{"id":1032840,"date":"2024-12-31T11:36:59","date_gmt":"2024-12-31T03:36:59","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1032840.html"},"modified":"2024-12-31T11:37:01","modified_gmt":"2024-12-31T03:37:01","slug":"python%e5%a6%82%e4%bd%95%e7%88%ac%e5%8f%96%e7%ac%a6%e5%90%88%e6%9d%a1%e4%bb%b6%e7%9a%84%e6%95%b0%e6%8d%ae","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1032840.html","title":{"rendered":"python\u5982\u4f55\u722c\u53d6\u7b26\u5408\u6761\u4ef6\u7684\u6570\u636e"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-docs.pingcode.com\/wp-content\/uploads\/2024\/12\/679e6f4c-f0d9-43e5-be89-9939379d94e1.webp?x-oss-process=image\/auto-orient,1\/format,webp\" alt=\"python\u5982\u4f55\u722c\u53d6\u7b26\u5408\u6761\u4ef6\u7684\u6570\u636e\" \/><\/p>\n<p><p> \u5728\u672c\u6587\u4e2d\uff0c\u6211\u4eec\u5c06\u63a2\u8ba8\u5982\u4f55\u4f7f\u7528Python\u722c\u53d6\u7b26\u5408\u6761\u4ef6\u7684\u6570\u636e\u3002<strong>\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u3001\u4f7f\u7528XPath\u6216CSS\u9009\u62e9\u5668\u5b9a\u4f4d\u5143\u7d20\u3001\u5904\u7406\u53cd\u722c\u866b\u673a\u5236<\/strong>\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u5176\u4e2d\u4e00\u4e2a\u5173\u952e\u6b65\u9aa4\u2014\u2014\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u3002<\/p>\n<\/p>\n<p><p>\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u662f\u5b9e\u73b0\u7f51\u9875\u6570\u636e\u722c\u53d6\u7684\u6838\u5fc3\u6b65\u9aa4\u4e4b\u4e00\u3002\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u5b89\u88c5BeautifulSoup\u5e93\uff0c\u53ef\u4ee5\u4f7f\u7528pip\u547d\u4ee4\u6765\u5b8c\u6210\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install beautifulsoup4<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5b89\u88c5\u5b8c\u6210\u540e\uff0c\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u4ee3\u7801\u6765\u8fdb\u884c\u57fa\u672c\u7684HTML\u89e3\u6790\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>from bs4 import BeautifulSoup<\/p>\n<p>url = &#39;https:\/\/example.com&#39;<\/p>\n<p>response = requests.get(url)<\/p>\n<p>soup = BeautifulSoup(response.content, &#39;html.parser&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u4e0a\u8ff0\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u7136\u540e\u901a\u8fc7BeautifulSoup\u89e3\u6790HTML\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528\u4e0d\u540c\u7684\u65b9\u6cd5\u6765\u5b9a\u4f4d\u6211\u4eec\u9700\u8981\u7684\u6570\u636e\u3002\u4f8b\u5982\uff0c\u4f7f\u7528<code>find<\/code>\u6216<code>find_all<\/code>\u65b9\u6cd5\u6765\u67e5\u627e\u7279\u5b9a\u6807\u7b7e\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u67e5\u627e\u7b2c\u4e00\u4e2a\u51fa\u73b0\u7684div\u6807\u7b7e<\/p>\n<p>div = soup.find(&#39;div&#39;)<\/p>\n<h2><strong>\u67e5\u627e\u6240\u6709\u7684div\u6807\u7b7e<\/strong><\/h2>\n<p>divs = soup.find_all(&#39;div&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u63a5\u4e0b\u6765\u6211\u4eec\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u722c\u53d6\u7b26\u5408\u7279\u5b9a\u6761\u4ef6\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n<h2><strong>\u4e00\u3001\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42<\/strong><\/h2>\n<p><p>requests\u5e93\u662fPython\u4e2d\u6700\u5e38\u7528\u7684HTTP\u8bf7\u6c42\u5e93\u4e4b\u4e00\uff0c\u5b83\u63d0\u4f9b\u4e86\u7b80\u5355\u6613\u7528\u7684API\u6765\u53d1\u9001\u5404\u79cdHTTP\u8bf7\u6c42\u3002\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u5b89\u88c5requests\u5e93\uff0c\u53ef\u4ee5\u4f7f\u7528pip\u547d\u4ee4\u6765\u5b8c\u6210\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install requests<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5b89\u88c5\u5b8c\u6210\u540e\uff0c\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u4ee3\u7801\u53d1\u9001\u4e00\u4e2a\u7b80\u5355\u7684GET\u8bf7\u6c42\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><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u4e0a\u8ff0\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528requests.get\u65b9\u6cd5\u53d1\u9001\u4e86\u4e00\u4e2aGET\u8bf7\u6c42\uff0c\u5e76\u5c06\u54cd\u5e94\u5b58\u50a8\u5728response\u53d8\u91cf\u4e2d\u3002\u6211\u4eec\u53ef\u4ee5\u901a\u8fc7response\u5bf9\u8c61\u6765\u83b7\u53d6\u8bf7\u6c42\u7684\u72b6\u6001\u7801\u3001\u54cd\u5e94\u5934\u548c\u54cd\u5e94\u5185\u5bb9\u7b49\u4fe1\u606f\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u83b7\u53d6\u72b6\u6001\u7801<\/p>\n<p>status_code = response.status_code<\/p>\n<h2><strong>\u83b7\u53d6\u54cd\u5e94\u5934<\/strong><\/h2>\n<p>headers = response.headers<\/p>\n<h2><strong>\u83b7\u53d6\u54cd\u5e94\u5185\u5bb9<\/strong><\/h2>\n<p>content = response.content<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7\u8fd9\u4e9b\u4fe1\u606f\uff0c\u6211\u4eec\u53ef\u4ee5\u5224\u65ad\u8bf7\u6c42\u662f\u5426\u6210\u529f\uff0c\u5e76\u8fdb\u4e00\u6b65\u5904\u7406\u54cd\u5e94\u5185\u5bb9\u3002<\/p>\n<\/p>\n<h2><strong>\u4e8c\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML<\/strong><\/h2>\n<p><p>BeautifulSoup\u662fPython\u4e2d\u5e38\u7528\u7684HTML\u89e3\u6790\u5e93\uff0c\u5b83\u63d0\u4f9b\u4e86\u4e30\u5bcc\u7684API\u6765\u5904\u7406\u548c\u89e3\u6790HTML\u6587\u6863\u3002\u5728\u524d\u9762\u63d0\u5230\u7684\u4f8b\u5b50\u4e2d\uff0c\u6211\u4eec\u5df2\u7ecf\u5c55\u793a\u4e86\u5982\u4f55\u4f7f\u7528BeautifulSoup\u6765\u89e3\u6790HTML\u6587\u6863\u3002\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u5c06\u4ecb\u7ecd\u4e00\u4e9b\u5e38\u7528\u7684BeautifulSoup\u65b9\u6cd5\u548c\u6280\u5de7\u3002<\/p>\n<\/p>\n<p><h2>1. \u67e5\u627e\u5143\u7d20<\/h2>\n<\/p>\n<p><p>\u5728HTML\u6587\u6863\u4e2d\u67e5\u627e\u5143\u7d20\u662f\u