{"id":1155139,"date":"2025-01-13T17:59:46","date_gmt":"2025-01-13T09:59:46","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1155139.html"},"modified":"2025-01-13T17:59:52","modified_gmt":"2025-01-13T09:59:52","slug":"python%e7%88%ac%e8%99%ab%e5%a6%82%e4%bd%95%e8%8e%b7%e5%8f%96%e6%ba%90%e7%a0%81","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1155139.html","title":{"rendered":"python\u722c\u866b\u5982\u4f55\u83b7\u53d6\u6e90\u7801"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/25184601\/a4a29aca-8b52-445e-9145-ff5ded91b710.webp\" alt=\"python\u722c\u866b\u5982\u4f55\u83b7\u53d6\u6e90\u7801\" \/><\/p>\n<p><p> \u8981\u83b7\u53d6\u7f51\u9875\u6e90\u7801\uff0cPython\u722c\u866b\u53ef\u4ee5\u4f7f\u7528\u8bf8\u5982Requests\u3001BeautifulSoup\u3001Selenium\u7b49\u5e93\u3002<strong>\u901a\u8fc7\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u89e3\u6790HTML\u6587\u6863\u3001\u5904\u7406\u52a8\u6001\u5185\u5bb9<\/strong>\uff0c\u722c\u866b\u53ef\u4ee5\u9ad8\u6548\u5730\u83b7\u53d6\u7f51\u9875\u6e90\u7801\u3002\u4ee5\u4e0b\u662f\u8be6\u7ec6\u63cf\u8ff0\u5982\u4f55\u901a\u8fc7\u53d1\u9001HTTP\u8bf7\u6c42\u6765\u83b7\u53d6\u7f51\u9875\u6e90\u7801\uff1a<\/p>\n<\/p>\n<p><p><strong>\u53d1\u9001HTTP\u8bf7\u6c42\uff1a<\/strong><\/p>\n<p>\u4f7f\u7528Requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u662f\u83b7\u53d6\u7f51\u9875\u6e90\u7801\u7684\u57fa\u7840\u6b65\u9aa4\u3002Requests\u5e93\u63d0\u4f9b\u4e86\u7b80\u6d01\u7684API\u6765\u5904\u7406HTTP\u8bf7\u6c42\uff0c\u53ea\u9700\u51e0\u884c\u4ee3\u7801\u5373\u53ef\u83b7\u53d6\u7f51\u9875\u7684HTML\u6e90\u7801\u3002\u901a\u8fc7\u5411\u76ee\u6807URL\u53d1\u9001GET\u8bf7\u6c42\uff0c\u63a5\u6536\u670d\u52a1\u5668\u54cd\u5e94\uff0c\u5e76\u63d0\u53d6\u54cd\u5e94\u5185\u5bb9\uff0c\u5373\u53ef\u83b7\u53d6\u7f51\u9875\u6e90\u7801\u3002\u4f8b\u5982\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>url = &#39;https:\/\/example.com&#39;<\/p>\n<p>response = requests.get(url)<\/p>\n<p>html_content = response.text<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u4e0a\u8ff0\u4ee3\u7801\u4e2d\uff0c<code>requests.get(url)<\/code>\u53d1\u9001GET\u8bf7\u6c42\uff0c<code>response.text<\/code>\u83b7\u53d6\u54cd\u5e94\u7684HTML\u5185\u5bb9\u3002<\/p>\n<\/p>\n<hr>\n<p><h3>\u4e00\u3001Requests\u5e93\u7684\u57fa\u672c\u4f7f\u7528<\/h3>\n<\/p>\n<p><p>Requests\u5e93\u662f\u4e00\u4e2a\u7b80\u5355\u6613\u7528\u7684HTTP\u5e93\uff0c\u5b83\u7b80\u5316\u4e86HTTP\u8bf7\u6c42\u7684\u53d1\u9001\u548c\u54cd\u5e94\u5904\u7406\u3002\u4ee5\u4e0b\u662fRequests\u5e93\u7684\u57fa\u672c\u4f7f\u7528\u65b9\u6cd5\uff1a<\/p>\n<\/p>\n<p><h4>1.1 \u5b89\u88c5\u548c\u5bfc\u5165<\/h4>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u786e\u4fdd\u5b89\u88c5\u4e86Requests\u5e93\u3002\u53ef\u4ee5\u4f7f\u7528pip\u8fdb\u884c\u5b89\u88c5\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install requests<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u7136\u540e\uff0c\u5728Python\u811a\u672c\u4e2d\u5bfc\u5165\u8be5\u5e93\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>1.2 \u53d1\u9001GET\u8bf7\u6c42<\/h4>\n<\/p>\n<p><p>GET\u8bf7\u6c42\u662f\u6700\u5e38\u89c1\u7684HTTP\u8bf7\u6c42\u7c7b\u578b\uff0c\u7528\u4e8e\u83b7\u53d6\u8d44\u6e90\u3002\u4ee5\u4e0b\u662f\u53d1\u9001GET\u8bf7\u6c42\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">url = &#39;https:\/\/example.com&#39;<\/p>\n<p>response = requests.get(url)<\/p>\n<p>print(response.