{"id":5441,"date":"2026-01-12T15:08:43","date_gmt":"2026-01-12T07:08:43","guid":{"rendered":"https:\/\/code.jishujc.com\/?p=5441"},"modified":"2026-01-12T15:08:43","modified_gmt":"2026-01-12T07:08:43","slug":"x-%e7%ab%99%e8%b5%84%e6%ba%90%e9%87%87%e9%9b%86%e8%84%9a%e6%9c%ac%e7%bc%96%e5%86%99%e6%95%99%e7%a8%8b%ef%bc%9apython-%e7%88%ac%e8%99%ab%e5%ae%9e%e7%8e%b0%e8%87%aa%e5%8a%a8%e9%87%87%e9%9b%86%ef%bc%88","status":"publish","type":"post","link":"https:\/\/www.qqjishu.com\/index.php\/2026\/01\/12\/x-%e7%ab%99%e8%b5%84%e6%ba%90%e9%87%87%e9%9b%86%e8%84%9a%e6%9c%ac%e7%bc%96%e5%86%99%e6%95%99%e7%a8%8b%ef%bc%9apython-%e7%88%ac%e8%99%ab%e5%ae%9e%e7%8e%b0%e8%87%aa%e5%8a%a8%e9%87%87%e9%9b%86%ef%bc%88\/","title":{"rendered":"x \u7ad9\u8d44\u6e90\u91c7\u96c6\u811a\u672c\u7f16\u5199\u6559\u7a0b\uff1aPython \u722c\u866b\u5b9e\u73b0\u81ea\u52a8\u91c7\u96c6\uff08\u9644\u6e90\u7801\uff09"},"content":{"rendered":"<p class=\"ds-markdown-paragraph\">\u4f7f\u7528 Python \u7f16\u5199\u722c\u866b\u811a\u672c\u662f\u5b9e\u73b0 x \u7ad9\u8d44\u6e90\u81ea\u52a8\u91c7\u96c6\u6700\u7075\u6d3b\u3001\u5f3a\u5927\u7684\u65b9\u6cd5\u3002\u672c\u6587\u5c06\u5f15\u5bfc\u4f60\u5b8c\u6210\u4e00\u4e2a\u57fa\u7840\u4f46\u5b8c\u6574\u7684 Python \u722c\u866b\u9879\u76ee\uff0c\u5e76\u63d0\u4f9b\u793a\u4f8b\u6e90\u7801\uff0c\u5e2e\u52a9\u4f60\u8e0f\u5165\u7f16\u7a0b\u91c7\u96c6\u7684\u5927\u95e8\u3002<\/p>\n<p class=\"ds-markdown-paragraph\">\u7b2c\u4e00\u6b65\uff1a\u73af\u5883\u51c6\u5907\u4e0e\u5e93\u5b89\u88c5\u3002\u786e\u4fdd\u4f60\u7684\u7535\u8111\u5b89\u88c5\u4e86 Python\uff08\u5efa\u8bae3.6\u4ee5\u4e0a\u7248\u672c\uff09\u3002\u6211\u4eec\u9700\u8981\u4e24\u4e2a\u6838\u5fc3\u5e93\uff1a<code>requests<\/code>\u00a0\u7528\u4e8e\u53d1\u9001HTTP\u8bf7\u6c42\uff0c<code>BeautifulSoup<\/code>\u00a0\u7528\u4e8e\u89e3\u6790HTML\u6587\u6863\u3002\u5728\u547d\u4ee4\u884c\u4e2d\u4f7f\u7528 pip \u5b89\u88c5\uff1a<code>pip install requests beautifulsoup4<\/code>\u3002<\/p>\n<p class=\"ds-markdown-paragraph\">\u7b2c\u4e8c\u6b65\uff1a\u5206\u6790\u76ee\u6807\u7f51\u9875\u7ed3\u6784\u3002\u8fd9\u662f\u722c\u866b\u7f16\u5199\u524d\u6700\u91cd\u8981\u7684\u51c6\u5907\u5de5\u4f5c\u3002\u6253\u5f00\u4f60\u8981\u91c7\u96c6\u7684\u7f51\u7ad9\uff0c\u6309F12\u6253\u5f00\u5f00\u53d1\u8005\u5de5\u5177\uff0c\u4f7f\u7528\u201c\u5143\u7d20\u9009\u62e9\u5668\u201d\u70b9\u51fb\u4f60\u60f3\u8981\u91c7\u96c6\u7684\u5185\u5bb9\uff08\u5982\u6587\u7ae0\u6807\u9898\uff09\uff0c\u5728\u4ee3\u7801\u9762\u677f\u4e2d\u89c2\u5bdf\u5176HTML\u7ed3\u6784\uff0c\u627e\u5230\u5305\u88f9\u5b83\u7684\u6807\u7b7e\u548c\u7c7b\u540d\uff08class\uff09\u3002\u4f8b\u5982\uff0c\u4f60\u53ef\u80fd\u53d1\u73b0\u6240\u6709\u6807\u9898\u90fd\u4f4d\u4e8e\u00a0<code>&lt;h2 