{"id":1094244,"date":"2025-01-08T14:39:13","date_gmt":"2025-01-08T06:39:13","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1094244.html"},"modified":"2025-01-08T14:39:15","modified_gmt":"2025-01-08T06:39:15","slug":"python%e7%88%ac%e8%99%ab%e5%a6%82%e4%bd%95%e4%ba%8c%e6%ac%a1%e7%ad%9b%e9%80%89%e6%a0%87%e7%ad%be-2","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1094244.html","title":{"rendered":"python\u722c\u866b\u5982\u4f55\u4e8c\u6b21\u7b5b\u9009\u6807\u7b7e"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/24210448\/4938c40d-eae4-4c9e-b388-6140eca3f156.webp\" alt=\"python\u722c\u866b\u5982\u4f55\u4e8c\u6b21\u7b5b\u9009\u6807\u7b7e\" \/><\/p>\n<p><p> <strong>Python\u722c\u866b\u4e8c\u6b21\u7b5b\u9009\u6807\u7b7e\u7684\u65b9\u6cd5\u4e3b\u8981\u6709\uff1a\u5229\u7528BeautifulSoup\u5e93\u8fdb\u884cHTML\u89e3\u6790\u3001\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u8fdb\u884c\u5339\u914d\u3001\u7ed3\u5408XPath\u8fdb\u884c\u7cbe\u7ec6\u7b5b\u9009\u3001\u901a\u8fc7\u7279\u5b9a\u5c5e\u6027\u8fdb\u884c\u8fc7\u6ee4\u3002<\/strong>\u5176\u4e2d\uff0c\u4f7f\u7528BeautifulSoup\u5e93\u8fdb\u884cHTML\u89e3\u6790\u662f\u6700\u5e38\u7528\u4e14\u9ad8\u6548\u7684\u65b9\u6cd5\u3002\u4e0b\u9762\u5c06\u8be6\u7ec6\u63cf\u8ff0\u5982\u4f55\u4f7f\u7528BeautifulSoup\u5e93\u8fdb\u884c\u4e8c\u6b21\u7b5b\u9009\u6807\u7b7e\u3002<\/p>\n<\/p>\n<p><h3>\u4e00\u3001Python\u722c\u866b\u7b80\u4ecb<\/h3>\n<\/p>\n<p><p>Python\u722c\u866b\u662f\u4e00\u79cd\u901a\u8fc7\u7f16\u7a0b\u81ea\u52a8\u5316\u8bbf\u95ee\u7f51\u9875\u5e76\u63d0\u53d6\u6570\u636e\u7684\u5de5\u5177\u3002\u901a\u5e38\uff0c\u722c\u866b\u4f1a\u5728\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u540e\u5bf9HTML\u6587\u6863\u8fdb\u884c\u89e3\u6790\uff0c\u7136\u540e\u63d0\u53d6\u51fa\u9700\u8981\u7684\u4fe1\u606f\u3002\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u901a\u5e38\u9700\u8981\u5bf9\u521d\u6b21\u63d0\u53d6\u7684\u6570\u636e\u8fdb\u884c\u4e8c\u6b21\u7b5b\u9009\uff0c\u4ee5\u83b7\u53d6\u66f4\u7cbe\u786e\u7684\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><h3>\u4e8c\u3001\u4f7f\u7528BeautifulSoup\u5e93\u8fdb\u884cHTML\u89e3\u6790<\/h3>\n<\/p>\n<p><p>BeautifulSoup\u662fPython\u4e2d\u4e00\u4e2a\u5e7f\u6cdb\u4f7f\u7528\u7684\u5e93\uff0c\u7528\u4e8e\u89e3\u6790HTML\u548cXML\u6587\u6863\u3002\u5b83\u63d0\u4f9b\u4e86\u4e00\u4e9b\u7b80\u5355\u7684\u65b9\u6cd5\u6765\u5bfc\u822a\u3001\u641c\u7d22\u548c\u4fee\u6539\u89e3\u6790\u6811\u3002\u6211\u4eec\u53ef\u4ee5\u5229\u7528\u5b83\u6765\u8fdb\u884c\u4e8c\u6b21\u7b5b\u9009\u6807\u7b7e\u3002<\/p>\n<\/p>\n<p><h4>1\u3001\u5b89\u88c5BeautifulSoup\u5e93<\/h4>\n<\/p>\n<p><p>\u5728\u4f7f\u7528BeautifulSoup\u4e4b\u524d\uff0c\u6211\u4eec\u9700\u8981\u5148\u5b89\u88c5\u5b83\u3002\u53ef\u4ee5\u4f7f\u7528pip\u547d\u4ee4\u6765\u5b89\u88c5\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install