{"id":1188422,"date":"2025-01-15T20:17:06","date_gmt":"2025-01-15T12:17:06","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1188422.html"},"modified":"2025-01-15T20:17:09","modified_gmt":"2025-01-15T12:17:09","slug":"%e5%a6%82%e4%bd%95%e4%bb%8epython%e4%b8%ad%e8%8e%b7%e5%8f%96%e7%bd%91%e9%a1%b5","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1188422.html","title":{"rendered":"\u5982\u4f55\u4ecepython\u4e2d\u83b7\u53d6\u7f51\u9875"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/25140733\/2d45811a-e5f3-4c2e-8b67-34c9e461d0ae.webp\" alt=\"\u5982\u4f55\u4ecepython\u4e2d\u83b7\u53d6\u7f51\u9875\" \/><\/p>\n<p><p> <strong>\u4ecePython\u4e2d\u83b7\u53d6\u7f51\u9875\u7684\u6b65\u9aa4\u5305\u62ec\uff1a\u4f7f\u7528<code>requests<\/code>\u5e93\u8fdb\u884cHTTP\u8bf7\u6c42\u3001\u4f7f\u7528<code>BeautifulSoup<\/code>\u5e93\u89e3\u6790HTML\u6570\u636e\u3001\u5904\u7406\u8bf7\u6c42\u5f02\u5e38\u3001\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\u3001\u4f7f\u7528<code>Scrapy<\/code>\u8fdb\u884c\u590d\u6742\u722c\u866b\u3002<\/strong> \u5176\u4e2d\uff0c<strong>\u4f7f\u7528<code>requests<\/code>\u5e93\u8fdb\u884cHTTP\u8bf7\u6c42<\/strong>\u662f\u6700\u5e38\u89c1\u7684\u65b9\u5f0f\u4e4b\u4e00\u3002<code>requests<\/code>\u5e93\u662f\u4e00\u4e2a\u7b80\u5355\u6613\u7528\u7684HTTP\u5e93\uff0c\u901a\u8fc7\u5b83\u53ef\u4ee5\u8f7b\u677e\u5730\u53d1\u9001HTTP\u8bf7\u6c42\u5e76\u83b7\u53d6\u670d\u52a1\u5668\u54cd\u5e94\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n<p><h3>\u4e00\u3001\u4f7f\u7528<code>requests<\/code>\u5e93\u8fdb\u884cHTTP\u8bf7\u6c42<\/h3>\n<\/p>\n<p><p><code>requests<\/code>\u5e93\u662f\u4e00\u4e2a\u7528\u4e8e\u53d1\u9001HTTP\u8bf7\u6c42\u7684Python\u5e93\uff0c\u5b83\u652f\u6301HTTP\u534f\u8bae\u7684\u6240\u6709\u65b9\u6cd5\uff0c\u5982GET\u3001POST\u3001PUT\u3001DELETE\u7b49\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u4f8b\u5b50\uff0c\u5c55\u793a\u5982\u4f55\u4f7f\u7528<code>requests<\/code>\u5e93\u4ece\u7f51\u9875\u83b7\u53d6\u6570\u636e\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<h2><strong>\u53d1\u9001HTTP GET\u8bf7\u6c42<\/strong><\/h2>\n<p>response = requests.get(&#39;https:\/\/www.example.com&#39;)<\/p>\n<h2><strong>\u83b7\u53d6\u54cd\u5e94\u5185\u5bb9<\/strong><\/h2>\n<p>html_content = response.text<\/p>\n<h2><strong>\u6253\u5370\u54cd\u5e94\u5185\u5bb9<\/strong><\/h2>\n<p>print(html_content)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u9996\u5148\u5bfc\u5165\u4e86<code>requests<\/code>\u5e93\uff0c\u7136\u540e\u4f7f\u7528<code>requests.get<\/code>\u65b9\u6cd5\u5411\u76ee\u6807URL\u53d1\u9001\u4e00\u4e2aGET\u8bf7\u6c42\uff0c\u5e76\u5c06\u54cd\u5e94\u5185\u5bb9\u5b58\u50a8\u5728<code>html_content<\/code>\u53d8\u91cf\u4e2d\u3002\u6700\u540e\uff0c\u6211\u4eec\u6253\u5370\u54cd\u5e94\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><h3>\u4e8c\u3001\u4f7f\u7528<code>BeautifulSoup<\/code>\u5e93\u89e3\u6790HTML\u6570\u636e<\/h3>\n<\/p>\n<p><p>\u83b7\u53d6\u7f51\u9875\u6570\u636e\u540e\uff0c\u901a\u5e38\u9700\u8981\u89e3\u6790HTML\u6570\u636e\u4ee5\u63d0\u53d6\u6240\u9700\u7684\u4fe1\u606f\u3002<code>BeautifulSoup<\/code>\u662f\u4e00\u4e2a\u7528\u4e8e\u89e3\u6790HTML\u548cXML\u7684Python\u5e93\uff0c\u5b83\u63d0\u4f9b\u4e86\u7b80\u5355\u6613\u7528\u7684\u65b9\u6cd5\u6765\u5bfc\u822a\u548c\u641c\u7d22\u89e3\u6790\u6811\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u4f8b\u5b50\uff0c\u5c55\u793a\u5982\u4f55\u4f7f\u7528<code>BeautifulSoup<\/code>\u89e3\u6790HTML\u6570\u636e\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from bs4 import BeautifulSoup<\/p>\n<h2><strong>\u5047\u8bbe\u6211\u4eec\u5df2\u7ecf\u4ece\u7f51\u9875\u83b7\u53d6\u4e86HTML\u5185\u5bb9<\/strong><\/h2>\n<p>html_content = &#39;&lt;html&gt;&lt;head&gt;&lt;title&gt;Example&lt;\/title&gt;&lt;\/head&gt;&lt;body&gt;&lt;h1&gt;Hello, World!&lt;\/h1&gt;&lt;\/body&gt;&lt;\/html&gt;&#39;<\/p>\n<h2><strong>\u521b\u5efaBeautifulSoup\u5bf9\u8c61<\/strong><\/h2>\n<p>soup = BeautifulSoup(html_content, &#39;html.parser&#39;)<\/p>\n<h2><strong>\u67e5\u627e\u6807\u9898\u6807\u7b7e<\/strong><\/h2>\n<p>title_tag = soup.title<\/p>\n<h2><strong>\u6253\u5370\u6807\u9898\u6807\u7b7e\u7684\u6587\u672c\u5185\u5bb9<\/strong><\/h2>\n<p>print(title_tag.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u9996\u5148\u5bfc\u5165\u4e86<code>BeautifulSoup<\/code>\u5e93\uff0c\u7136\u540e\u4f7f\u7528\u4ece\u7f51\u9875\u83b7\u53d6\u7684HTML\u5185\u5bb9\u521b\u5efa\u4e86\u4e00\u4e2a<code>BeautifulSoup<\/code>\u5bf9\u8c61\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u4f7f\u7528<code>soup.title<\/code>\u65b9\u6cd5\u67e5\u627eHTML\u6587\u6863\u4e2d\u7684\u6807\u9898\u6807\u7b7e\uff0c\u5e76\u6253\u5370\u5176\u6587\u672c\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><h3>\u4e09\u3001\u5904\u7406\u8bf7\u6c42\u5f02\u5e38<\/h3>\n<\/p>\n<p><p>\u5728\u8fdb\u884cHTTP\u8bf7\u6c42\u65f6\uff0c\u5904\u7406\u8bf7\u6c42\u5f02\u5e38\u662f\u975e\u5e38\u91cd\u8981\u7684\u3002<code>requests<\/code>\u5e93\u63d0\u4f9b\u4e86\u591a\u79cd\u65b9\u6cd5\u6765\u5904\u7406\u8bf7\u6c42\u5f02\u5e38\uff0c\u5982\u8d85\u65f6\u3001\u8fde\u63a5\u9519\u8bef\u7b49\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u4f8b\u5b50\uff0c\u5c55\u793a\u5982\u4f55\u5904\u7406\u8bf7\u6c42\u5f02\u5e38\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>from