{"id":955500,"date":"2024-12-27T02:17:19","date_gmt":"2024-12-26T18:17:19","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/955500.html"},"modified":"2024-12-27T02:17:21","modified_gmt":"2024-12-26T18:17:21","slug":"python%e4%b8%ad%e5%a6%82%e4%bd%95%e4%bf%9d%e7%95%99%e6%b1%89%e5%ad%97","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/955500.html","title":{"rendered":"python\u4e2d\u5982\u4f55\u4fdd\u7559\u6c49\u5b57"},"content":{"rendered":"

\"python\u4e2d\u5982\u4f55\u4fdd\u7559\u6c49\u5b57\"<\/p>\n

\u5728Python\u4e2d\u4fdd\u7559\u6c49\u5b57\u7684\u65b9\u6cd5\u5305\u62ec\u4f7f\u7528Unicode\u7f16\u7801\u3001\u6b63\u5219\u8868\u8fbe\u5f0f\u7b5b\u9009\u3001\u5b57\u7b26\u4e32\u8fc7\u6ee4\u7b49\u3002<\/strong>\u5176\u4e2d\uff0c\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u7b5b\u9009\u662f\u6700\u5e38\u7528\u7684\u65b9\u6cd5\u4e4b\u4e00\u3002\u901a\u8fc7\u5b9a\u4e49\u5339\u914d\u6c49\u5b57\u7684\u6b63\u5219\u8868\u8fbe\u5f0f\u6a21\u5f0f\uff0c\u53ef\u4ee5\u8f7b\u677e\u4ece\u5b57\u7b26\u4e32\u4e2d\u63d0\u53d6\u6216\u4fdd\u7559\u6c49\u5b57\u3002\u5177\u4f53\u5b9e\u73b0\u4e2d\uff0c\u6b63\u5219\u8868\u8fbe\u5f0f[\\u4e00-\\u9fa5]<\/code>\u53ef\u7528\u4e8e\u5339\u914d\u6240\u6709\u7684\u4e2d\u6587\u5b57\u7b26\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u5c06\u8be6\u7ec6\u8ba8\u8bba\u8fd9\u4e9b\u65b9\u6cd5\uff0c\u5e76\u63d0\u4f9b\u76f8\u5e94\u7684\u4ee3\u7801\u793a\u4f8b\u3002<\/p>\n<\/p>\n

\u4e00\u3001UNICODE\u7f16\u7801<\/p>\n<\/p>\n

Unicode\u662f\u4e00\u79cd\u5b57\u7b26\u7f16\u7801\u6807\u51c6\uff0c\u5b83\u80fd\u591f\u6db5\u76d6\u4e16\u754c\u4e0a\u5927\u90e8\u5206\u7684\u6587\u5b57\u7cfb\u7edf\u3002Python 3 \u9ed8\u8ba4\u4f7f\u7528Unicode\u7f16\u7801\uff0c\u8fd9\u4f7f\u5f97\u5728Python\u4e2d\u5904\u7406\u6c49\u5b57\u53d8\u5f97\u76f8\u5bf9\u7b80\u5355\u3002<\/p>\n<\/p>\n

    \n
  1. Unicode\u5728Python\u4e2d\u7684\u4f7f\u7528<\/strong><\/li>\n<\/ol>\n

    \u5728Python\u4e2d\uff0c\u5b57\u7b26\u4e32\u9ed8\u8ba4\u662fUnicode\u683c\u5f0f\uff0c\u56e0\u6b64\u53ef\u4ee5\u76f4\u63a5\u5728\u4ee3\u7801\u4e2d\u4f7f\u7528\u6c49\u5b57\u800c\u65e0\u9700\u7279\u6b8a\u5904\u7406\u3002\u4f8b\u5982\uff1a<\/p>\n<\/p>\n

    # \u793a\u4f8b\u4ee3\u7801<\/p>\n
    text = "\u8fd9\u662f\u4e00\u6bb5\u5305\u542b\u6c49\u5b57\u7684\u6587\u672c"<\/p>\n
    print(text)<\/p>\n
    <\/code><\/pre>\n<\/p>\n
    \u8fd9\u6bb5\u4ee3\u7801\u5c06\u76f4\u63a5\u8f93\u51fa\u201c\u8fd9\u662f\u4e00\u6bb5\u5305\u542b\u6c49\u5b57\u7684\u6587\u672c\u201d\u3002\u5bf9\u4e8e\u9700\u8981\u4ece\u5916\u90e8\u6587\u4ef6\u8bfb\u53d6\u6216\u5199\u5165\u5305\u542b\u6c49\u5b57\u7684\u6587\u672c\uff0c\u786e\u4fdd\u6587\u4ef6\u7f16\u7801\u4e3aUTF-8\u6216\u5176\u4ed6\u517c\u5bb9Unicode\u7684\u7f16\u7801\u683c\u5f0f\u5373\u53ef\u3002<\/p>\n<\/p>\n
