{"id":1171807,"date":"2025-01-15T16:40:09","date_gmt":"2025-01-15T08:40:09","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1171807.html"},"modified":"2025-01-15T16:40:11","modified_gmt":"2025-01-15T08:40:11","slug":"python%e9%87%8c%e9%9d%a2%e5%a6%82%e4%bd%95%e7%bc%96%e7%a0%81%e6%a0%bc%e5%bc%8f","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1171807.html","title":{"rendered":"python\u91cc\u9762\u5982\u4f55\u7f16\u7801\u683c\u5f0f"},"content":{"rendered":"

\"python\u91cc\u9762\u5982\u4f55\u7f16\u7801\u683c\u5f0f\"<\/p>\n

\u5728Python\u4e2d\uff0c\u7f16\u7801\u683c\u5f0f\u7684\u5904\u7406\u4e3b\u8981\u6d89\u53ca\u5b57\u7b26\u7f16\u7801\u548c\u89e3\u7801\u3002\u4f7f\u7528\u6b63\u786e\u7684\u7f16\u7801\u683c\u5f0f\u5904\u7406\u6587\u672c\u3001\u4f7f\u7528encode()<\/code>\u548cdecode()<\/code>\u65b9\u6cd5\u3001\u5904\u7406\u6587\u4ef6\u65f6\u6307\u5b9a\u7f16\u7801\u683c\u5f0f<\/strong>\u662f\u5173\u952e\u3002\u4f7f\u7528\u6b63\u786e\u7684\u7f16\u7801\u683c\u5f0f\u5904\u7406\u6587\u672c<\/strong>\u975e\u5e38\u91cd\u8981\uff0c\u56e0\u4e3a\u5b83\u786e\u4fdd\u4e86\u7a0b\u5e8f\u80fd\u591f\u6b63\u786e\u5904\u7406\u5404\u79cd\u5b57\u7b26\u96c6\uff0c\u907f\u514d\u51fa\u73b0\u4e71\u7801\u6216\u7f16\u7801\u9519\u8bef\u3002<\/p>\n<\/p>\n

\u4f7f\u7528\u6b63\u786e\u7684\u7f16\u7801\u683c\u5f0f\u5904\u7406\u6587\u672c<\/h3>\n<\/p>\n

\u5b57\u7b26\u7f16\u7801\u662f\u5c06\u5b57\u7b26\u8f6c\u6362\u4e3a\u4e8c\u8fdb\u5236\u6570\u636e\u7684\u8fc7\u7a0b\uff0c\u800c\u89e3\u7801\u662f\u5c06\u4e8c\u8fdb\u5236\u6570\u636e\u8f6c\u6362\u56de\u5b57\u7b26\u7684\u8fc7\u7a0b\u3002\u5728Python\u4e2d\uff0c\u9ed8\u8ba4\u7684\u5b57\u7b26\u7f16\u7801\u662fUTF-8\uff0c\u8fd9\u662f\u4e00\u79cd\u5e7f\u6cdb\u4f7f\u7528\u7684\u7f16\u7801\u683c\u5f0f\uff0c\u80fd\u591f\u8868\u793a\u51e0\u4e4e\u6240\u6709\u7684\u5b57\u7b26\u3002\u4e3a\u4e86\u786e\u4fdd\u7a0b\u5e8f\u5904\u7406\u6587\u672c\u6570\u636e\u65f6\u4e0d\u4f1a\u51fa\u73b0\u95ee\u9898\uff0c\u6700\u597d\u5728\u5904\u7406\u6587\u672c\u65f6\u663e\u5f0f\u6307\u5b9a\u7f16\u7801\u683c\u5f0f\u3002<\/p>\n<\/p>\n

\u8be6\u7ec6\u63cf\u8ff0\uff1a<\/h4>\n<\/p>\n

