5\u5b50\uff0c\u5305\u542b\u4e86\u8bb8\u591a\u6709\u8da3\u7684\u5185\u5bb9\u3002"<\/p>\n
sub_sentence = extract_chinese_substring(sentence, 2, 7)<\/p>\n
print(sub_sentence)  # \u8f93\u51fa\uff1a\u4e00\u4e2a\u4e2d\u6587\u53e5\u5b50<\/p>\n
words = cut_sentence(sentence)<\/p>\n
print("\/".join(words))  # \u8f93\u51fa\uff1a\u8fd9\u662f\/\u4e00\u4e2a\/\u4e2d\u6587\/\u53e5\u5b50\/\uff0c\/\u5305\u542b\/\u4e86\/\u8bb8\u591a\/\u6709\u8da3\/\u7684\/\u5185\u5bb9\/\u3002<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u4e2a\u793a\u4f8b\u4e2d\uff0c\u6211\u4eec\u9996\u5148\u4f7f\u7528jieba\u8fdb\u884c\u5206\u8bcd\uff0c\u7136\u540e\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u63d0\u53d6\u4e2d\u6587\u5b50\u4e32\u3002\u901a\u8fc7\u8fd9\u79cd\u65b9\u6cd5\uff0c\u6211\u4eec\u53ef\u4ee5\u5b9e\u73b0\u5bf9\u4e2d\u6587\u53e5\u5b50\u7684\u7075\u6d3b\u5207\u7247\u548c\u5904\u7406\u3002<\/p>\n<\/p>\n
\u4e94\u3001\u4f18\u5316\u548c\u6027\u80fd<\/h3>\n<\/p>\n
\u5728\u5904\u7406\u5927\u89c4\u6a21\u6587\u672c\u65f6\uff0c\u6027\u80fd\u662f\u4e00\u4e2a\u91cd\u8981\u8003\u8651\u56e0\u7d20\u3002\u6211\u4eec\u53ef\u4ee5\u901a\u8fc7\u4e00\u4e9b\u4f18\u5316\u6280\u5de7\u6765\u63d0\u9ad8\u5904\u7406\u6548\u7387\u3002<\/p>\n<\/p>\n
1. \u7f13\u5b58\u5206\u8bcd\u7ed3\u679c<\/h4>\n<\/p>\n
\u5bf9\u4e8e\u9891\u7e41\u4f7f\u7528\u7684\u6587\u672c\uff0c\u53ef\u4ee5\u5c06\u5206\u8bcd\u7ed3\u679c\u7f13\u5b58\u8d77\u6765\uff0c\u907f\u514d\u91cd\u590d\u8ba1\u7b97\u3002<\/p>\n<\/p>\n
import jieba<\/p>\n
from functools import lru_cache<\/p>\n
@lru_cache(maxsize=128)<\/p>\n
def cached_cut_sentence(sentence):<\/p>\n
    return list(jieba.cut(sentence, cut_all=False))<\/p>\n
\u793a\u4f8b<\/strong><\/h2>\n
sentence = "\u8fd9\u662f\u4e00\u4e2a\u4e2d\u6587\u53e5\u5b50\uff0c\u5305\u542b\u4e86\u8bb8\u591a\u6709\u8da3\u7684\u5185\u5bb9\u3002"<\/p>\n
words = cached_cut_sentence(sentence)<\/p>\n
print("\/".join(words))  # \u8f93\u51fa\uff1a\u8fd9\u662f\/\u4e00\u4e2a\/\u4e2d\u6587\/\u53e5\u5b50\/\uff0c\/\u5305\u542b\/\u4e86\/\u8bb8\u591a\/\u6709\u8da3\/\u7684\/\u5185\u5bb9\/\u3002<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u5e76\u884c\u5904\u7406<\/h4>\n<\/p>\n
\u5bf9\u4e8e\u5927\u89c4\u6a21\u6587\u672c\uff0c\u53ef\u4ee5\u4f7f\u7528\u591a\u7ebf\u7a0b\u6216\u591a\u8fdb\u7a0b\u8fdb\u884c\u5e76\u884c\u5904\u7406\u3002<\/p>\n<\/p>\n
import jieba<\/p>\n
from concurrent.futures import ThreadPoolExecutor<\/p>\n