      \n
    1. \u5b57\u7b26\u4e32\u64cd\u4f5c\u4e2d\u7684Unicode<\/strong><\/li>\n<\/ol>\n
      \u5728\u8fdb\u884c\u5b57\u7b26\u4e32\u64cd\u4f5c\u65f6\uff0c\u6bd4\u5982\u5207\u7247\u3001\u62fc\u63a5\u6216\u66ff\u6362\uff0cPython\u7684\u5b57\u7b26\u4e32\u64cd\u4f5c\u65b9\u6cd5\u53ef\u4ee5\u76f4\u63a5\u5e94\u7528\u4e8e\u5305\u542b\u6c49\u5b57\u7684\u5b57\u7b26\u4e32\uff1a<\/p>\n<\/p>\n
      # \u5b57\u7b26\u4e32\u64cd\u4f5c\u793a\u4f8b<\/p>\n
      text = "Python\u7f16\u7a0b"<\/p>\n
      sub_text = text[6:]  # \u63d0\u53d6\u201c\u7f16\u7a0b\u201d<\/p>\n
      print(sub_text)<\/p>\n
      <\/code><\/pre>\n<\/p>\n
      \u4e8c\u3001\u6b63\u5219\u8868\u8fbe\u5f0f\u7b5b\u9009<\/p>\n<\/p>\n
      \u6b63\u5219\u8868\u8fbe\u5f0f\u63d0\u4f9b\u4e86\u4e00\u79cd\u5f3a\u5927\u7684\u65b9\u5f0f\u6765\u5339\u914d\u5b57\u7b26\u4e32\u4e2d\u7684\u7279\u5b9a\u6a21\u5f0f\u3002\u5728Python\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528re<\/code>\u6a21\u5757\u6765\u8fdb\u884c\u6b63\u5219\u8868\u8fbe\u5f0f\u64cd\u4f5c\u3002<\/p>\n<\/p>\n
        \n
      1. \u5339\u914d\u6c49\u5b57\u7684\u6b63\u5219\u8868\u8fbe\u5f0f<\/strong><\/li>\n<\/ol>\n
        \u6b63\u5219\u8868\u8fbe\u5f0f[\\u4e00-\\u9fa5]<\/code>\u7528\u4e8e\u5339\u914d\u6c49\u5b57\u3002\u5728Python\u4e2d\uff0c\u53ef\u4ee5\u7ed3\u5408re<\/code>\u6a21\u5757\u7684findall<\/code>\u51fd\u6570\u6765\u7b5b\u9009\u5b57\u7b26\u4e32\u4e2d\u7684\u6c49\u5b57\u3002<\/p>\n<\/p>\n
        # \u793a\u4f8b\u4ee3\u7801\uff1a\u4ece\u5b57\u7b26\u4e32\u4e2d\u63d0\u53d6\u6c49\u5b57<\/p>\n
        import re<\/p>\n
        text = "Hello, \u4f60\u597d! Welcome to Python\u7f16\u7a0b."<\/p>\n
        hanzi = re.findall(r'[\\u4e00-\\u9fa5]', text)<\/p>\n
        print("\u63d0\u53d6\u7684\u6c49\u5b57:", ''.join(hanzi))<\/p>\n
        <\/code><\/pre>\n<\/p>\n
          \n
        1. \u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u8fdb\u884c\u8fc7\u6ee4<\/strong><\/li>\n<\/ol>\n
          \u9664\u4e86\u63d0\u53d6\u6c49\u5b57\uff0c\u8fd8\u53ef\u4ee5\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u6765\u8fc7\u6ee4\u6389\u975e\u6c49\u5b57\u5b57\u7b26\uff0c\u4fdd\u7559\u5b57\u7b26\u4e32\u4e2d\u7684\u6c49\u5b57\uff1a<\/p>\n<\/p>\n
          # \u793a\u4f8b\u4ee3\u7801\uff1a\u4fdd\u7559\u5b57\u7b26\u4e32\u4e2d\u7684\u6c49\u5b57<\/p>\n
          text = "Hello, \u4f60\u597d! Welcome to Python\u7f16\u7a0b."<\/p>\n
          filtered_text = ''.join(re.findall(r'[\\u4e00-\\u9fa5]', text))<\/p>\n
          print("\u8fc7\u6ee4\u540e\u7684\u6587\u672c:", filtered_text)<\/p>\n
