{"id":1057383,"date":"2024-12-31T15:07:41","date_gmt":"2024-12-31T07:07:41","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1057383.html"},"modified":"2024-12-31T15:07:43","modified_gmt":"2024-12-31T07:07:43","slug":"python%e7%88%ac%e8%99%ab%e5%85%a5%e9%97%a8%e6%95%99%e7%a8%8b%e6%95%99%e4%bd%a0%e5%a6%82%e4%bd%95%e5%ad%a6","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1057383.html","title":{"rendered":"python\u722c\u866b\u5165\u95e8\u6559\u7a0b\u6559\u4f60\u5982\u4f55\u5b66"},"content":{"rendered":"

\"python\u722c\u866b\u5165\u95e8\u6559\u7a0b\u6559\u4f60\u5982\u4f55\u5b66\"<\/p>\n

Python \u722c\u866b\u5165\u95e8\u6559\u7a0b\u7684\u5173\u952e\u5728\u4e8e\u4e86\u89e3\u57fa\u672c\u6982\u5ff5\u3001\u719f\u6089\u5e38\u7528\u5de5\u5177\u3001\u638c\u63e1\u6570\u636e\u89e3\u6790\u3001\u5904\u7406\u4e0e\u5b58\u50a8\uff0c\u638c\u63e1\u53cd\u722c\u866b\u673a\u5236\u3002<\/strong> \u5176\u4e2d\uff0c\u638c\u63e1\u53cd\u722c\u866b\u673a\u5236\u5c24\u4e3a\u91cd\u8981\u3002\u53cd\u722c\u866b\u673a\u5236\u662f\u6307\u7f51\u7ad9\u4e3a\u4e86\u9632\u6b62\u88ab\u6076\u610f\u722c\u53d6\uff0c\u6240\u91c7\u53d6\u7684\u4e00\u7cfb\u5217\u63aa\u65bd\uff0c\u5982\u9a8c\u8bc1\u7801\u3001IP\u5c01\u9501\u3001\u52a8\u6001\u5185\u5bb9\u52a0\u8f7d\u7b49\u3002\u4e86\u89e3\u8fd9\u4e9b\u673a\u5236\uff0c\u624d\u80fd\u66f4\u597d\u5730\u8bbe\u8ba1\u722c\u866b\u7a0b\u5e8f\uff0c\u63d0\u9ad8\u5176\u7a33\u5b9a\u6027\u548c\u6548\u7387\u3002<\/p>\n<\/p>\n

\n

\u4e00\u3001\u57fa\u672c\u6982\u5ff5<\/h2>\n<\/p>\n

\u4ec0\u4e48\u662f\u722c\u866b\uff1f<\/h3>\n<\/p>\n

\u7f51\u7edc\u722c\u866b\uff08Web Crawler\uff09\uff0c\u4e5f\u79f0\u4e3a\u7f51\u7edc\u8718\u86db\uff08Web Spider\uff09\uff0c\u662f\u4e00\u79cd\u7a0b\u5e8f\u6216\u811a\u672c\uff0c\u7528\u4e8e\u81ea\u52a8\u6d4f\u89c8\u7f51\u9875\u5e76\u63d0\u53d6\u6709\u7528\u4fe1\u606f\u3002\u722c\u866b\u5e7f\u6cdb\u5e94\u7528\u4e8e\u641c\u7d22\u5f15\u64ce\u3001\u6570\u636e\u6536\u96c6\u3001\u5e02\u573a\u5206\u6790\u7b49\u9886\u57df\u3002<\/p>\n<\/p>\n

\u722c\u866b\u7684\u5de5\u4f5c\u6d41\u7a0b<\/h3>\n<\/p>\n
    \n
  1. \u53d1\u9001\u8bf7\u6c42<\/strong>\uff1a\u5411\u76ee\u6807\u7f51\u7ad9\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3002<\/li>\n
  2. \u89e3\u6790\u6570\u636e<\/strong>\uff1a\u89e3\u6790\u7f51\u9875\u5185\u5bb9\uff0c\u63d0\u53d6\u6240\u9700\u6570\u636e\u3002<\/li>\n
  3. \u6570\u636e\u5b58\u50a8<\/strong>\uff1a\u5c06\u63d0\u53d6\u7684\u6570\u636e\u8fdb\u884c\u5b58\u50a8\uff0c\u4fbf\u4e8e\u540e\u7eed\u5206\u6790\u548c\u5904\u7406\u3002<\/li>\n<\/ol>\n