\u5047\u8bbe\u4f60\u9700\u8981\u5904\u7406\u5305\u542b\u4e2d\u6587\u5b57\u7b26\u7684\u6587\u672c\u6587\u4ef6\u3002\u5982\u679c\u4e0d\u6307\u5b9a\u7f16\u7801\u683c\u5f0f\uff0c\u53ef\u80fd\u4f1a\u5bfc\u81f4\u8bfb\u53d6\u6216\u5199\u5165\u6587\u4ef6\u65f6\u51fa\u73b0\u7f16\u7801\u9519\u8bef\u3002\u4ee5\u4e0b\u662f\u5982\u4f55\u6b63\u786e\u5904\u7406\u6587\u672c\u6587\u4ef6\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n

# \u8bfb\u53d6\u6587\u4ef6\u65f6\u6307\u5b9a\u7f16\u7801\u683c\u5f0f<\/p>\n
with open('example.txt', 'r', encoding='utf-8') as file:<\/p>\n
    content = file.read()<\/p>\n
\u5199\u5165\u6587\u4ef6\u65f6\u6307\u5b9a\u7f16\u7801\u683c\u5f0f<\/strong><\/h2>\n
with open('output.txt', 'w', encoding='utf-8') as file:<\/p>\n
    file.write(content)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u901a\u8fc7\u663e\u5f0f\u6307\u5b9a\u7f16\u7801\u683c\u5f0f\uff0c\u786e\u4fdd\u4e86\u7a0b\u5e8f\u5728\u5904\u7406\u5305\u542b\u4e2d\u6587\u5b57\u7b26\u7684\u6587\u672c\u6587\u4ef6\u65f6\u4e0d\u4f1a\u51fa\u73b0\u7f16\u7801\u9519\u8bef\u3002<\/p>\n<\/p>\n
\u4e00\u3001\u5b57\u7b26\u7f16\u7801\u57fa\u7840<\/h3>\n<\/p>\n
1\u3001\u5b57\u7b26\u7f16\u7801\u7684\u6982\u5ff5<\/h4>\n<\/p>\n
\u5b57\u7b26\u7f16\u7801\u662f\u4e00\u79cd\u5c06\u5b57\u7b26\u6620\u5c04\u4e3a\u4e8c\u8fdb\u5236\u6570\u636e\u7684\u89c4\u5219\u3002\u5e38\u89c1\u7684\u5b57\u7b26\u7f16\u7801\u5305\u62ecASCII\u3001UTF-8\u3001UTF-16\u548cISO-8859-1\u7b49\u3002\u4e0d\u540c\u7684\u5b57\u7b26\u7f16\u7801\u4f7f\u7528\u4e0d\u540c\u7684\u89c4\u5219\u6765\u8868\u793a\u5b57\u7b26\uff0c\u56e0\u6b64\u5728\u5904\u7406\u6587\u672c\u6570\u636e\u65f6\uff0c\u4e86\u89e3\u5b57\u7b26\u7f16\u7801\u7684\u6982\u5ff5\u975e\u5e38\u91cd\u8981\u3002<\/p>\n<\/p>\n
ASCII\u662f\u4e00\u79cd\u65e9\u671f\u7684\u5b57\u7b26\u7f16\u7801\u6807\u51c6\uff0c\u4f7f\u75287\u4f4d\u4e8c\u8fdb\u5236\u6570\u8868\u793a128\u4e2a\u5b57\u7b26\uff0c\u5305\u62ec\u82f1\u6587\u5b57\u6bcd\u3001\u6570\u5b57\u548c\u57fa\u672c\u7684\u6807\u70b9\u7b26\u53f7\u3002\u7531\u4e8e\u53ea\u80fd\u8868\u793a128\u4e2a\u5b57\u7b26\uff0cASCII\u65e0\u6cd5\u8868\u793a\u975e\u82f1\u8bed\u5b57\u7b26\u3002<\/p>\n<\/p>\n