requests.exceptions import RequestException<\/p>\n<p>try:<\/p>\n<p>    # \u53d1\u9001HTTP GET\u8bf7\u6c42<\/p>\n<p>    response = requests.get(&#39;https:\/\/www.example.com&#39;, timeout=10)<\/p>\n<p>    # \u83b7\u53d6\u54cd\u5e94\u5185\u5bb9<\/p>\n<p>    html_content = response.text<\/p>\n<p>    # \u6253\u5370\u54cd\u5e94\u5185\u5bb9<\/p>\n<p>    print(html_content)<\/p>\n<p>except RequestException as e:<\/p>\n<p>    # \u6253\u5370\u5f02\u5e38\u4fe1\u606f<\/p>\n<p>    print(f&#39;Request f<a href=\"https:\/\/docs.pingcode.com\/blog\/59162.html\" target=\"_blank\">AI<\/a>led: {e}&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528\u4e86\u4e00\u4e2a<code>try<\/code>\u5757\u6765\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u5e76\u5728\u8bf7\u6c42\u5931\u8d25\u65f6\u6355\u83b7<code>RequestException<\/code>\u5f02\u5e38\u5e76\u6253\u5370\u5f02\u5e38\u4fe1\u606f\u3002<\/p>\n<\/p>\n<p><h3>\u56db\u3001\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a<\/h3>\n<\/p>\n<p><p>\u6709\u4e9b\u7f51\u7ad9\u4f1a\u68c0\u6d4b\u8bf7\u6c42\u7684\u6765\u6e90\uff0c\u5e76\u5bf9\u6765\u81ea\u975e\u6d4f\u89c8\u5668\u7684\u8bf7\u6c42\u8fdb\u884c\u9650\u5236\u3002\u4e3a\u4e86\u7ed5\u8fc7\u8fd9\u79cd\u9650\u5236\uff0c\u53ef\u4ee5\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\u3002\u4f8b\u5982\uff0c\u53ef\u4ee5\u5728HTTP\u8bf7\u6c42\u4e2d\u6dfb\u52a0User-Agent\u5934\u90e8\u4fe1\u606f\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<h2><strong>\u5b9a\u4e49\u8bf7\u6c42\u5934<\/strong><\/h2>\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\/91.0.4472.124 Safari\/537.36&#39;<\/p>\n<p>}<\/p>\n<h2><strong>\u53d1\u9001HTTP GET\u8bf7\u6c42<\/strong><\/h2>\n<p>response = requests.get(&#39;https:\/\/www.example.com&#39;, headers=headers)<\/p>\n<h2><strong>\u83b7\u53d6\u54cd\u5e94\u5185\u5bb9<\/strong><\/h2>\n<p>html_content = response.text<\/p>\n<h2><strong>\u6253\u5370\u54cd\u5e94\u5185\u5bb9<\/strong><\/h2>\n<p>print(html_content)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u5b9a\u4e49\u4e86\u4e00\u4e2a\u5305\u542bUser-Agent\u4fe1\u606f\u7684\u8bf7\u6c42\u5934\uff0c\u5e76\u5728\u53d1\u9001\u8bf7\u6c42\u65f6\u5c06\u5176\u6dfb\u52a0\u5230\u8bf7\u6c42\u4e2d\u3002<\/p>\n<\/p>\n<p><h3>\u4e94\u3001\u4f7f\u7528<code>Scrapy<\/code>\u8fdb\u884c\u590d\u6742\u722c\u866b<\/h3>\n<\/p>\n<p><p>\u5bf9\u4e8e\u66f4\u590d\u6742\u7684\u7f51\u9875\u6293\u53d6\u4efb\u52a1\uff0c\u53ef\u4ee5\u4f7f\u7528<code>Scrapy<\/code>\u6846\u67b6\u3002<code>Scrapy<\/code>\u662f\u4e00\u4e2a\u7528\u4e8e\u722c\u53d6\u7f51\u7ad9\u5e76\u63d0\u53d6\u7ed3\u6784\u5316\u6570\u636e\u7684Python\u6846\u67b6\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u4f8b\u5b50\uff0c\u5c55\u793a\u5982\u4f55\u4f7f\u7528<code>Scrapy<\/code>\u6293\u53d6\u6570\u636e\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import