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u4e2a\u793a\u4f8b\u4e2d\uff0c<code>requests.get(url)<\/code>\u53d1\u9001\u4e86\u4e00\u4e2aGET\u8bf7\u6c42\uff0c<code>response.text<\/code>\u5305\u542b\u4e86\u670d\u52a1\u5668\u8fd4\u56de\u7684HTML\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><h4>1.3 \u5904\u7406\u54cd\u5e94<\/h4>\n<\/p>\n<p><p>Requests\u5e93\u63d0\u4f9b\u4e86\u591a\u79cd\u65b9\u6cd5\u6765\u5904\u7406HTTP\u54cd\u5e94\uff1a<\/p>\n<\/p>\n<ul>\n<li><code>response.status_code<\/code>: \u83b7\u53d6HTTP\u72b6\u6001\u7801<\/li>\n<li><code>response.headers<\/code>: \u83b7\u53d6\u54cd\u5e94\u5934<\/li>\n<li><code>response.content<\/code>: \u83b7\u53d6\u54cd\u5e94\u5185\u5bb9\uff08\u4e8c\u8fdb\u5236\u5f62\u5f0f\uff09<\/li>\n<li><code>response.text<\/code>: \u83b7\u53d6\u54cd\u5e94\u5185\u5bb9\uff08\u5b57\u7b26\u4e32\u5f62\u5f0f\uff09<\/li>\n<\/ul>\n<p><p>\u4f8b\u5982\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">url = &#39;https:\/\/example.com&#39;<\/p>\n<p>response = requests.get(url)<\/p>\n<p>print(&#39;Status Code:&#39;, response.status_code)<\/p>\n<p>print(&#39;Headers:&#39;, response.headers)<\/p>\n<p>print(&#39;Content:&#39;, response.content)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e8c\u3001\u89e3\u6790HTML\u6587\u6863<\/h3>\n<\/p>\n<p><p>\u83b7\u53d6\u7f51\u9875\u6e90\u7801\u540e\uff0c\u901a\u5e38\u9700\u8981\u89e3\u6790HTML\u6587\u6863\u4ee5\u63d0\u53d6\u6240\u9700\u6570\u636e\u3002BeautifulSoup\u662f\u4e00\u4e2a\u5f3a\u5927\u7684HTML\u89e3\u6790\u5e93\uff0c\u5e38\u4e0eRequests\u5e93\u914d\u5408\u4f7f\u7528\u3002<\/p>\n<\/p>\n<p><h4>2.1 \u5b89\u88c5\u548c\u5bfc\u5165BeautifulSoup<\/h4>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u786e\u4fdd\u5b89\u88c5\u4e86BeautifulSoup\u5e93\u3002\u53ef\u4ee5\u4f7f\u7528pip\u8fdb\u884c\u5b89\u88c5\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install beautifulsoup4<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u7136\u540e\uff0c\u5728Python\u811a\u672c\u4e2d\u5bfc\u5165\u8be5\u5e93\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from bs4 import BeautifulSoup<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2.2 \u521b\u5efaBeautifulSoup\u5bf9\u8c61<\/h4>\n<\/p>\n<p><p>\u521b\u5efaBeautifulSoup\u5bf9\u8c61\u4ee5\u89e3\u6790HTML\u6587\u6863\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">url = &#39;https:\/\/example.com&#39;<\/p>\n<p>response = requests.get(url)<\/p>\n<p>soup = BeautifulSoup(response.text, &#39;html.parser&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u4e2a\u793a\u4f8b\u4e2d\uff0c<code>BeautifulSoup(response.text, &#39;html.parser&#39;)<\/code>\u521b\u5efa\u4e86\u4e00\u4e2aBeautifulSoup\u5bf9\u8c61\uff0c\u4f7f\u7528HTML\u89e3\u6790\u5668\u89e3\u6790\u54cd\u5e94\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><h4>2.3 \u67e5\u627e\u5143\u7d20<\/h4>\n<\/p>\n<p><p>BeautifulSoup\u63d0\u4f9b\u4e86\u591a\u79cd\u65b9\u6cd5\u6765\u67e5\u627eHTML\u5143\u7d20\uff0c\u5305\u62ec<code>find<\/code>\u3001<code>find_all<\/code>\u3001<code>select<\/code>\u7b49\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u67e5\u627e\u7b2c\u4e00\u4e2a\u5339\u914d\u7684\u5143\u7d20<\/p>\n<p>first_h1 = soup.find(&#39;h1&#39;)<\/p>\n<p>print(first_h1.text)<\/p>\n<h2><strong>\u67e5\u627e\u6240\u6709\u5339\u914d\u7684\u5143\u7d20<\/strong><\/h2>\n<p>all_paragraphs = soup.find_all(&#39;p&#39;)<\/p>\n<p>for p in all_paragraphs:<\/p>\n<p>    print(p.text)<\/p>\n<h2><strong>\u4f7f\u7528CSS\u9009\u62e9\u5668\u67e5\u627e\u5143\u7d20<\/strong><\/h2>\n<p>selected_elements = soup.select(&#39;.class-name&#39;)<\/p>\n<p>for element in selected_elements:<\/p>\n<p>    print(element.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e09\u3001\u5904\u7406\u52a8\u6001\u5185\u5bb9<\/h3>\n<\/p>\n<p><p>\u6709\u4e9b\u7f51\u9875\u5185\u5bb9\u662f\u901a\u8fc7JavaScript\u52a8\u6001\u52a0\u8f7d\u7684\uff0c\u4f7f\u7528Requests\u548cBeautifulSoup\u53ef\u80fd\u65e0\u6cd5\u76f4\u63a5\u83b7\u53d6\u3002\u8fd9\u65f6\u53ef\u4ee5\u4f7f\u7528Selenium\u5e93\uff0c\u5b83\u80fd\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\uff0c\u52a0\u8f7d\u52a8\u6001\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><h4>3.1 \u5b89\u88c5\u548c\u914d\u7f6eSelenium<\/h4>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u786e\u4fdd\u5b89\u88c5\u4e86Selenium\u5e93\u548c\u76f8\u5e94\u7684\u6d4f\u89c8\u5668\u9a71\u52a8\u3002\u4f8b\u5982\uff0c\u5b89\u88c5Selenium\u548cChrome\u6d4f\u89c8\u5668\u9a71\u52a8\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install selenium<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4e0b\u8f7dChrome\u6d4f\u89c8\u5668\u9a71\u52a8\uff0c\u5e76\u5c06\u5176\u8def\u5f84\u6dfb\u52a0\u5230\u7cfb\u7edf\u73af\u5883\u53d8\u91cf\u4e2d\u3002<\/p>\n<\/p>\n<p><h4>3.2 \u521b\u5efaWebDriver\u5bf9\u8c61<\/h4>\n<\/p>\n<p><p>\u4f7f\u7528Selenium\u521b\u5efaWebDriver\u5bf9\u8c61\uff0c\u63a7\u5236\u6d4f\u89c8\u5668\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from selenium import webdriver<\/p>\n<h2><strong>\u521b\u5efaChrome\u6d4f\u89c8\u5668\u9a71\u52a8\u5bf9\u8c61<\/strong><\/h2>\n<p>driver = webdriver.Chrome()<\/p>\n<h2><strong>\u8bbf\u95ee\u76ee\u6807URL<\/strong><\/h2>\n<p>url = &#39;https:\/\/example.com&#39;<\/p>\n<p>driver.get(url)<\/p>\n<h2><strong>\u83b7\u53d6\u7f51\u9875\u6e90\u7801<\/strong><\/h2>\n<p>html_content = driver.page_source<\/p>\n<p>print(html_content)<\/p>\n<h2><strong>\u5173\u95ed\u6d4f\u89c8\u5668<\/strong><\/h2>\n<p>driver.quit()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u4e2a\u793a\u4f8b\u4e2d\uff0c<code>webdriver.Chrome()<\/code>\u521b\u5efa\u4e86\u4e00\u4e2aChrome\u6d4f\u89c8\u5668\u9a71\u52a8\u5bf9\u8c61\uff0c<code>driver.get(url)<\/code>\u8bbf\u95ee\u76ee\u6807URL\uff0c<code>driver.page_source<\/code>\u83b7\u53d6\u7f51\u9875\u6e90\u7801\u3002<\/p>\n<\/p>\n<p><h4>3.3 \u67e5\u627e\u5143\u7d20\u5e76\u63d0\u53d6\u6570\u636e<\/h4>\n<\/p>\n<p><p>Selenium\u63d0\u4f9b\u4e86\u591a\u79cd\u65b9\u6cd5\u6765\u67e5\u627e\u5143\u7d20\u5e76\u63d0\u53d6\u6570\u636e\uff0c\u4f8b\u5982<code>find_element_by_id<\/code>\u3001<code>find_elements_by_class_name<\/code>\u7b49\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from selenium import webdriver<\/p>\n<p>driver = webdriver.Chrome()<\/p>\n<p>url = &#39;https:\/\/example.com&#39;<\/p>\n<p>driver.get(url)<\/p>\n<h2><strong>\u67e5\u627e\u5143\u7d20\u5e76\u63d0\u53d6\u6570\u636e<\/strong><\/h2>\n<p>element = driver.find_element_by_id(&#39;element-id&#39;)<\/p>\n<p>print(element.text)<\/p>\n<h2><strong>\u5173\u95ed\u6d4f\u89c8\u5668<\/strong><\/h2>\n<p>driver.quit()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u4e2a\u793a\u4f8b\u4e2d\uff0c<code>driver.find_element_by_id(&#39;element-id&#39;)<\/code>\u67e5\u627e\u6307\u5b9aID\u7684\u5143\u7d20\uff0c\u5e76\u63d0\u53d6\u5176\u6587\u672c\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><h3>\u56db\u3001\u5904\u7406Ajax\u8bf7\u6c42<\/h3>\n<\/p>\n<p><p>\u6709\u4e9b\u7f51\u9875\u901a\u8fc7Ajax\u8bf7\u6c42\u52a0\u8f7d\u5185\u5bb9\uff0c\u4f7f\u7528\u666e\u901a\u7684HTTP\u8bf7\u6c42\u65e0\u6cd5\u76f4\u63a5\u83b7\u53d6\u3002\u53ef\u4ee5\u4f7f\u7528Selenium\u6216\u76f4\u63a5\u53d1\u9001Ajax\u8bf7\u6c42\u83b7\u53d6\u6570\u636e\u3002<\/p>\n<\/p>\n<p><h4>4.1 \u4f7f\u7528Selenium\u5904\u7406Ajax\u8bf7\u6c42<\/h4>\n<\/p>\n<p><p>Selenium\u53ef\u4ee5\u7b49\u5f85\u9875\u9762\u52a0\u8f7d\u5b8c\u6210\uff0c\u518d\u83b7\u53d6\u52a8\u6001\u5185\u5bb9\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from selenium import webdriver<\/p>\n<p>from selenium.webdriver.common.by import By<\/p>\n<p>from selenium.webdriver.support.ui import WebDriverW<a href=\"https:\/\/docs.pingcode.com\/blog\/59162.html\" target=\"_blank\">AI<\/a>t<\/p>\n<p>from selenium.webdriver.support import expected_conditions as EC<\/p>\n<p>driver = webdriver.Chrome()<\/p>\n<p>url = &#39;https:\/\/example.com&#39;<\/p>\n<p>driver.get(url)<\/p>\n<h2><strong>\u7b49\u5f85\u7279\u5b9a\u5143\u7d20\u52a0\u8f7d\u5b8c\u6210<\/strong><\/h2>\n<p>element = WebDriverWait(driver, 10).until(<\/p>\n<p>    EC.presence_of_element_located((By.ID, &#39;element-id&#39;))<\/p>\n<p>)<\/p>\n<p>print(element.text)<\/p>\n<h2><strong>\u5173\u95ed\u6d4f\u89c8\u5668<\/strong><\/h2>\n<p>driver.quit()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u4e2a\u793a\u4f8b\u4e2d\uff0c<code>WebDriverWait<\/code>\u7b49\u5f85\u7279\u5b9a\u5143\u7d20\u52a0\u8f7d\u5b8c\u6210\uff0c\u518d\u63d0\u53d6\u5176\u6587\u672c\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><h4>4.2 \u76f4\u63a5\u53d1\u9001Ajax\u8bf7\u6c42<\/h4>\n<\/p>\n<p><p>\u6709\u4e9bAjax\u8bf7\u6c42\u53ef\u4ee5\u76f4\u63a5\u53d1\u9001HTTP\u8bf7\u6c42\u83b7\u53d6\u6570\u636e\u3002\u901a\u8fc7\u5206\u6790\u7f51\u9875\u7684\u7f51\u7edc\u8bf7\u6c42\uff0c\u627e\u5230\u5bf9\u5e94\u7684Ajax\u63a5\u53e3\uff0c\u4f7f\u7528Requests\u5e93\u53d1\u9001\u8bf7\u6c42\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>url = &#39;https:\/\/example.com\/ajax-endpoint&#39;<\/p>\n<p>params = {<\/p>\n<p>    &#39;param1&#39;: &#39;value1&#39;,<\/p>\n<p>    &#39;param2&#39;: &#39;value2&#39;<\/p>\n<p>}<\/p>\n<p>response = requests.get(url, params=params)<\/p>\n<p>print(response.json())<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u4e2a\u793a\u4f8b\u4e2d\uff0c<code>requests.get(url, params=params)<\/code>\u53d1\u9001\u4e86\u4e00\u4e2aGET\u8bf7\u6c42\uff0c\u83b7\u53d6Ajax\u63a5\u53e3\u8fd4\u56de\u7684JSON\u6570\u636e\u3002<\/p>\n<\/p>\n<p><h3>\u4e94\u3001\u5904\u7406Cookies\u548c\u4f1a\u8bdd<\/h3>\n<\/p>\n<p><p>\u6709\u4e9b\u7f51\u9875\u9700\u8981\u767b\u5f55\u6216\u4f7f\u7528\u7279\u5b9a\u7684Cookies\u624d\u80fd\u8bbf\u95ee\u3002\u53ef\u4ee5\u4f7f\u7528Requests\u5e93\u5904\u7406Cookies\u548c\u4f1a\u8bdd\u3002<\/p>\n<\/p>\n<p><h4>5.1 \u4f7f\u7528Requests\u5e93\u5904\u7406\u4f1a\u8bdd<\/h4>\n<\/p>\n<p><p>\u4f7f\u7528Requests\u5e93\u7684\u4f1a\u8bdd\u5bf9\u8c61\uff0c\u53ef\u4ee5\u5728\u591a\u4e2a\u8bf7\u6c42\u4e4b\u95f4\u4fdd\u6301Cookies\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>session = requests.Session()<\/p>\n<h2><strong>\u53d1\u9001\u767b\u5f55\u8bf7\u6c42\uff0c\u4fdd\u5b58Cookies<\/strong><\/h2>\n<p>login_url = &#39;https:\/\/example.com\/login&#39;<\/p>\n<p>login_data = {<\/p>\n<p>    &#39;username&#39;: &#39;your-username&#39;,<\/p>\n<p>    &#39;password&#39;: &#39;your-password&#39;<\/p>\n<p>}<\/p>\n<p>session.post(login_url, data=login_data)<\/p>\n<h2><strong>\u53d1\u9001\u5176\u4ed6\u8bf7\u6c42\uff0c\u4f7f\u7528\u4fdd\u5b58\u7684Cookies<\/strong><\/h2>\n<p>url = &#39;https:\/\/example.com\/protected-page&#39;<\/p>\n<p>response = session.get(url)<\/p>\n<p>print(response.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u4e2a\u793a\u4f8b\u4e2d\uff0c<code>requests.Session()<\/code>\u521b\u5efa\u4e86\u4e00\u4e2a\u4f1a\u8bdd\u5bf9\u8c61\uff0c<code>session.post<\/code>\u53d1\u9001\u767b\u5f55\u8bf7\u6c42\u5e76\u4fdd\u5b58Cookies\uff0c<code>session.get<\/code>\u53d1\u9001\u5176\u4ed6\u8bf7\u6c42\u65f6\u4f7f\u7528\u4fdd\u5b58\u7684Cookies\u3002<\/p>\n<\/p>\n<p><h4>5.2 \u4f7f\u7528Selenium\u5904\u7406\u4f1a\u8bdd<\/h4>\n<\/p>\n<p><p>Selenium\u53ef\u4ee5\u6a21\u62df\u6d4f\u89c8\u5668\u64cd\u4f5c\uff0c\u81ea\u52a8\u5904\u7406Cookies\u548c\u4f1a\u8bdd\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from selenium import webdriver<\/p>\n<p>driver = webdriver.Chrome()<\/p>\n<p>url = &#39;https:\/\/example.com\/login&#39;<\/p>\n<h2><strong>\u8bbf\u95ee\u767b\u5f55\u9875\u9762<\/strong><\/h2>\n<p>driver.get(url)<\/p>\n<h2><strong>\u8f93\u5165\u7528\u6237\u540d\u548c\u5bc6\u7801\uff0c\u63d0\u4ea4\u8868\u5355<\/strong><\/h2>\n<p>driver.find_element_by_name(&#39;username&#39;).send_keys(&#39;your-username&#39;)<\/p>\n<p>driver.find_element_by_name(&#39;password&#39;).send_keys(&#39;your-password&#39;)<\/p>\n<p>driver.find_element_by_name(&#39;submit&#39;).click()<\/p>\n<h2><strong>\u8bbf\u95ee\u53d7\u4fdd\u62a4\u7684\u9875\u9762<\/strong><\/h2>\n<p>protected_url = &#39;https:\/\/example.com\/protected-page&#39;<\/p>\n<p>driver.get(protected_url)<\/p>\n<p>print(driver.page_source)<\/p>\n<h2><strong>\u5173\u95ed\u6d4f\u89c8\u5668<\/strong><\/h2>\n<p>driver.quit()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u4e2a\u793a\u4f8b\u4e2d\uff0cSelenium\u6a21\u62df\u6d4f\u89c8\u5668\u64cd\u4f5c\uff0c\u81ea\u52a8\u5904\u7406\u767b\u5f55\u548c\u4f1a\u8bdd\uff0c\u83b7\u53d6\u53d7\u4fdd\u62a4\u9875\u9762\u7684\u6e90\u7801\u3002<\/p>\n<\/p>\n<p><h3>\u516d\u3001\u5904\u7406\u53cd\u722c\u866b\u673a\u5236<\/h3>\n<\/p>\n<p><p>\u6709\u4e9b\u7f51\u7ad9\u91c7\u7528\u53cd\u722c\u866b\u673a\u5236\uff0c\u9650\u5236\u722c\u866b\u8bbf\u95ee\u3002\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u65b9\u6cd5\u7ed5\u8fc7\u53cd\u722c\u866b\u673a\u5236\uff1a<\/p>\n<\/p>\n<p><h4>6.1 \u8bbe\u7f6e\u8bf7\u6c42\u5934<\/h4>\n<\/p>\n<p><p>\u8bbe\u7f6e\u8bf7\u6c42\u5934\uff0c\u6a21\u62df\u771f\u5b9e\u6d4f\u89c8\u5668\u8bf7\u6c42\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>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>url = &#39;https:\/\/example.com&#39;<\/p>\n<p>response = requests.get(url, headers=headers)<\/p>\n<p>print(response.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u4e2a\u793a\u4f8b\u4e2d\uff0c\u8bbe\u7f6e\u4e86<code>User-Agent<\/code>\u8bf7\u6c42\u5934\uff0c\u6a21\u62dfChrome\u6d4f\u89c8\u5668\u8bf7\u6c42\u3002<\/p>\n<\/p>\n<p><h4>6.2 \u4f7f\u7528\u4ee3\u7406<\/h4>\n<\/p>\n<p><p>\u4f7f\u7528\u4ee3\u7406IP\uff0c\u907f\u514d\u88ab\u5c01\u7981\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>proxies = {<\/p>\n<p>    &#39;http&#39;: &#39;http:\/\/your-proxy-ip:port&#39;,<\/p>\n<p>    &#39;https&#39;: &#39;https:\/\/your-proxy-ip:port&#39;<\/p>\n<p>}<\/p>\n<p>url = &#39;https:\/\/example.com&#39;<\/p>\n<p>response = requests.get(url, proxies=proxies)<\/p>\n<p>print(response.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u4e2a\u793a\u4f8b\u4e2d\uff0c\u901a\u8fc7\u8bbe\u7f6e\u4ee3\u7406IP\uff0c\u7ed5\u8fc7IP\u5c01\u7981\u3002<\/p>\n<\/p>\n<p><h4>6.3 \u8bbe\u7f6e\u8bf7\u6c42\u95f4\u9694<\/h4>\n<\/p>\n<p><p>\u8bbe\u7f6e\u8bf7\u6c42\u95f4\u9694\uff0c\u907f\u514d\u9891\u7e41\u8bf7\u6c42\u5bfc\u81f4\u5c01\u7981\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>import time<\/p>\n<p>url = &#39;https:\/\/example.com&#39;<\/p>\n<p>for i in range(10):<\/p>\n<p>    response = requests.get(url)<\/p>\n<p>    print(response.text)<\/p>\n<p>    time.sleep(2)  # \u8bbe\u7f6e\u8bf7\u6c42\u95f4\u96942\u79d2<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u4e2a\u793a\u4f8b\u4e2d\uff0c\u901a\u8fc7\u8bbe\u7f6e\u8bf7\u6c42\u95f4\u9694\uff0c\u907f\u514d\u9891\u7e41\u8bf7\u6c42\u5bfc\u81f4\u5c01\u7981\u3002<\/p>\n<\/p>\n<p><h3>\u4e03\u3001\u5904\u7406\u9a8c\u8bc1\u7801<\/h3>\n<\/p>\n<p><p>\u6709\u4e9b\u7f51\u7ad9\u4f7f\u7528\u9a8c\u8bc1\u7801\u9632\u6b62\u81ea\u52a8\u5316\u8bbf\u95ee\u3002\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u65b9\u6cd5\u5904\u7406\u9a8c\u8bc1\u7801\uff1a<\/p>\n<\/p>\n<p><h4>7.1 \u624b\u52a8\u8f93\u5165\u9a8c\u8bc1\u7801<\/h4>\n<\/p>\n<p><p>\u5bf9\u4e8e\u7b80\u5355\u7684\u9a8c\u8bc1\u7801\uff0c\u53ef\u4ee5\u624b\u52a8\u8f93\u5165\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from selenium import webdriver<\/p>\n<p>driver = webdriver.Chrome()<\/p>\n<p>url = &#39;https:\/\/example.com\/login&#39;<\/p>\n<h2><strong>\u8bbf\u95ee\u767b\u5f55\u9875\u9762<\/strong><\/h2>\n<p>driver.get(url)<\/p>\n<h2><strong>\u8f93\u5165\u7528\u6237\u540d\u548c\u5bc6\u7801<\/strong><\/h2>\n<p>driver.find_element_by_name(&#39;username&#39;).send_keys(&#39;your-username&#39;)<\/p>\n<p>driver.find_element_by_name(&#39;password&#39;).send_keys(&#39;your-password&#39;)<\/p>\n<h2><strong>\u6682\u505c\u7a0b\u5e8f\uff0c\u624b\u52a8\u8f93\u5165\u9a8c\u8bc1\u7801<\/strong><\/h2>\n<p>input(&#39;\u8f93\u5165\u9a8c\u8bc1\u7801\u540e\u6309\u56de\u8f66\u952e\u7ee7\u7eed\uff1a&#39;)<\/p>\n<h2><strong>\u63d0\u4ea4\u8868\u5355<\/strong><\/h2>\n<p>driver.find_element_by_name(&#39;submit&#39;).click()<\/p>\n<h2><strong>\u5173\u95ed\u6d4f\u89c8\u5668<\/strong><\/h2>\n<p>driver.quit()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u4e2a\u793a\u4f8b\u4e2d\uff0c\u7a0b\u5e8f\u6682\u505c\u7b49\u5f85\u624b\u52a8\u8f93\u5165\u9a8c\u8bc1\u7801\uff0c\u518d\u7ee7\u7eed\u6267\u884c\u3002<\/p>\n<\/p>\n<p><h4>7.2 \u4f7f\u7528\u6253\u7801\u5e73\u53f0<\/h4>\n<\/p>\n<p><p>\u5bf9\u4e8e\u590d\u6742\u7684\u9a8c\u8bc1\u7801\uff0c\u53ef\u4ee5\u4f7f\u7528\u6253\u7801\u5e73\u53f0\u81ea\u52a8\u8bc6\u522b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<h2><strong>\u4e0a\u4f20\u9a8c\u8bc1\u7801\u56fe\u7247\u5230\u6253\u7801\u5e73\u53f0<\/strong><\/h2>\n<p>captcha_image = open(&#39;captcha.jpg&#39;, &#39;rb&#39;)<\/p>\n<p>response = requests.post(&#39;https:\/\/captcha-api.com\/upload&#39;, files={&#39;file&#39;: captcha_image})<\/p>\n<p>captcha_image.close()<\/p>\n<h2><strong>\u83b7\u53d6\u9a8c\u8bc1\u7801\u8bc6\u522b\u7ed3\u679c<\/strong><\/h2>\n<p>captcha_code = response.json()[&#39;code&#39;]<\/p>\n<h2><strong>\u8f93\u5165\u9a8c\u8bc1\u7801<\/strong><\/h2>\n<p>driver.find_element_by_name(&#39;captcha&#39;).send_keys(captcha_code)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u4e2a\u793a\u4f8b\u4e2d\uff0c\u5c06\u9a8c\u8bc1\u7801\u56fe\u7247\u4e0a\u4f20\u5230\u6253\u7801\u5e73\u53f0\uff0c\u83b7\u53d6\u8bc6\u522b\u7ed3\u679c\u5e76\u8f93\u5165\u9a8c\u8bc1\u7801\u3002<\/p>\n<\/p>\n<p><h3>\u516b\u3001\u603b\u7ed3<\/h3>\n<\/p>\n<p><p>\u901a\u8fc7\u672c\u6587\u7684\u4ecb\u7ecd\uff0c\u6211\u4eec\u4e86\u89e3\u4e86Python\u722c\u866b\u83b7\u53d6\u7f51\u9875\u6e90\u7801\u7684\u591a\u79cd\u65b9\u6cd5\uff0c\u5305\u62ec\u4f7f\u7528Requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u6587\u6863\u3001\u4f7f\u7528Selenium\u5904\u7406\u52a8\u6001\u5185\u5bb9\u3001\u5904\u7406Ajax\u8bf7\u6c42\u3001\u5904\u7406Cookies\u548c\u4f1a\u8bdd\u3001\u7ed5\u8fc7\u53cd\u722c\u866b\u673a\u5236\u3001\u5904\u7406\u9a8c\u8bc1\u7801\u7b49\u3002<\/p>\n<\/p>\n<p><p>\u901a\u8fc7\u8fd9\u4e9b\u65b9\u6cd5\uff0c\u53ef\u4ee5\u9ad8\u6548\u5730\u83b7\u53d6\u7f51\u9875\u6e90\u7801\uff0c\u5e76\u63d0\u53d6\u6240\u9700\u6570\u636e\u3002\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u6839\u636e\u5177\u4f53\u9700\u6c42\u9009\u62e9\u5408\u9002\u7684\u65b9\u6cd5\uff0c\u7075\u6d3b\u5e94\u5bf9\u5404\u79cd\u6311\u6218\u3002\u5e0c\u671b\u672c\u6587\u5bf9\u60a8\u5b66\u4e60Python\u722c\u866b\u6709\u6240\u5e2e\u52a9\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u4f7f\u7528Python\u722c\u866b\u83b7\u53d6\u7f51\u9875\u7684HTML\u6e90\u7801\uff1f<\/strong><br \/>\u8981\u83b7\u53d6\u7f51\u9875\u7684HTML\u6e90\u7801\uff0c\u53ef\u4ee5\u4f7f\u7528Python\u4e2d\u7684requests\u5e93\u3002\u9996\u5148\uff0c\u5b89\u88c5requests\u5e93\u5e76\u5bfc\u5165\uff0c\u7136\u540e\u4f7f\u7528requests.get()\u65b9\u6cd5\u8bf7\u6c42\u7f51\u9875\uff0c\u63a5\u7740\u53ef\u4ee5\u901a\u8fc7response.text\u5c5e\u6027\u83b7\u53d6\u6e90\u7801\u3002\u793a\u4f8b\u4ee3\u7801\u5982\u4e0b\uff1a  <\/p>\n<pre><code class=\"language-python\">import requests\n\nurl = &#39;https:\/\/example.com&#39;\nresponse = requests.get(url)\nhtml_source = response.text\nprint(html_source)\n<\/code><\/pre>\n<p><strong>\u83b7\u53d6\u6e90\u7801\u65f6\u9047\u5230403 Forbidden\u9519\u8bef\u8be5\u5982\u4f55\u5904\u7406\uff1f<\/strong><br \/>403 Forbidden\u9519\u8bef\u901a\u5e38\u662f\u56e0\u4e3a\u670d\u52a1\u5668\u62d2\u7edd\u4e86\u8bf7\u6c42\u3002\u8fd9\u53ef\u80fd\u662f\u56e0\u4e3a\u7f3a\u5c11\u5fc5\u8981\u7684\u8bf7\u6c42\u5934\uff0c\u5982User-Agent\u3002\u53ef\u4ee5\u901a\u8fc7\u5728\u8bf7\u6c42\u4e2d\u6dfb\u52a0headers\u6765\u89e3\u51b3\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\uff1a  <\/p>\n<pre><code class=\"language-python\">headers = {&#39;User-Agent&#39;: &#39;Mozilla\/5.0&#39;}\nresponse = requests.get(url, headers=headers)\n<\/code><\/pre>\n<p><strong>\u5982\u4f55\u5904\u7406\u52a8\u6001\u52a0\u8f7d\u5185\u5bb9\u7684\u7f51\u9875\uff1f<\/strong><br \/>\u8bb8\u591a\u73b0\u4ee3\u7f51\u9875\u4f7f\u7528JavaScript\u52a8\u6001\u52a0\u8f7d\u5185\u5bb9\uff0c\u56e0\u6b64\u4ec5\u83b7\u53d6\u521d\u59cb\u7684HTML\u6e90\u7801\u53ef\u80fd\u4e0d\u8db3\u3002\u53ef\u4ee5\u4f7f\u7528Selenium\u5e93\u6a21\u62df\u6d4f\u89c8\u5668\u64cd\u4f5c\uff0c\u7b49\u5f85\u9875\u9762\u52a0\u8f7d\u5b8c\u6210\u540e\u518d\u83b7\u53d6\u6e90\u7801\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u57fa\u672c\u793a\u4f8b\uff1a  <\/p>\n<pre><code class=\"language-python\">from selenium import webdriver\n\ndriver = webdriver.Chrome()\ndriver.get(url)\nhtml_source = driver.page_source\ndriver.quit()\n<\/code><\/pre>\n<p>\u8fd9\u6837\u53ef\u4ee5\u786e\u4fdd\u83b7\u53d6\u5230\u52a8\u6001\u5185\u5bb9\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u8981\u83b7\u53d6\u7f51\u9875\u6e90\u7801\uff0cPython\u722c\u866b\u53ef\u4ee5\u4f7f\u7528\u8bf8\u5982Requests\u3001BeautifulSoup\u3001Selenium\u7b49\u5e93 [&hellip;]","protected":false},"author":3,"featured_media":1155152,"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\/1155139"}],"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=1155139"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1155139\/revisions"}],"predecessor-version":[{"id":1155154,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1155139\/revisions\/1155154"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1155152"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1155139"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1155139"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1155139"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}