          <\/code><\/pre>\n<\/p>\n
          \u4e09\u3001\u5b57\u7b26\u4e32\u8fc7\u6ee4<\/p>\n<\/p>\n
          \u9664\u4e86\u6b63\u5219\u8868\u8fbe\u5f0f\uff0c\u8fd8\u53ef\u4ee5\u901a\u8fc7\u904d\u5386\u5b57\u7b26\u4e32\u7684\u6bcf\u4e2a\u5b57\u7b26\uff0c\u7ed3\u5408\u5b57\u7b26\u7684Unicode\u7f16\u7801\u8303\u56f4\uff0c\u624b\u52a8\u5b9e\u73b0\u6c49\u5b57\u7684\u7b5b\u9009\u548c\u4fdd\u7559\u3002<\/p>\n<\/p>\n
            \n
          1. \u624b\u52a8\u7b5b\u9009\u6c49\u5b57<\/strong><\/li>\n<\/ol>\n
            \u901a\u8fc7\u904d\u5386\u5b57\u7b26\u4e32\uff0c\u68c0\u67e5\u6bcf\u4e2a\u5b57\u7b26\u7684Unicode\u7f16\u7801\u662f\u5426\u5728\u6c49\u5b57\u7684\u8303\u56f4\u5185\uff0c\u53ef\u4ee5\u5b9e\u73b0\u6c49\u5b57\u7684\u7b5b\u9009\uff1a<\/p>\n<\/p>\n
            # \u793a\u4f8b\u4ee3\u7801\uff1a\u624b\u52a8\u7b5b\u9009\u6c49\u5b57<\/p>\n
            text = "Hello, \u4f60\u597d! Welcome to Python\u7f16\u7a0b."<\/p>\n
            hanzi = [char for char in text if '\\u4e00' <= char <= '\\u9fa5']<\/p>\n
            print("\u624b\u52a8\u7b5b\u9009\u7684\u6c49\u5b57:", ''.join(hanzi))<\/p>\n
            <\/code><\/pre>\n<\/p>\n
              \n
            1. \u7ed3\u5408\u6761\u4ef6\u8fdb\u884c\u590d\u6742\u8fc7\u6ee4<\/strong><\/li>\n<\/ol>\n
              \u5728\u67d0\u4e9b\u60c5\u51b5\u4e0b\uff0c\u53ef\u80fd\u9700\u8981\u7ed3\u5408\u5176\u4ed6\u6761\u4ef6\u5bf9\u5b57\u7b26\u4e32\u8fdb\u884c\u590d\u6742\u7684\u8fc7\u6ee4\u548c\u5904\u7406\u3002\u8fd9\u65f6\uff0c\u53ef\u4ee5\u5728\u624b\u52a8\u7b5b\u9009\u7684\u57fa\u7840\u4e0a\uff0c\u6dfb\u52a0\u5176\u4ed6\u903b\u8f91\u5224\u65ad\u3002<\/p>\n<\/p>\n
              # \u793a\u4f8b\u4ee3\u7801\uff1a\u7ed3\u5408\u6761\u4ef6\u8fdb\u884c\u590d\u6742\u8fc7\u6ee4<\/p>\n
              text = "Hello, \u4f60\u597d! Welcome to Python\u7f16\u7a0b."<\/p>\n
              filtered_hanzi = []<\/p>\n
              for char in text:<\/p>\n
                  if '\\u4e00' <= char <= '\\u9fa5':<\/p>\n
                      # \u53ef\u4ee5\u5728\u6b64\u6dfb\u52a0\u5176\u4ed6\u6761\u4ef6<\/p>\n
                      filtered_hanzi.append(char)<\/p>\n
              print("\u590d\u6742\u8fc7\u6ee4\u540e\u7684\u6c49\u5b57:", ''.join(filtered_hanzi))<\/p>\n
              <\/code><\/pre>\n<\/p>\n
              \u56db\u3001\u6587\u672c\u6587\u4ef6\u7684\u8bfb\u53d6\u4e0e\u5199\u5165<\/p>\n<\/p>\n
              \u5728\u5904\u7406\u6587\u672c\u6587\u4ef6\u65f6\uff0c\u901a\u5e38\u9700\u8981\u8bfb\u53d6\u5305\u542b\u6c49\u5b57\u7684\u5185\u5bb9\uff0c\u5e76\u5728\u5904\u7406\u540e\u5199\u56de\u6587\u4ef6\u3002\u4f7f\u7528\u6b63\u786e\u7684\u7f16\u7801\u683c\u5f0f\u662f\u5173\u952e\u3002<\/p>\n<\/p>\n