UTF-8\u662f\u4e00\u79cd\u53d8\u957f\u5b57\u7b26\u7f16\u7801\uff0c\u4f7f\u75281\u52304\u4e2a\u5b57\u8282\u8868\u793a\u4e00\u4e2a\u5b57\u7b26\u3002\u5b83\u5177\u6709\u826f\u597d\u7684\u5411\u540e\u517c\u5bb9\u6027\uff0c\u80fd\u591f\u8868\u793a\u51e0\u4e4e\u6240\u6709\u7684\u5b57\u7b26\u96c6\uff0c\u662f\u73b0\u4ee3\u5e94\u7528\u4e2d\u6700\u5e38\u7528\u7684\u7f16\u7801\u683c\u5f0f\u3002<\/p>\n<\/p>\n
2\u3001Python\u4e2d\u7684\u5b57\u7b26\u7f16\u7801<\/h4>\n<\/p>\n
\u5728Python\u4e2d\uff0c\u5b57\u7b26\u4e32\u7c7b\u578b\u5206\u4e3a\u4e24\u79cd\uff1astr<\/code>\u548cbytes<\/code>\u3002str<\/code>\u7c7b\u578b\u8868\u793aUnicode\u5b57\u7b26\u4e32\uff0cbytes<\/code>\u7c7b\u578b\u8868\u793a\u4e8c\u8fdb\u5236\u6570\u636e\u3002\u5728Python 3\u4e2d\uff0c\u9ed8\u8ba4\u7684\u5b57\u7b26\u4e32\u7c7b\u578b\u662fUnicode\u5b57\u7b26\u4e32\uff0c\u8fd9\u610f\u5473\u7740\u5b57\u7b26\u4e32\u6570\u636e\u5728\u5185\u90e8\u4f7f\u7528Unicode\u7f16\u7801\u8868\u793a\u3002<\/p>\n<\/p>\n
\u5c06\u5b57\u7b26\u4e32\u7f16\u7801\u4e3a\u4e8c\u8fdb\u5236\u6570\u636e\u4f7f\u7528encode()<\/code>\u65b9\u6cd5\uff0c\u5c06\u4e8c\u8fdb\u5236\u6570\u636e\u89e3\u7801\u4e3a\u5b57\u7b26\u4e32\u4f7f\u7528decode()<\/code>\u65b9\u6cd5\u3002\u4f8b\u5982\uff1a<\/p>\n<\/p>\n
# \u5c06\u5b57\u7b26\u4e32\u7f16\u7801\u4e3a\u4e8c\u8fdb\u5236\u6570\u636e<\/p>\n
text = "\u4f60\u597d"<\/p>\n
encoded_text = text.encode('utf-8')<\/p>\n
\u5c06\u4e8c\u8fdb\u5236\u6570\u636e\u89e3\u7801\u4e3a\u5b57\u7b26\u4e32<\/strong><\/h2>\n
decoded_text = encoded_text.decode('utf-8')<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u901a\u8fc7\u663e\u5f0f\u6307\u5b9a\u7f16\u7801\u683c\u5f0f\uff0c\u53ef\u4ee5\u786e\u4fdd\u7f16\u7801\u548c\u89e3\u7801\u8fc7\u7a0b\u4e2d\u7684\u4e00\u81f4\u6027\uff0c\u907f\u514d\u51fa\u73b0\u7f16\u7801\u9519\u8bef\u3002<\/p>\n<\/p>\n
\u4e8c\u3001\u6587\u4ef6\u7f16\u7801\u5904\u7406<\/h3>\n<\/p>\n
1\u3001\u8bfb\u53d6\u6587\u4ef6\u65f6\u6307\u5b9a\u7f16\u7801\u683c\u5f0f<\/h4>\n<\/p>\n
\u5728\u8bfb\u53d6\u6587\u4ef6\u65f6\uff0c\u6307\u5b9a\u6b63\u786e\u7684\u7f16\u7801\u683c\u5f0f\u975e\u5e38\u91cd\u8981\u3002\u5982\u679c\u6587\u4ef6\u5305\u542b\u975eASCII\u5b57\u7b26\uff0c\u4f7f\u7528\u9ed8\u8ba4\u7f16\u7801\u683c\u5f0f\u53ef\u80fd\u4f1a\u5bfc\u81f4\u8bfb\u53d6\u9519\u8bef\u3002\u4ee5\u4e0b\u662f\u8bfb\u53d6\u6587\u4ef6\u65f6\u6307\u5b9a\u7f16\u7801\u683c\u5f0f\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n
