{"id":1100132,"date":"2025-01-08T15:37:17","date_gmt":"2025-01-08T07:37:17","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1100132.html"},"modified":"2025-01-08T15:37:19","modified_gmt":"2025-01-08T07:37:19","slug":"python%e5%a6%82%e4%bd%95%e5%b0%86%e7%9c%81%e5%b8%82%e5%8c%ba%e6%8b%86%e5%88%86-2","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1100132.html","title":{"rendered":"python\u5982\u4f55\u5c06\u7701\u5e02\u533a\u62c6\u5206"},"content":{"rendered":"

\"python\u5982\u4f55\u5c06\u7701\u5e02\u533a\u62c6\u5206\"<\/p>\n

Python\u5c06\u7701\u5e02\u533a\u62c6\u5206\u4e3b\u8981\u6709\u4ee5\u4e0b\u51e0\u79cd\u65b9\u6cd5\uff1a\u5229\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u3001\u4f7f\u7528\u4e2d\u6587\u5206\u8bcd\u5de5\u5177\u3001\u53c2\u8003\u7701\u5e02\u533a\u6570\u636e\u5b57\u5178<\/strong>\u3002\u4e0b\u9762\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u5229\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u7684\u65b9\u6cd5\u3002<\/p>\n<\/p>\n

\u5728\u5904\u7406\u7701\u5e02\u533a\u4fe1\u606f\u65f6\uff0c\u6700\u5e38\u89c1\u7684\u9700\u6c42\u4e4b\u4e00\u662f\u5c06\u4e00\u4e2a\u5b8c\u6574\u7684\u5730\u5740\u62c6\u5206\u6210\u7701\u3001\u5e02\u3001\u533a\u4e09\u4e2a\u90e8\u5206\u3002\u5229\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u53ef\u4ee5\u9ad8\u6548\u5730\u5b8c\u6210\u8fd9\u4e00\u4efb\u52a1<\/strong>\uff0c\u56e0\u4e3a\u6b63\u5219\u8868\u8fbe\u5f0f\u80fd\u591f\u7075\u6d3b\u5730\u5339\u914d\u6587\u672c\u6a21\u5f0f\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u6765\u62c6\u5206\u7701\u5e02\u533a\u4fe1\u606f\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u6b63\u5219\u8868\u8fbe\u5f0f\u65b9\u6cd5<\/h3>\n<\/p>\n

\u6b63\u5219\u8868\u8fbe\u5f0f\u662f\u4e00\u79cd\u5f3a\u5927\u7684\u5de5\u5177\uff0c\u80fd\u591f\u7528\u6765\u5339\u914d\u590d\u6742\u7684\u6587\u672c\u6a21\u5f0f<\/strong>\u3002\u5728Python\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528re<\/code>\u6a21\u5757\u6765\u5904\u7406\u6b63\u5219\u8868\u8fbe\u5f0f\u3002<\/p>\n<\/p>\n

1\u3001\u5bfc\u5165\u6240\u9700\u6a21\u5757<\/h4>\n<\/p>\n

\u9996\u5148\uff0c\u9700\u8981\u5bfc\u5165Python\u7684re<\/code>\u6a21\u5757\uff0c\u8be5\u6a21\u5757\u63d0\u4f9b\u4e86\u652f\u6301\u6b63\u5219\u8868\u8fbe\u5f0f\u7684\u51fd\u6570\u3002<\/p>\n<\/p>\n

import re<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u5b9a\u4e49\u6b63\u5219\u8868\u8fbe\u5f0f\u6a21\u5f0f<\/h4>\n<\/p>\n
\u5b9a\u4e49\u4e00\u4e2a\u6b63\u5219\u8868\u8fbe\u5f0f\u6a21\u5f0f\uff0c\u7528\u4e8e\u5339\u914d\u7701\u3001\u5e02\u3001\u533a\u4fe1\u606f\u3002\u5047\u8bbe\u6211\u4eec\u6709\u4e00\u4e2a\u5305\u542b\u7701\u5e02\u533a\u7684\u5b57\u7b26\u4e32\uff0c\u4f8b\u5982\uff1a"\u5e7f\u4e1c\u7701\u5e7f\u5dde\u5e02\u5929\u6cb3\u533a"\uff0c\u6211\u4eec\u53ef\u4ee5\u5b9a\u4e49\u5982\u4e0b\u7684\u6b63\u5219\u8868\u8fbe\u5f0f\uff1a<\/p>\n<\/p>\n