    \u4e8c\u3001\u5e38\u7528\u5de5\u5177<\/h2>\n<\/p>\n

    Requests\u5e93<\/h3>\n<\/p>\n

    Requests\u662fPython\u4e2d\u6700\u5e38\u7528\u7684HTTP\u5e93\u4e4b\u4e00\uff0c\u7b80\u5355\u6613\u7528\uff0c\u529f\u80fd\u5f3a\u5927\u3002\u901a\u8fc7Requests\u5e93\u53ef\u4ee5\u65b9\u4fbf\u5730\u53d1\u9001\u5404\u79cdHTTP\u8bf7\u6c42\uff0c\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3002<\/p>\n<\/p>\n

    import requests<\/p>\n
    response = requests.get('https:\/\/example.com')<\/p>\n
    print(response.text)<\/p>\n
    <\/code><\/pre>\n<\/p>\n
    BeautifulSoup\u5e93<\/h3>\n<\/p>\n
    BeautifulSoup\u662f\u4e00\u4e2a\u7528\u4e8e\u89e3\u6790HTML\u548cXML\u6587\u6863\u7684\u5e93\uff0c\u80fd\u591f\u65b9\u4fbf\u5730\u4ece\u7f51\u9875\u4e2d\u63d0\u53d6\u6570\u636e\u3002\u4e0eRequests\u5e93\u914d\u5408\u4f7f\u7528\uff0c\u53ef\u4ee5\u5feb\u901f\u5b9e\u73b0\u6570\u636e\u722c\u53d6\u3002<\/p>\n<\/p>\n
    from bs4 import BeautifulSoup<\/p>\n
    html = response.text<\/p>\n
    soup = BeautifulSoup(html, 'html.parser')<\/p>\n
    print(soup.title.text)<\/p>\n
    <\/code><\/pre>\n<\/p>\n
    Selenium\u5e93<\/h3>\n<\/p>\n
    Selenium\u662f\u4e00\u4e2a\u7528\u4e8eWeb\u5e94\u7528\u7a0b\u5e8f\u6d4b\u8bd5\u7684\u5de5\u5177\uff0c\u4e5f\u5e38\u7528\u4e8e\u722c\u53d6\u52a8\u6001\u52a0\u8f7d\u7684\u7f51\u9875\u5185\u5bb9\u3002\u901a\u8fc7\u6a21\u62df\u6d4f\u89c8\u5668\u64cd\u4f5c\uff0c\u53ef\u4ee5\u7ed5\u8fc7\u4e00\u4e9b\u53cd\u722c\u866b\u673a\u5236\u3002<\/p>\n<\/p>\n
    from selenium import webdriver<\/p>\n
    driver = webdriver.Chrome()<\/p>\n
    driver.get('https:\/\/example.com')<\/p>\n
    print(driver.page_source)<\/p>\n
    driver.quit()<\/p>\n
    <\/code><\/pre>\n<\/p>\n
    \u4e09\u3001\u6570\u636e\u89e3\u6790<\/h2>\n<\/p>\n
    HTML\u89e3\u6790<\/h3>\n<\/p>\n
    HTML\u89e3\u6790\u662f\u722c\u866b\u7684\u6838\u5fc3\u90e8\u5206\uff0c\u901a\u8fc7\u89e3\u6790HTML\u6587\u6863\u7ed3\u6784\uff0c\u63d0\u53d6\u6240\u9700\u6570\u636e\u3002\u5e38\u7528\u7684\u65b9\u6cd5\u5305\u62ec\uff1a<\/p>\n<\/p>\n
      \n
    • XPath<\/strong>\uff1a\u4e00\u79cd\u8def\u5f84\u8bed\u8a00\uff0c\u7528\u4e8e\u5728XML\u6587\u6863\u4e2d\u67e5\u627e\u8282\u70b9\u3002<\/li>\n
    • CSS\u9009\u62e9\u5668<\/strong>\uff1a\u4e00\u79cd\u4f7f\u7528CSS\u9009\u62e9\u5668\u8bed\u6cd5\u6765\u9009\u62e9HTML\u5143\u7d20\u7684\u65b9\u6cd5\u3002<\/li>\n<\/ul>\n
      # \u4f7f\u7528BeautifulSoup\u89e3\u6790HTML<\/p>\n
      soup = BeautifulSoup(html, 'html.parser')<\/p>\n
      data = soup.find_all('div', class_='example-class')<\/p>\n
      <\/code><\/pre>\n<\/p>\n
      JSON\u89e3\u6790<\/h3>\n<\/p>\n
      \u6709\u4e9b\u7f51\u7ad9\u8fd4\u56de\u7684\u6570\u636e\u662fJSON\u683c\u5f0f\uff0c\u9700\u8981\u5bf9JSON\u8fdb\u884c\u89e3\u6790\u3002Python\u81ea\u5e26\u7684json<\/code>\u5e93\u53ef\u4ee5\u65b9\u4fbf\u5730\u89e3\u6790JSON\u6570\u636e\u3002<\/p>\n<\/p>\n