with open('example.txt', 'r', encoding='utf-8') as file:<\/p>\n
    content = file.read()<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u901a\u8fc7\u6307\u5b9a\u7f16\u7801\u683c\u5f0futf-8<\/code>\uff0c\u786e\u4fdd\u4e86\u6587\u4ef6\u8bfb\u53d6\u8fc7\u7a0b\u4e2d\u7684\u6b63\u786e\u6027\u3002<\/p>\n<\/p>\n
2\u3001\u5199\u5165\u6587\u4ef6\u65f6\u6307\u5b9a\u7f16\u7801\u683c\u5f0f<\/h4>\n<\/p>\n
\u5728\u5199\u5165\u6587\u4ef6\u65f6\uff0c\u540c\u6837\u9700\u8981\u6307\u5b9a\u7f16\u7801\u683c\u5f0f\uff0c\u4ee5\u786e\u4fdd\u5199\u5165\u7684\u6587\u672c\u6570\u636e\u80fd\u591f\u6b63\u786e\u8868\u793a\u3002\u4f8b\u5982\uff1a<\/p>\n<\/p>\n
with open('output.txt', 'w', encoding='utf-8') as file:<\/p>\n
    file.write(content)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u901a\u8fc7\u6307\u5b9a\u7f16\u7801\u683c\u5f0futf-8<\/code>\uff0c\u786e\u4fdd\u4e86\u6587\u4ef6\u5199\u5165\u8fc7\u7a0b\u4e2d\u7684\u6b63\u786e\u6027\u3002<\/p>\n<\/p>\n
\u4e09\u3001\u5904\u7406\u4e0d\u540c\u7f16\u7801\u683c\u5f0f\u7684\u6587\u672c<\/h3>\n<\/p>\n
1\u3001\u8f6c\u6362\u7f16\u7801\u683c\u5f0f<\/h4>\n<\/p>\n
\u5728\u5904\u7406\u4e0d\u540c\u7f16\u7801\u683c\u5f0f\u7684\u6587\u672c\u65f6\uff0c\u53ef\u80fd\u9700\u8981\u5c06\u6587\u672c\u4ece\u4e00\u79cd\u7f16\u7801\u683c\u5f0f\u8f6c\u6362\u4e3a\u53e6\u4e00\u79cd\u7f16\u7801\u683c\u5f0f\u3002\u53ef\u4ee5\u5148\u5c06\u6587\u672c\u89e3\u7801\u4e3aUnicode\u5b57\u7b26\u4e32\uff0c\u7136\u540e\u518d\u7f16\u7801\u4e3a\u76ee\u6807\u7f16\u7801\u683c\u5f0f\u3002\u4f8b\u5982\uff1a<\/p>\n<\/p>\n
# \u5c06GBK\u7f16\u7801\u7684\u6587\u672c\u8f6c\u6362\u4e3aUTF-8\u7f16\u7801<\/p>\n
with open('gbk_text.txt', 'r', encoding='gbk') as file:<\/p>\n
    content = file.read()<\/p>\n
with open('utf8_text.txt', 'w', encoding='utf-8') as file:<\/p>\n
    file.write(content)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u901a\u8fc7\u5148\u89e3\u7801\u4e3aUnicode\u5b57\u7b26\u4e32\uff0c\u7136\u540e\u518d\u7f16\u7801\u4e3a\u76ee\u6807\u7f16\u7801\u683c\u5f0f\uff0c\u5b9e\u73b0\u4e86\u7f16\u7801\u683c\u5f0f\u7684\u8f6c\u6362\u3002<\/p>\n<\/p>\n
2\u3001\u5904\u7406\u672a\u77e5\u7f16\u7801\u683c\u5f0f\u7684\u6587\u672c<\/h4>\n<\/p>\n
