{"id":1109398,"date":"2025-01-08T17:09:46","date_gmt":"2025-01-08T09:09:46","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1109398.html"},"modified":"2025-01-08T17:09:51","modified_gmt":"2025-01-08T09:09:51","slug":"python%e7%88%ac%e5%8f%96div%e4%b8%ad%e6%95%b0%e6%8d%ae%e5%a6%82%e4%bd%95%e5%8e%bb%e9%99%a4js","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1109398.html","title":{"rendered":"python\u722c\u53d6div\u4e2d\u6570\u636e\u5982\u4f55\u53bb\u9664js"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/25072702\/b25aa6c5-610d-464c-84d9-f9f91dca12be.webp\" alt=\"python\u722c\u53d6div\u4e2d\u6570\u636e\u5982\u4f55\u53bb\u9664js\" \/><\/p>\n<p><p> <strong>Python\u722c\u53d6div\u4e2d\u6570\u636e\u5982\u4f55\u53bb\u9664js\u7684\u65b9\u6cd5\u6709\uff1a\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u3001\u901a\u8fc7requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3001\u4f7f\u7528Selenium\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\u3001\u901a\u8fc7\u6b63\u5219\u8868\u8fbe\u5f0f\u63d0\u53d6\u6570\u636e<\/strong>\u3002\u4e0b\u9762\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u901a\u8fc7\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u7684\u65b9\u6cd5\u3002<\/p>\n<\/p>\n<p><p>\u4e00\u3001\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML<\/p>\n<\/p>\n<p><p>BeautifulSoup\u662f\u4e00\u4e2a\u975e\u5e38\u5f3a\u5927\u7684Python\u5e93\uff0c\u7528\u4e8e\u89e3\u6790HTML\u548cXML\u6587\u6863\u3002\u5b83\u521b\u5efa\u4e86\u4e00\u4e2a\u53ef\u4ee5\u7528\u6765\u67e5\u627e\u89e3\u6790\u6811\u4e2d\u7279\u5b9a\u8282\u70b9\u7684\u89e3\u6790\u6811\u3002\u4ee5\u4e0b\u662f\u8be6\u7ec6\u6b65\u9aa4\uff1a<\/p>\n<\/p>\n<ol>\n<li>\u5b89\u88c5BeautifulSoup\u548crequests\u5e93<\/li>\n<\/ol>\n<p><p>\u5728\u5f00\u59cb\u4e4b\u524d\uff0c\u9700\u8981\u786e\u4fdd\u5df2\u7ecf\u5b89\u88c5\u4e86BeautifulSoup\u548crequests\u5e93\u3002\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u8fdb\u884c\u5b89\u88c5\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-bash\">pip install beautifulsoup4<\/p>\n<p>pip install requests<\/p>\n<p><\/code><\/pre>\n<\/p>\n<ol start=\"2\">\n<li>\u83b7\u53d6\u7f51\u9875\u5185\u5bb9<\/li>\n<\/ol>\n<p><p>\u4f7f\u7528requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3002\u6211\u4eec\u53ef\u4ee5\u901a\u8fc7requests.get()\u65b9\u6cd5\u83b7\u53d6\u7f51\u9875\u7684HTML\u5185\u5bb9\u3002<\/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>html_content = response.content<\/p>\n<p><\/code><\/pre>\n<\/p>\n<ol start=\"3\">\n<li>\u89e3\u6790HTML\u5185\u5bb9<\/li>\n<\/ol>\n<p><p>\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u5185\u5bb9\u3002\u521b\u5efa\u4e00\u4e2aBeautifulSoup\u5bf9\u8c61\uff0c\u5e76\u89e3\u6790\u83b7\u53d6\u7684HTML\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">soup = BeautifulSoup(html_content, &#39;html.parser&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<ol start=\"4\">\n<li>\u67e5\u627e\u7279\u5b9a\u7684div<\/li>\n<\/ol>\n<p><p>\u4f7f\u7528BeautifulSoup\u7684find()\u6216find_all()\u65b9\u6cd5\u67e5\u627e\u7279\u5b9a\u7684div\u6807\u7b7e\u3002\u53ef\u4ee5\u6839\u636e\u6807\u7b7e\u7684id\u3001class\u6216\u5176\u4ed6\u5c5e\u6027\u8fdb\u884c\u67e5\u627e\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">div_content = soup.find(&#39;div&#39;, {&#39;class&#39;: &#39;target-class&#39;})<\/p>\n<p>print(div_content.