beautifulsoup4<\/p>\n<p>pip install lxml<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2\u3001\u89e3\u6790HTML\u6587\u6863<\/h4>\n<\/p>\n<p><p>\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u5e76\u89e3\u6790HTML\u6587\u6863\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u4f8b\u5b50\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>from bs4 import BeautifulSoup<\/p>\n<p>url = &quot;https:\/\/example.com&quot;<\/p>\n<p>response = requests.get(url)<\/p>\n<p>soup = BeautifulSoup(response.content, &quot;lxml&quot;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>3\u3001\u521d\u6b21\u7b5b\u9009\u6807\u7b7e<\/h4>\n<\/p>\n<p><p>\u5047\u8bbe\u6211\u4eec\u8981\u63d0\u53d6\u6240\u6709\u7684<code>div<\/code>\u6807\u7b7e\uff0c\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u4ee3\u7801\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">divs = soup.find_all(&#39;div&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>4\u3001\u4e8c\u6b21\u7b5b\u9009\u6807\u7b7e<\/h4>\n<\/p>\n<p><p>\u5728\u521d\u6b21\u7b5b\u9009\u7684\u57fa\u7840\u4e0a\uff0c\u6211\u4eec\u53ef\u4ee5\u8fdb\u4e00\u6b65\u7b5b\u9009\u51fa\u7279\u5b9a\u7684<code>div<\/code>\u6807\u7b7e\u3002\u4ee5\u4e0b\u662f\u4e00\u4e9b\u5e38\u89c1\u7684\u65b9\u6cd5\uff1a<\/p>\n<\/p>\n<p><h5>\u901a\u8fc7\u5c5e\u6027\u8fdb\u884c\u7b5b\u9009<\/h5>\n<\/p>\n<p><p>\u5047\u8bbe\u6211\u4eec\u53ea\u60f3\u8981\u90a3\u4e9b\u5177\u6709\u7279\u5b9a\u7c7b\u540d\u7684<code>div<\/code>\u6807\u7b7e\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">filtered_divs = [div for div in divs if &#39;specific-class&#39; in div.get(&#39;class&#39;, [])]<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h5>\u901a\u8fc7\u5d4c\u5957\u6807\u7b7e\u8fdb\u884c\u7b5b\u9009<\/h5>\n<\/p>\n<p><p>\u5047\u8bbe\u6211\u4eec\u53ea\u60f3\u8981\u90a3\u4e9b\u5305\u542b\u7279\u5b9a\u5b50\u6807\u7b7e\u7684<code>div<\/code>\u6807\u7b7e\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">filtered_divs = [div for div in divs if div.find(&#39;span&#39;)]<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h5>\u901a\u8fc7\u6587\u672c\u5185\u5bb9\u8fdb\u884c\u7b5b\u9009<\/h5>\n<\/p>\n<p><p>\u5047\u8bbe\u6211\u4eec\u53ea\u60f3\u8981\u90a3\u4e9b\u5305\u542b\u7279\u5b9a\u6587\u672c\u5185\u5bb9\u7684<code>div<\/code>\u6807\u7b7e\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">filtered_divs = [div for div in divs if &#39;specific text&#39; in