pattern = re.compile(r'(?P<province>[^\u7701]+\u7701|[^\u81ea\u6cbb\u533a]+\u81ea\u6cbb\u533a|[^\u5e02]+\u5e02|[^\u7279\u522b\u884c\u653f\u533a]+\u7279\u522b\u884c\u653f\u533a)(?P<city>[^\u5e02]+\u5e02|[^\u5730\u533a]+\u5730\u533a|[^\u76df]+\u76df)(?P<district>[^\u533a]+\u533a|[^\u53bf]+\u53bf|[^\u65d7]+\u65d7|[^\u5e02]+\u5e02|[^\u9547]+\u9547)')<\/p>\n
<\/code><\/pre>\n<\/p>\n
3\u3001\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u5339\u914d\u5e76\u62c6\u5206<\/h4>\n<\/p>\n
\u4f7f\u7528re.match<\/code>\u65b9\u6cd5\u5bf9\u5730\u5740\u5b57\u7b26\u4e32\u8fdb\u884c\u5339\u914d\uff0c\u5e76\u63d0\u53d6\u7701\u3001\u5e02\u3001\u533a\u4fe1\u606f\u3002<\/p>\n<\/p>\n
address = "\u5e7f\u4e1c\u7701\u5e7f\u5dde\u5e02\u5929\u6cb3\u533a"<\/p>\n
match = pattern.match(address)<\/p>\n
if match:<\/p>\n
    province = match.group('province')<\/p>\n
    city = match.group('city')<\/p>\n
    district = match.group('district')<\/p>\n
    print(f"\u7701: {province}, \u5e02: {city}, \u533a: {district}")<\/p>\n
else:<\/p>\n
    print("\u5730\u5740\u683c\u5f0f\u4e0d\u6b63\u786e")<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e0a\u8ff0\u4ee3\u7801\u5c06\u4f1a\u8f93\u51fa\uff1a<\/strong><\/p>\n<\/p>\n
\u7701: \u5e7f\u4e1c\u7701, \u5e02: \u5e7f\u5dde\u5e02, \u533a: \u5929\u6cb3\u533a<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e8c\u3001\u4e2d\u6587\u5206\u8bcd\u5de5\u5177<\/h3>\n<\/p>\n
\u4e2d\u6587\u5206\u8bcd\u5de5\u5177\uff0c\u4f8b\u5982Jieba\uff0c\u4e5f\u53ef\u4ee5\u7528\u4e8e\u5c06\u7701\u5e02\u533a\u4fe1\u606f\u62c6\u5206<\/strong>\u3002Jieba\u662f\u4e00\u6b3e\u975e\u5e38\u6d41\u884c\u7684\u4e2d\u6587\u5206\u8bcd\u5de5\u5177\uff0c\u80fd\u591f\u9ad8\u6548\u5730\u5904\u7406\u4e2d\u6587\u6587\u672c\u3002<\/p>\n<\/p>\n
1\u3001\u5b89\u88c5Jieba<\/h4>\n<\/p>\n
\u9996\u5148\uff0c\u9700\u8981\u5b89\u88c5Jieba\u5e93\uff0c\u53ef\u4ee5\u4f7f\u7528pip\u8fdb\u884c\u5b89\u88c5\uff1a<\/p>\n<\/p>\n
pip install jieba<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u4f7f\u7528Jieba\u8fdb\u884c\u5206\u8bcd<\/h4>\n<\/p>\n
\u4f7f\u7528Jieba\u8fdb\u884c\u5206\u8bcd\uff0c\u5e76\u4ece\u5206\u8bcd\u7ed3\u679c\u4e2d\u63d0\u53d6\u7701\u3001\u5e02\u3001\u533a\u4fe1\u606f\u3002<\/p>\n<\/p>\n
import jieba<\/p>\n
address = "\u5e7f\u4e1c\u7701\u5e7f\u5dde\u5e02\u5929\u6cb3\u533a"<\/p>\n
seg_list = jieba.cut(address)<\/p>\n
\u5c06\u5206\u8bcd\u7ed3\u679c\u8f6c\u6362\u4e3a\u5217\u8868<\/strong><\/h2>\n
words = list(seg_list)<\/p>\n
print(words)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e0a\u8ff0\u4ee3\u7801\u5c06\u4f1a\u8f93\u51fa\uff1a<\/strong><\/p>\n<\/p>\n
