{"id":1101479,"date":"2025-01-08T15:50:07","date_gmt":"2025-01-08T07:50:07","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1101479.html"},"modified":"2025-01-08T15:50:09","modified_gmt":"2025-01-08T07:50:09","slug":"python%e5%a6%82%e4%bd%95%e7%94%a8bs%e5%ba%93%e7%88%ac%e5%8f%96span%e5%86%85%e5%ae%b9-2","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1101479.html","title":{"rendered":"python\u5982\u4f55\u7528bs\u5e93\u722c\u53d6span\u5185\u5bb9"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/25064234\/2cfa8e76-98e7-4baf-b72d-938d7d212436.webp\" alt=\"python\u5982\u4f55\u7528bs\u5e93\u722c\u53d6span\u5185\u5bb9\" \/><\/p>\n<p><p> <strong>\u4f7f\u7528BeautifulSoup\u5e93\u722c\u53d6span\u6807\u7b7e\u5185\u5bb9\u7684\u65b9\u6cd5\u5305\u62ec\u4ee5\u4e0b\u6b65\u9aa4\uff1a\u5b89\u88c5\u5e93\u3001\u53d1\u9001\u8bf7\u6c42\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3001\u89e3\u6790HTML\u3001\u67e5\u627e\u5e76\u63d0\u53d6span\u6807\u7b7e\u5185\u5bb9<\/strong>\u3002\u5176\u4e2d\uff0c\u89e3\u6790HTML\u662f\u6700\u91cd\u8981\u7684\u4e00\u6b65\uff0c\u56e0\u4e3a\u8fd9\u4e00\u6b65\u51b3\u5b9a\u4e86\u540e\u7eed\u6570\u636e\u63d0\u53d6\u7684\u51c6\u786e\u6027\u3002<\/p>\n<\/p>\n<p><h3>\u4e00\u3001\u5b89\u88c5BeautifulSoup\u5e93\u548c\u76f8\u5173\u4f9d\u8d56<\/h3>\n<\/p>\n<p><p>\u5728\u5f00\u59cb\u4e4b\u524d\uff0c\u9996\u5148\u9700\u8981\u5b89\u88c5BeautifulSoup\u5e93\u4ee5\u53ca\u53d1\u9001HTTP\u8bf7\u6c42\u7684\u5e93\uff08\u5982requests\uff09\u3002\u4f60\u53ef\u4ee5\u4f7f\u7528pip\u6765\u5b89\u88c5\u8fd9\u4e9b\u5e93\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<p><h3>\u4e8c\u3001\u53d1\u9001\u8bf7\u6c42\u83b7\u53d6\u7f51\u9875\u5185\u5bb9<\/h3>\n<\/p>\n<p><p>\u6211\u4eec\u9700\u8981\u4ece\u76ee\u6807\u7f51\u9875\u83b7\u53d6HTML\u5185\u5bb9\u3002\u53ef\u4ee5\u4f7f\u7528requests\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>url = &#39;http:\/\/example.com&#39;<\/p>\n<p>response = requests.get(url)<\/p>\n<h2><strong>\u786e\u4fdd\u8bf7\u6c42\u6210\u529f<\/strong><\/h2>\n<p>if response.status_code == 200:<\/p>\n<p>    html_content = response.text<\/p>\n<p>else:<\/p>\n<p>    print(f&quot;F<a href=\"https:\/\/docs.pingcode.com\/blog\/59162.html\" target=\"_blank\">AI<\/a>led to retrieve content: {response.status_code}&quot;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e09\u3001\u89e3\u6790HTML\u5185\u5bb9<\/h3>\n<\/p>\n<p><p>\u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u5185\u5bb9\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><h3>\u56db\u3001\u67e5\u627e\u5e76\u63d0\u53d6span\u6807\u7b7e\u5185\u5bb9<\/h3>\n<\/p>\n<p><p>\u4f7f\u7528BeautifulSoup\u63d0\u4f9b\u7684\u67e5\u627e\u65b9\u6cd5\u6765\u63d0\u53d6span\u6807\u7b7e\u5185\u5bb9\u3002\u53ef\u4ee5\u6839\u636e\u6807\u7b7e\u540d\u3001\u5c5e\u6027\u7b49\u6761\u4ef6\u6765\u67e5\u627e\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u67e5\u627e\u6240\u6709span\u6807\u7b7e<\/p>\n<p>spans = soup.find_all(&#39;span&#39;)<\/p>\n<p>for span in spans:<\/p>\n<p>    print(span.