scrapy<\/p>\n<p>class ExampleSpider(scrapy.Spider):<\/p>\n<p>    name = &#39;example&#39;<\/p>\n<p>    start_urls = [&#39;https:\/\/www.example.com&#39;]<\/p>\n<p>    def parse(self, response):<\/p>\n<p>        # \u63d0\u53d6\u6807\u9898\u6587\u672c<\/p>\n<p>        title = response.xpath(&#39;\/\/title\/text()&#39;).get()<\/p>\n<p>        # \u6253\u5370\u6807\u9898\u6587\u672c<\/p>\n<p>        print(title)<\/p>\n<h2><strong>\u8fd0\u884c\u722c\u866b<\/strong><\/h2>\n<p>from scrapy.crawler import CrawlerProcess<\/p>\n<p>process = CrawlerProcess()<\/p>\n<p>process.crawl(ExampleSpider)<\/p>\n<p>process.start()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u5b9a\u4e49\u4e86\u4e00\u4e2a<code>ExampleSpider<\/code>\u7c7b\uff0c\u5b83\u7ee7\u627f\u81ea<code>scrapy.Spider<\/code>\u3002\u5728<code>parse<\/code>\u65b9\u6cd5\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528XPath\u9009\u62e9\u5668\u63d0\u53d6\u6807\u9898\u6587\u672c\uff0c\u5e76\u6253\u5370\u5176\u5185\u5bb9\u3002\u6700\u540e\uff0c\u6211\u4eec\u4f7f\u7528<code>CrawlerProcess<\/code>\u8fd0\u884c\u722c\u866b\u3002<\/p>\n<\/p>\n<p><h3>\u516d\u3001\u5904\u7406\u52a8\u6001\u7f51\u9875\u5185\u5bb9<\/h3>\n<\/p>\n<p><p>\u6709\u4e9b\u7f51\u7ad9\u4f7f\u7528JavaScript\u52a8\u6001\u52a0\u8f7d\u5185\u5bb9\uff0c<code>requests<\/code>\u5e93\u548c<code>BeautifulSoup<\/code>\u5e93\u65e0\u6cd5\u76f4\u63a5\u83b7\u53d6\u8fd9\u4e9b\u52a8\u6001\u5185\u5bb9\u3002\u4e3a\u4e86\u89e3\u51b3\u8fd9\u4e2a\u95ee\u9898\uff0c\u53ef\u4ee5\u4f7f\u7528<code>Selenium<\/code>\u5e93\u6765\u6a21\u62df\u6d4f\u89c8\u5668\u64cd\u4f5c\u5e76\u83b7\u53d6\u52a8\u6001\u5185\u5bb9\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u4f8b\u5b50\uff0c\u5c55\u793a\u5982\u4f55\u4f7f\u7528<code>Selenium<\/code>\u83b7\u53d6\u52a8\u6001\u5185\u5bb9\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<\/strong><\/h2>\n<p>driver = webdriver.Chrome()<\/p>\n<h2><strong>\u6253\u5f00\u76ee\u6807\u7f51\u9875<\/strong><\/h2>\n<p>driver.get(&#39;https:\/\/www.example.com&#39;)<\/p>\n<h2><strong>\u83b7\u53d6\u7f51\u9875\u5185\u5bb9<\/strong><\/h2>\n<p>html_content = driver.page_source<\/p>\n<h2><strong>\u6253\u5370\u7f51\u9875\u5185\u5bb9<\/strong><\/h2>\n<p>print(html_content)<\/p>\n<h2><strong>\u5173\u95ed\u6d4f\u89c8\u5668\u9a71\u52a8<\/strong><\/h2>\n<p>driver.quit()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528<code>webdriver.Chrome<\/code>\u521b\u5efa\u4e86\u4e00\u4e2aChrome\u6d4f\u89c8\u5668\u9a71\u52a8\uff0c\u5e76\u6253\u5f00\u4e86\u76ee\u6807\u7f51\u9875\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u4f7f\u7528<code>driver.page_source<\/code>\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u5e76\u6253\u5370\u5176\u5185\u5bb9\u3002\u6700\u540e\uff0c\u6211\u4eec\u5173\u95ed\u6d4f\u89c8\u5668\u9a71\u52a8\u3002<\/p>\n<\/p>\n<p><h3>\u4e03\u3001\u4f7f\u7528\u4ee3\u7406<\/h3>\n<\/p>\n<p><p>\u6709\u4e9b\u7f51\u7ad9\u4f1a\u9650\u5236\u6765\u81ea\u540c\u4e00IP\u5730\u5740\u7684\u8bf7\u6c42\u9891\u7387\uff0c\u4e3a\u4e86\u7ed5\u8fc7\u8fd9\u79cd\u9650\u5236\uff0c\u53ef\u4ee5\u4f7f\u7528\u4ee3\u7406\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u4f8b\u5b50\uff0c\u5c55\u793a\u5982\u4f55\u5728<code>requests<\/code>\u5e93\u4e2d\u4f7f\u7528\u4ee3\u7406\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<h2><strong>\u5b9a\u4e49\u4ee3\u7406<\/strong><\/h2>\n<p>proxies = {<\/p>\n<p>    &#39;http&#39;: &#39;http:\/\/proxy.example.com:8080&#39;,<\/p>\n<p>    &#39;https&#39;: &#39;http:\/\/proxy.example.com:8080&#39;<\/p>\n<p>}<\/p>\n<h2><strong>\u53d1\u9001HTTP GET\u8bf7\u6c42<\/strong><\/h2>\n<p>response = requests.get(&#39;https:\/\/www.example.com&#39;, proxies=proxies)<\/p>\n<h2><strong>\u83b7\u53d6\u54cd\u5e94\u5185\u5bb9<\/strong><\/h2>\n<p>html_content = response.text<\/p>\n<h2><strong>\u6253\u5370\u54cd\u5e94\u5185\u5bb9<\/strong><\/h2>\n<p>print(html_content)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u5b9a\u4e49\u4e86\u4e00\u4e2a\u5305\u542b\u4ee3\u7406\u4fe1\u606f\u7684\u5b57\u5178\uff0c\u5e76\u5728\u53d1\u9001\u8bf7\u6c42\u65f6\u5c06\u5176\u6dfb\u52a0\u5230\u8bf7\u6c42\u4e2d\u3002<\/p>\n<\/p>\n<p><h3>\u516b\u3001\u4f7f\u7528Session\u4fdd\u6301\u4f1a\u8bdd<\/h3>\n<\/p>\n<p><p>\u5728\u67d0\u4e9b\u60c5\u51b5\u4e0b\uff0c\u9700\u8981\u5728\u591a\u4e2a\u8bf7\u6c42\u4e4b\u95f4\u4fdd\u6301\u4f1a\u8bdd\u72b6\u6001\uff0c\u4f8b\u5982\u767b\u5f55\u540e\u8bbf\u95ee\u53d7\u4fdd\u62a4\u7684\u9875\u9762\u3002<code>requests<\/code>\u5e93\u63d0\u4f9b\u4e86\u4e00\u4e2a<code>Session<\/code>\u5bf9\u8c61\u6765\u5904\u7406\u8fd9\u79cd\u60c5\u51b5\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u4f8b\u5b50\uff0c\u5c55\u793a\u5982\u4f55\u4f7f\u7528<code>Session<\/code>\u4fdd\u6301\u4f1a\u8bdd\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<h2><strong>\u521b\u5efaSession\u5bf9\u8c61<\/strong><\/h2>\n<p>session = requests.Session()<\/p>\n<h2><strong>\u53d1\u9001\u767b\u5f55\u8bf7\u6c42<\/strong><\/h2>\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(&#39;https:\/\/www.example.com\/login&#39;, data=login_data)<\/p>\n<h2><strong>\u53d1\u9001\u53d7\u4fdd\u62a4\u9875\u9762\u7684\u8bf7\u6c42<\/strong><\/h2>\n<p>response = session.get(&#39;https:\/\/www.example.com\/protected&#39;)<\/p>\n<h2><strong>\u83b7\u53d6\u54cd\u5e94\u5185\u5bb9<\/strong><\/h2>\n<p>html_content = response.text<\/p>\n<h2><strong>\u6253\u5370\u54cd\u5e94\u5185\u5bb9<\/strong><\/h2>\n<p>print(html_content)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u9996\u5148\u521b\u5efa\u4e86\u4e00\u4e2a<code>Session<\/code>\u5bf9\u8c61\uff0c\u7136\u540e\u4f7f\u7528<code>session.post<\/code>\u65b9\u6cd5\u53d1\u9001\u767b\u5f55\u8bf7\u6c42\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u4f7f\u7528<code>session.get<\/code>\u65b9\u6cd5\u8bbf\u95ee\u53d7\u4fdd\u62a4\u7684\u9875\u9762\u5e76\u83b7\u53d6\u54cd\u5e94\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><h3>\u4e5d\u3001\u5904\u7406Cookies<\/h3>\n<\/p>\n<p><p>\u6709\u4e9b\u7f51\u7ad9\u4f7f\u7528Cookies\u6765\u8ddf\u8e2a\u4f1a\u8bdd\u72b6\u6001\u6216\u5b58\u50a8\u7528\u6237\u504f\u597d\u3002<code>requests<\/code>\u5e93\u63d0\u4f9b\u4e86\u65b9\u6cd5\u6765\u5904\u7406Cookies\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u4f8b\u5b50\uff0c\u5c55\u793a\u5982\u4f55\u5728<code>requests<\/code>\u5e93\u4e2d\u5904\u7406Cookies\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<h2><strong>\u521b\u5efaSession\u5bf9\u8c61<\/strong><\/h2>\n<p>session = requests.Session()<\/p>\n<h2><strong>\u53d1\u9001\u8bf7\u6c42\u5e76\u83b7\u53d6\u54cd\u5e94<\/strong><\/h2>\n<p>response = session.get(&#39;https:\/\/www.example.com&#39;)<\/p>\n<h2><strong>\u6253\u5370Cookies<\/strong><\/h2>\n<p>print(session.cookies)<\/p>\n<h2><strong>\u8bbe\u7f6e\u81ea\u5b9a\u4e49Cookie<\/strong><\/h2>\n<p>session.cookies.set(&#39;my_cookie&#39;, &#39;cookie_value&#39;)<\/p>\n<h2><strong>\u53d1\u9001\u8bf7\u6c42\u5e76\u83b7\u53d6\u54cd\u5e94<\/strong><\/h2>\n<p>response = session.get(&#39;https:\/\/www.example.com&#39;)<\/p>\n<h2><strong>\u6253\u5370\u54cd\u5e94\u5185\u5bb9<\/strong><\/h2>\n<p>html_content = response.text<\/p>\n<p>print(html_content)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u9996\u5148\u521b\u5efa\u4e86\u4e00\u4e2a<code>Session<\/code>\u5bf9\u8c61\uff0c\u5e76\u4f7f\u7528<code>session.get<\/code>\u65b9\u6cd5\u53d1\u9001\u8bf7\u6c42\u5e76\u83b7\u53d6\u54cd\u5e94\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u6253\u5370\u4e86\u4f1a\u8bdd\u4e2d\u7684Cookies\uff0c\u5e76\u8bbe\u7f6e\u4e86\u4e00\u4e2a\u81ea\u5b9a\u4e49Cookie\u3002\u6700\u540e\uff0c\u6211\u4eec\u518d\u6b21\u53d1\u9001\u8bf7\u6c42\u5e76\u6253\u5370\u54cd\u5e94\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><