      import json<\/p>\n
      response = requests.get('https:\/\/api.example.com\/data')<\/p>\n
      data = json.loads(response.text)<\/p>\n
      print(data)<\/p>\n
      <\/code><\/pre>\n<\/p>\n
      \u56db\u3001\u6570\u636e\u5904\u7406\u4e0e\u5b58\u50a8<\/h2>\n<\/p>\n
      \u6570\u636e\u5904\u7406<\/h3>\n<\/p>\n
      \u6570\u636e\u5904\u7406\u5305\u62ec\u6570\u636e\u6e05\u6d17\u3001\u683c\u5f0f\u8f6c\u6362\u3001\u6570\u636e\u7b5b\u9009\u7b49\u3002\u53ef\u4ee5\u4f7f\u7528Pandas\u5e93\u8fdb\u884c\u6570\u636e\u5904\u7406\uff0cPandas\u529f\u80fd\u5f3a\u5927\uff0c\u9002\u7528\u4e8e\u5404\u79cd\u6570\u636e\u5206\u6790\u4efb\u52a1\u3002<\/p>\n<\/p>\n
      import pandas as pd<\/p>\n
      data = {'name': ['Alice', 'Bob'], 'age': [25, 30]}<\/p>\n
      df = pd.DataFrame(data)<\/p>\n
      print(df)<\/p>\n
      <\/code><\/pre>\n<\/p>\n
      \u6570\u636e\u5b58\u50a8<\/h3>\n<\/p>\n
      \u722c\u53d6\u7684\u6570\u636e\u9700\u8981\u8fdb\u884c\u5b58\u50a8\uff0c\u5e38\u7528\u7684\u65b9\u6cd5\u5305\u62ec\uff1a<\/p>\n<\/p>\n
        \n
      • \u6587\u4ef6\u5b58\u50a8<\/strong>\uff1a\u5c06\u6570\u636e\u5b58\u50a8\u4e3aCSV\u3001JSON\u3001Excel\u7b49\u683c\u5f0f\u7684\u6587\u4ef6\u3002<\/li>\n
      • \u6570\u636e\u5e93\u5b58\u50a8<\/strong>\uff1a\u5c06\u6570\u636e\u5b58\u50a8\u5230\u6570\u636e\u5e93\u4e2d\uff0c\u5982MySQL\u3001MongoDB\u7b49\u3002<\/li>\n<\/ul>\n
        # \u5c06\u6570\u636e\u5b58\u50a8\u4e3aCSV\u6587\u4ef6<\/p>\n
        df.to_csv('data.csv', index=False)<\/p>\n
        \u5c06\u6570\u636e\u5b58\u50a8\u5230MySQL\u6570\u636e\u5e93<\/strong><\/h2>\n
        from sqlalchemy import create_engine<\/p>\n
        engine = create_engine('mysql+pymysql:\/\/user:password@host\/dbname')<\/p>\n
        df.to_sql('table_name', engine, index=False)<\/p>\n
        <\/code><\/pre>\n<\/p>\n
        \u4e94\u3001\u53cd\u722c\u866b\u673a\u5236<\/h2>\n<\/p>\n
        \u5e38\u89c1\u53cd\u722c\u866b\u673a\u5236<\/h3>\n<\/p>\n
          \n
        1. IP\u5c01\u9501<\/strong>\uff1a\u7f51\u7ad9\u4f1a\u6839\u636eIP\u5730\u5740\u9650\u5236\u8bbf\u95ee\u9891\u7387\uff0c\u8fc7\u9891\u7e41\u7684\u8bbf\u95ee\u4f1a\u5bfc\u81f4IP\u88ab\u5c01\u9501\u3002<\/li>\n
        2. \u9a8c\u8bc1\u7801<\/strong>\uff1a\u901a\u8fc7\u9a8c\u8bc1\u7801\u6765\u786e\u8ba4\u8bf7\u6c42\u662f\u7531\u4eba\u7c7b\u53d1\u8d77\u7684\uff0c\u800c\u4e0d\u662f\u7a0b\u5e8f\u3002<\/li>\n
        3. \u52a8\u6001\u5185\u5bb9\u52a0\u8f7d<\/strong>\uff1a\u901a\u8fc7JavaScript\u52a8\u6001\u52a0\u8f7d\u5185\u5bb9\uff0c\u589e\u52a0\u722c\u53d6\u96be\u5ea6\u3002<\/li>\n<\/ol>\n
          \u53cd\u53cd\u722c\u866b\u7b56\u7565<\/h3>\n<\/p>\n