                \n
              1. \u8bfb\u53d6\u6587\u672c\u6587\u4ef6<\/strong><\/li>\n<\/ol>\n
                \u5728\u8bfb\u53d6\u5305\u542b\u6c49\u5b57\u7684\u6587\u4ef6\u65f6\uff0c\u6307\u5b9a\u7f16\u7801\u683c\u5f0f\u53ef\u4ee5\u786e\u4fdd\u6b63\u786e\u8bfb\u53d6\u5185\u5bb9\uff1a<\/p>\n<\/p>\n
                # \u793a\u4f8b\u4ee3\u7801\uff1a\u8bfb\u53d6\u6587\u672c\u6587\u4ef6<\/p>\n
                with open('example.txt', 'r', encoding='utf-8') as file:<\/p>\n
                    content = file.read()<\/p>\n
                    print("\u6587\u4ef6\u5185\u5bb9:", content)<\/p>\n
                <\/code><\/pre>\n<\/p>\n
                  \n
                1. \u5199\u5165\u6587\u672c\u6587\u4ef6<\/strong><\/li>\n<\/ol>\n
                  \u5728\u5c06\u5904\u7406\u540e\u7684\u6c49\u5b57\u5199\u56de\u6587\u4ef6\u65f6\uff0c\u4e5f\u9700\u8981\u6307\u5b9a\u7f16\u7801\u683c\u5f0f\uff0c\u4ee5\u907f\u514d\u4e71\u7801\u95ee\u9898\uff1a<\/p>\n<\/p>\n
                  # \u793a\u4f8b\u4ee3\u7801\uff1a\u5199\u5165\u6587\u672c\u6587\u4ef6<\/p>\n
                  filtered_text = "\u8fd9\u662f\u5904\u7406\u540e\u7684\u6c49\u5b57\u6587\u672c"<\/p>\n
                  with open('output.txt', 'w', encoding='utf-8') as file:<\/p>\n
                      file.write(filtered_text)<\/p>\n
                  <\/code><\/pre>\n<\/p>\n
                  \u4e94\u3001\u7ed3\u8bba<\/p>\n<\/p>\n
                  \u901a\u8fc7\u4ee5\u4e0a\u65b9\u6cd5\uff0cPython\u53ef\u4ee5\u65b9\u4fbf\u5730\u4fdd\u7559\u6c49\u5b57\u5e76\u8fdb\u884c\u76f8\u5173\u5904\u7406\u3002\u4f7f\u7528Unicode\u7f16\u7801\u3001\u6b63\u5219\u8868\u8fbe\u5f0f\u7b5b\u9009\u3001\u5b57\u7b26\u4e32\u8fc7\u6ee4\u7b49\u65b9\u5f0f\uff0c\u80fd\u591f\u6ee1\u8db3\u5927\u591a\u6570\u573a\u666f\u4e0b\u7684\u9700\u6c42<\/strong>\u3002\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u6839\u636e\u5177\u4f53\u60c5\u51b5\u9009\u62e9\u5408\u9002\u7684\u65b9\u6cd5\uff0c\u5e76\u786e\u4fdd\u6587\u4ef6\u7f16\u7801\u683c\u5f0f\u4e00\u81f4\uff0c\u53ef\u4ee5\u6709\u6548\u907f\u514d\u4e71\u7801\u95ee\u9898\u3002<\/p>\n<\/p>\n
                  \u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
                   \u5982\u4f55\u5728Python\u4e2d\u5904\u7406\u5305\u542b\u6c49\u5b57\u7684\u5b57\u7b26\u4e32\uff1f<\/strong>
                  \u5728Python\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528Unicode\u7f16\u7801\u6765\u5904\u7406\u5305\u542b\u6c49\u5b57\u7684\u5b57\u7b26\u4e32\u3002\u786e\u4fdd\u4f60\u7684\u4ee3\u7801\u6587\u4ef6\u4f7f\u7528UTF-8\u7f16\u7801\uff0c\u5e76\u4f7f\u7528print()<\/code>\u51fd\u6570\u76f4\u63a5\u8f93\u51fa\u5b57\u7b26\u4e32\uff0cPython\u4f1a\u81ea\u52a8\u5904\u7406\u6c49\u5b57\u7684\u663e\u793a\u3002\u6b64\u5916\uff0c\u4f7f\u7528str.encode('utf-8')<\/code>\u548cbytes.decode('utf-8')<\/code>\u65b9\u6cd5\u53ef\u4ee5\u65b9\u4fbf\u5730\u8fdb\u884c\u7f16\u7801\u548c\u89e3\u7801\u3002<\/p>\n
