{"id":204984,"date":"2025-05-29T12:48:58","date_gmt":"2025-05-29T04:48:58","guid":{"rendered":"https:\/\/server.hk\/cnblog\/204984\/"},"modified":"2025-05-29T12:48:58","modified_gmt":"2025-05-29T04:48:58","slug":"%e5%a6%82%e4%bd%95%e4%bb%8e%e7%bd%91%e9%a1%b5%e4%b8%ad%e6%8f%90%e5%8f%96%e7%bd%91%e5%9d%80%ef%bc%8c%e9%81%bf%e5%85%8d%e6%8b%ac%e5%8f%b7%e5%92%8c%e5%8d%95%e5%bc%95%e5%8f%b7%e7%9a%84%e5%b9%b2%e6%89%b0","status":"publish","type":"post","link":"https:\/\/server.hk\/cnblog\/204984\/","title":{"rendered":"\u5982\u4f55\u4ece\u7f51\u9875\u4e2d\u63d0\u53d6\u7f51\u5740\uff0c\u907f\u514d\u62ec\u53f7\u548c\u5355\u5f15\u53f7\u7684\u5e72\u6270\uff1f"},"content":{"rendered":"<p><b><\/b>     <\/p>\n<h1>\u5982\u4f55\u4ece\u7f51\u9875\u4e2d\u63d0\u53d6\u7f51\u5740\uff0c\u907f\u514d\u62ec\u53f7\u548c\u5355\u5f15\u53f7\u7684\u5e72\u6270\uff1f<\/h1>\n<p>\u77e5\u8bc6\u70b9\u638c\u63e1\u4e86\uff0c\u8fd8\u9700\u8981\u4e0d\u65ad\u7ec3\u4e60\u624d\u80fd\u719f\u7ec3\u8fd0\u7528\u3002\u4e0b\u9762\u7ed9\u5927\u5bb6\u5e26\u6765\u4e00\u4e2a\u6587\u7ae0\u5f00\u53d1\u5b9e\u6218\uff0c\u624b\u628a\u624b\u6559\u5927\u5bb6\u5b66\u4e60\u300a\u5982\u4f55\u4ece\u7f51\u9875\u4e2d\u63d0\u53d6\u7f51\u5740\uff0c\u907f\u514d\u62ec\u53f7\u548c\u5355\u5f15\u53f7\u7684\u5e72\u6270\uff1f\u300b\uff0c\u5728\u5b9e\u73b0\u529f\u80fd\u7684\u8fc7\u7a0b\u4e2d\u4e5f\u5e26\u5927\u5bb6\u91cd\u65b0\u6e29\u4e60\u76f8\u5173\u77e5\u8bc6\u70b9\uff0c\u6e29\u6545\u800c\u77e5\u65b0\uff0c\u56de\u5934\u770b\u770b\u8bf4\u4e0d\u5b9a\u53c8\u6709\u4e0d\u4e00\u6837\u7684\u611f\u609f\uff01<\/p>\n<p><img decoding=\"async\" src=\"https:\/\/www.17golang.com\/uploads\/20241120\/1732108899673de2634dc4e.jpg\" class=\"aligncenter\"><\/p>\n<p><strong>\u5982\u4f55\u6446\u8131\u722c\u53d6\u7f51\u5740\u4e2d\u51fa\u73b0\u7684\u62ec\u53f7\u548c\u5355\u5f15\u53f7<\/strong><\/p>\n<p>\u5f53\u4f60\u4f7f\u7528beautifulsoup\u7b49html\u89e3\u6790\u5668\u722c\u53d6\u7f51\u9875\u65f6\uff0c\u4f60\u53ef\u80fd\u4f1a\u9047\u5230\u4e00\u4e9b\u60c5\u51b5\u4e0b\uff0c\u6240\u6293\u53d6\u7684\u7f51\u5740\u4e2d\u4f1a\u5e26\u6709\u62ec\u53f7\u548c\u5355\u5f15\u53f7\u3002\u8fd9\u4f1a\u7ed9\u540e\u7eed\u6570\u636e\u5904\u7406\u5e26\u6765\u4e0d\u4fbf\u3002\u4ee5\u4e0b\u662f\u5982\u4f55\u89e3\u51b3\u8fd9\u4e2a\u95ee\u9898\u7684\u65b9\u6cd5\uff1a<\/p>\n<p><strong>\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f<\/strong><\/p>\n<p>\u6b63\u5219\u8868\u8fbe\u5f0f\uff08regex\uff09\u662f\u4e00\u79cd\u5f3a\u5927\u7684\u5de5\u5177\uff0c\u53ef\u4ee5\u7528\u4e8e\u5339\u914d\u548c\u63d0\u53d6\u6587\u672c\u4e2d\u7684\u7279\u5b9a\u6a21\u5f0f\u3002\u5728\u4f60\u7684\u4f8b\u5b50\u91cc\uff0c\u4f60\u53ef\u4ee5\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u6765\u5339\u914d\u7f51\u5740\uff0c\u5e76\u63d0\u53d6\u5b83\u4eec\u800c\u4e0d\u5305\u62ec\u62ec\u53f7\u548c\u5355\u5f15\u53f7\u3002<\/p>\n<p><strong>\u4f8b\u5982:<\/strong><\/p>\n<pre>import re\n\npattern = r'href=\"(.