div.get_text()]<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e09\u3001\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u8fdb\u884c\u5339\u914d<\/h3>\n<\/p>\n<p><p>\u6b63\u5219\u8868\u8fbe\u5f0f\u662f\u4e00\u79cd\u5f3a\u5927\u7684\u5de5\u5177\uff0c\u53ef\u4ee5\u7528\u6765\u5339\u914d\u590d\u6742\u7684\u5b57\u7b26\u4e32\u6a21\u5f0f\u3002\u5728\u8fdb\u884c\u4e8c\u6b21\u7b5b\u9009\u65f6\uff0c\u6211\u4eec\u53ef\u4ee5\u7ed3\u5408BeautifulSoup\u548c\u6b63\u5219\u8868\u8fbe\u5f0f\u6765\u5b9e\u73b0\u66f4\u7cbe\u786e\u7684\u7b5b\u9009\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import re<\/p>\n<h2><strong>\u793a\u4f8b\uff1a\u7b5b\u9009\u51fa\u5305\u542b\u7279\u5b9a\u6b63\u5219\u6a21\u5f0f\u7684div\u6807\u7b7e<\/strong><\/h2>\n<p>pattern = re.compile(r&#39;specific pattern&#39;)<\/p>\n<p>filtered_divs = [div for div in divs if pattern.search(div.get_text())]<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u56db\u3001\u7ed3\u5408XPath\u8fdb\u884c\u7cbe\u7ec6\u7b5b\u9009<\/h3>\n<\/p>\n<p><p>XPath\u662f\u4e00\u79cd\u7528\u4e8e\u5728XML\u6587\u6863\u4e2d\u67e5\u627e\u4fe1\u606f\u7684\u8bed\u8a00\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528lxml\u5e93\u6765\u89e3\u6790HTML\uff0c\u5e76\u7ed3\u5408XPath\u8fdb\u884c\u7cbe\u7ec6\u7b5b\u9009\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from lxml import html<\/p>\n<p>tree = html.fromstring(response.content)<\/p>\n<p>filtered_divs = tree.xpath(&#39;\/\/div[cont<a href=\"https:\/\/docs.pingcode.com\/blog\/59162.html\" target=\"_blank\">AI<\/a>ns(@class, &quot;specific-class&quot;)]&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e94\u3001\u901a\u8fc7\u7279\u5b9a\u5c5e\u6027\u8fdb\u884c\u8fc7\u6ee4<\/h3>\n<\/p>\n<p><p>\u5728\u67d0\u4e9b\u60c5\u51b5\u4e0b\uff0c\u6807\u7b7e\u7684\u67d0\u4e9b\u5c5e\u6027\uff08\u5982ID\u3001class\u3001data-*\u5c5e\u6027\u7b49\uff09\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u8fdb\u884c\u4e8c\u6b21\u7b5b\u9009\u3002\u4f8b\u5982\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u793a\u4f8b\uff1a\u7b5b\u9009\u51fa\u5305\u542b\u7279\u5b9aID\u5c5e\u6027\u7684div\u6807\u7b7e<\/p>\n<p>filtered_divs = [div for div in divs if div.get(&#39;id&#39;) == &#39;specific-id&#39;]<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u516d\u3001\u7ed3\u5408\u591a\u79cd\u65b9\u6cd5\u8fdb\u884c\u7b5b\u9009<\/h3>\n<\/p>\n<p><p>\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u6211\u4eec\u53ef\u4ee5\u7ed3\u5408\u591a\u79cd\u65b9\u6cd5\u8fdb\u884c\u6807\u7b7e\u7684\u4e8c\u6b21\u7b5b\u9009\uff0c\u4ee5\u63d0\u9ad8\u7b5b\u9009\u7684\u7cbe\u786e\u5ea6\u3002\u4f8b\u5982\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u793a\u4f8b\uff1a\u7ed3\u5408\u7c7b\u540d\u548c\u6587\u672c\u5185\u5bb9\u8fdb\u884c\u7b5b\u9009<\/p>\n<p>filtered_divs = [div for div in divs if &#39;specific-class&#39; in div.get(&#39;class&#39;, []) and &#39;specific text&#39; in div.get_text()]<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e03\u3001\u5904\u7406\u590d\u6742\u7ed3\u6784\u7684HTML\u6587\u6863<\/h3>\n<\/p>\n<p><p>\u6709\u65f6\uff0cHTML\u6587\u6863\u7684\u7ed3\u6784\u53ef\u80fd\u975e\u5e38\u590d\u6742\uff0c\u6807\u7b7e\u5d4c\u5957\u5c42\u6b21\u8f83\u6df1\u3002\u5728\u8fd9\u79cd\u60c5\u51b5\u4e0b\uff0c\u6211\u4eec\u53ef\u4ee5\u9012\u5f52\u5730\u8fdb\u884c\u6807\u7b7e\u7b5b\u9009\u3002\u4f8b\u5982\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">def recursive_filter(tags, condition):<\/p>\n<p>    result = []<\/p>\n<p>    for tag in tags:<\/p>\n<p>        if condition(tag):<\/p>\n<p>            result.append(tag)<\/p>\n<p>        result.extend(recursive_filter(tag.find_all(), condition))<\/p>\n<p>    return result<\/p>\n<h2><strong>\u793a\u4f8b\uff1a\u7b5b\u9009\u51fa\u5305\u542b\u7279\u5b9a\u6587\u672c\u5185\u5bb9\u7684\u6240\u6709\u5d4c\u5957div\u6807\u7b7e<\/strong><\/h2>\n<p>filtered_divs = recursive_filter(divs, lambda tag: &#39;specific text&#39; in tag.get_text())<\/p>\n<p><\/code><\/pre>\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\u8be6\u7ec6\u4e86\u89e3\u4e86Python\u722c\u866b\u4e8c\u6b21\u7b5b\u9009\u6807\u7b7e\u7684\u65b9\u6cd5\u3002\u6211\u4eec\u53ef\u4ee5\u5229\u7528BeautifulSoup\u5e93\u8fdb\u884cHTML\u89e3\u6790\u3001\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u8fdb\u884c\u5339\u914d\u3001\u7ed3\u5408XPath\u8fdb\u884c\u7cbe\u7ec6\u7b5b\u9009\u3001\u901a\u8fc7\u7279\u5b9a\u5c5e\u6027\u8fdb\u884c\u8fc7\u6ee4\uff0c\u751a\u81f3\u53ef\u4ee5\u7ed3\u5408\u591a\u79cd\u65b9\u6cd5\u8fdb\u884c\u7b5b\u9009\u3002\u5e0c\u671b\u8fd9\u4e9b\u65b9\u6cd5\u80fd\u591f\u5e2e\u52a9\u4f60\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\u66f4\u9ad8\u6548\u5730\u8fdb\u884c\u6570\u636e\u63d0\u53d6\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u5728Python\u722c\u866b\u4e2d\u5b9e\u73b0\u4e8c\u6b21\u7b5b\u9009\u6807\u7b7e\u7684\u529f\u80fd\uff1f<\/strong><br \/>\u5728Python\u722c\u866b\u4e2d\uff0c\u4e8c\u6b21\u7b5b\u9009\u6807\u7b7e\u901a\u5e38\u901a\u8fc7\u89e3\u6790\u521d\u6b21\u6293\u53d6\u7684\u6570\u636e\u6765\u5b9e\u73b0\u3002\u4f7f\u7528Beautiful