def cut_sentence(sentence):<\/p>\n
    return list(jieba.cut(sentence, cut_all=False))<\/p>\n
sentences = [<\/p>\n
    "\u8fd9\u662f\u7b2c\u4e00\u4e2a\u53e5\u5b50\u3002",<\/p>\n
    "\u8fd9\u662f\u7b2c\u4e8c\u4e2a\u53e5\u5b50\u3002",<\/p>\n
    "\u8fd9\u662f\u7b2c\u4e09\u4e2a\u53e5\u5b50\u3002",<\/p>\n
    # \u6dfb\u52a0\u66f4\u591a\u53e5\u5b50<\/p>\n
]<\/p>\n
with ThreadPoolExecutor(max_workers=4) as executor:<\/p>\n
    results = list(executor.map(cut_sentence, sentences))<\/p>\n
for words in results:<\/p>\n
    print("\/".join(words))<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u4e2a\u793a\u4f8b\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528ThreadPoolExecutor\u8fdb\u884c\u5e76\u884c\u5904\u7406\uff0c\u63d0\u9ad8\u4e86\u5904\u7406\u6548\u7387\u3002<\/p>\n<\/p>\n
\u516d\u3001\u603b\u7ed3<\/h3>\n<\/p>\n
\u901a\u8fc7\u672c\u6587\u7684\u4ecb\u7ecd\uff0c\u6211\u4eec\u8be6\u7ec6\u4e86\u89e3\u4e86Python\u5bf9\u4e2d\u6587\u53e5\u5b50\u8fdb\u884c\u5207\u7247\u7684\u591a\u79cd\u65b9\u6cd5\uff0c\u5305\u62ec\u5b57\u7b26\u4e32\u5207\u7247\u3001\u6b63\u5219\u8868\u8fbe\u5f0f\u3001jieba\u5e93\u7b49\u3002\u6bcf\u79cd\u65b9\u6cd5\u90fd\u6709\u5176\u9002\u7528\u7684\u573a\u666f\u548c\u4f18\u7f3a\u70b9\u3002\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u53ef\u4ee5\u6839\u636e\u5177\u4f53\u9700\u6c42\u9009\u62e9\u5408\u9002\u7684\u65b9\u6cd5\uff0c\u5e76\u7ed3\u5408\u4f18\u5316\u6280\u5de7\u63d0\u5347\u5904\u7406\u6548\u7387\u3002\u5e0c\u671b\u672c\u6587\u5bf9\u4f60\u5728\u5904\u7406\u4e2d\u6587\u6587\u672c\u65f6\u6709\u6240\u5e2e\u52a9\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u5982\u4f55\u5728Python\u4e2d\u6709\u6548\u5730\u5bf9\u4e2d\u6587\u53e5\u5b50\u8fdb\u884c\u5207\u7247\uff1f<\/strong>
\u5728Python\u4e2d\u5bf9\u4e2d\u6587\u53e5\u5b50\u8fdb\u884c\u5207\u7247\u53ef\u4ee5\u4f7f\u7528\u5b57\u7b26\u4e32\u7684\u5207\u7247\u529f\u80fd\u3002\u5b57\u7b26\u4e32\u5728Python\u4e2d\u662f\u53ef\u4ee5\u88ab\u89c6\u4e3a\u5b57\u7b26\u7684\u6570\u7ec4\uff0c\u56e0\u6b64\u53ef\u4ee5\u901a\u8fc7\u7d22\u5f15\u6765\u8bbf\u95ee\u7279\u5b9a\u7684\u5b57\u7b26\u3002\u4f8b\u5982\uff0c\u8981\u83b7\u53d6\u4e2d\u6587\u53e5\u5b50\u7684\u524d5\u4e2a\u5b57\u7b26\uff0c\u53ef\u4ee5\u4f7f\u7528sentence[:5]<\/code>\u3002\u9700\u8981\u6ce8\u610f\u7684\u662f\uff0c\u5207\u7247\u65f6\u786e\u4fdd\u5b57\u7b26\u7684\u5b8c\u6574\u6027\uff0c\u907f\u514d\u51fa\u73b0\u4e71\u7801\u3002<\/p>\n
