{"id":1034029,"date":"2024-12-31T11:46:51","date_gmt":"2024-12-31T03:46:51","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1034029.html"},"modified":"2024-12-31T11:46:54","modified_gmt":"2024-12-31T03:46:54","slug":"python%e6%95%b0%e6%8d%ae%e7%88%ac%e5%8f%96%e6%98%af%e5%a6%82%e4%bd%95%e5%ae%9e%e7%8e%b0%e7%9a%84","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1034029.html","title":{"rendered":"python\u6570\u636e\u722c\u53d6\u662f\u5982\u4f55\u5b9e\u73b0\u7684"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-docs.pingcode.com\/wp-content\/uploads\/2024\/12\/9eea0d11-b694-46b2-9c02-8636123cf248.webp?x-oss-process=image\/auto-orient,1\/format,webp\" alt=\"python\u6570\u636e\u722c\u53d6\u662f\u5982\u4f55\u5b9e\u73b0\u7684\" \/><\/p>\n<p><p> <strong>Python\u6570\u636e\u722c\u53d6\u662f\u901a\u8fc7\u4f7f\u7528Python\u7f16\u7a0b\u8bed\u8a00\u548c\u76f8\u5173\u5e93\uff08\u5982BeautifulSoup\u3001Scrapy\u3001Requests\u7b49\uff09\u6765\u81ea\u52a8\u5316\u63d0\u53d6\u7f51\u9875\u4e0a\u7684\u6570\u636e\u3001\u89e3\u6790HTML\u5185\u5bb9\u3001\u6a21\u62df\u7528\u6237\u64cd\u4f5c\u7b49\u65b9\u5f0f\u5b9e\u73b0\u7684\u3002<\/strong> Python\u6570\u636e\u722c\u53d6\u6d89\u53ca\u591a\u4e2a\u6b65\u9aa4\uff0c\u5305\u62ec\u53d1\u9001HTTP\u8bf7\u6c42\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3001\u89e3\u6790HTML\u6587\u6863\u3001\u63d0\u53d6\u6240\u9700\u6570\u636e\u3001\u5904\u7406\u548c\u5b58\u50a8\u6570\u636e\u7b49\u3002\u5728\u8fd9\u4e9b\u6b65\u9aa4\u4e2d\uff0c\u9009\u62e9\u5408\u9002\u7684\u5de5\u5177\u548c\u5e93\u80fd\u591f\u5927\u5927\u63d0\u9ad8\u6548\u7387\u548c\u51c6\u786e\u6027\u3002\u4e0b\u9762\u5c06\u8be6\u7ec6\u4ecb\u7ecdPython\u6570\u636e\u722c\u53d6\u7684\u5b9e\u73b0\u65b9\u6cd5\u548c\u6280\u5de7\u3002<\/p>\n<\/p>\n<p><h3>\u4e00\u3001\u9009\u62e9\u5408\u9002\u7684\u5e93<\/h3>\n<\/p>\n<p><p>\u5728\u8fdb\u884c\u6570\u636e\u722c\u53d6\u65f6\uff0c\u9009\u62e9\u5408\u9002\u7684\u5e93\u662f\u5173\u952e\u3002Python\u6709\u591a\u4e2a\u7528\u4e8e\u722c\u53d6\u6570\u636e\u7684\u5e93\uff0c\u6bcf\u4e2a\u5e93\u90fd\u6709\u5176\u72ec\u7279\u7684\u529f\u80fd\u548c\u9002\u7528\u573a\u666f\u3002\u4ee5\u4e0b\u662f\u4e00\u4e9b\u5e38\u7528\u7684Python\u722c\u866b\u5e93\uff1a<\/p>\n<\/p>\n<ol>\n<li>\n<p><strong>Requests<\/strong>\uff1a\u7528\u4e8e\u53d1\u9001HTTP\u8bf7\u6c42\u548c\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u7684\u5e93\u3002Requests\u5e93\u975e\u5e38\u7b80\u5355\u6613\u7528\uff0c\u9002\u5408\u521d\u5b66\u8005\u4f7f\u7528\u3002\u901a\u8fc7Requests\u5e93\uff0c\u53ef\u4ee5\u8f7b\u677e\u5730\u53d1\u9001GET\u3001POST\u7b49\u8bf7\u6c42\uff0c\u5e76\u83b7\u53d6\u7f51\u9875\u7684HTML\u5185\u5bb9\u3002<\/p>\n<\/p>\n<\/li>\n<li>\n<p><strong>BeautifulSoup<\/strong>\uff1a\u7528\u4e8e\u89e3\u6790HTML\u548cXML\u6587\u6863\u7684\u5e93\u3002BeautifulSoup\u53ef\u4ee5\u65b9\u4fbf\u5730\u63d0\u53d6\u7f51\u9875\u4e2d\u7684\u6570\u636e\uff0c\u9002\u5408\u5904\u7406\u9759\u6001\u7f51\u9875\u3002\u5b83\u80fd\u591f\u5c06\u590d\u6742\u7684HTML\u6587\u6863\u89e3\u6790\u6210\u6811\u7ed3\u6784\uff0c\u65b9\u4fbf\u7528\u6237\u8fdb\u884c\u6570\u636e\u63d0\u53d6\u3002<\/p>\n<\/p>\n<\/li>\n<li>\n<p><strong>Scrapy<\/strong>\uff1a\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684\u722c\u866b\u6846\u67b6\uff0c\u9002\u5408\u5904\u7406\u590d\u6742\u7684\u722c\u53d6\u4efb\u52a1\u3002Scrapy\u4e0d\u4ec5\u53ef\u4ee5\u53d1\u9001HTTP\u8bf7\u6c42\u548c\u89e3\u6790HTML\uff0c\u8fd8\u53ef\u4ee5\u5904\u7406\u91cd\u5b9a\u5411\u3001\u8ddf\u8e2a\u94fe\u63a5\u7b49\u9ad8\u7ea7\u529f\u80fd\u3002\u5b83\u652f\u6301\u5f02\u6b65\u5904\u7406\uff0c\u80fd\u591f\u5927\u5927\u63d0\u9ad8\u722c\u53d6\u6548\u7387\u3002<\/p>\n<\/p>\n<\/li>\n<li>\n<p><strong>Selenium<\/strong>\uff1a\u7528\u4e8e\u6a21\u62df\u6d4f\u89c8\u5668\u64cd\u4f5c\u7684\u5e93\uff0c\u9002\u5408\u5904\u7406\u52a8\u6001\u7f51\u9875\u3002Selenium\u53ef\u4ee5\u6a21\u62df\u7528\u6237\u7684\u70b9\u51fb\u3001\u8f93\u5165\u7b49\u64cd\u4f5c\uff0c\u9002\u7528\u4e8e\u9700\u8981\u4e0e\u7f51\u9875\u8fdb\u884c\u4ea4\u4e92\u7684\u573a\u666f\u3002\u5b83\u652f\u6301\u591a\u79cd\u6d4f\u89c8\u5668\uff0c\u5982Chrome\u3001Firefox\u7b49\u3002<\/p>\n<\/p>\n<\/li>\n<\/ol>\n<p><h3>\u4e8c\u3001\u53d1\u9001HTTP\u8bf7\u6c42<\/h3>\n<\/p>\n<p><p>\u6570\u636e\u722c\u53d6\u7684\u7b2c\u4e00\u6b65\u662f\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u83b7\u53d6\u7f51\u9875\u7684\u5185\u5bb9\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Requests\u5e93\u6765\u5b9e\u73b0\u8fd9\u4e00\u529f\u80fd\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u793a\u4f8b\u4ee3\u7801\uff0c\u6f14\u793a\u5982\u4f55\u4f7f\u7528Requests\u5e93\u53d1\u9001GET\u8bf7\u6c42\u5e76\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\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>print(html_content)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u4e0a\u8ff0\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u9996\u5148\u5bfc\u5165Requests\u5e93\uff0c\u7136\u540e\u4f7f\u7528<code>requests.get()<\/code>\u65b9\u6cd5\u53d1\u9001GET\u8bf7\u6c42\uff0c\u5e76\u5c06\u54cd\u5e94\u7684\u5185\u5bb9\u5b58\u50a8\u5728<code>html_content<\/code>\u53d8\u91cf\u4e2d\u3002\u6700\u540e\uff0c\u6211\u4eec\u6253\u5370\u51fa\u7f51\u9875\u7684HTML\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><h3>\u4e09\u3001\u89e3\u6790HTML\u6587\u6863<\/h3>\n<\/p>\n<p><p>\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u540e\uff0c\u6211\u4