Soup\u6216lxml\u7b49\u5e93\uff0c\u53ef\u4ee5\u5bf9\u6293\u53d6\u7684HTML\u6587\u6863\u8fdb\u884c\u8fdb\u4e00\u6b65\u89e3\u6790\uff0c\u63d0\u53d6\u51fa\u9700\u8981\u7684\u6807\u7b7e\u3002\u901a\u8fc7\u6b63\u5219\u8868\u8fbe\u5f0f\u6216\u6761\u4ef6\u5224\u65ad\uff0c\u53ef\u4ee5\u51c6\u786e\u7b5b\u9009\u51fa\u7b26\u5408\u7279\u5b9a\u6807\u51c6\u7684\u6807\u7b7e\u5185\u5bb9\u3002<\/p>\n<p><strong>\u4f7f\u7528\u54ea\u4e9b\u5e93\u53ef\u4ee5\u5e2e\u52a9\u6211\u8fdb\u884c\u6807\u7b7e\u7684\u4e8c\u6b21\u7b5b\u9009\uff1f<\/strong><br \/>\u5e38\u7528\u7684\u5e93\u5305\u62ecBeautiful Soup\u3001Scrapy\u3001lxml\u7b49\u3002Beautiful Soup\u975e\u5e38\u9002\u5408HTML\u6587\u6863\u7684\u89e3\u6790\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u67e5\u627e\u3001\u7b5b\u9009\u548c\u4fee\u6539\u6807\u7b7e\u3002Scrapy\u5219\u662f\u4e00\u4e2a\u529f\u80fd\u5f3a\u5927\u7684\u6846\u67b6\uff0c\u9002\u5408\u5904\u7406\u590d\u6742\u7684\u722c\u866b\u4efb\u52a1\uff0c\u800clxml\u5728\u5904\u7406\u5927\u89c4\u6a21\u6570\u636e\u65f6\u6027\u80fd\u66f4\u4f73\u3002<\/p>\n<p><strong>\u5728\u8fdb\u884c\u4e8c\u6b21\u7b5b\u9009\u65f6\uff0c\u6709\u54ea\u4e9b\u5e38\u89c1\u7684\u7b56\u7565\u6216\u6280\u5de7\uff1f<\/strong><br \/>\u5728\u8fdb\u884c\u4e8c\u6b21\u7b5b\u9009\u65f6\uff0c\u5efa\u8bae\u4f7f\u7528CSS\u9009\u62e9\u5668\u6216XPath\u8868\u8fbe\u5f0f\uff0c\u8fd9\u4e24\u8005\u53ef\u4ee5\u5e2e\u52a9\u5feb\u901f\u5b9a\u4f4d\u6240\u9700\u7684\u6807\u7b7e\u3002\u6b64\u5916\uff0c\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u5bf9\u6587\u672c\u5185\u5bb9\u8fdb\u884c\u5339\u914d\uff0c\u4e5f\u80fd\u6709\u6548\u63d0\u5347\u7b5b\u9009\u7684\u51c6\u786e\u6027\u3002\u5229\u7528\u591a\u6761\u4ef6\u7ec4\u5408\u8fdb\u884c\u7b5b\u9009\u4e5f\u662f\u4e00\u79cd\u5e38\u89c1\u4e14\u6709\u6548\u7684\u7b56\u7565\uff0c\u53ef\u4ee5\u5e2e\u52a9\u83b7\u53d6\u66f4\u7cbe\u786e\u7684\u6570\u636e\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u722c\u866b\u4e8c\u6b21\u7b5b\u9009\u6807\u7b7e\u7684\u65b9\u6cd5\u4e3b\u8981\u6709\uff1a\u5229\u7528BeautifulSoup\u5e93\u8fdb\u884cHTML\u89e3\u6790\u3001\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u8fdb\u884c [&hellip;]","protected":false},"author":3,"featured_media":1094251,"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\/1094244"}],"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=1094244"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1094244\/revisions"}],"predecessor-version":[{"id":1094253,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1094244\/revisions\/1094253"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1094251"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1094244"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1094244"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1094244"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}