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7\u4e0a\u8ff0\u6b65\u9aa4\uff0c\u6211\u4eec\u53ef\u4ee5\u6210\u529f\u83b7\u53d6\u5e76\u89e3\u6790\u7f51\u9875\u4e2d\u7684\u7279\u5b9adiv\u5185\u5bb9\uff0c\u53bb\u9664\u5176\u4e2d\u7684JavaScript\u5185\u5bb9\u3002\u4e0b\u9762\u5c06\u8fdb\u4e00\u6b65\u8be6\u7ec6\u4ecb\u7ecd\u5176\u4ed6\u65b9\u6cd5\u3002<\/p>\n<\/p>\n<p><p>\u4e8c\u3001\u901a\u8fc7requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9<\/p>\n<\/p>\n<p><p>requests\u5e93\u662fPython\u4e2d\u7528\u4e8e\u53d1\u9001HTTP\u8bf7\u6c42\u7684\u7b80\u5355\u6613\u7528\u7684\u5e93\u3002\u5b83\u5141\u8bb8\u6211\u4eec\u8f7b\u677e\u5730\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u5e76\u5c06\u5176\u89e3\u6790\u4e3aHTML\u6587\u6863\u3002<\/p>\n<\/p>\n<ol>\n<li>\u5b89\u88c5requests\u5e93<\/li>\n<\/ol>\n<p><pre><code class=\"language-bash\">pip install requests<\/p>\n<p><\/code><\/pre>\n<\/p>\n<ol start=\"2\">\n<li>\u4f7f\u7528requests.get()\u65b9\u6cd5\u83b7\u53d6\u7f51\u9875\u5185\u5bb9<\/li>\n<\/ol>\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.content<\/p>\n<p><\/code><\/pre>\n<\/p>\n<ol start=\"3\">\n<li>\u89e3\u6790HTML\u5185\u5bb9<\/li>\n<\/ol>\n<p><p>\u89e3\u6790HTML\u5185\u5bb9\u53ef\u4ee5\u4f7f\u7528BeautifulSoup\u6216lxml\u5e93\u3002\u4ee5\u4e0b\u662f\u4f7f\u7528BeautifulSoup\u89e3\u6790\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from bs4 import BeautifulSoup<\/p>\n<p>soup = BeautifulSoup(html_content, &#39;html.parser&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4e09\u3001\u4f7f\u7528Selenium\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a<\/p>\n<\/p>\n<p><p>Selenium\u662f\u4e00\u4e2a\u7528\u4e8e\u81ea\u52a8\u5316Web\u6d4f\u89c8\u5668\u64cd\u4f5c\u7684\u5de5\u5177\u3002\u5b83\u53ef\u4ee5\u6a21\u62df\u7528\u6237\u5728\u6d4f\u89c8\u5668\u4e2d\u7684\u64cd\u4f5c\uff0c\u5305\u62ec\u70b9\u51fb\u3001\u8f93\u5165\u3001\u6eda\u52a8\u7b49\u3002\u901a\u8fc7Selenium\uff0c\u6211\u4eec\u53ef\u4ee5\u52a0\u8f7dJavaScript\u751f\u6210\u7684\u52a8\u6001\u5185\u5bb9\uff0c\u5e76\u83b7\u53d6\u6240\u9700\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n<ol>\n<li>\u5b89\u88c5Selenium<\/li>\n<\/ol>\n<p><pre><code class=\"language-bash\">pip install selenium<\/p>\n<p><\/code><\/pre>\n<\/p>\n<ol start=\"2\">\n<li>\u4e0b\u8f7d\u6d4f\u89c8\u5668\u9a71\u52a8<\/li>\n<\/ol>\n<p><p>\u6839\u636e\u6240\u4f7f\u7528\u7684\u6d4f\u89c8\u5668\uff0c\u4e0b\u8f7d\u5bf9\u5e94\u7684\u6d4f\u89c8\u5668\u9a71\u52a8\u3002\u4f8b\u5982\uff0c\u4f7f\u7528Chrome\u6d4f\u89c8\u5668\u65f6\uff0c\u9700\u8981\u4e0b\u8f7dChromeDriver\u3002<\/p>\n<\/p>\n<ol start=\"3\">\n<li>\u4f7f\u7528Selenium\u83b7\u53d6\u7f51\u9875\u5185\u5bb9<\/li>\n<\/ol>\n<p><pre><code class=\"language-python\">from selenium import webdriver<\/p>\n<p>driver = webdriver.Chrome(executable_path=&#39;\/path\/to\/chromedriver&#39;)<\/p>\n<p>driver.get(&#39;https:\/\/example.com&#39;)<\/p>\n<p>html_content = driver.page_source<\/p>\n<p><\/code><\/pre>\n<\/p>\n<ol start=\"4\">\n<li>\u89e3\u6790HTML\u5185\u5bb9<\/li>\n<\/ol>\n<p><pre><code