['\u5e7f\u4e1c\u7701', '\u5e7f\u5dde\u5e02', '\u5929\u6cb3\u533a']<\/p>\n
<\/code><\/pre>\n<\/p>\n
3\u3001\u63d0\u53d6\u7701\u3001\u5e02\u3001\u533a\u4fe1\u606f<\/h4>\n<\/p>\n
\u63d0\u53d6\u5206\u8bcd\u7ed3\u679c\u4e2d\u7684\u7701\u3001\u5e02\u3001\u533a\u4fe1\u606f\uff1a<\/p>\n<\/p>\n
province = words[0] if len(words) > 0 else ""<\/p>\n
city = words[1] if len(words) > 1 else ""<\/p>\n
district = words[2] if len(words) > 2 else ""<\/p>\n
print(f"\u7701: {province}, \u5e02: {city}, \u533a: {district}")<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e0a\u8ff0\u4ee3\u7801\u5c06\u4f1a\u8f93\u51fa\uff1a<\/strong><\/p>\n<\/p>\n
\u7701: \u5e7f\u4e1c\u7701, \u5e02: \u5e7f\u5dde\u5e02, \u533a: \u5929\u6cb3\u533a<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e09\u3001\u53c2\u8003\u7701\u5e02\u533a\u6570\u636e\u5b57\u5178<\/h3>\n<\/p>\n
\u4f7f\u7528\u7701\u5e02\u533a\u6570\u636e\u5b57\u5178\u53ef\u4ee5\u7cbe\u786e\u5730\u5c06\u5730\u5740\u62c6\u5206\u6210\u7701\u3001\u5e02\u3001\u533a<\/strong>\u3002\u8fd9\u79cd\u65b9\u6cd5\u9700\u8981\u4e00\u4e2a\u5305\u542b\u6240\u6709\u7701\u3001\u5e02\u3001\u533a\u4fe1\u606f\u7684\u6570\u636e\u5b57\u5178\u3002<\/p>\n<\/p>\n
1\u3001\u51c6\u5907\u7701\u5e02\u533a\u6570\u636e\u5b57\u5178<\/h4>\n<\/p>\n
\u53ef\u4ee5\u4ece\u7f51\u4e0a\u4e0b\u8f7d\u6216\u81ea\u5df1\u6574\u7406\u4e00\u4e2a\u5305\u542b\u6240\u6709\u7701\u3001\u5e02\u3001\u533a\u4fe1\u606f\u7684\u6570\u636e\u5b57\u5178\uff0c\u4f8b\u5982\uff1a<\/p>\n<\/p>\n
province_city_district = {<\/p>\n
    "\u5e7f\u4e1c\u7701": {<\/p>\n
        "\u5e7f\u5dde\u5e02": ["\u5929\u6cb3\u533a", "\u8d8a\u79c0\u533a", "\u6d77\u73e0\u533a", ...],<\/p>\n
        "\u6df1\u5733\u5e02": ["\u5357\u5c71\u533a", "\u798f\u7530\u533a", "\u7f57\u6e56\u533a", ...],<\/p>\n
        ...<\/p>\n
    },<\/p>\n
    ...<\/p>\n
}<\/p>\n
<\/code><\/pre>\n<\/p>\n
2\u3001\u904d\u5386\u6570\u636e\u5b57\u5178\u8fdb\u884c\u5339\u914d<\/h4>\n<\/p>\n
\u904d\u5386\u6570\u636e\u5b57\u5178\uff0c\u627e\u5230\u5339\u914d\u7684\u7701\u3001\u5e02\u3001\u533a\u4fe1\u606f\u3002<\/p>\n<\/p>\n
address = "\u5e7f\u4e1c\u7701\u5e7f\u5dde\u5e02\u5929\u6cb3\u533a"<\/p>\n
province = ""<\/p>\n
city = ""<\/p>\n
district = ""<\/p>\n
for p, cities in province_city_district.items():<\/p>\n
    if address.startswith(p):<\/p>\n
        province = p<\/p>\n
        address = address[len(p):]<\/p>\n
        for c, districts in cities.items():<\/p>\n
            if address.startswith(c):<\/p>\n
                city = c<\/p>\n
                address = address[len(c):]<\/p>\n
                for d in districts:<\/p>\n
                    if address.startswith(d):<\/p>\n
                        district = d<\/p>\n