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5982\u679c\u4f60\u53ea\u60f3\u67e5\u627e\u7279\u5b9a\u5c5e\u6027\u7684span\u6807\u7b7e\uff0c\u6bd4\u5982class\u4e3a&#39;some-class&#39;\u7684span\u6807\u7b7e\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u67e5\u627e\u7279\u5b9aclass\u7684span\u6807\u7b7e<\/p>\n<p>spans = soup.find_all(&#39;span&#39;, class_=&#39;some-class&#39;)<\/p>\n<p>for span in spans:<\/p>\n<p>    print(span.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e94\u3001\u5904\u7406\u590d\u6742\u7684HTML\u7ed3\u6784<\/h3>\n<\/p>\n<p><p>\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0cHTML\u7ed3\u6784\u53ef\u80fd\u4f1a\u6bd4\u8f83\u590d\u6742\uff0c\u4f60\u9700\u8981\u6839\u636e\u5b9e\u9645\u60c5\u51b5\u6765\u8c03\u6574\u67e5\u627e\u6761\u4ef6\u3002\u4f60\u53ef\u4ee5\u7ed3\u5408\u5176\u4ed6BeautifulSoup\u65b9\u6cd5\uff0c\u6bd4\u5982select()\u65b9\u6cd5\uff0c\u901a\u8fc7CSS\u9009\u62e9\u5668\u6765\u67e5\u627e\u6807\u7b7e\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u4f7f\u7528CSS\u9009\u62e9\u5668\u67e5\u627e<\/p>\n<p>spans = soup.select(&#39;div.some-div &gt; span.some-class&#39;)<\/p>\n<p>for span in spans:<\/p>\n<p>    print(span.text)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u516d\u3001\u5e94\u5bf9\u52a8\u6001\u5185\u5bb9<\/h3>\n<\/p>\n<p><p>\u6709\u4e9b\u7f51\u9875\u7684\u5185\u5bb9\u662f\u901a\u8fc7JavaScript\u52a8\u6001\u52a0\u8f7d\u7684\uff0c\u8fd9\u79cd\u60c5\u51b5\u4e0b\u4ec5\u4f7f\u7528requests\u548cBeautifulSoup\u53ef\u80fd\u65e0\u6cd5\u83b7\u53d6\u5230\u5b8c\u6574\u5185\u5bb9\u3002\u4f60\u53ef\u4ee5\u4f7f\u7528Selenium\u6216Playwright\u7b49\u5e93\u6765\u5904\u7406\u52a8\u6001\u5185\u5bb9\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">from selenium import webdriver<\/p>\n<h2><strong>\u8bbe\u7f6e\u6d4f\u89c8\u5668\u9a71\u52a8\u8def\u5f84<\/strong><\/h2>\n<p>driver = webdriver.Chrome(executable_path=&#39;\/path\/to\/chromedriver&#39;)<\/p>\n<p>driver.get(&#39;http:\/\/example.com&#39;)<\/p>\n<p>html_content = driver.page_source<\/p>\n<p>soup = BeautifulSoup(html_content, &#39;html.parser&#39;)<\/p>\n<p>spans = soup.find_all(&#39;span&#39;)<\/p>\n<p>for span in spans:<\/p>\n<p>    print(span.text)<\/p>\n<p>driver.quit()<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e03\u3001\u5904\u7406\u53cd\u722c\u866b\u673a\u5236<\/h3>\n<\/p>\n<p><p>\u6709\u4e9b\u7f51\u7ad9\u4f1a\u6709\u53cd\u722c\u866b\u673a\u5236\uff0c\u53ef\u80fd\u4f1a\u9650\u5236\u9891\u7e41\u8bf7\u6c42\u6216\u8005\u68c0\u6d4b\u5230\u722c\u866b\u884c\u4e3a\u65f6\u8fd4\u56de\u9519\u8bef\u4fe1\u606f\u3002\u4f60\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u7b56\u7565\u6765\u5e94\u5bf9\uff1a<\/p>\n<\/p>\n<ol>\n<li><strong>\u6dfb\u52a0\u8bf7\u6c42\u5934<\/strong>\uff1a\u6a21\u4eff\u6d4f\u89c8\u5668\u53d1\u9001\u8bf7\u6c42\uff0c\u6dfb\u52a0User-Agent\u5934\u7b49\u3002<\/li>\n<li><strong>\u8bf7\u6c42\u95f4\u9694<\/strong>\uff1a\u5728\u8bf7\u6c42\u4e4b\u95f4\u6dfb\u52a0\u968f\u673a\u7684\u65f6\u95f4\u95f4\u9694\uff0c\u907f\u514d\u9891\u7e41\u8bf7\u6c42\u3002<\/li>\n<li><strong>\u4ee3\u7406IP<\/strong>\uff1a\u4f7f\u7528\u4ee3\u7406IP\u6765\u5206\u6563\u8bf7\u6c42\u6765\u6e90\uff0c\u907f\u514d\u88ab\u5c01\u9501\u3002<\/li>\n<\/ol>\n<p><pre><code