*?)\"'\nurls = re.findall(pattern, html)<\/pre>\n<p>\u8fd9\u5c06\u4ecehtml\u4e2d\u5339\u914d\u6240\u6709href\u5c5e\u6027\uff0c\u5e76\u5c06\u503c\u5b58\u50a8\u5728urls\u5217\u8868\u4e2d\uff0c\u800c\u4e0d\u4f1a\u5305\u542b\u5f15\u53f7\u3002<\/p>\n<p><strong>\u4f7f\u7528lxml<\/strong><\/p>\n<p>lxml\u662f\u4e00\u4e2apython\u5e93\uff0c\u5b83\u63d0\u4f9b\u4e86\u53e6\u4e00\u79cd\u89e3\u6790xml\u548chtml\u7684\u65b9\u6cd5\u3002\u5b83\u4f7f\u7528xpath\u8bed\u6cd5\u6765\u67e5\u627e\u548c\u63d0\u53d6\u5143\u7d20\u3002<\/p>\n<p><strong>\u4f8b\u5982:<\/strong><\/p>\n<pre>import requests\nfrom lxml import etree\n\nheaders = {\n    'User-Agent': 'Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/87.0.4280.66 Safari\/537.36'\n}\nres = requests.get(url, headers=headers)\nres_dom = etree.HTML(res.text)\nurls = res_dom.xpath('\/\/h3\/a\/@href')<\/pre>\n<p>\u8fd9\u5c06\u6293\u53d6\u6240\u6709h3\u6807\u8bb0\u4e2da\u5143\u7d20\u7684href\u5c5e\u6027\uff0c\u5e76\u4e14\u4e0d\u4f1a\u5305\u542b\u62ec\u53f7\u548c\u5355\u5f15\u53f7\u3002<\/p>\n<p>\u597d\u4e86\uff0c\u672c\u6587\u5230\u6b64\u7ed3\u675f\uff0c\u5e26\u5927\u5bb6\u4e86\u89e3\u4e86\u300a\u5982\u4f55\u4ece\u7f51\u9875\u4e2d\u63d0\u53d6\u7f51\u5740\uff0c\u907f\u514d\u62ec\u53f7\u548c\u5355\u5f15\u53f7\u7684\u5e72\u6270\uff1f\u300b\uff0c\u5e0c\u671b\u672c\u6587\u5bf9\u4f60\u6709\u6240\u5e2e\u52a9\uff01\u5173\u6ce8\u516c\u4f17\u53f7\uff0c\u7ed9\u5927\u5bb6\u5206\u4eab\u66f4\u591a\u6587\u7ae0\u77e5\u8bc6\uff01<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u5982\u4f55\u4ece\u7f51\u9875\u4e2d\u63d0\u53d6\u7f51\u5740\uff0c\u907f\u514d\u62ec\u53f7\u548c&#46;&#46;&#46;<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[4925],"tags":[],"class_list":["post-204984","post","type-post","status-publish","format-standard","hentry","category-4925"],"_links":{"self":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/204984","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/comments?post=204984"}],"version-history":[{"count":0,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/204984\/revisions"}],"wp:attachment":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/media?parent=204984"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/categories?post=204984"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/tags?post=204984"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}