{"id":1150078,"date":"2025-01-13T16:57:17","date_gmt":"2025-01-13T08:57:17","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1150078.html"},"modified":"2025-01-13T16:57:20","modified_gmt":"2025-01-13T08:57:20","slug":"python%e5%a6%82%e4%bd%95%e5%ae%9e%e7%8e%b0%e7%bd%91%e9%a1%b5%e6%8a%93%e5%8f%96","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1150078.html","title":{"rendered":"python\u5982\u4f55\u5b9e\u73b0\u7f51\u9875\u6293\u53d6"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/25180636\/0c44fe69-31ad-46d6-bc92-02678569150a.webp\" alt=\"python\u5982\u4f55\u5b9e\u73b0\u7f51\u9875\u6293\u53d6\" \/><\/p>\n<p><p> <strong>Python\u5b9e\u73b0\u7f51\u9875\u6293\u53d6\u7684\u4e3b\u8981\u65b9\u6cd5\u6709\uff1a\u4f7f\u7528requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u3001\u4f7f\u7528Selenium\u8fdb\u884c\u52a8\u6001\u7f51\u9875\u6293\u53d6\u3002<\/strong> \u5176\u4e2d\uff0c<strong>\u4f7f\u7528requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9<\/strong>\u662f\u6700\u5e38\u89c1\u7684\u4e00\u79cd\u65b9\u6cd5\u3002<\/p>\n<\/p>\n<p><p>\u4f7f\u7528requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff1a<\/p>\n<\/p>\n<ol>\n<li>\u53d1\u9001HTTP\u8bf7\u6c42\u5e76\u83b7\u53d6\u54cd\u5e94\u5185\u5bb9\u3002<\/li>\n<li>\u89e3\u6790\u54cd\u5e94\u5185\u5bb9\uff0c\u63d0\u53d6\u6240\u9700\u6570\u636e\u3002<\/li>\n<li>\u5904\u7406\u5f02\u5e38\u548c\u9519\u8bef\uff0c\u4fdd\u8bc1\u7a0b\u5e8f\u7a33\u5b9a\u6027\u3002<\/li>\n<\/ol>\n<p><p>\u8be6\u7ec6\u63cf\u8ff0\uff1a<\/p>\n<p>\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u5e76\u83b7\u53d6\u54cd\u5e94\u5185\u5bb9\u662f\u4e00\u79cd\u7b80\u5355\u6709\u6548\u7684\u65b9\u6cd5\u3002\u9996\u5148\uff0c\u5b89\u88c5requests\u5e93\uff08<code>pip install requests<\/code>\uff09\uff0c\u7136\u540e\u4f7f\u7528<code>requests.get(url)<\/code>\u65b9\u6cd5\u53d1\u9001\u8bf7\u6c42\uff0c\u83b7\u53d6\u54cd\u5e94\u5bf9\u8c61\u3002\u53ef\u4ee5\u901a\u8fc7<code>response.content<\/code>\u6216<code>response.text<\/code>\u6765\u83b7\u53d6\u7f51\u9875\u7684\u5185\u5bb9\u3002\u63a5\u4e0b\u6765\uff0c\u53ef\u4ee5\u4f7f\u7528BeautifulSoup\u6216\u5176\u4ed6HTML\u89e3\u6790\u5e93\u89e3\u6790\u54cd\u5e94\u5185\u5bb9\uff0c\u63d0\u53d6\u6240\u9700\u7684\u6570\u636e\u3002\u5904\u7406\u8fc7\u7a0b\u4e2d\uff0c\u8fd8\u9700\u8981\u6ce8\u610f\u5904\u7406\u5f02\u5e38\u548c\u9519\u8bef\uff0c\u786e\u4fdd\u7a0b\u5e8f\u7684\u7a33\u5b9a\u6027\u3002<\/p>\n<\/p>\n<p><p>\u4e0b\u9762\u6211\u4eec\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u5b9e\u73b0\u7f51\u9875\u6293\u53d6\u7684\u5404\u4e2a\u6b65\u9aa4\u548c\u65b9\u6cd5\u3002<\/p>\n<\/p>\n<p><h3>\u4e00\u3001\u5b89\u88c5\u548c\u914d\u7f6e<\/h3>\n<\/p>\n<p><p>\u5728\u5f00\u59cb\u8fdb\u884c\u7f51\u9875\u6293\u53d6\u4e4b\u524d\uff0c\u9700\u8981\u5b89\u88c5\u4e00\u4e9bPython\u5e93\uff0c\u8fd9\u4e9b\u5e93\u5c06\u5728\u6574\u4e2a\u8fc7\u7a0b\u4e2d\u53d1\u6325\u91cd\u8981\u4f5c\u7528\u3002\u4e3b\u8981\u5305\u62ec\uff1arequests\u3001BeautifulSoup\u548cSelenium\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install