class=\"language-python\">import random<\/p>\n<p>import time<\/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\/91.0.4472.124 Safari\/537.36&#39;<\/p>\n<p>}<\/p>\n<p>response = requests.get(url, headers=headers)<\/p>\n<h2><strong>\u968f\u673a\u7b49\u5f85<\/strong><\/h2>\n<p>time.sleep(random.uniform(1, 3))<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u516b\u3001\u793a\u4f8b\u4ee3\u7801<\/h3>\n<\/p>\n<p><p>\u4ee5\u4e0b\u662f\u4e00\u4e2a\u5b8c\u6574\u7684\u793a\u4f8b\u4ee3\u7801\uff0c\u5c55\u793a\u4e86\u5982\u4f55\u4f7f\u7528BeautifulSoup\u5e93\u722c\u53d6span\u6807\u7b7e\u5185\u5bb9\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import requests<\/p>\n<p>from bs4 import BeautifulSoup<\/p>\n<h2><strong>\u53d1\u9001HTTP\u8bf7\u6c42\u83b7\u53d6\u7f51\u9875\u5185\u5bb9<\/strong><\/h2>\n<p>url = &#39;http:\/\/example.com&#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\/91.0.4472.124 Safari\/537.36&#39;<\/p>\n<p>}<\/p>\n<p>response = requests.get(url, headers=headers)<\/p>\n<p>if response.status_code == 200:<\/p>\n<p>    html_content = response.text<\/p>\n<p>    # \u89e3\u6790HTML\u5185\u5bb9<\/p>\n<p>    soup = BeautifulSoup(html_content, &#39;html.parser&#39;)<\/p>\n<p>    # \u67e5\u627e\u6240\u6709span\u6807\u7b7e<\/p>\n<p>    spans = soup.find_all(&#39;span&#39;)<\/p>\n<p>    for span in spans:<\/p>\n<p>        print(span.text)<\/p>\n<p>else:<\/p>\n<p>    print(f&quot;Failed to retrieve content: {response.status_code}&quot;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7\u4ee5\u4e0a\u6b65\u9aa4\uff0c\u4f60\u53ef\u4ee5\u4f7f\u7528BeautifulSoup\u5e93\u8f7b\u677e\u722c\u53d6\u7f51\u9875\u4e2d\u7684span\u6807\u7b7e\u5185\u5bb9\u3002\u6839\u636e\u5b9e\u9645\u9700\u6c42\uff0c\u4f60\u53ef\u4ee5\u8c03\u6574\u4ee3\u7801\u4e2d\u7684\u67e5\u627e\u6761\u4ef6\u548c\u5904\u7406\u903b\u8f91\uff0c\u4ee5\u4fbf\u66f4\u7cbe\u51c6\u5730\u63d0\u53d6\u6240\u9700\u6570\u636e\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u4f7f\u7528Beautiful Soup\u5e93\u63d0\u53d6\u7279\u5b9a\u7684HTML\u5143\u7d20\u5185\u5bb9\uff1f<\/strong><br \/>\u4f7f\u7528Beautiful Soup\u5e93\u53ef\u4ee5\u8f7b\u677e\u63d0\u53d6HTML\u6587\u6863\u4e2d\u7684\u7279\u5b9a\u5143\u7d20\u5185\u5bb9\u3002\u9996\u5148\uff0c\u5b89\u88c5Beautiful Soup\u548crequests\u5e93\u3002\u7136\u540e\uff0c\u901a\u8fc7requests\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u5e76\u4f7f\u7528Beautiful