89e3\u6790\u548c\u63d0\u53d6\u6570\u636e\u7684\u5173\u952e\u6b65\u9aa4\u3002BeautifulSoup\u63d0\u4f9b\u4e86\u591a\u79cd\u65b9\u6cd5\u6765\u67e5\u627e\u5143\u7d20\uff0c\u4f8b\u5982<code>find<\/code>\u3001<code>find_all<\/code>\u3001<code>select<\/code>\u7b49\u3002\u4ee5\u4e0b\u662f\u4e00\u4e9b\u5e38\u7528\u7684\u65b9\u6cd5\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u67e5\u627e\u7b2c\u4e00\u4e2a\u51fa\u73b0\u7684div\u6807\u7b7e<\/p>\n<p>div = soup.find(&#39;div&#39;)<\/p>\n<h2><strong>\u67e5\u627e\u6240\u6709\u7684div\u6807\u7b7e<\/strong><\/h2>\n<p>divs = soup.find_all(&#39;div&#39;)<\/p>\n<h2><strong>\u4f7f\u7528CSS\u9009\u62e9\u5668\u67e5\u627e\u5143\u7d20<\/strong><\/h2>\n<p>elements = soup.select(&#39;div.classname&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h2>2. \u83b7\u53d6\u5143\u7d20\u5c5e\u6027\u548c\u6587\u672c<\/h2>\n<\/p>\n<p><p>\u5728\u627e\u5230\u76ee\u6807\u5143\u7d20\u540e\uff0c\u6211\u4eec\u901a\u5e38\u9700\u8981\u83b7\u53d6\u5143\u7d20\u7684\u5c5e\u6027\u503c\u548c\u6587\u672c\u5185\u5bb9\u3002BeautifulSoup\u63d0\u4f9b\u4e86\u65b9\u4fbf\u7684\u65b9\u6cd5\u6765\u83b7\u53d6\u8fd9\u4e9b\u4fe1\u606f\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u83b7\u53d6\u5143\u7d20\u7684\u5c5e\u6027\u503c<\/p>\n<p>attribute_value = element[&#39;attribute_name&#39;]<\/p>\n<h2><strong>\u83b7\u53d6\u5143\u7d20\u7684\u6587\u672c\u5185\u5bb9<\/strong><\/h2>\n<p>text_content = element.get_text()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h2>3. \u5904\u7406\u5d4c\u5957\u5143\u7d20<\/h2>\n<\/p>\n<p><p>HTML\u6587\u6863\u4e2d\u901a\u5e38\u5305\u542b\u5d4c\u5957\u7684\u5143\u7d20\u7ed3\u6784\uff0c\u6211\u4eec\u53ef\u4ee5\u901a\u8fc7BeautifulSoup\u7684\u591a\u7ea7\u67e5\u627e\u65b9\u6cd5\u6765\u5904\u7406\u8fd9\u4e9b\u5d4c\u5957\u5143\u7d20\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u67e5\u627e\u7236\u5143\u7d20<\/p>\n<p>parent_element = soup.find(&#39;div&#39;, {&#39;class&#39;: &#39;parent&#39;})<\/p>\n<h2><strong>\u5728\u7236\u5143\u7d20\u4e2d\u67e5\u627e\u5b50\u5143\u7d20<\/strong><\/h2>\n<p>child_element = parent_element.find(&#39;span&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7\u8fd9\u4e9b\u65b9\u6cd5\uff0c\u6211\u4eec\u53ef\u4ee5\u65b9\u4fbf\u5730\u89e3\u6790\u548c\u63d0\u53d6HTML\u6587\u6863\u4e2d\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n<h2><strong>\u4e09\u3001\u4f7f\u7528XPath\u6216CSS\u9009\u62e9\u5668\u5b9a\u4f4d\u5143\u7d20<\/strong><\/h2>\n<p><p>\u5728\u5904\u7406\u590d\u6742\u7684HTML\u6587\u6863\u65f6\uff0c\u4f7f\u7528XPath\u6216CSS\u9009\u62e9\u5668\u53ef\u4ee5\u66f4\u52a0\u7cbe\u786e\u5730\u5b9a\u4f4d\u5143\u7d20\u3002XPath\u662f\u4e00\u79cd\u7528\u4e8e\u5728XML\u6587\u6863\u4e2d\u67e5\u627e\u4fe1\u606f\u7684\u8bed\u8a00\uff0c\u800cCSS\u9009\u62e9\u5668\u5219\u662f\u7528\u4e8e\u9009\u62e9HTML\u5143