            \n
          1. \u4f7f\u7528\u4ee3\u7406<\/strong>\uff1a\u901a\u8fc7\u4f7f\u7528\u4ee3\u7406IP\uff0c\u907f\u514dIP\u5c01\u9501\u3002<\/li>\n
          2. \u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a<\/strong>\uff1a\u4f7f\u7528Selenium\u7b49\u5de5\u5177\uff0c\u6a21\u62df\u771f\u5b9e\u7528\u6237\u7684\u6d4f\u89c8\u5668\u64cd\u4f5c\u3002<\/li>\n
          3. \u8bbe\u7f6e\u8bf7\u6c42\u5934<\/strong>\uff1a\u8bbe\u7f6e\u5408\u7406\u7684\u8bf7\u6c42\u5934\u4fe1\u606f\uff0c\u6a21\u62df\u771f\u5b9e\u7684\u6d4f\u89c8\u5668\u8bf7\u6c42\u3002<\/li>\n
          4. \u8bf7\u6c42\u95f4\u9694<\/strong>\uff1a\u8bbe\u7f6e\u5408\u9002\u7684\u8bf7\u6c42\u95f4\u9694\uff0c\u907f\u514d\u8fc7\u4e8e\u9891\u7e41\u7684\u8bf7\u6c42\u3002<\/li>\n<\/ol>\n
            # \u4f7f\u7528\u4ee3\u7406\u53d1\u9001\u8bf7\u6c42<\/p>\n
            proxies = {<\/p>\n
                'http': 'http:\/\/user:password@proxy.example.com:8080',<\/p>\n
                'https': 'http:\/\/user:password@proxy.example.com:8080',<\/p>\n
            }<\/p>\n
            response = requests.get('https:\/\/example.com', proxies=proxies)<\/p>\n
            <\/code><\/pre>\n<\/p>\n
            \n
            \u901a\u8fc7\u4ee5\u4e0a\u51e0\u4e2a\u65b9\u9762\u7684\u5b66\u4e60\u548c\u5b9e\u8df5\uff0c\u53ef\u4ee5\u5e2e\u52a9\u521d\u5b66\u8005\u5feb\u901f\u5165\u95e8Python\u722c\u866b\u3002\u722c\u866b\u6280\u672f\u65e2\u6709\u5e7f\u6cdb\u7684\u5e94\u7528\u524d\u666f\uff0c\u53c8\u5145\u6ee1\u6311\u6218\uff0c\u9700\u8981\u4e0d\u65ad\u5b66\u4e60\u548c\u63a2\u7d22\u3002\u5e0c\u671b\u672c\u6587\u80fd\u591f\u4e3a\u4f60\u7684\u722c\u866b\u5b66\u4e60\u4e4b\u8def\u63d0\u4f9b\u4e00\u4e9b\u5e2e\u52a9\u3002<\/p>\n<\/p>\n
            \u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
             \u5982\u4f55\u9009\u62e9\u5408\u9002\u7684Python\u722c\u866b\u6846\u67b6\uff1f<\/strong>
            \u5728\u5b66\u4e60Python\u722c\u866b\u65f6\uff0c\u6709\u591a\u4e2a\u6846\u67b6\u53ef\u4f9b\u9009\u62e9\uff0c\u6bd4\u5982Scrapy\u3001Beautiful Soup\u548cRequests\u7b49\u3002\u9009\u62e9\u5408\u9002\u7684\u6846\u67b6\u53d6\u51b3\u4e8e\u4f60\u7684\u9879\u76ee\u9700\u6c42\u3002Scrapy\u9002\u5408\u5904\u7406\u5927\u578b\u9879\u76ee\uff0c\u5177\u6709\u5f3a\u5927\u7684\u529f\u80fd\u548c\u6269\u5c55\u6027\uff1bBeautiful Soup\u5219\u9002\u5408\u4e8e\u89e3\u6790HTML\u548cXML\u6587\u6863\uff0c\u4f7f\u7528\u7b80\u5355\uff1b\u800cRequests\u5219\u66f4\u4fa7\u91cd\u4e8e\u53d1\u9001\u7f51\u7edc\u8bf7\u6c42\uff0c\u9002\u5408\u5c0f\u578b\u722c\u866b\u3002\u4e86\u89e3\u5404\u4e2a\u6846\u67b6\u7684\u7279\u6027\uff0c\u80fd\u5e2e\u52a9\u4f60\u66f4\u9ad8\u6548\u5730\u8fdb\u884c\u722c\u866b\u5f00\u53d1\u3002<\/p>\n
            \u5b66\u4e60Python\u722c\u866b\u9700\u8981\u638c\u63e1\u54ea\u4e9b\u57fa\u7840\u77e5\u8bc6\uff1f<\/strong>