                        break<\/p>\n
                break<\/p>\n
        break<\/p>\n
print(f"\u7701: {province}, \u5e02: {city}, \u533a: {district}")<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e0a\u8ff0\u4ee3\u7801\u5c06\u4f1a\u8f93\u51fa\uff1a<\/strong><\/p>\n<\/p>\n
\u7701: \u5e7f\u4e1c\u7701, \u5e02: \u5e7f\u5dde\u5e02, \u533a: \u5929\u6cb3\u533a<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u56db\u3001\u603b\u7ed3<\/h3>\n<\/p>\n
\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u3001\u4e2d\u6587\u5206\u8bcd\u5de5\u5177\u548c\u7701\u5e02\u533a\u6570\u636e\u5b57\u5178\u90fd\u662f\u62c6\u5206\u7701\u5e02\u533a\u4fe1\u606f\u7684\u6709\u6548\u65b9\u6cd5<\/strong>\u3002\u9009\u62e9\u54ea\u79cd\u65b9\u6cd5\u53d6\u51b3\u4e8e\u5177\u4f53\u7684\u9700\u6c42\u548c\u6570\u636e\u683c\u5f0f\u3002\u5982\u679c\u5730\u5740\u683c\u5f0f\u8f83\u4e3a\u89c4\u8303\uff0c\u6b63\u5219\u8868\u8fbe\u5f0f\u662f\u4e00\u4e2a\u9ad8\u6548\u7684\u9009\u62e9\uff1b\u5982\u679c\u9700\u8981\u5904\u7406\u4e0d\u89c4\u8303\u7684\u5730\u5740\uff0c\u4e2d\u6587\u5206\u8bcd\u5de5\u5177\u53ef\u80fd\u66f4\u4e3a\u5408\u9002\uff1b\u5982\u679c\u9700\u8981\u7cbe\u786e\u5339\u914d\uff0c\u4f7f\u7528\u7701\u5e02\u533a\u6570\u636e\u5b57\u5178\u662f\u6700\u4f73\u9009\u62e9\u3002<\/p>\n<\/p>\n
\u5e0c\u671b\u4ee5\u4e0a\u5185\u5bb9\u5bf9\u60a8\u6709\u6240\u5e2e\u52a9\uff01<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u5982\u4f55\u5728Python\u4e2d\u5c06\u7701\u5e02\u533a\u4fe1\u606f\u62c6\u5206\u6210\u72ec\u7acb\u7684\u90e8\u5206\uff1f<\/strong>
\u5728Python\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528\u5b57\u7b26\u4e32\u7684split()\u65b9\u6cd5\u6765\u62c6\u5206\u7701\u5e02\u533a\u4fe1\u606f\u3002\u901a\u5e38\u60c5\u51b5\u4e0b\uff0c\u7701\u5e02\u533a\u4fe1\u606f\u662f\u4ee5\u7279\u5b9a\u7684\u5206\u9694\u7b26\uff08\u5982\u9017\u53f7\u3001\u7a7a\u683c\u6216\u201c\/\u201d\uff09\u8fde\u63a5\u7684\u3002\u4f8b\u5982\uff0c\u82e5\u6709\u5b57\u7b26\u4e32\u201c\u5e7f\u4e1c\u7701\/\u5e7f\u5dde\u5e02\/\u5929\u6cb3\u533a\u201d\uff0c\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u4ee3\u7801\u5c06\u5176\u62c6\u5206\u4e3a\u5217\u8868\uff1a  <\/p>\n
address = "\u5e7f\u4e1c\u7701\/\u5e7f\u5dde\u5e02\/\u5929\u6cb3\u533a"\nparts = address.split("\/")\nprint(parts)  # \u8f93\u51fa: ['\u5e7f\u4e1c\u7701', '\u5e7f\u5dde\u5e02', '\u5929\u6cb3\u533a']\n<\/code><\/pre>\n
\u8fd9\u6837\u5c31\u53ef\u4ee5\u5c06\u7701\u5e02\u533a\u4fe1\u606f\u62c6\u5206\u4e3a\u72ec\u7acb\u7684\u90e8\u5206\uff0c\u4ee5\u4fbf\u8fdb\u884c\u8fdb\u4e00\u6b65\u5904\u7406\u3002<\/p>\n
\u5728\u5904\u7406\u7701\u5e02\u533a\u6570\u636e\u65f6\uff0c\u5982\u4f55\u786e\u4fdd\u6570\u636e\u7684\u51c6\u786e\u6027\uff1f<\/strong>