class=\"title\"&gt;<\/code>\u00a0\u6807\u7b7e\u5185\u3002<\/p>\n<p class=\"ds-markdown-paragraph\">\u7b2c\u4e09\u6b65\uff1a\u7f16\u5199\u722c\u866b\u4ee3\u7801\u3002\u4e0b\u9762\u662f\u4e00\u4e2a\u91c7\u96c6\u9759\u6001\u7f51\u9875\u6587\u7ae0\u6807\u9898\u548c\u94fe\u63a5\u7684\u793a\u4f8b\u811a\u672c\uff1a<\/p>\n<p class=\"ds-markdown-paragraph\">import requests<br \/>\nfrom bs4 import BeautifulSoup<\/p>\n<h1>\u76ee\u6807\u7f51\u5740\uff08\u6b64\u5904\u4e3a\u793a\u4f8b\uff0c\u8bf7\u66ff\u6362\u4e3a\u5b9e\u9645\u7f51\u5740\uff09<\/h1>\n<p class=\"ds-markdown-paragraph\">url = &#8216;<a href=\"https:\/\/example-news-site.com\/news\" target=\"_blank\" rel=\"noopener noreferrer\">https:\/\/example-news-site.com\/news<\/a>&#8216;<\/p>\n<h1>\u8bbe\u7f6e\u8bf7\u6c42\u5934\uff0c\u6a21\u62df\u6d4f\u89c8\u5668\u8bbf\u95ee<\/h1>\n<p class=\"ds-markdown-paragraph\">headers = {<br \/>\n&#8216;User-Agent&#8217;: &#8216;Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36&#8217;<br \/>\n}<\/p>\n<h1>\u53d1\u9001GET\u8bf7\u6c42<\/h1>\n<p class=\"ds-markdown-paragraph\">response = requests.get(url, headers=headers)<\/p>\n<h1>\u68c0\u67e5\u8bf7\u6c42\u662f\u5426\u6210\u529f<\/h1>\n<p class=\"ds-markdown-paragraph\">if response.status_code == 200:<br \/>\n# \u4f7f\u7528BeautifulSoup\u89e3\u6790HTML\u5185\u5bb9<br \/>\nsoup = BeautifulSoup(response.text, &#8216;html.parser&#8217;)<\/p>\n<div class=\"md-code-block md-code-block-light\">\n<div class=\"md-code-block-banner-wrap\">\n<div class=\"md-code-block-banner md-code-block-banner-lite\">\n<div class=\"_121d384\">\n<div class=\"d2a24f03\"><span class=\"d813de27\">text<\/span><\/div>\n<\/div>\n<\/div>\n<\/div>\n<pre># \u6839\u636e\u4e4b\u524d\u5206\u6790\u7684HTML\u7ed3\u6784\uff0c\u627e\u5230\u6240\u6709\u6587\u7ae0\u6761\u76ee\n# \u5047\u8bbe\u6bcf\u4e2a\u6587\u7ae0\u6761\u76ee\u90fd\u5728\u4e00\u4e2aclass\u4e3a\u2018article-item\u2019\u7684div\u4e2d\narticle_items = soup.find_all('div', class_='article-item')\n\nfor item in article_items:\n    # \u5728\u6bcf\u4e2a\u6761\u76ee\u4e2d\u67e5\u627e\u6807\u9898\uff08\u5047\u8bbe\u5728h2\u7684a\u6807\u7b7e\u91cc\uff09\n    