eec\u9700\u8981\u89e3\u6790HTML\u6587\u6863\uff0c\u63d0\u53d6\u6240\u9700\u7684\u6570\u636e\u3002BeautifulSoup\u662f\u4e00\u4e2a\u975e\u5e38\u6d41\u884c\u7684\u89e3\u6790\u5e93\uff0c\u5b83\u53ef\u4ee5\u5c06HTML\u6587\u6863\u89e3\u6790\u6210\u6811\u7ed3\u6784\uff0c\u65b9\u4fbf\u6211\u4eec\u8fdb\u884c\u6570\u636e\u63d0\u53d6\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\u4ee3\u7801\uff0c\u6f14\u793a\u5982\u4f55\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u6587\u6863\u5e76\u63d0\u53d6\u6570\u636e\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from bs4 import BeautifulSoup<\/p>\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<p>soup = BeautifulSoup(html_content, &#39;html.parser&#39;)<\/p>\n<h2><strong>\u63d0\u53d6\u6807\u9898<\/strong><\/h2>\n<p>title = soup.title.string<\/p>\n<p>print(&#39;Title:&#39;, title)<\/p>\n<h2><strong>\u63d0\u53d6\u6b63\u6587\u5185\u5bb9<\/strong><\/h2>\n<p>body = soup.body.h1.string<\/p>\n<p>print(&#39;Body:&#39;, body)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u4e0a\u8ff0\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u9996\u5148\u5bfc\u5165BeautifulSoup\u5e93\uff0c\u7136\u540e\u5c06HTML\u5185\u5bb9\u89e3\u6790\u6210BeautifulSoup\u5bf9\u8c61\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u53ef\u4ee5\u901a\u8fc7\u5bf9\u8c61\u7684\u5c5e\u6027\u548c\u65b9\u6cd5\u63d0\u53d6\u6240\u9700\u7684\u6570\u636e\uff0c\u4f8b\u5982\u83b7\u53d6\u6807\u9898\u548c\u6b63\u6587\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><h3>\u56db\u3001\u5904\u7406\u52a8\u6001\u7f51\u9875<\/h3>\n<\/p>\n<p><p>\u5bf9\u4e8e\u4e00\u4e9b\u52a8\u6001\u7f51\u9875\uff0c\u4f7f\u7528Requests\u548cBeautifulSoup\u53ef\u80fd\u65e0\u6cd5\u83b7\u53d6\u5230\u5b8c\u6574\u7684\u7f51\u9875\u5185\u5bb9\u3002\u8fd9\u65f6\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Selenium\u5e93\u6765\u6a21\u62df\u6d4f\u89c8\u5668\u64cd\u4f5c\uff0c\u83b7\u53d6\u52a8\u6001\u52a0\u8f7d\u7684\u6570\u636e\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\u4ee3\u7801\uff0c\u6f14\u793a\u5982\u4f55\u4f7f\u7528Selenium\u83b7\u53d6\u52a8\u6001\u7f51\u9875\u5185\u5bb9\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from selenium import webdriver<\/p>\n<p>url = &#39;https:\/\/example.com&#39;<\/p>\n<p>driver = webdriver.Chrome()<\/p>\n<p>driver.get(url)<\/p>\n<h2><strong>\u83b7\u53d6\u7f51\u9875\u5185\u5bb9<\/strong><\/h2>\n<p>html_content = driver.page_source<\/p>\n<p>print(html_content)<\/p>\n<p>driver.quit()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u4e0a\u8ff0\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u9996\u5148\u5bfc\u5165Selenium\u5e93\u5e76\u521d\u59cb\u5316Chrome\u6d4f\u89c8\u5668\u9a71\u52a8\uff0c\u7136\u540e\u4f7f\u7528<code>driver.get()<\/code>\u65b9\u6cd5\u6253\u5f00\u7f51\u9875\uff0c\u5e76\u901a\u8fc7<code>driver.page_source<\/code>\u83b7\u53d6\u7f51\u9875\u7684HTML\u5185\u5bb9\u3002\u6700\u540e\uff0c\u6211\u4eec\u5173\u95ed\u6d4f\u89c8\u5668\u9a71\u52a8\u3002<\/p>\n<\/p>\n<p><h3>\u4e94\u3001\u5904\u7406\u548c\u5b58\u50a8\u6570\u636e<\/h3>\n<\/p>\n<p><p>\u5728\u6210\u529f\u63d0\u53d6\u5230\u6240\u9700\u7684\u6570\u636e\u540e\uff0c\u6211\u4eec\u9700\u8981\u5bf9\u6570\u636e\u8fdb\u884c\u5904\u7406\u548c\u5b58\u50a8\u3002\u5904\u7406\u6570\u636e\u7684\u65b9\u5f0f\u53d6\u51b3\u4e8e\u5177\u4f53\u9700\u6c42\uff0c\u53ef\u80fd\u5305\u62ec\u6e05\u6d17\u3001\u683c\u5f0f\u5316\u3001\u53bb\u91cd\u7b49\u64cd\u4f5c\u3002\u5b58\u50a8\u6570\u636e\u7684\u65b9\u5f0f\u4e5f\u6709\u591a\u79cd\u9009\u62e9\uff0c\u53ef\u4ee5\u5b58\u50a8\u5728\u672c\u5730\u6587\u4ef6\u3001\u6570\u636e\u5e93\u3001\u4e91\u5b58\u50a8\u7b49\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u793a\u4f8b\u4ee3\u7801\uff0c\u6f14\u793a\u5982\u4f55\u5c06\u63d0\u53d6\u7684\u6570\u636e\u5b58\u50a8\u5230CSV\u6587\u4ef6\u4e2d\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import csv<\/p>\n<p>data = [<\/p>\n<p>    [&#39;Title&#39;, &#39;Body&#39;],<\/p>\n<p>    [&#39;Example&#39;, &#39;Hello, World!&#39;]<\/p>\n<p>]<\/p>\n<p>with open(&#39;data.csv&#39;, &#39;w&#39;, newline=&#39;&#39;) as file:<\/p>\n<p>    writer = csv.writer(file)<\/p>\n<p>    writer.writerows(data)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u4e0a\u8ff0\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u9996\u5148\u5b9a\u4e49\u4e00\u4e2a\u5305\u542b\u6570\u636e\u7684\u5217\u8868\uff0c\u7136\u540e\u4f7f\u7528<code>csv.writer<\/code>\u5c06\u6570\u636e\u5199\u5165\u5230CSV\u6587\u4ef6\u4e2d\u3002<\/p>\n<\/p>\n<p><h3>\u516d\u3001\u9075\u5b88\u722c\u866b\u89c4\u8303<\/h3>\n<\/p>\n<p><p>\u5728\u8fdb\u884c\u6570\u636e\u722c\u53d6\u65f6\uff0c\u6211\u4eec\u9700\u8981\u9075\u5b88\u722c\u866b\u89c4\u8303\uff0c\u907f\u514d\u5bf9\u76ee\u6807\u7f51\u7ad9\u9020\u6210\u8d1f\u62c5\u6216\u5f15\u8d77\u6cd5\u5f8b\u95ee\u9898\u3002\u4ee5\u4e0b\u662f\u4e00\u4e9b\u5e38\u89c1\u7684\u722c\u866b\u89c4\u8303\uff1a<\/p>\n<\/p>\n<ol>\n<li>\n<p><strong>\u9075\u5b88robots.txt<\/strong>\uff1a\u5927\u591a\u6570\u7f51\u7ad9\u90fd\u6709\u4e00\u4e2a<code>robots.txt<\/code>\u6587\u4ef6\uff0c\u7528\u4e8e\u6307\u5b9a\u54ea\u4e9b\u9875\u9762\u5141\u8bb8\u722c\u53d6\uff0c\u54ea\u4e9b\u9875\u9762\u7981\u6b62\u722c\u53d6\u3002\u5728\u5f00\u59cb\u722c\u53d6\u4e4b\u524d\uff0c\u6211\u4eec\u5e94\u8be5\u68c0\u67e5\u76ee\u6807\u7f51\u7ad9\u7684<code>robots.txt<\/code>\u6587\u4ef6\uff0c\u5e76\u9075\u5b88\u5176\u89c4\u5b9a\u3002<\/p>\n<\/p>\n<\/li>\n<li>\n<p><strong>\u8bbe\u