class=\"language-python\">from bs4 import BeautifulSoup<\/p>\n<p>soup = BeautifulSoup(html_content, &#39;html.parser&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u56db\u3001\u901a\u8fc7\u6b63\u5219\u8868\u8fbe\u5f0f\u63d0\u53d6\u6570\u636e<\/p>\n<\/p>\n<p><p>\u6b63\u5219\u8868\u8fbe\u5f0f\u662f\u4e00\u79cd\u5f3a\u5927\u7684\u6587\u672c\u5904\u7406\u5de5\u5177\uff0c\u53ef\u4ee5\u7528\u4e8e\u5339\u914d\u548c\u63d0\u53d6\u7279\u5b9a\u6a21\u5f0f\u7684\u6587\u672c\u3002\u901a\u8fc7\u6b63\u5219\u8868\u8fbe\u5f0f\uff0c\u6211\u4eec\u53ef\u4ee5\u4eceHTML\u5185\u5bb9\u4e2d\u63d0\u53d6\u6240\u9700\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n<ol>\n<li>\u5b89\u88c5re\u5e93<\/li>\n<\/ol>\n<p><p>Python\u5185\u7f6e\u4e86re\u5e93\uff0c\u65e0\u9700\u5b89\u88c5\u3002<\/p>\n<\/p>\n<ol start=\"2\">\n<li>\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u63d0\u53d6\u6570\u636e<\/li>\n<\/ol>\n<p><pre><code class=\"language-python\">import re<\/p>\n<p>html_content = &#39;&lt;div class=&quot;target-class&quot;&gt;Hello, world!&lt;\/div&gt;&#39;<\/p>\n<p>pattern = re.compile(r&#39;&lt;div class=&quot;target-class&quot;&gt;(.*?)&lt;\/div&gt;&#39;)<\/p>\n<p>matches = pattern.findall(html_content)<\/p>\n<p>for match in matches:<\/p>\n<p>    print(match)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u4e94\u3001\u7ed3\u5408\u4f7f\u7528BeautifulSoup\u548crequests\u5e93<\/p>\n<\/p>\n<p><p>\u4e3a\u4e86\u66f4\u9ad8\u6548\u5730\u722c\u53d6\u548c\u89e3\u6790\u7f51\u9875\u5185\u5bb9\uff0c\u53ef\u4ee5\u7ed3\u5408\u4f7f\u7528BeautifulSoup\u548crequests\u5e93\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u5b8c\u6574\u7684\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>from bs4 import BeautifulSoup<\/p>\n<h2><strong>\u83b7\u53d6\u7f51\u9875\u5185\u5bb9<\/strong><\/h2>\n<p>url = &#39;https:\/\/example.com&#39;<\/p>\n<p>response = requests.get(url)<\/p>\n<p>html_content = response.content<\/p>\n<h2><strong>\u89e3\u6790HTML\u5185\u5bb9<\/strong><\/h2>\n<p>soup = BeautifulSoup(html_content, &#39;html.parser&#39;)<\/p>\n<h2><strong>\u67e5\u627e\u7279\u5b9a\u7684div<\/strong><\/h2>\n<p>div_content = soup.find(&#39;div&#39;, {&#39;class&#39;: &#39;target-class&#39;})<\/p>\n<p>print(div_content.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7\u4e0a\u8ff0\u65b9\u6cd5\uff0c\u6211\u4eec\u53ef\u4ee5\u9ad8\u6548\u5730\u722c\u53d6\u7f51\u9875\u4e2d\u7684\u7279\u5b9adiv\u5185\u5bb9\uff0c\u5e76\u53bb\u9664\u5176\u4e2d\u7684JavaScript\u5185\u5bb9\u3002\u65e0\u8bba\u662f\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u3001\u901a\u8fc7requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3001\u4f7f\u7528Selenium\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\uff0c\u8fd8\u662f\u901a\u8fc7\u6b63\u5219\u8868\u8fbe\u5f0f\u63d0\u53d6\u6570\u636e\uff0c\u90fd\u53ef\u4ee5\u8fbe\u5230\u6211\u4eec\u7684\u76ee\u7684\u3002\u6839\u636e\u5b9e\u9645\u9700\u6c42\u9009\u62e9\u5408\u9002\u7684\u65b9\u6cd5\uff0c\u53ef\u4ee5\u5927\u5927\u63d0\u9ad8\u722c\u53d6\u548c\u89e3\u6790\u7f51\u9875\u5185\u5bb9\u7684\u6548\u7387\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u4f7f\u7528Python\u53bb\u9664\u722c\u53d6\u6570\u636e\u4e2d\u7684JavaScript\u4ee3\u7801\uff1f<\/strong><br \/>\u5728\u4f7f\u7528Python\u722c\u53d6\u7f51\u9875\u6570\u636e\u65f6\uff0cJavaScript\u4ee3\u7801\u53ef\u80fd\u4f1a\u5e72\u6270\u6570\u636e\u7684\u6e05\u6670\u5ea6\u3002\u53ef\u4ee5\u901a\u8fc7\u4f7f\u7528BeautifulSoup\u5e93\u6765\u89e3\u6790HTML\uff0c\u5e76\u8fd0\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u6216\u5b57\u7b26\u4e32\u5904\u7406\u65b9\u6cd5\u53bb\u9664\u4e0d\u5fc5\u8981\u7684JavaScript\u4ee3\u7801\u3002\u4f8b\u5982\uff0c\u4f7f\u7528<code>re<\/code>\u6a21\u5757\u53ef\u4ee5\u627e\u5230\u5e76\u5220\u9664\u5305\u542b<code>&lt;script&gt;<\/code>\u6807\u7b7e\u7684\u5185\u5bb9\uff0c\u786e\u4fdd\u53ea\u63d0\u53d6\u7eaf\u6587\u672c\u6216\u6240\u9700\u7684HTML\u5143\u7d20\u3002<\/p>\n<p><strong>\u722c\u53d6div\u4e2d\u7684\u6570\u636e\u65f6\uff0c\u5982\u4f55\u4fdd\u8bc1\u6570\u636e\u7684\u5b8c\u6574\u6027\uff1f<\/strong><br \/>\u4e3a\u4e86\u786e\u4fdd\u6570\u636e\u7684\u5b8c\u6574\u6027\uff0c\u5efa\u8bae\u5728\u722c\u53d6\u524d\u5bf9\u76ee\u6807\u7f51\u9875\u8fdb\u884c\u5206\u6790\uff0c\u627e\u51fa\u9700\u8981\u7684div\u5143\u7d20\u5e76\u660e\u786e\u5176\u7ed3\u6784\u3002\u4f7f\u7528requests\u5e93\u83b7\u53d6\u9875\u9762\u6570\u636e\u540e\uff0c\u8fd0\u7528BeautifulSoup\u8fdb\u884c\u89e3\u6790\uff0c\u63d0\u53d6\u6240\u9700\u5185\u5bb9\uff0c\u5e76\u5728\u63d0\u53d6\u540e\u8fdb\u884c\u6570\u636e\u6e05\u6d17\uff0c\u53bb\u9664\u591a\u4f59\u7684\u7a7a\u683c\u548c\u6362\u884c\u7b26\uff0c\u4ee5\u4fdd\u6301\u6570\u636e\u7684\u5e72\u51c0\u548c\u5b8c\u6574\u3002<\/p>\n<p><strong>\u6709\u6ca1\u6709\u63a8\u8350\u7684Python\u5e93\u6765\u5904\u7406\u722c\u53d6\u540e\u7684\u6570\u636e\u6e05\u6d17\uff1f<\/strong><br \/>\u9664\u4e86BeautifulSoup\uff0cpandas\u4e5f\u662f\u4e00\u4e2a\u5f3a\u5927\u7684\u6570\u636e\u5904\u7406\u5e93\uff0c\u53ef\u4ee5\u7528\u4e8e\u6570\u636e\u6e05\u6d17\u548c\u5206\u6790\u3002\u5728\u722c\u53d6\u6570\u636e\u540e\uff0c\u53ef\u4ee5\u5c06\u7ed3\u679c\u5b58\u50a8\u5230DataFrame\u4e2d\uff0c\u5229\u7528pandas\u63d0\u4f9b\u7684\u5404\u79cd\u65b9\u6cd5\u5bf9\u6570\u636e\u8fdb\u884c\u8fdb\u4e00\u6b65\u5904\u7406\uff0c\u5982\u53bb\u91cd\u3001\u586b\u5145\u7f3a\u5931\u503c\u7b49\u3002\u6b64\u5916\uff0c\u4f7f\u7528lxml\u5e93\u4e5f\u53ef\u4ee5\u63d0\u9ad8\u89e3\u6790\u901f\u5ea6\uff0c\u5c24\u5176\u662f\u5728\u5904\u7406\u5927\u89c4\u6a21\u6570\u636e\u65f6\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u722c\u53d6div\u4e2d\u6570\u636e\u5982\u4f55\u53bb\u9664js\u7684\u65b9\u6cd5\u6709\uff1a\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u3001\u901a\u8fc7reques [&hellip;]","protected":false},"author":3,"featured_media":1109411,"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\/1109398"}],"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=1109398"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1109398\/revisions"}],"predecessor-version":[{"id":1109415,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1109398\/revisions\/1109415"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1109411"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1109398"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1109398"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1109398"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}