\u786e\u4fdd\u6570\u636e\u51c6\u786e\u6027\u7684\u65b9\u6cd5\u5305\u62ec\uff1a\u4f7f\u7528\u6807\u51c6\u5316\u7684\u6570\u636e\u6e90\u3001\u9a8c\u8bc1\u6570\u636e\u683c\u5f0f\u3001\u4ee5\u53ca\u5bf9\u6570\u636e\u8fdb\u884c\u6e05\u6d17\u3002\u5728\u62c6\u5206\u7701\u5e02\u533a\u6570\u636e\u4e4b\u524d\uff0c\u53ef\u4ee5\u5148\u68c0\u67e5\u6570\u636e\u662f\u5426\u7b26\u5408\u9884\u671f\u683c\u5f0f\uff0c\u5e76\u53bb\u9664\u591a\u4f59\u7684\u7a7a\u683c\u6216\u7279\u6b8a\u5b57\u7b26\u3002\u6b64\u5916\uff0c\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u4e5f\u53ef\u4ee5\u5e2e\u52a9\u9a8c\u8bc1\u548c\u63d0\u53d6\u7279\u5b9a\u683c\u5f0f\u7684\u6570\u636e\u3002<\/p>\n
\u62c6\u5206\u7701\u5e02\u533a\u540e\uff0c\u5982\u4f55\u5c06\u5176\u5b58\u50a8\u5230\u5b57\u5178\u6216\u5176\u4ed6\u6570\u636e\u7ed3\u6784\u4e2d\uff1f<\/strong>
\u53ef\u4ee5\u5c06\u62c6\u5206\u540e\u7684\u7701\u5e02\u533a\u4fe1\u606f\u5b58\u50a8\u5230\u5b57\u5178\u4e2d\uff0c\u4ee5\u4fbf\u4e8e\u540e\u7eed\u7684\u8bbf\u95ee\u548c\u7ba1\u7406\u3002\u4ee5\u4e0b\u793a\u4f8b\u5c55\u793a\u4e86\u5982\u4f55\u5c06\u62c6\u5206\u540e\u7684\u7ed3\u679c\u5b58\u50a8\u5728\u5b57\u5178\u4e2d\uff1a  <\/p>\n
address = "\u5e7f\u4e1c\u7701\/\u5e7f\u5dde\u5e02\/\u5929\u6cb3\u533a"\nparts = address.split("\/")\naddress_dict = {\n    "province": parts[0],\n    "city": parts[1],\n    "district": parts[2]\n}\nprint(address_dict)  # \u8f93\u51fa: {'province': '\u5e7f\u4e1c\u7701', 'city': '\u5e7f\u5dde\u5e02', 'district': '\u5929\u6cb3\u533a'}\n<\/code><\/pre>\n
\u8fd9\u79cd\u65b9\u5f0f\u65b9\u4fbf\u5bf9\u5404\u4e2a\u90e8\u5206\u8fdb\u884c\u8bbf\u95ee\u548c\u64cd\u4f5c\uff0c\u6709\u52a9\u4e8e\u540e\u7eed\u6570\u636e\u5904\u7406\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u5c06\u7701\u5e02\u533a\u62c6\u5206\u4e3b\u8981\u6709\u4ee5\u4e0b\u51e0\u79cd\u65b9\u6cd5\uff1a\u5229\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u3001\u4f7f\u7528\u4e2d\u6587\u5206\u8bcd\u5de5\u5177\u3001\u53c2\u8003\u7701\u5e02\u533a\u6570\u636e\u5b57\u5178\u3002\u4e0b\u9762\u5c06\u8be6\u7ec6\u4ecb […]","protected":false},"author":3,"featured_media":1100144,"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\/1100132"}],"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=1100132"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1100132\/revisions"}],"predecessor-version":[{"id":1100148,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1100132\/revisions\/1100148"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1100144"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1100132"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1100132"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1100132"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}