Soup\u89e3\u6790HTML\u3002\u901a\u8fc7<code>find<\/code>\u6216<code>find_all<\/code>\u65b9\u6cd5\u5b9a\u4f4d\u5230\u5177\u4f53\u7684<code>&lt;span&gt;<\/code>\u6807\u7b7e\uff0c\u6700\u540e\u53ef\u4ee5\u4f7f\u7528<code>.text<\/code>\u6216<code>.get_text()<\/code>\u65b9\u6cd5\u63d0\u53d6\u5176\u4e2d\u7684\u6587\u672c\u5185\u5bb9\u3002<\/p>\n<p><strong>\u5728\u722c\u53d6\u8fc7\u7a0b\u4e2d\u5982\u4f55\u5904\u7406\u53cd\u722c\u866b\u673a\u5236\uff1f<\/strong><br \/>\u8bb8\u591a\u7f51\u7ad9\u4f1a\u91c7\u53d6\u53cd\u722c\u866b\u63aa\u65bd\u6765\u4fdd\u62a4\u5176\u5185\u5bb9\u3002\u4e3a\u4e86\u6709\u6548\u5e94\u5bf9\u8fd9\u4e9b\u673a\u5236\uff0c\u53ef\u4ee5\u901a\u8fc7\u4f2a\u88c5User-Agent\u6765\u6a21\u62df\u6d4f\u89c8\u5668\u8bf7\u6c42\u3002\u6b64\u5916\uff0c\u5408\u7406\u8bbe\u7f6e\u8bf7\u6c42\u95f4\u9694\uff0c\u907f\u514d\u9891\u7e41\u8bf7\u6c42\u540c\u4e00\u7f51\u9875\uff0c\u6709\u52a9\u4e8e\u964d\u4f4e\u88ab\u5c01\u7981\u7684\u98ce\u9669\u3002\u6b64\u5916\uff0c\u5229\u7528\u4ee3\u7406\u670d\u52a1\u5668\u4e5f\u662f\u4e00\u79cd\u5e38\u89c1\u7684\u624b\u6bb5\uff0c\u53ef\u4ee5\u5e2e\u52a9\u9690\u85cf\u771f\u5b9eIP\u5730\u5740\u3002<\/p>\n<p><strong>\u4f7f\u7528Beautiful Soup\u722c\u53d6\u6570\u636e\u65f6\u6709\u54ea\u4e9b\u5e38\u89c1\u7684\u9519\u8bef\u9700\u8981\u6ce8\u610f\uff1f<\/strong><br \/>\u5728\u4f7f\u7528Beautiful Soup\u8fdb\u884c\u6570\u636e\u722c\u53d6\u65f6\uff0c\u5e38\u89c1\u9519\u8bef\u5305\u62ecHTML\u89e3\u6790\u5931\u8d25\u3001\u672a\u6b63\u786e\u6307\u5b9a\u67e5\u627e\u6761\u4ef6\u6216\u9009\u62e9\u5668\u3001\u672a\u5904\u7406\u7f51\u7edc\u5f02\u5e38\u7b49\u3002\u786e\u4fdd\u7f51\u9875\u7ed3\u6784\u4e0e\u9009\u62e9\u5668\u5339\u914d\u662f\u5173\u952e\uff0c\u5efa\u8bae\u5728\u722c\u53d6\u524d\u4f7f\u7528\u6d4f\u89c8\u5668\u7684\u5f00\u53d1\u8005\u5de5\u5177\u68c0\u67e5\u76ee\u6807\u5143\u7d20\u7684HTML\u7ed3\u6784\u3002\u540c\u65f6\uff0c\u5904\u7406\u7f51\u7edc\u8bf7\u6c42\u65f6\uff0c\u4f7f\u7528\u5f02\u5e38\u5904\u7406\u673a\u5236\u53ef\u4ee5\u63d0\u5347\u7a0b\u5e8f\u7684\u7a33\u5b9a\u6027\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u4f7f\u7528BeautifulSoup\u5e93\u722c\u53d6span\u6807\u7b7e\u5185\u5bb9\u7684\u65b9\u6cd5\u5305\u62ec\u4ee5\u4e0b\u6b65\u9aa4\uff1a\u5b89\u88c5\u5e93\u3001\u53d1\u9001\u8bf7\u6c42\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3001\u89e3\u6790HT [&hellip;]","protected":false},"author":3,"featured_media":1101486,"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\/1101479"}],"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=1101479"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1101479\/revisions"}],"predecessor-version":[{"id":1101489,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1101479\/revisions\/1101489"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1101486"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1101479"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1101479"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1101479"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}