\u7d20\u7684\u6a21\u5f0f\u3002Python\u4e2d\u5e38\u7528\u7684XPath\u89e3\u6790\u5e93\u662flxml\uff0c\u4f7f\u7528CSS\u9009\u62e9\u5668\u7684\u5e93\u662fBeautifulSoup\u3002<\/p>\n<\/p>\n<p><h2>1. \u4f7f\u7528lxml\u548cXPath<\/h2>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u5b89\u88c5lxml\u5e93\uff0c\u53ef\u4ee5\u4f7f\u7528pip\u547d\u4ee4\u6765\u5b8c\u6210\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install lxml<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5b89\u88c5\u5b8c\u6210\u540e\uff0c\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u4ee3\u7801\u4f7f\u7528XPath\u6765\u67e5\u627e\u5143\u7d20\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from lxml import html<\/p>\n<p>url = &#39;https:\/\/example.com&#39;<\/p>\n<p>response = requests.get(url)<\/p>\n<p>tree = html.fromstring(response.content)<\/p>\n<h2><strong>\u4f7f\u7528XPath\u67e5\u627e\u5143\u7d20<\/strong><\/h2>\n<p>elements = tree.xpath(&#39;\/\/div[@class=&quot;classname&quot;]&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h2>2. \u4f7f\u7528BeautifulSoup\u548cCSS\u9009\u62e9\u5668<\/h2>\n<\/p>\n<p><p>\u5728\u524d\u9762\u5df2\u7ecf\u4ecb\u7ecd\u4e86\u4f7f\u7528BeautifulSoup\u548cCSS\u9009\u62e9\u5668\u7684\u65b9\u6cd5\uff0c\u8fd9\u91cc\u518d\u8865\u5145\u4e00\u4e9b\u590d\u6742\u9009\u62e9\u5668\u7684\u4f7f\u7528\u65b9\u6cd5\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u67e5\u627e\u5177\u6709\u7279\u5b9a\u7c7b\u540d\u7684\u5143\u7d20<\/p>\n<p>elements = soup.select(&#39;.classname&#39;)<\/p>\n<h2><strong>\u67e5\u627e\u5177\u6709\u7279\u5b9aID\u7684\u5143\u7d20<\/strong><\/h2>\n<p>element = soup.select(&#39;#idname&#39;)<\/p>\n<h2><strong>\u67e5\u627e\u5d4c\u5957\u5143\u7d20<\/strong><\/h2>\n<p>nested_elements = soup.select(&#39;div.classname span&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7\u8fd9\u4e9b\u65b9\u6cd5\uff0c\u6211\u4eec\u53ef\u4ee5\u66f4\u52a0\u7cbe\u786e\u5730\u5b9a\u4f4d\u548c\u63d0\u53d6HTML\u6587\u6863\u4e2d\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n<h2><strong>\u56db\u3001\u5904\u7406\u53cd\u722c\u866b\u673a\u5236<\/strong><\/h2>\n<p><p>\u5728\u5b9e\u9645\u7684\u7f51\u9875\u722c\u53d6\u8fc7\u7a0b\u4e2d\uff0c\u6211\u4eec\u7ecf\u5e38\u4f1a\u9047\u5230\u4e00\u4e9b\u53cd\u722c\u866b\u673a\u5236\uff0c\u4f8b\u5982IP\u5c01\u7981\u3001\u9a8c\u8bc1\u7801\u3001\u52a8\u6001\u52a0\u8f7d\u7b49\u3002\u4e3a\u4e86\u5e94\u5bf9\u8fd9\u4e9b\u95ee\u9898\uff0c\u6211\u4eec\u9700\u8981\u91c7\u53d6\u4e00\u4e9b\u63aa\u65bd\u6765\u7ed5\u8fc7\u53cd\u722c\u866b\u673a\u5236\u3002<\/p>\n<\/p>\n<p><h2>1. \u4f7f\u7528\u4ee3\u7406IP<\/h2>\n<\/p>\n<p><p>\u4f7f\u7528\u4ee3\u7406IP\u53ef\u4ee5\u6709\u6548\u5730\u907f\u514d\u88ab\u7f51\u7ad9\u5c01\u7981IP\u3002\u6211\u4eec\u53ef\u4ee5\u901a\u8fc7\u4e00\u4e9b\u514d\u8d39\u6216\u4ed8\u8d39\u7684\u4ee3\u7406IP\u670d\u52a1\u6765\u83b7\u53d6\u4ee3\u7406IP\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u4f7f\u7528\u4ee3\u7406IP\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">proxies = {<\/p>\n<p>    &#39;http&#39;: &#39;http:\/\/proxy_ip:proxy_port&#39;,<\/p>\n<p>    &#39;https&#39;: &#39;https:\/\/proxy_ip:proxy_port&#39;<\/p>\n<p>}<\/p>\n<p>response = requests.get(url, proxies=proxies)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h2>2. \u8bbe\u7f6e\u8bf7\u6c42\u5934<\/h2>\n<\/p>\n<p><p>\u8bbe\u7f6e\u8bf7\u6c42\u5934\u53ef\u4ee5\u6a21\u62df\u771f\u5b9e\u7528\u6237\u7684\u8bf7\u6c42\uff0c\u4ece\u800c\u907f\u514d\u88ab\u8bc6\u522b\u4e3a\u722c\u866b\u3002\u5e38\u89c1\u7684\u8bf7\u6c42\u5934\u5305\u62ecUser-Agent\u3001Referer\u3001Cookie\u7b49\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u8bbe\u7f6e\u8bf7\u6c42\u5934\u7684\u793a\u4f8b\uff1a<\/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\/537.36&#39;,<\/p>\n<p>    &#39;Referer&#39;: &#39;https:\/\/example.com&#39;<\/p>\n<p>}<\/p>\n<p>response = requests.get(url, headers=headers)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h2>3. \u5904\u7406\u9a8c\u8bc1\u7801<\/h2>\n<\/p>\n<p><p>\u5904\u7406\u9a8c\u8bc1\u7801\u662f\u4e00\u4e2a\u6bd4\u8f83\u590d\u6742\u7684\u95ee\u9898\uff0c\u901a\u5e38\u9700\u8981\u4f7f\u7528OCR\u6280\u672f\u6765\u8bc6\u522b\u9a8c\u8bc1\u7801\u3002\u53ef\u4ee5\u4f7f\u7528\u4e00\u4e9bOCR\u5e93\uff0c\u4f8b\u5982Tesseract OCR\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u4f7f\u7528Tesseract OCR\u8bc6\u522b\u9a8c\u8bc1\u7801\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from PIL import Image<\/p>\n<p>import pytesseract<\/p>\n<h2><strong>\u6253\u5f00\u9a8c\u8bc1\u7801\u56fe\u7247<\/strong><\/h2>\n<p>image = Image.open(&#39;captcha.png&#39;)<\/p>\n<h2><strong>\u4f7f\u7528Tesseract OCR\u8bc6\u522b\u9a8c\u8bc1\u7801<\/strong><\/h2>\n<p>captcha_text = pytesseract.image_to_string(image)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h2>4. \u5904\u7406\u52a8\u6001\u52a0\u8f7d<\/h2>\n<\/p>\n<p><p>\u5bf9\u4e8e\u52a8\u6001\u52a0\u8f7d\u7684\u7f51\u9875\uff0c\u53ef\u4ee5\u4f7f\u7528Selenium\u5e93\u6765\u6a21\u62df\u6d4f\u89c8\u5668\u64cd\u4f5c\uff0c\u4ece\u800c\u83b7\u53d6\u52a8\u6001\u52a0\u8f7d\u7684\u6570\u636e\u3002\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u5b89\u88c5Selenium\u5e93\uff0c\u53ef\u4ee5\u4f7f\u7528pip\u547d\u4ee4\u6765\u5b8c\u6210\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install selenium<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u7136\u540e\uff0c\u4e0b\u8f7d\u76f8\u5e94\u7684\u6d4f\u89c8\u5668\u9a71\u52a8\uff0c\u4f8b\u5982ChromeDriver\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u4f7f\u7528Selenium\u83b7\u53d6\u52a8\u6001\u52a0\u8f7d\u6570\u636e\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from selenium import