title_tag = item.find('h2').find('a') if item.find('h2') else None\n    if title_tag:\n        title = title_tag.get_text(strip=True)  # \u83b7\u53d6\u6587\u672c\u5e76\u53bb\u9664\u7a7a\u767d\n        link = title_tag.get('href')            # \u83b7\u53d6\u94fe\u63a5\u5c5e\u6027\n        # \u5904\u7406\u53ef\u80fd\u7684\u76f8\u5bf9\u94fe\u63a5\n        if link and not link.startswith('http'):\n            link = requests.compat.urljoin(url, link)\n        print(f\"\u6807\u9898\uff1a{title}\")\n        print(f\"\u94fe\u63a5\uff1a{link}\")\n        print(\"-\" * 30)<\/pre>\n<\/div>\n<p class=\"ds-markdown-paragraph\">else:<br \/>\nprint(f&#8221;\u8bf7\u6c42\u9875\u9762\u5931\u8d25\uff0c\u72b6\u6001\u7801\uff1a{response.status_code}&#8221;)<\/p>\n<p class=\"ds-markdown-paragraph\">\u4e00\u4e2a\u5b9e\u7528\u6280\u5de7\u662f\u5904\u7406\u52a8\u6001\u52a0\u8f7d\u5185\u5bb9\u3002\u5982\u679c\u4e0a\u8ff0\u4ee3\u7801\u6293\u53d6\u4e0d\u5230\u6570\u636e\uff0c\u53ef\u80fd\u662f\u56e0\u4e3a\u5185\u5bb9\u7531JavaScript\u52a8\u6001\u751f\u6210\u3002\u6b64\u65f6\u53ef\u4ee5\u8003\u8651\u4f7f\u7528\u00a0<code>Selenium<\/code>\u00a0\u6216\u00a0<code>Playwright<\/code>\u00a0\u5e93\u6765\u6a21\u62df\u6d4f\u89c8\u5668\u64cd\u4f5c\uff0c\u6216\u8005\u66f4\u4f18\u7684\u65b9\u6cd5\u662f\u5c1d\u8bd5\u5728\u5f00\u53d1\u8005\u5de5\u5177\u7684\u201c\u7f51\u7edc\u201d\u9009\u9879\u5361\u4e2d\u5bfb\u627e\u771f\u6b63\u7684\u6570\u636eAPI\u63a5\u53e3\uff0c\u76f4\u63a5\u8bf7\u6c42JSON\u6570\u636e\u3002\u66f4\u591a\u5e94\u5bf9\u53cd\u722c\u7684\u8fdb\u9636\u6280\u5de7\uff0c\u53ef\u4ee5\u5728\u6a21\u677f\u6c47<a href=\"https:\/\/www.qqjishu.com\/\" target=\"_blank\" rel=\"noopener noreferrer\">www.qqjishu.com\/<\/a>\u67e5\u627e\u76f8\u5173\u811a\u672c\u6848\u4f8b\u3002<\/p>\n<p class=\"ds-markdown-paragraph\">\u603b\u7ed3\u6765\u8bf4\uff0c\u7f16\u5199Python\u722c\u866b\u7684\u6838\u5fc3\u6b65\u9aa4\u662f\uff1a\u5206\u6790\u7f51\u9875\u7ed3\u6784 -&gt; \u53d1\u9001\u8bf7\u6c42\u83b7\u53d6HTML -&gt; \u89e3\u6790HTML\u63d0\u53d6\u6570\u636e -&gt; \u5b58\u50a8\u6570\u636e\u3002\u4ece\u4e0a\u9762\u7684\u7b80\u5355\u793a\u4f8b\u5f00\u59cb\uff0c\u4f60\u53ef\u4ee5\u9010\u6b65\u5b66\u4e60\u5982\u4f55\u6dfb\u52a0\u7ffb\u9875\u3001\u5904\u7406\u5f02\u5e38\u3001\u4f7f\u7528\u4ee3\u7406\u3001\u5b58\u50a8\u5230\u6570\u636e\u5e93\u7b49\u9ad8\u7ea7\u529f\u80fd\uff0c\u6700\u7ec8\u6253\u9020\u51fa\u5b8c\u5168\u9002\u5408\u81ea\u5df1\u7684\u81ea\u52a8\u5316\u91c7\u96c6\u811a\u672c\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u4f7f\u7528 