7f6e\u5408\u7406\u7684\u722c\u53d6\u95f4\u9694<\/strong>\uff1a\u907f\u514d\u9891\u7e41\u53d1\u9001\u8bf7\u6c42\uff0c\u7ed9\u76ee\u6807\u7f51\u7ad9\u9020\u6210\u8d1f\u62c5\u3002\u53ef\u4ee5\u4f7f\u7528<code>time.sleep()<\/code>\u65b9\u6cd5\u8bbe\u7f6e\u722c\u53d6\u95f4\u9694\uff0c\u6216\u8005\u4f7f\u7528Scrapy\u7684\u4e0b\u8f7d\u5ef6\u8fdf\u529f\u80fd\u3002<\/p>\n<\/p>\n<\/li>\n<li>\n<p><strong>\u8bbe\u7f6eUser-Agent<\/strong>\uff1a\u5728\u53d1\u9001HTTP\u8bf7\u6c42\u65f6\uff0c\u8bbe\u7f6e\u5408\u7406\u7684User-Agent\uff0c\u4ee5\u6a21\u62df\u6b63\u5e38\u7528\u6237\u8bbf\u95ee\u3002\u53ef\u4ee5\u901a\u8fc7Requests\u5e93\u7684<code>headers<\/code>\u53c2\u6570\u8bbe\u7f6eUser-Agent\u3002<\/p>\n<\/p>\n<\/li>\n<li>\n<p><strong>\u5904\u7406\u53cd\u722c\u673a\u5236<\/strong>\uff1a\u4e00\u4e9b\u7f51\u7ad9\u4f1a\u8bbe\u7f6e\u53cd\u722c\u673a\u5236\uff0c\u5982IP\u5c01\u7981\u3001\u9a8c\u8bc1\u7801\u7b49\u3002\u6211\u4eec\u53ef\u4ee5\u901a\u8fc7\u4f7f\u7528\u4ee3\u7406\u3001\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\u7b49\u65b9\u5f0f\u7ed5\u8fc7\u53cd\u722c\u673a\u5236\uff0c\u4f46\u9700\u8981\u6ce8\u610f\u5408\u6cd5\u5408\u89c4\u3002<\/p>\n<\/p>\n<\/li>\n<\/ol>\n<p><h3>\u4e03\u3001\u5b9e\u6218\u6848\u4f8b<\/h3>\n<\/p>\n<p><p>\u4e3a\u4e86\u66f4\u597d\u5730\u7406\u89e3Python\u6570\u636e\u722c\u53d6\u7684\u5b9e\u73b0\uff0c\u6211\u4eec\u901a\u8fc7\u4e00\u4e2a\u5b9e\u6218\u6848\u4f8b\u6765\u6f14\u793a\u5b8c\u6574\u7684\u722c\u53d6\u8fc7\u7a0b\u3002\u5047\u8bbe\u6211\u4eec\u8981\u722c\u53d6\u4e00\u4e2a\u65b0\u95fb\u7f51\u7ad9\u7684\u6807\u9898\u548c\u6b63\u6587\u5185\u5bb9\uff0c\u5e76\u5c06\u6570\u636e\u5b58\u50a8\u5230CSV\u6587\u4ef6\u4e2d\u3002<\/p>\n<\/p>\n<p><h4>1. \u5bfc\u5165\u6240\u9700\u5e93<\/h4>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u5bfc\u5165\u6240\u9700\u7684\u5e93\uff0c\u5305\u62ecRequests\u3001BeautifulSoup\u548cCSV\u5e93\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>from bs4 import BeautifulSoup<\/p>\n<p>import csv<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2. \u53d1\u9001HTTP\u8bf7\u6c42\u5e76\u83b7\u53d6\u7f51\u9875\u5185\u5bb9<\/h4>\n<\/p>\n<p><p>\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u83b7\u53d6\u7f51\u9875\u7684HTML\u5185\u5bb9\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">url = &#39;https:\/\/example-news-website.