webdriver<\/p>\n<h2><strong>\u521d\u59cb\u5316Chrome\u6d4f\u89c8\u5668<\/strong><\/h2>\n<p>driver = webdriver.Chrome(executable_path=&#39;path\/to\/chromedriver&#39;)<\/p>\n<h2><strong>\u8bbf\u95ee\u7f51\u9875<\/strong><\/h2>\n<p>driver.get(&#39;https:\/\/example.com&#39;)<\/p>\n<h2><strong>\u83b7\u53d6\u7f51\u9875\u5185\u5bb9<\/strong><\/h2>\n<p>content = driver.page_source<\/p>\n<p>driver.quit()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7\u4e0a\u8ff0\u65b9\u6cd5\uff0c\u6211\u4eec\u53ef\u4ee5\u6709\u6548\u5730\u5904\u7406\u53cd\u722c\u866b\u673a\u5236\uff0c\u63d0\u9ad8\u6570\u636e\u722c\u53d6\u7684\u6210\u529f\u7387\u3002<\/p>\n<\/p>\n<h2><strong>\u4e94\u3001\u793a\u4f8b\u9879\u76ee\uff1a\u722c\u53d6\u8c46\u74e3\u7535\u5f71Top250<\/strong><\/h2>\n<p><p>\u4e3a\u4e86\u66f4\u597d\u5730\u7406\u89e3\u5982\u4f55\u4f7f\u7528Python\u722c\u53d6\u7b26\u5408\u6761\u4ef6\u7684\u6570\u636e\uff0c\u6211\u4eec\u5c06\u4ee5\u722c\u53d6\u8c46\u74e3\u7535\u5f71Top250\u4e3a\u4f8b\uff0c\u5c55\u793a\u5b8c\u6574\u7684\u4ee3\u7801\u5b9e\u73b0\u3002<\/p>\n<\/p>\n<p><h2>1. \u5b89\u88c5\u4f9d\u8d56\u5e93<\/h2>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u5b89\u88c5requests\u548cBeautifulSoup\u5e93\uff0c\u53ef\u4ee5\u4f7f\u7528pip\u547d\u4ee4\u6765\u5b8c\u6210\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install requests beautifulsoup4<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h2>2. \u7f16\u5199\u722c\u866b\u4ee3\u7801<\/h2>\n<\/p>\n<p><p>\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u7f16\u5199\u722c\u866b\u4ee3\u7801\uff0c\u722c\u53d6\u8c46\u74e3\u7535\u5f71Top250\u7684\u6570\u636e\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>from bs4 import BeautifulSoup<\/p>\n<h2><strong>\u722c\u53d6\u8c46\u74e3\u7535\u5f71Top250<\/strong><\/h2>\n<p>def get_top250_movies():<\/p>\n<p>    url = &#39;https:\/\/movie.douban.com\/top250&#39;<\/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\/537.36&#39;<\/p>\n<p>    }<\/p>\n<p>    movies = []<\/p>\n<p>    for start in range(0, 250, 25):<\/p>\n<p>        response = requests.get(url, headers=headers, params={&#39;start&#39;: start})<\/p>\n<p>        soup = BeautifulSoup(response.content, &#39;html.parser&#39;)<\/p>\n<p>        for item in soup.find_all(&#39;div&#39;, class_=&#39;item&#39;):<\/p>\n<p>            title = item.find(&#39;span&#39;, class_=&#39;title&#39;).get_text()<\/p>\n<p>            rating = item.find(&#39;span&#39;, class_=&#39;rating_num&#39;).get_text()<\/p>\n<p>            movies.append({&#39;title&#39;: title, &#39;rating&#39;: rating})<\/p>\n<p>    return movies<\/p>\n<h2><strong>\u6253\u5370\u722c\u53d6\u7684\u7535\u5f71\u6570\u636e<\/strong><\/h2>\n<p>movies = get_top250_movies()<\/p>\n<p>for movie in movies:<\/p>\n<p>    print(f&quot;Title: {movie[&#39;title&#39;]}, Rating: {movie[&#39;rating&#39;]}&quot;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5728\u4e0a\u8ff0\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u9996\u5148\u5b9a\u4e49\u4e86\u4e00\u4e2a\u51fd\u6570<code>get_top250_movies<\/code>\uff0c\u7528\u4e8e\u722c\u53d6\u8c46\u74e3\u7535\u5f71Top250\u7684\u6570\u636e\u3002\u5728\u51fd\u6570\u5185\u90e8\uff0c\u6211\u4eec\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u5e76\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u6587\u6863\u3002\u901a\u8fc7\u904d\u5386\u6bcf\u4e00\u9875\u7684\u6570\u636e\uff0c\u5c06\u7535\u5f71\u7684\u6807\u9898\u548c\u8bc4\u5206\u63d0\u53d6\u51fa\u6765\uff0c\u5e76\u5b58\u50a8\u5728\u4e00\u4e2a\u5217\u8868\u4e2d\u3002\u6700\u540e\uff0c\u6211\u4eec\u6253\u5370\u51fa\u722c\u53d6\u7684\u7535\u5f71\u6570\u636e\u3002<\/p>\n<\/p>\n<p><p>\u901a\u8fc7\u8fd9\u4e2a\u793a\u4f8b\u9879\u76ee\uff0c\u6211\u4eec\u53ef\u4ee5\u66f4\u597d\u5730\u7406\u89e3\u5982\u4f55\u4f7f\u7528Python\u722c\u53d6\u7b26\u5408\u6761\u4ef6\u7684\u6570\u636e\uff0c\u5e76\u638c\u63e1\u76f8\u5173\u7684\u6280\u672f\u548c\u6280\u5de7\u3002<\/p>\n<\/p>\n<h2><strong>\u603b\u7ed3<\/strong><\/h2>\n<p><p>\u5728\u672c\u6587\u4e2d\uff0c\u6211\u4eec\u8be6\u7ec6\u4ecb\u7ecd\u4e86\u5982\u4f55\u4f7f\u7528Python\u722c\u53d6\u7b26\u5408\u6761\u4ef6\u7684\u6570\u636e\u3002\u6211\u4eec\u4ece\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u3001\u4f7f\u7528XPath\u6216CSS\u9009\u62e9\u5668\u5b9a\u4f4d\u5143\u7d20\u3001\u5904\u7406\u53cd\u722c\u866b\u673a\u5236\u7b49\u65b9\u9762\u8fdb\u884c\u4e86\u6df1\u5165\u63a2\u8ba8\uff0c\u5e76\u901a\u8fc7\u4e00\u4e2a\u5b9e\u9645\u7684\u793a\u4f8b\u9879\u76ee\u5c55\u793a\u4e86\u5b8c\u6574\u7684\u4ee3\u7801\u5b9e\u73b0\u3002\u5e0c\u671b\u901a\u8fc7\u672c\u6587\u7684\u4ecb\u7ecd\uff0c\u8bfb\u8005\u80fd\u591f\u638c\u63e1Python\u7f51\u9875\u6570\u636e\u722c\u53d6\u7684\u57fa\u672c\u65b9\u6cd5\u548c\u6280\u5de7\uff0c\u5e76\u80fd\u591f\u5728\u5b9e\u9645\u9879\u76ee\u4e2d\u52a0\u4ee5\u5e94\u7528\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u786e\u5b9a\u8981\u722c\u53d6\u7684\u7f51\u7ad9\u548c\u6570\u636e\u7c7b\u578b\uff1f<\/strong><br \/>\u5728\u8fdb\u884cPython\u6570\u636e\u722c\u53d6\u4e4b\u524d\uff0c\u660e\u786e\u76ee\u6807\u7f51\u7ad9\u548c\u9700\u8981\u83b7\u53d6\u7684\u6570\u636e\u7c7b\u578b\u81f3\u5173\u91cd\u8981\u3002\u9996\u5148\uff0c\u5206\u6790\u7f51\u7ad9\u7684\u7ed3\u6784\uff0c\u4e86\u89e3\u6570\u636e\u662f\u5982\u4f55\u5448\u73b0\u7684\uff0c\u4f8b\u5982\u662f\u5b58\u653e\u5728HTML\u6807\u7b7e\u4e2d\u8fd8\u662f\u901a\u8fc7JavaScript\u52a8\u6001\u52a0\u8f7d\u3002\u786e\u4fdd\u4f60\u4e86\u89e3\u7f51\u7ad9\u7684\u4f7f\u7528\u6761\u6b3e\uff0c\u907f\u514d\u8fdd\u53cd\u76f8\u5173\u89c4\u5b9a\u3002\u4f7f\u7528\u5de5\u5177\u5982Chrome\u5f00\u53d1\u8005\u5de5\u5177\uff0c\u53ef\u4ee5\u5e2e\u52a9\u4f60\u67e5\u770bDOM\u7ed3\u6784\u5e76\u627e\u5230\u6240\u9700\u7684\u6570\u636e\u3002<\/p>\n<p><strong>\u4f7f\u7528\u54ea\u4e9bPython\u5e93\u6765\u8fdb\u884c\u6570\u636e\u722c\u53d6\uff1f<\/strong><br \/>Python\u4e2d\u6709\u591a\u4e2a\u5f3a\u5927\u7684\u5e93\u53ef\u4ee5\u7528\u6765\u8fdb\u884c\u6570\u636e\u722c\u53d6\u3002\u5e38\u7528\u7684\u5305\u62ec<code>requests<\/code>\uff0c\u7528\u4e8e\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff1b<code>BeautifulSoup<\/code>\uff0c\u7528\u4e8e\u89e3\u6790HTML\u548cXML\u6587\u6863\uff0c\u4ece\u4e2d\u63d0\u53d6\u6240\u9700\u4fe1\u606f\uff1b<code>Scrapy<\/code>\uff0c\u662f\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684\u722c\u866b\u6846\u67b6\uff0c\u9002\u5408\u5927\u89c4\u6a21\u722c\u53d6\u548c\u6570\u636e\u63d0\u53d6\u3002\u4e86\u89e3\u8fd9\u4e9b\u5e93\u7684\u4f7f\u7528\u65b9\u6cd5\uff0c\u53ef\u4ee5\u5927\u5927\u63d0\u9ad8\u722c\u53d6\u6548\u7387\u548c\u6570\u636e\u5904\u7406\u80fd\u529b\u3002<\/p>\n<p><strong>\u5982\u4f55\u5904\u7406\u722c\u53d6\u8fc7\u7a0b\u4e2d\u9047\u5230\u7684\u53cd\u722c\u866b\u673a\u5236\uff1f<\/strong><br \/>\u8bb8\u591a\u7f51\u7ad9\u4f1a\u91c7\u53d6\u53cd\u722c\u866b\u63aa\u65bd\u6765\u4fdd\u62a4\u5176\u6570\u636e\u3002\u5728\u722c\u53d6\u6570\u636e\u65f6\uff0c\u53ef\u80fd\u4f1a\u9047\u5230IP\u5c01\u7981\u3001\u8bf7\u6c42\u9891\u7387\u9650\u5236\u7b49\u95ee\u9898\u3002\u4e3a\u4e86\u5e94\u5bf9\u8fd9\u4e9b\u6311\u6218\uff0c\u53ef\u4ee5\u91c7\u7528\u591a\u79cd\u7b56\u7565\uff0c\u5982\u4f7f\u7528\u4ee3\u7406\u670d\u52a1\u5668\uff0c\u968f\u673a\u8bbe\u7f6e\u8bf7\u6c42\u5934\uff0c\u8c03\u6574\u8bf7\u6c42\u7684\u9891\u7387\uff0c\u751a\u81f3\u4f7f\u7528selenium\u7b49\u5de5\u5177\u6a21\u62df\u771f\u5b9e\u7528\u6237\u884c\u4e3a\u3002\u786e\u4fdd\u9075\u5faa\u7f51\u7ad9\u7684\u722c\u53d6\u89c4\u5219\uff0c\u907f\u514d\u9020\u6210\u4e0d\u5fc5\u8981\u7684\u9ebb\u70e6\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5728\u672c\u6587\u4e2d\uff0c\u6211\u4eec\u5c06\u63a2\u8ba8\u5982\u4f55\u4f7f\u7528Python\u722c\u53d6\u7b26\u5408\u6761\u4ef6\u7684\u6570\u636e\u3002\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\u3001\u4f7f\u7528Bea [&hellip;]","protected":false},"author":3,"featured_media":1032848,"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\/1032840"}],"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=1032840"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1032840\/revisions"}],"predecessor-version":[{"id":1032851,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1032840\/revisions\/1032851"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1032848"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1032840"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1032840"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1032840"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}