Python \u7f16\u5199\u722c\u866b\u811a\u672c\u662f\u5b9e\u73b0 x \u7ad9\u8d44\u6e90\u81ea\u52a8\u91c7\u96c6\u6700\u7075\u6d3b\u3001\u5f3a\u5927\u7684\u65b9\u6cd5\u3002\u672c\u6587\u5c06\u5f15\u5bfc\u4f60\u5b8c\u6210\u4e00\u4e2a\u57fa\u7840\u4f46\u5b8c\u6574\u7684 Python \u722c\u866b\u9879\u76ee\uff0c\u5e76\u63d0\u4f9b\u793a\u4f8b\u6e90\u7801\uff0c\u5e2e\u52a9\u4f60\u8e0f\u5165\u7f16\u7a0b\u91c7\u96c6\u7684\u5927\u95e8\u3002 \u7b2c\u4e00\u6b65\uff1a\u73af\u5883\u51c6\u5907\u4e0e\u5e93\u5b89\u88c5\u3002\u786e\u4fdd\u4f60\u7684\u7535\u8111\u5b89\u88c5\u4e86 Python\uff08\u5efa\u8bae3.6\u4ee5\u4e0a\u7248\u672c\uff09\u3002\u6211\u4eec\u9700\u8981\u4e24\u4e2a\u6838\u5fc3\u5e93\uff1arequests\u00a0\u7528\u4e8e\u53d1\u9001HTTP\u8bf7\u6c42\uff0cBeautifulSoup\u00a0\u7528\u4e8e\u89e3\u6790HTML\u6587\u6863\u3002\u5728\u547d\u4ee4\u884c\u4e2d\u4f7f\u7528 pip \u5b89\u88c5\uff1apip install requests beautifulsoup4\u3002 \u7b2c\u4e8c\u6b65\uff1a\u5206\u6790\u76ee\u6807\u7f51\u9875\u7ed3\u6784\u3002\u8fd9\u662f\u722c\u866b\u7f16\u5199\u524d\u6700\u91cd<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[28],"tags":[],"collection":[],"class_list":["post-5441","post","type-post","status-publish","format-standard","hentry","category-qtjc"],"_links":{"self":[{"href":"https:\/\/www.qqjishu.com\/index.php\/wp-json\/wp\/v2\/posts\/5441","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.qqjishu.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.qqjishu.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.qqjishu.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.qqjishu.com\/index.php\/wp-json\/wp\/v2\/comments?post=5441"}],"version-history":[{"count":0,"href":"https:\/\/www.qqjishu.com\/index.php\/wp-json\/wp\/v2\/posts\/5441\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.qqjishu.com\/index.php\/wp-json\/wp\/v2\/media?parent=5441"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.qqjishu.com\/index.php\/wp-json\/wp\/v2\/categories?post=5441"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.qqjishu.com\/index.php\/wp-json\/wp\/v2\/tags?post=5441"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.qqjishu.com\/index.php\/wp-json\/wp\/v2\/collection?post=5441"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}