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><h4>3. \u89e3\u6790HTML\u6587\u6863\u5e76\u63d0\u53d6\u6570\u636e<\/h4>\n<\/p>\n<p><p>\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u6587\u6863\uff0c\u5e76\u63d0\u53d6\u65b0\u95fb\u6807\u9898\u548c\u6b63\u6587\u5185\u5bb9\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">soup = BeautifulSoup(html_content, &#39;html.parser&#39;)<\/p>\n<p>articles = soup.find_all(&#39;div&#39;, class_=&#39;article&#39;)<\/p>\n<p>data = []<\/p>\n<p>for article in articles:<\/p>\n<p>    title = article.find(&#39;h2&#39;).string<\/p>\n<p>    body = article.find(&#39;p&#39;).string<\/p>\n<p>    data.append([title, body])<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>4. \u5b58\u50a8\u6570\u636e\u5230CSV\u6587\u4ef6<\/h4>\n<\/p>\n<p><p>\u5c06\u63d0\u53d6\u5230\u7684\u6570\u636e\u5b58\u50a8\u5230CSV\u6587\u4ef6\u4e2d\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">with open(&#39;news_data.csv&#39;, &#39;w&#39;, newline=&#39;&#39;) as file:<\/p>\n<p>    writer = csv.writer(file)<\/p>\n<p>    writer.writerow([&#39;Title&#39;, &#39;Body&#39;])<\/p>\n<p>    writer.writerows(data)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7\u4e0a\u8ff0\u6b65\u9aa4\uff0c\u6211\u4eec\u6210\u529f\u5730\u722c\u53d6\u4e86\u65b0\u95fb\u7f51\u7ad9\u7684\u6807\u9898\u548c\u6b63\u6587\u5185\u5bb9\uff0c\u5e76\u5c06\u6570\u636e\u5b58\u50a8\u5230CSV\u6587\u4ef6\u4e2d\u3002\u8fd9\u4e2a\u6848\u4f8b\u5c55\u793a\u4e86Python\u6570\u636e\u722c\u53d6\u7684\u5b8c\u6574\u8fc7\u7a0b\uff0c\u5305\u62ec\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u89e3\u6790HTML\u6587\u6863\u3001\u63d0\u53d6\u6570\u636e\u548c\u5b58\u50a8\u6570\u636e\u3002<\/p>\n<\/p>\n<p><h3>\u603b\u7ed3<\/h3>\n<\/p>\n<p><p>Python\u6570\u636e\u722c\u53d6\u662f\u4e00\u4e2a\u5f3a\u5927\u4e14\u7075\u6d3b\u7684\u5de5\u5177\uff0c\u80fd\u591f\u5e2e\u52a9\u6211\u4eec\u81ea\u52a8\u5316\u5730\u4ece\u7f51\u9875\u4e0a\u63d0\u53d6\u6570\u636e\u3002\u901a\u8fc7\u9009\u62e9\u5408\u9002\u7684\u5e93\uff08\u5982Requests\u3001BeautifulSoup\u3001Scrapy\u3001Selenium\u7b49\uff09\uff0c\u6211\u4eec\u53ef\u4ee5\u9ad8\u6548\u5730\u5b8c\u6210\u722c\u53d6\u4efb\u52a1\u3002\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u6211\u4eec\u9700\u8981\u9075\u5b88\u722c\u866b\u89c4\u8303\uff0c\u907f\u514d\u5bf9\u76ee\u6807\u7f51\u7ad9\u9020\u6210\u8d1f\u62c5\uff0c\u5e76\u786e\u4fdd\u5408\u6cd5\u5408\u89c4\u3002\u5e0c\u671b\u672c\u6587\u80fd\u591f\u5e2e\u52a9\u4f60\u66f4\u597d\u5730\u7406\u89e3\u548c\u638c\u63e1Python\u6570\u636e\u722c\u53d6\u7684\u5b9e\u73b0\u65b9\u6cd5\u548c\u6280\u5de7\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u4f7f\u7528Python\u8fdb\u884c\u7f51\u9875\u6570\u636e\u722c\u53d6\uff1f<\/strong><br \/>Python\u6570\u636e\u722c\u53d6\u901a\u5e38\u901a\u8fc7\u4f7f\u7528\u5e93\u5982Requests\u548cBeautifulSoup\u5b9e\u73b0\u3002Requests\u5e93\u7528\u4e8e\u53d1\u9001HTTP\u8bf7\u6c42\u5e76\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u800cBeautifulSoup\u5219\u7528\u4e8e\u89e3\u6790HTML\u6587\u6863\uff0c\u63d0\u53d6\u6240\u9700\u7684\u6570\u636e\u3002\u7528\u6237\u53ef\u4ee5\u901a\u8fc7\u5b89\u88c5\u8fd9\u4e24\u4e2a\u5e93\uff0c\u5e76\u7f16\u5199\u811a\u672c\u6765\u63d0\u53d6\u7279\u5b9a\u7684\u4fe1\u606f\uff0c\u5982\u6587\u672c\u3001\u56fe\u50cf\u6216\u94fe\u63a5\u3002<\/p>\n<p><strong>Python\u722c\u866b\u9700\u8981\u6ce8\u610f\u54ea\u4e9b\u6cd5\u5f8b\u548c\u9053\u5fb7\u95ee\u9898\uff1f<\/strong><br \/>\u5728\u8fdb\u884c\u6570\u636e\u722c\u53d6\u65f6\uff0c\u9075\u5b88\u6cd5\u5f8b\u548c\u9053\u5fb7\u89c4\u8303\u662f\u975e\u5e38\u91cd\u8981\u7684\u3002\u7528\u6237\u5e94\u4e86\u89e3\u76ee\u6807\u7f51\u7ad9\u7684robots.txt\u6587\u4ef6\uff0c\u67e5\u770b\u54ea\u4e9b\u5185\u5bb9\u5141\u8bb8\u722c\u53d6\u3002\u6b64\u5916\uff0c\u907f\u514d\u9891\u7e41\u8bf7\u6c42\u540c\u4e00\u7f51\u9875\uff0c\u4ee5\u514d\u5bf9\u7f51\u7ad9\u9020\u6210\u8d1f\u62c5\uff0c\u6216\u8005\u88ab\u89c6\u4e3a\u6076\u610f\u884c\u4e3a\u3002\u786e\u4fdd\u9075\u5faa\u6570\u636e\u4f7f\u7528\u7684\u76f8\u5173\u6cd5\u5f8b\u89c4\u5b9a\uff0c\u5c0a\u91cd\u4e2a\u4eba\u9690\u79c1\u548c\u7248\u6743\u3002<\/p>\n<p><strong>\u5982\u4f55\u63d0\u9ad8Python\u722c\u866b\u7684\u6548\u7387\u548c\u7a33\u5b9a\u6027\uff1f<\/strong><br \/>\u4e3a\u4e86\u63d0\u9ad8\u722c\u866b\u7684\u6548\u7387\u548c\u7a33\u5b9a\u6027\uff0c\u53ef\u4ee5\u4f7f\u7528\u591a\u7ebf\u7a0b\u6216\u5f02\u6b65\u7f16\u7a0b\u6765\u5e76\u53d1\u8bf7\u6c42\u591a\u4e2a\u7f51\u9875\u3002\u4f7f\u7528\u4ee3\u7406\u53ef\u4ee5\u907f\u514dIP\u88ab\u5c01\u7981\uff0c\u8bbe\u7f6e\u8bf7\u6c42\u95f4\u9694\u65f6\u95f4\u53ef\u4ee5\u51cf\u5c11\u5bf9\u76ee\u6807\u7f51\u7ad9\u7684\u538b\u529b\u3002\u6b64\u5916\uff0c\u7528\u6237\u53ef\u4ee5\u4f18\u5316\u89e3\u6790\u8fc7\u7a0b\uff0c\u9009\u62e9\u5408\u9002\u7684\u89e3\u6790\u5e93\u548c\u65b9\u6cd5\uff0c\u4ee5\u52a0\u901f\u6570\u636e\u63d0\u53d6\u7684\u901f\u5ea6\u548c\u51c6\u786e\u6027\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u6570\u636e\u722c\u53d6\u662f\u901a\u8fc7\u4f7f\u7528Python\u7f16\u7a0b\u8bed\u8a00\u548c\u76f8\u5173\u5e93\uff08\u5982BeautifulSoup\u3001Scrapy\u3001Req [&hellip;]","protected":false},"author":3,"featured_media":1034042,"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\/1034029"}],"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=1034029"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1034029\/revisions"}],"predecessor-version":[{"id":1034046,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1034029\/revisions\/1034046"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1034042"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1034029"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1034029"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1034029"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}