\u5728\u5904\u7406\u672a\u77e5\u7f16\u7801\u683c\u5f0f\u7684\u6587\u672c\u65f6\uff0c\u53ef\u4ee5\u4f7f\u7528chardet<\/code>\u5e93\u6765\u68c0\u6d4b\u6587\u672c\u7684\u7f16\u7801\u683c\u5f0f\u3002\u4ee5\u4e0b\u662f\u793a\u4f8b\u4ee3\u7801\uff1a<\/p>\n<\/p>\n
import chardet<\/p>\n
\u8bfb\u53d6\u4e8c\u8fdb\u5236\u6570\u636e<\/strong><\/h2>\n
with open('unknown_encoding_text.txt', 'rb') as file:<\/p>\n
    data = file.read()<\/p>\n
\u68c0\u6d4b\u7f16\u7801\u683c\u5f0f<\/strong><\/h2>\n
result = chardet.detect(data)<\/p>\n
encoding = result['encoding']<\/p>\n
\u89e3\u7801\u4e3aUnicode\u5b57\u7b26\u4e32<\/strong><\/h2>\n
text = data.decode(encoding)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u901a\u8fc7\u68c0\u6d4b\u6587\u672c\u7684\u7f16\u7801\u683c\u5f0f\uff0c\u53ef\u4ee5\u6b63\u786e\u89e3\u7801\u4e3aUnicode\u5b57\u7b26\u4e32\uff0c\u907f\u514d\u51fa\u73b0\u7f16\u7801\u9519\u8bef\u3002<\/p>\n<\/p>\n
\u56db\u3001\u7f16\u7801\u9519\u8bef\u5904\u7406<\/h3>\n<\/p>\n
1\u3001\u5904\u7406\u7f16\u7801\u9519\u8bef<\/h4>\n<\/p>\n
\u5728\u7f16\u7801\u548c\u89e3\u7801\u8fc7\u7a0b\u4e2d\uff0c\u53ef\u80fd\u4f1a\u9047\u5230\u7f16\u7801\u9519\u8bef\u3002\u4f8b\u5982\uff0c\u5c1d\u8bd5\u89e3\u7801\u5305\u542b\u65e0\u6548\u5b57\u8282\u7684\u4e8c\u8fdb\u5236\u6570\u636e\u65f6\u4f1a\u5f15\u53d1UnicodeDecodeError<\/code>\u3002\u53ef\u4ee5\u4f7f\u7528errors<\/code>\u53c2\u6570\u6765\u6307\u5b9a\u9519\u8bef\u5904\u7406\u7b56\u7565\uff0c\u4f8b\u5982\uff1a<\/p>\n<\/p>\n
# \u5ffd\u7565\u7f16\u7801\u9519\u8bef<\/p>\n
text = data.decode('utf-8', errors='ignore')<\/p>\n
\u4f7f\u7528\u66ff\u4ee3\u5b57\u7b26\u66ff\u6362\u65e0\u6548\u5b57\u8282<\/strong><\/h2>\n
text = data.decode('utf-8', errors='replace')<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u901a\u8fc7\u6307\u5b9a\u9519\u8bef\u5904\u7406\u7b56\u7565\uff0c\u53ef\u4ee5\u907f\u514d\u7a0b\u5e8f\u56e0\u7f16\u7801\u9519\u8bef\u800c\u5d29\u6e83\u3002<\/p>\n<\/p>\n
2\u3001\u5e38\u89c1\u7f16\u7801\u9519\u8bef\u53ca\u89e3\u51b3\u65b9\u6848<\/h4>\n<\/p>\n
\u5e38\u89c1\u7684\u7f16\u7801\u9519\u8bef\u5305\u62ecUnicodeDecodeError<\/code>\u548cUnicodeEncodeError<\/code>\u3002\u89e3\u51b3\u8fd9\u4e9b\u9519\u8bef\u7684\u65b9\u6cd5\u5305\u62ec\uff1a<\/p>\n<\/p>\n