                  \u5728Python\u4e2d\u5982\u4f55\u8bfb\u53d6\u548c\u5199\u5165\u5305\u542b\u6c49\u5b57\u7684\u6587\u4ef6\uff1f<\/strong>
                  \u8bfb\u53d6\u548c\u5199\u5165\u6587\u4ef6\u65f6\uff0c\u6307\u5b9a\u6587\u4ef6\u7684\u7f16\u7801\u683c\u5f0f\u4e3aUTF-8\u662f\u975e\u5e38\u91cd\u8981\u7684\u3002\u4f7f\u7528open()<\/code>\u51fd\u6570\u65f6\uff0c\u53ef\u4ee5\u901a\u8fc7encoding='utf-8'<\/code>\u53c2\u6570\u6765\u786e\u4fdd\u6c49\u5b57\u80fd\u591f\u6b63\u786e\u8bfb\u5199\u3002\u4f8b\u5982\uff0c\u8bfb\u53d6\u6587\u4ef6\u53ef\u4ee5\u4f7f\u7528with open('filename.txt', 'r', encoding='utf-8') as f:<\/code>\uff0c\u800c\u5199\u5165\u6587\u4ef6\u65f6\u540c\u6837\u9700\u8981\u6307\u5b9a\u7f16\u7801\u683c\u5f0f\u3002<\/p>\n
                  \u5728Python\u7684\u6b63\u5219\u8868\u8fbe\u5f0f\u4e2d\u5982\u4f55\u5339\u914d\u6c49\u5b57\uff1f<\/strong>
                  \u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u5339\u914d\u6c49\u5b57\u65f6\uff0c\u53ef\u4ee5\u4f7f\u7528\\u4e00-\\u9fa5<\/code>\u7684\u8303\u56f4\u6765\u5339\u914d\u6240\u6709\u6c49\u5b57\u3002\u4f8b\u5982\uff0cre.findall(r'[\\u4e00-\\u9fa5]+', text)<\/code>\u53ef\u4ee5\u7528\u6765\u63d0\u53d6\u6587\u672c\u4e2d\u7684\u6240\u6709\u6c49\u5b57\u3002\u8fd9\u79cd\u65b9\u6cd5\u5bf9\u5904\u7406\u542b\u6709\u6c49\u5b57\u7684\u6587\u672c\u6570\u636e\u975e\u5e38\u6709\u6548\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5728Python\u4e2d\u4fdd\u7559\u6c49\u5b57\u7684\u65b9\u6cd5\u5305\u62ec\u4f7f\u7528Unicode\u7f16\u7801\u3001\u6b63\u5219\u8868\u8fbe\u5f0f\u7b5b\u9009\u3001\u5b57\u7b26\u4e32\u8fc7\u6ee4\u7b49\u3002\u5176\u4e2d\uff0c\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u7b5b […]","protected":false},"author":3,"featured_media":955503,"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\/955500"}],"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=955500"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/955500\/revisions"}],"predecessor-version":[{"id":955506,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/955500\/revisions\/955506"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/955503"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=955500"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=955500"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=955500"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}