            \u5728\u5f00\u59cb\u5b66\u4e60Python\u722c\u866b\u4e4b\u524d\uff0c\u4f60\u9700\u8981\u5177\u5907\u4e00\u5b9a\u7684Python\u7f16\u7a0b\u57fa\u7840\u3002\u4e86\u89e3\u57fa\u672c\u7684\u8bed\u6cd5\u3001\u6570\u636e\u7ed3\u6784\uff08\u5982\u5217\u8868\u3001\u5b57\u5178\u7b49\uff09\u4ee5\u53ca\u51fd\u6570\u7684\u4f7f\u7528\u662f\u975e\u5e38\u5fc5\u8981\u7684\u3002\u6b64\u5916\uff0c\u719f\u6089HTML\u548cCSS\u7684\u57fa\u672c\u77e5\u8bc6\uff0c\u80fd\u591f\u5e2e\u52a9\u4f60\u66f4\u597d\u5730\u89e3\u6790\u7f51\u9875\u5185\u5bb9\u3002\u7f51\u7edc\u534f\u8bae\uff08\u5982HTTP\uff09\u548c\u8bf7\u6c42\/\u54cd\u5e94\u7684\u5de5\u4f5c\u539f\u7406\u4e5f\u662f\u503c\u5f97\u638c\u63e1\u7684\u6838\u5fc3\u5185\u5bb9\u3002<\/p>\n
            \u722c\u866b\u5f00\u53d1\u4e2d\u5e38\u89c1\u7684\u9519\u8bef\u6709\u54ea\u4e9b\uff0c\u5982\u4f55\u907f\u514d\uff1f<\/strong>
            \u5728\u8fdb\u884c\u722c\u866b\u5f00\u53d1\u65f6\uff0c\u5e38\u89c1\u7684\u9519\u8bef\u5305\u62ec\u53cd\u722c\u673a\u5236\u5bfc\u81f4\u7684\u8bf7\u6c42\u5931\u8d25\u3001\u6570\u636e\u89e3\u6790\u9519\u8bef\u4ee5\u53ca\u6570\u636e\u5b58\u50a8\u95ee\u9898\u3002\u4e3a\u907f\u514d\u8fd9\u4e9b\u95ee\u9898\uff0c\u53ef\u4ee5\u901a\u8fc7\u8bbe\u7f6e\u9002\u5f53\u7684\u8bf7\u6c42\u5934\u3001\u4f7f\u7528\u4ee3\u7406IP\u4ee5\u53ca\u5408\u7406\u63a7\u5236\u8bf7\u6c42\u9891\u7387\u6765\u89c4\u907f\u53cd\u722c\u673a\u5236\u3002\u540c\u65f6\uff0c\u786e\u4fdd\u4f7f\u7528\u6b63\u786e\u7684\u89e3\u6790\u65b9\u6cd5\u6765\u5904\u7406\u7f51\u9875\u6570\u636e\uff0c\u6ce8\u610f\u68c0\u67e5\u6570\u636e\u5b58\u50a8\u7684\u683c\u5f0f\u548c\u8def\u5f84\uff0c\u80fd\u6709\u6548\u51cf\u5c11\u9519\u8bef\u7684\u53d1\u751f\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python \u722c\u866b\u5165\u95e8\u6559\u7a0b\u7684\u5173\u952e\u5728\u4e8e\u4e86\u89e3\u57fa\u672c\u6982\u5ff5\u3001\u719f\u6089\u5e38\u7528\u5de5\u5177\u3001\u638c\u63e1\u6570\u636e\u89e3\u6790\u3001\u5904\u7406\u4e0e\u5b58\u50a8\uff0c\u638c\u63e1\u53cd\u722c\u866b\u673a\u5236\u3002 \u5176 […]","protected":false},"author":3,"featured_media":1057403,"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\/1057383"}],"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=1057383"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1057383\/revisions"}],"predecessor-version":[{"id":1057406,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1057383\/revisions\/1057406"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1057403"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1057383"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1057383"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1057383"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}