requests<\/p>\n<p>pip install beautifulsoup4<\/p>\n<p>pip install selenium<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e8c\u3001\u4f7f\u7528requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9<\/h3>\n<\/p>\n<p><h4>1\u3001\u53d1\u9001HTTP\u8bf7\u6c42<\/h4>\n<\/p>\n<p><p>\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u975e\u5e38\u7b80\u5355\uff0c\u53ea\u9700\u51e0\u884c\u4ee3\u7801\u5373\u53ef\u5b8c\u6210\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>url = &#39;http:\/\/example.com&#39;<\/p>\n<p>response = requests.get(url)<\/p>\n<p>print(response.status_code)  # \u8f93\u51fa\u54cd\u5e94\u72b6\u6001\u7801<\/p>\n<p>print(response.content)  # \u8f93\u51fa\u7f51\u9875\u5185\u5bb9<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u6bb5\u4ee3\u7801\u53d1\u9001\u4e00\u4e2aGET\u8bf7\u6c42\u5230\u6307\u5b9a\u7684URL\uff0c\u5e76\u8f93\u51fa\u54cd\u5e94\u72b6\u6001\u7801\u548c\u7f51\u9875\u5185\u5bb9\u3002\u72b6\u6001\u7801200\u8868\u793a\u8bf7\u6c42\u6210\u529f\uff0c\u5176\u4ed6\u72b6\u6001\u7801\u5219\u8868\u793a\u8bf7\u6c42\u5931\u8d25\u6216\u6709\u5176\u4ed6\u95ee\u9898\u3002<\/p>\n<\/p>\n<p><h4>2\u3001\u5904\u7406\u54cd\u5e94\u5185\u5bb9<\/h4>\n<\/p>\n<p><p>\u83b7\u53d6\u5230\u7f51\u9875\u5185\u5bb9\u540e\uff0c\u53ef\u4ee5\u4f7f\u7528BeautifulSoup\u8fdb\u884c\u89e3\u6790\u3002BeautifulSoup\u662f\u4e00\u4e2a\u975e\u5e38\u5f3a\u5927\u7684HTML\u89e3\u6790\u5e93\uff0c\u652f\u6301\u591a\u79cd\u89e3\u6790\u5668\uff0c\u4f8b\u5982lxml\u548chtml.parser\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from bs4 import BeautifulSoup<\/p>\n<p>soup = BeautifulSoup(response.content, &#39;html.parser&#39;)<\/p>\n<p>print(soup.prettify())  # \u8f93\u51fa\u683c\u5f0f\u5316\u540e\u7684HTML<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u6bb5\u4ee3\u7801\u5c06\u7f51\u9875\u5185\u5bb9\u4f20\u9012\u7ed9BeautifulSoup\uff0c\u5e76\u4f7f\u7528html.parser\u89e3\u6790\u5668\u8fdb\u884c\u89e3\u6790\u3002<code>soup.prettify()<\/code>\u65b9\u6cd5\u53ef\u4ee5\u683c\u5f0f\u5316\u8f93\u51faHTML\uff0c\u4fbf\u4e8e\u9605\u8bfb\u3002<\/p>\n<\/p>\n<p><h4>3\u3001\u63d0\u53d6\u6570\u636e<\/h4>\n<\/p>\n<p><p>\u89e3\u6790HTML\u540e\uff0c\u53ef\u4ee5\u4f7f\u7528BeautifulSoup\u63d0\u4f9b\u7684\u5404\u79cd\u65b9\u6cd5\u548c\u5c5e\u6027\u6765\u63d0\u53d6\u6570\u636e\u3002\u4f8b\u5982\uff0c\u67e5\u627e\u6240\u6709\u7684\u94fe\u63a5\uff08a\u6807\u7b7e\uff09\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">for