\u4f7f\u7528\u4ec0\u4e48\u5e93\u53ef\u4ee5\u66f4\u597d\u5730\u5904\u7406\u4e2d\u6587\u53e5\u5b50\u7684\u5207\u7247\uff1f<\/strong>
\u5bf9\u4e8e\u4e2d\u6587\u5904\u7406\uff0c\u4f7f\u7528jieba<\/code>\u5e93\u662f\u4e00\u4e2a\u4e0d\u9519\u7684\u9009\u62e9\u3002jieba<\/code>\u53ef\u4ee5\u5bf9\u4e2d\u6587\u53e5\u5b50\u8fdb\u884c\u5206\u8bcd\uff0c\u8fd9\u6837\u5728\u5207\u7247\u65f6\u53ef\u4ee5\u907f\u514d\u56e0\u4e3a\u5355\u4e2a\u6c49\u5b57\u7684\u5207\u7247\u800c\u5bfc\u81f4\u7684\u8bed\u4e49\u6a21\u7cca\u3002\u901a\u8fc7\u5206\u8bcd\u540e\uff0c\u53ef\u4ee5\u66f4\u6e05\u6670\u5730\u8fdb\u884c\u53e5\u5b50\u7684\u5206\u6790\u548c\u5904\u7406\u3002<\/p>\n
\u5982\u4f55\u5904\u7406\u5207\u7247\u8fc7\u7a0b\u4e2d\u51fa\u73b0\u7684\u7f16\u7801\u95ee\u9898\uff1f<\/strong>
\u5728Python\u4e2d\u5904\u7406\u4e2d\u6587\u65f6\uff0c\u786e\u4fdd\u4f7f\u7528UTF-8<\/code>\u7f16\u7801\u4ee5\u907f\u514d\u7f16\u7801\u9519\u8bef\u3002\u5728\u8bfb\u53d6\u6216\u5199\u5165\u6587\u4ef6\u65f6\uff0c\u6307\u5b9a\u7f16\u7801\u683c\u5f0f\u53ef\u4ee5\u6709\u6548\u9632\u6b62\u4e71\u7801\u3002\u4f8b\u5982\uff0c\u4f7f\u7528open('file.txt', 'r', encoding='utf-8')<\/code>\u6765\u8bfb\u53d6\u6587\u4ef6\u3002\u786e\u4fdd\u5728\u5bf9\u4e2d\u6587\u53e5\u5b50\u8fdb\u884c\u5207\u7247\u65f6\uff0c\u5b57\u7b26\u4e32\u662f\u4ee5\u6b63\u786e\u7684\u7f16\u7801\u683c\u5f0f\u8fdb\u884c\u5904\u7406\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u5bf9\u4e2d\u6587\u53e5\u5b50\u8fdb\u884c\u5207\u7247\uff0c\u53ef\u4ee5\u4f7f\u7528\u5b57\u7b26\u4e32\u5207\u7247\u3001\u6b63\u5219\u8868\u8fbe\u5f0f\u3001jieba\u5e93\u3002\u5b57\u7b26\u4e32\u5207\u7247\u662f\u6700\u57fa\u7840\u7684\u65b9\u6cd5\uff0c\u6b63\u5219\u8868 […]","protected":false},"author":3,"featured_media":1031560,"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\/1031553"}],"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=1031553"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1031553\/revisions"}],"predecessor-version":[{"id":1031564,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1031553\/revisions\/1031564"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1031560"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1031553"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1031553"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1031553"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}