h3>\u5341\u3001\u5904\u7406\u91cd\u5b9a\u5411<\/h3>\n<\/p>\n<p><p>\u6709\u4e9b\u7f51\u7ad9\u4f1a\u5728\u67d0\u4e9b\u60c5\u51b5\u4e0b\u8fdb\u884c\u91cd\u5b9a\u5411\u3002<code>requests<\/code>\u5e93\u9ed8\u8ba4\u5904\u7406\u91cd\u5b9a\u5411\uff0c\u4f46\u53ef\u4ee5\u7981\u7528\u81ea\u52a8\u91cd\u5b9a\u5411\u5e76\u624b\u52a8\u5904\u7406\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u4f8b\u5b50\uff0c\u5c55\u793a\u5982\u4f55\u5904\u7406\u91cd\u5b9a\u5411\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<h2><strong>\u53d1\u9001\u8bf7\u6c42\u5e76\u7981\u7528\u81ea\u52a8\u91cd\u5b9a\u5411<\/strong><\/h2>\n<p>response = requests.get(&#39;https:\/\/www.example.com&#39;, allow_redirects=False)<\/p>\n<h2><strong>\u6253\u5370\u91cd\u5b9a\u5411\u5730\u5740<\/strong><\/h2>\n<p>if response.is_redirect:<\/p>\n<p>    print(response.headers[&#39;Location&#39;])<\/p>\n<h2><strong>\u53d1\u9001\u91cd\u5b9a\u5411\u540e\u7684\u8bf7\u6c42<\/strong><\/h2>\n<p>redirect_url = response.headers[&#39;Location&#39;]<\/p>\n<p>response = requests.get(redirect_url)<\/p>\n<h2><strong>\u83b7\u53d6\u54cd\u5e94\u5185\u5bb9<\/strong><\/h2>\n<p>html_content = response.text<\/p>\n<h2><strong>\u6253\u5370\u54cd\u5e94\u5185\u5bb9<\/strong><\/h2>\n<p>print(html_content)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u8fd9\u4e2a\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528<code>allow_redirects=False<\/code>\u7981\u7528\u4e86\u81ea\u52a8\u91cd\u5b9a\u5411\uff0c\u5e76\u624b\u52a8\u5904\u7406\u91cd\u5b9a\u5411\u5730\u5740\u3002<\/p>\n<\/p>\n<p><p>\u901a\u8fc7\u4ee5\u4e0a\u65b9\u6cd5\uff0c\u53ef\u4ee5\u5728Python\u4e2d\u6709\u6548\u5730\u83b7\u53d6\u7f51\u9875\u5e76\u5904\u7406\u5404\u79cd\u590d\u6742\u60c5\u51b5\u3002\u65e0\u8bba\u662f\u7b80\u5355\u7684HTTP\u8bf7\u6c42\u8fd8\u662f\u590d\u6742\u7684\u7f51\u9875\u6293\u53d6\u4efb\u52a1\uff0c\u90fd\u53ef\u4ee5\u4f7f\u7528\u8fd9\u4e9b\u6280\u5de7\u6765\u5b9e\u73b0\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u4f7f\u7528Python\u83b7\u53d6\u7f51\u9875\u7684\u5185\u5bb9\uff1f<\/strong><br \/>\u4f7f\u7528Python\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u53ef\u4ee5\u901a\u8fc7\u591a\u79cd\u5e93\u5b9e\u73b0\uff0c\u6700\u5e38\u7528\u7684\u5305\u62ec<code>requests<\/code>\u548c<code>BeautifulSoup<\/code>\u3002<code>requests<\/code>\u5e93\u53ef\u4ee5\u5e2e\u52a9\u4f60\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u83b7\u53d6\u7f51\u9875\u7684\u539f\u59cbHTML\u5185\u5bb9\uff0c\u800c<code>BeautifulSoup<\/code>\u5219\u53ef\u4ee5\u7528\u6765\u89e3\u6790\u8fd9\u4e9bHTML\u5185\u5bb9\uff0c\u63d0\u53d6\u6240\u9700\u7684\u6570\u636e\u3002\u9996\u5148\uff0c\u4f60\u9700\u8981\u5b89\u88c5\u8fd9\u4e24\u4e2a\u5e93\uff0c\u7136\u540e\u901a\u8fc7\u7b80\u5355\u7684\u4ee3\u7801\u5373\u53ef\u83b7\u53d6\u5e76\u89e3\u6790\u7f51\u9875\u3002<\/p>\n<p><strong>\u5728Python\u4e2d\u5982\u4f55\u5904\u7406\u83b7\u53d6\u7684\u7f51\u9875\u6570\u636e\uff1f<\/strong><br \/>\u83b7\u53d6\u7f51\u9875\u540e\uff0c\u4f60\u53ef\u80fd\u9700\u8981\u5bf9\u6570\u636e\u8fdb\u884c\u5904\u7406\u548c\u5206\u6790\u3002\u53ef\u4ee5\u4f7f\u7528<code>BeautifulSoup<\/code>\u5e93\u6765\u67e5\u627e\u7279\u5b9a\u7684HTML\u6807\u7b7e\u548c\u5185\u5bb9\uff0c\u6bd4\u5982\u63d0\u53d6\u6587\u672c\u3001\u94fe\u63a5\u6216\u56fe\u7247\u7b49\u3002\u6b64\u5916\uff0c\u7ed3\u5408<code>pandas<\/code>\u5e93\u53ef\u4ee5\u5c06\u6570\u636e\u6574\u7406\u6210\u8868\u683c\u5f62\u5f0f\uff0c\u4fbf\u4e8e\u8fdb\u4e00\u6b65\u5206\u6790\u548c\u4f7f\u7528\u3002<\/p>\n<p><strong>\u4f7f\u7528Python\u83b7\u53d6\u7f51\u9875\u65f6\u9700\u8981\u6ce8\u610f\u54ea\u4e9b\u95ee\u9898\uff1f<\/strong><br \/>\u5728\u4f7f\u7528Python\u83b7\u53d6\u7f51\u9875\u65f6\uff0c\u6709\u51e0\u4e2a\u91cd\u8981\u7684\u6ce8\u610f\u4e8b\u9879\u3002\u9996\u5148\uff0c\u786e\u4fdd\u9075\u5faa\u7f51\u7ad9\u7684<code>robots.txt<\/code>\u6587\u4ef6\uff0c\u4e86\u89e3\u7f51\u7ad9\u5141\u8bb8\u722c\u53d6\u7684\u5185\u5bb9\u3002\u5176\u6b21\uff0c\u9891\u7e41\u8bf7\u6c42\u53ef\u80fd\u5bfc\u81f4IP\u88ab\u5c01\u7981\uff0c\u56e0\u6b64\u53ef\u4ee5\u4f7f\u7528\u65f6\u95f4\u95f4\u9694\u6216\u968f\u673a\u5ef6\u8fdf\u6765\u63a7\u5236\u8bf7\u6c42\u9891\u7387\u3002\u6b64\u5916\uff0c\u5bf9\u4e8e\u4e00\u4e9b\u9700\u8981\u767b\u5f55\u6216\u4f7f\u7528API\u7684\u7f51\u9875\uff0c\u53ef\u80fd\u9700\u8981\u5904\u7406\u8eab\u4efd\u9a8c\u8bc1\u548c\u4f1a\u8bdd\u7ba1\u7406\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u4ecePython\u4e2d\u83b7\u53d6\u7f51\u9875\u7684\u6b65\u9aa4\u5305\u62ec\uff1a\u4f7f\u7528requests\u5e93\u8fdb\u884cHTTP\u8bf7\u6c42\u3001\u4f7f\u7528BeautifulSoup\u5e93\u89e3 [&hellip;]","protected":false},"author":3,"featured_media":1188430,"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\/1188422"}],"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=1188422"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1188422\/revisions"}],"predecessor-version":[{"id":1188433,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1188422\/revisions\/1188433"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1188430"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1188422"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1188422"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1188422"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}