link in soup.find_all(&#39;a&#39;):<\/p>\n<p>    print(link.get(&#39;href&#39;))<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u6bb5\u4ee3\u7801\u67e5\u627e\u7f51\u9875\u4e2d\u6240\u6709\u7684a\u6807\u7b7e\uff0c\u5e76\u8f93\u51fa\u5b83\u4eec\u7684href\u5c5e\u6027\u503c\u3002<\/p>\n<\/p>\n<p><h3>\u4e09\u3001\u5904\u7406\u5f02\u5e38\u548c\u9519\u8bef<\/h3>\n<\/p>\n<p><p>\u5728\u8fdb\u884c\u7f51\u9875\u6293\u53d6\u65f6\uff0c\u53ef\u80fd\u4f1a\u9047\u5230\u5404\u79cd\u5f02\u5e38\u548c\u9519\u8bef\uff0c\u4f8b\u5982\u7f51\u7edc\u8fde\u63a5\u5931\u8d25\u3001\u8bf7\u6c42\u8d85\u65f6\u3001\u89e3\u6790\u9519\u8bef\u7b49\u3002\u9700\u8981\u5728\u4ee3\u7801\u4e2d\u5904\u7406\u8fd9\u4e9b\u5f02\u5e38\uff0c\u4fdd\u8bc1\u7a0b\u5e8f\u7684\u7a33\u5b9a\u6027\u3002<\/p>\n<\/p>\n<p><h4>1\u3001\u5904\u7406\u7f51\u7edc\u5f02\u5e38<\/h4>\n<\/p>\n<p><p>\u4f7f\u7528requests\u5e93\u65f6\uff0c\u53ef\u4ee5\u901a\u8fc7\u6355\u83b7\u5f02\u5e38\u6765\u5904\u7406\u7f51\u7edc\u9519\u8bef\uff0c\u4f8b\u5982\u8fde\u63a5\u5931\u8d25\u3001\u8bf7\u6c42\u8d85\u65f6\u7b49\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>from requests.exceptions import RequestException<\/p>\n<p>url = &#39;http:\/\/example.com&#39;<\/p>\n<p>try:<\/p>\n<p>    response = requests.get(url)<\/p>\n<p>    response.r<a href=\"https:\/\/docs.pingcode.com\/blog\/59162.html\" target=\"_blank\">AI<\/a>se_for_status()  # \u5982\u679c\u54cd\u5e94\u72b6\u6001\u7801\u4e0d\u662f200\uff0c\u629b\u51faHTTPError\u5f02\u5e38<\/p>\n<p>except RequestException as e:<\/p>\n<p>    print(f&#39;\u7f51\u7edc\u5f02\u5e38\uff1a{e}&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u6bb5\u4ee3\u7801\u6355\u83b7\u6240\u6709\u8bf7\u6c42\u5f02\u5e38\uff0c\u5e76\u8f93\u51fa\u9519\u8bef\u4fe1\u606f\u3002<\/p>\n<\/p>\n<p><h4>2\u3001\u5904\u7406\u89e3\u6790\u9519\u8bef<\/h4>\n<\/p>\n<p><p>\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u65f6\uff0c\u4e5f\u53ef\u80fd\u4f1a\u9047\u5230\u89e3\u6790\u9519\u8bef\u3002\u53ef\u4ee5\u901a\u8fc7\u6355\u83b7\u5f02\u5e38\u6765\u5904\u7406\u8fd9\u4e9b\u9519\u8bef\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from bs4 import BeautifulSoup<\/p>\n<p>try:<\/p>\n<p>    soup = BeautifulSoup(response.content, &#39;html.parser&#39;)<\/p>\n<p>except Exception as e:<\/p>\n<p>    print(f&#39;\u89e3\u6790\u9519\u8bef\uff1a{e}&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u6bb5\u4ee3\u7801\u6355\u83b7\u6240\u6709\u89e3\u6790\u5f02\u5e38\uff0c\u5e76\u8f93\u51fa\u9519\u8bef\u4fe1\u606f\u3002<\/p>\n<\/p>\n<p><h3>\u56db\u3001\u4f7f\u7528Selenium\u8fdb\u884c\u52a8\u6001\u7f51\u9875\u6293\u53d6<\/h3>\n<\/p>\n<p><p>\u6709\u4e9b\u7f51\u9875\u5185\u5bb9\u662f\u901a\u8fc7JavaScript\u52a8\u6001\u52a0\u8f7d\u7684\uff0c\u4f7f\u7528requests\u5e93\u65e0\u6cd5\u83b7\u53d6\u5230\u8fd9\u4e9b\u5185\u5bb9\u3002\u8fd9\u65f6\u53ef\u4ee5\u4f7f\u7528Selenium\uff0c\u5b83\u53ef\u4ee5\u6a21\u62df\u7528\u6237\u64cd\u4f5c\u6d4f\u89c8\u5668\uff0c\u83b7\u53d6\u52a8\u6001\u52a0\u8f7d\u7684\u7f51\u9875\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><h4>1\u3001\u5b89\u88c5\u548c\u914d\u7f6eSelenium<\/h4>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u5b89\u88c5Selenium\u5e93\uff0c\u5e76\u4e0b\u8f7d\u5bf9\u5e94\u7684\u6d4f\u89c8\u5668\u9a71\u52a8\u7a0b\u5e8f\uff08\u5982ChromeDriver\uff09\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install selenium<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4e0b\u8f7dChromeDriver\uff1a<a href=\"https:\/\/sites.google.com\/a\/chromium.org\/chromedriver\/downloads\">https:\/\/sites.google.com\/a\/chromium.org\/chromedriver\/downloads<\/a><\/p>\n<\/p>\n<p><h4>2\u3001\u4f7f\u7528Selenium\u83b7\u53d6\u52a8\u6001\u7f51\u9875\u5185\u5bb9<\/h4>\n<\/p>\n<p><p>\u4f7f\u7528Selenium\u83b7\u53d6\u52a8\u6001\u7f51\u9875\u5185\u5bb9\u9700\u8981\u51e0\u6b65\uff1a<\/p>\n<\/p>\n<ol>\n<li>\u521b\u5efa\u6d4f\u89c8\u5668\u5b9e\u4f8b<\/li>\n<li>\u6253\u5f00\u7f51\u9875<\/li>\n<li>\u7b49\u5f85\u7f51\u9875\u52a0\u8f7d\u5b8c\u6210<\/li>\n<li>\u83b7\u53d6\u7f51\u9875\u5185\u5bb9<\/li>\n<\/ol>\n<p><pre><code class=\"language-python\">from selenium import webdriver<\/p>\n<p>from selenium.webdriver.chrome.service import Service<\/p>\n<p>from selenium.webdriver.common.by import By<\/p>\n<p>from selenium.webdriver.support.ui import WebDriverWait<\/p>\n<p>from selenium.webdriver.support import expected_conditions as EC<\/p>\n<h2><strong>\u521b\u5efaChrome\u6d4f\u89c8\u5668\u5b9e\u4f8b<\/strong><\/h2>\n<p>service = Service(&#39;path\/to\/chromedriver&#39;)  # \u66ff\u6362\u4e3aChromeDriver\u7684\u8def\u5f84<\/p>\n<p>driver = webdriver.Chrome(service=service)<\/p>\n<p>url = &#39;http:\/\/example.com&#39;<\/p>\n<p>driver.get(url)  # \u6253\u5f00\u7f51\u9875<\/p>\n<p>try:<\/p>\n<p>    # \u7b49\u5f85\u67d0\u4e2a\u5143\u7d20\u52a0\u8f7d\u5b8c\u6210\uff08\u4f8b\u5982id\u4e3acontent\u7684\u5143\u7d20\uff09<\/p>\n<p>    element = WebDriverWait(driver, 10).until(<\/p>\n<p>        EC.presence_of_element_located((By.ID, &#39;content&#39;))<\/p>\n<p>    )<\/p>\n<p>    print(driver.page_source)  # \u8f93\u51fa\u7f51\u9875\u5185\u5bb9<\/p>\n<p>finally:<\/p>\n<p>    driver.quit()  # \u5173\u95ed\u6d4f\u89c8\u5668<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u6bb5\u4ee3\u7801\u521b\u5efa\u4e00\u4e2aChrome\u6d4f\u89c8\u5668\u5b9e\u4f8b\uff0c\u6253\u5f00\u6307\u5b9a\u7684URL\uff0c\u5e76\u7b49\u5f85id\u4e3acontent\u7684\u5143\u7d20\u52a0\u8f7d\u5b8c\u6210\u3002\u5b8c\u6210\u540e\uff0c\u8f93\u51fa\u7f51\u9875\u5185\u5bb9\uff0c\u5e76\u5173\u95ed\u6d4f\u89c8\u5668\u3002<\/p>\n<\/p>\n<p><h3>\u4e94\u3001\u7efc\u5408\u5b9e\u4f8b<\/h3>\n<\/p>\n<p><p>\u4e0b\u9762\u662f\u4e00\u4e2a\u7efc\u5408\u5b9e\u4f8b\uff0c\u6f14\u793a\u5982\u4f55\u4f7f\u7528requests\u548cBeautifulSoup\u6293\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u63d0\u53d6\u6570\u636e\uff0c\u5e76\u5904\u7406\u5f02\u5e38\u548c\u9519\u8bef\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>from bs4 import BeautifulSoup<\/p>\n<p>from requests.exceptions import RequestException<\/p>\n<p>url = &#39;http:\/\/example.com&#39;<\/p>\n<p>try:<\/p>\n<p>    response = requests.get(url)<\/p>\n<p>    response.raise_for_status()<\/p>\n<p>except RequestException as e:<\/p>\n<p>    print(f&#39;\u7f51\u7edc\u5f02\u5e38\uff1a{e}&#39;)<\/p>\n<p>else:<\/p>\n<p>    try:<\/p>\n<p>        soup = BeautifulSoup(response.content, &#39;html.parser&#39;)<\/p>\n<p>    except Exception as e:<\/p>\n<p>        print(f&#39;\u89e3\u6790\u9519\u8bef\uff1a{e}&#39;)<\/p>\n<p>    else:<\/p>\n<p>        for link in soup.find_all(&#39;a&#39;):<\/p>\n<p>            print(link.get(&#39;href&#39;))<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u6bb5\u4ee3\u7801\u53d1\u9001\u4e00\u4e2aGET\u8bf7\u6c42\u5230\u6307\u5b9a\u7684URL\uff0c\u5904\u7406\u7f51\u7edc\u5f02\u5e38\u548c\u89e3\u6790\u9519\u8bef\uff0c\u5e76\u63d0\u53d6\u7f51\u9875\u4e2d\u7684\u6240\u6709\u94fe\u63a5\u3002<\/p>\n<\/p>\n<p><h3>\u516d\u3001\u5176\u4ed6\u5b9e\u7528\u5de5\u5177\u548c\u6280\u5de7<\/h3>\n<\/p>\n<p><h4>1\u3001\u4f7f\u7528\u4ee3\u7406<\/h4>\n<\/p>\n<p><p>\u5728\u8fdb\u884c\u5927\u91cf\u7f51\u9875\u6293\u53d6\u65f6\uff0c\u53ef\u80fd\u4f1a\u9047\u5230IP\u88ab\u5c01\u7981\u7684\u60c5\u51b5\u3002\u53ef\u4ee5\u4f7f\u7528\u4ee3\u7406\u6765\u907f\u514d\u8fd9\u79cd\u95ee\u9898\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">proxies = {<\/p>\n<p>    &#39;http&#39;: &#39;http:\/\/10.10.1.10:3128&#39;,<\/p>\n<p>    &#39;https&#39;: &#39;http:\/\/10.10.1.10:1080&#39;,<\/p>\n<p>}<\/p>\n<p>response = requests.get(url, proxies=proxies)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u6bb5\u4ee3\u7801\u4f7f\u7528\u6307\u5b9a\u7684\u4ee3\u7406\u53d1\u9001\u8bf7\u6c42\u3002<\/p>\n<\/p>\n<p><h4>2\u3001\u8bbe\u7f6e\u8bf7\u6c42\u5934<\/h4>\n<\/p>\n<p><p>\u6709\u4e9b\u7f51\u7ad9\u4f1a\u68c0\u67e5\u8bf7\u6c42\u5934\uff0c\u4ee5\u786e\u5b9a\u8bf7\u6c42\u662f\u5426\u6765\u81ea\u6d4f\u89c8\u5668\u3002\u53ef\u4ee5\u901a\u8fc7\u8bbe\u7f6e\u8bf7\u6c42\u5934\uff0c\u4f2a\u88c5\u6210\u6d4f\u89c8\u5668\u53d1\u9001\u8bf7\u6c42\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">headers = {<\/p>\n<p>    &#39;User-Agent&#39;: &#39;Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/58.0.3029.110 Safari\/537.3&#39;<\/p>\n<p>}<\/p>\n<p>response = requests.get(url, headers=headers)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u6bb5\u4ee3\u7801\u8bbe\u7f6eUser-Agent\u8bf7\u6c42\u5934\uff0c\u4f2a\u88c5\u6210Chrome\u6d4f\u89c8\u5668\u53d1\u9001\u8bf7\u6c42\u3002<\/p>\n<\/p>\n<p><h4>3\u3001\u5904\u7406Cookies<\/h4>\n<\/p>\n<p><p>\u6709\u4e9b\u7f51\u7ad9\u9700\u8981\u901a\u8fc7Cookies\u6765\u4fdd\u6301\u4f1a\u8bdd\u72b6\u6001\u3002\u53ef\u4ee5\u4f7f\u7528requests\u5e93\u5904\u7406Cookies\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">session = requests.Session()<\/p>\n<p>response = session.get(url)<\/p>\n<p>cookies = session.cookies.get_dict()<\/p>\n<p>print(cookies)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u8fd9\u6bb5\u4ee3\u7801\u521b\u5efa\u4e00\u4e2a\u4f1a\u8bdd\uff0c\u53d1\u9001\u8bf7\u6c42\uff0c\u5e76\u83b7\u53d6Cookies\u3002<\/p>\n<\/p>\n<p><h3>\u4e03\u3001\u603b\u7ed3<\/h3>\n<\/p>\n<p><p>\u901a\u8fc7\u672c\u6587\u7684\u4ecb\u7ecd\uff0c\u6211\u4eec\u5b66\u4e60\u4e86\u5982\u4f55\u4f7f\u7528Python\u8fdb\u884c\u7f51\u9875\u6293\u53d6\u3002\u4e3b\u8981\u65b9\u6cd5\u5305\u62ec\u4f7f\u7528requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u3001\u4f7f\u7528Selenium\u8fdb\u884c\u52a8\u6001\u7f51\u9875\u6293\u53d6\u3002\u6b64\u5916\uff0c\u8fd8\u4ecb\u7ecd\u4e86\u5982\u4f55\u5904\u7406\u5f02\u5e38\u548c\u9519\u8bef\uff0c\u4f7f\u7528\u4ee3\u7406\uff0c\u8bbe\u7f6e\u8bf7\u6c42\u5934\uff0c\u5904\u7406Cookies\u7b49\u5b9e\u7528\u6280\u5de7\u3002\u5e0c\u671b\u901a\u8fc7\u8fd9\u4e9b\u65b9\u6cd5\u548c\u6280\u5de7\uff0c\u80fd\u591f\u5e2e\u52a9\u4f60\u66f4\u597d\u5730\u8fdb\u884c\u7f51\u9875\u6293\u53d6\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5728Python\u4e2d\uff0c\u7f51\u9875\u6293\u53d6\u7684\u57fa\u672c\u6b65\u9aa4\u662f\u4ec0\u4e48\uff1f<\/strong><br \/>\u7f51\u9875\u6293\u53d6\u7684\u57fa\u672c\u6b65\u9aa4\u5305\u62ec\u53d1\u9001HTTP\u8bf7\u6c42\u4ee5\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3001\u89e3\u6790HTML\u6587\u6863\u3001\u63d0\u53d6\u6240\u9700\u6570\u636e\u4ee5\u53ca\u5904\u7406\u6570\u636e\u3002\u5e38\u7528\u7684\u5e93\u6709<code>requests<\/code>\u7528\u4e8e\u53d1\u9001\u8bf7\u6c42\u548c<code>BeautifulSoup<\/code>\u6216<code>lxml<\/code>\u7528\u4e8e\u89e3\u6790HTML\u3002\u901a\u8fc7\u8fd9\u4e9b\u6b65\u9aa4\uff0c\u7528\u6237\u53ef\u4ee5\u83b7\u53d6\u7f51\u9875\u4e2d\u7684\u6587\u672c\u3001\u56fe\u7247\u548c\u5176\u4ed6\u4fe1\u606f\u3002<\/p>\n<p><strong>\u54ea\u4e9bPython\u5e93\u9002\u5408\u7528\u4e8e\u7f51\u9875\u6293\u53d6\uff1f<\/strong><br \/>\u5728Python\u4e2d\uff0c\u5e38\u7528\u7684\u7f51\u9875\u6293\u53d6\u5e93\u5305\u62ec<code>requests<\/code>\u3001<code>BeautifulSoup<\/code>\u3001<code>lxml<\/code>\u3001<code>Scrapy<\/code>\u548c<code>Selenium<\/code>\u3002<code>requests<\/code>\u7b80\u5316\u4e86HTTP\u8bf7\u6c42\u7684\u53d1\u9001\uff0c<code>BeautifulSoup<\/code>\u548c<code>lxml<\/code>\u7528\u4e8e\u89e3\u6790\u548c\u63d0\u53d6HTML\u5185\u5bb9\uff0c\u800c<code>Scrapy<\/code>\u662f\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684\u6846\u67b6\uff0c\u9002\u5408\u5927\u89c4\u6a21\u6293\u53d6\u3002<code>Selenium<\/code>\u5219\u53ef\u4ee5\u7528\u6765\u6293\u53d6\u52a8\u6001\u52a0\u8f7d\u7684\u7f51\u9875\u3002<\/p>\n<p><strong>\u5982\u4f55\u5904\u7406\u7f51\u9875\u6293\u53d6\u4e2d\u7684\u53cd\u722c\u866b\u673a\u5236\uff1f<\/strong><br \/>\u7f51\u9875\u6293\u53d6\u65f6\uff0c\u53ef\u80fd\u4f1a\u9047\u5230\u53cd\u722c\u866b\u673a\u5236\uff0c\u5982IP\u5c01\u7981\u3001\u9a8c\u8bc1\u7801\u7b49\u3002\u53ef\u4ee5\u91c7\u53d6\u4e00\u4e9b\u7b56\u7565\u6765\u5e94\u5bf9\u8fd9\u4e9b\u95ee\u9898\uff0c\u4f8b\u5982\u4f7f\u7528\u4ee3\u7406IP\u3001\u8bbe\u7f6e\u8bf7\u6c42\u5934\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\u3001\u63a7\u5236\u8bf7\u6c42\u9891\u7387\u4ee5\u907f\u514d\u8fc7\u4e8e\u9891\u7e41\u5730\u8bf7\u6c42\u540c\u4e00\u7f51\u9875\uff0c\u6216\u8005\u4f7f\u7528<code>Selenium<\/code>\u6a21\u62df\u7528\u6237\u64cd\u4f5c\u6765\u7ed5\u8fc7\u4e00\u4e9b\u7b80\u5355\u7684\u53cd\u722c\u866b\u63aa\u65bd\u3002\u4fdd\u6301\u793c\u8c8c\u548c\u9075\u5faa\u7f51\u7ad9\u7684robots.txt\u6587\u4ef6\u662f\u975e\u5e38\u91cd\u8981\u7684\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u5b9e\u73b0\u7f51\u9875\u6293\u53d6\u7684\u4e3b\u8981\u65b9\u6cd5\u6709\uff1a\u4f7f\u7528requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790H [&hellip;]","protected":false},"author":3,"featured_media":1150081,"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\/1150078"}],"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=1150078"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1150078\/revisions"}],"predecessor-version":[{"id":1150082,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1150078\/revisions\/1150082"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1150081"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1150078"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1150078"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1150078"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}