{"id":204762,"date":"2025-05-29T11:20:19","date_gmt":"2025-05-29T03:20:19","guid":{"rendered":"https:\/\/server.hk\/cnblog\/204762\/"},"modified":"2025-05-29T11:20:19","modified_gmt":"2025-05-29T03:20:19","slug":"%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8-python-%e7%88%ac%e8%99%ab%e6%8a%93%e5%8f%96%e5%b8%a6%e6%9c%89%e8%b6%85%e9%93%be%e6%8e%a5%e7%9a%84%e6%96%87%e6%9c%ac%e5%ad%97%e6%ae%b5%ef%bc%9f","status":"publish","type":"post","link":"https:\/\/server.hk\/cnblog\/204762\/","title":{"rendered":"\u5982\u4f55\u4f7f\u7528 Python \u722c\u866b\u6293\u53d6\u5e26\u6709\u8d85\u94fe\u63a5\u7684\u6587\u672c\u5b57\u6bb5\uff1f"},"content":{"rendered":"<p><b><\/b>     <\/p>\n<h1>\u5982\u4f55\u4f7f\u7528 Python \u722c\u866b\u6293\u53d6\u5e26\u6709\u8d85\u94fe\u63a5\u7684\u6587\u672c\u5b57\u6bb5\uff1f<\/h1>\n<p>\u4eca\u5929\u7ed9\u5927\u5bb6\u5e26\u6765\u4e86\uff0c\u5176\u4e2d\u6d89\u53ca\u5230\u7684\u77e5\u8bc6\u70b9\u5305\u62ec<span style=\"color: #FF6600;, Helvetica, Arial, sans-serif;font-size: 14px;background-color: #FFFFFF\"><\/span>\u7b49\u7b49\uff0c\u65e0\u8bba\u4f60\u662f\u5c0f\u767d\u8fd8\u662f\u8001\u624b\uff0c\u90fd\u9002\u5408\u770b\u4e00\u770b\u54e6~\u6709\u597d\u7684\u5efa\u8bae\u4e5f\u6b22\u8fce\u5927\u5bb6\u5728\u8bc4\u8bba\u7559\u8a00\uff0c\u82e5\u662f\u770b\u5b8c\u6709\u6240\u6536\u83b7\uff0c\u4e5f\u5e0c\u671b\u5927\u5bb6\u80fd\u591a\u591a\u70b9\u8d5e\u652f\u6301\u5440\uff01\u4e00\u8d77\u52a0\u6cb9\u5b66\u4e60~<\/p>\n<p><img decoding=\"async\" src=\"https:\/\/www.17golang.com\/uploads\/20241115\/17316598076737081f64845.jpg\" class=\"aligncenter\"><\/p>\n<p><strong>\u5982\u4f55\u4fee\u6539\u4ee3\u7801\u4ee5\u722c\u53d6\u5e26\u6709\u8d85\u94fe\u63a5\u7684\u6587\u672c\u5b57\u6bb5<\/strong><\/p>\n<p>\u5728\u4f7f\u7528python\u722c\u866b\u83b7\u53d6\u7f51\u9875\u6b63\u6587\u65f6\uff0c\u53ef\u80fd\u4f1a\u9047\u5230\u65e0\u6cd5\u6293\u53d6\u5e26\u6709\u8d85\u94fe\u63a5\u7684\u6587\u672c\u7247\u6bb5\u7684\u60c5\u51b5\u3002\u4e0b\u9762\u4ecb\u7ecd\u4e00\u79cd\u65b9\u6cd5\u4fee\u6539\u4ee3\u7801\u6765\u89e3\u51b3\u6b64\u95ee\u9898\uff1a<\/p>\n<p>\u9996\u5148\uff0c\u67e5\u770b\u7f51\u9875\u7ed3\u6784\uff0c\u786e\u8ba4\u6240\u8981\u6293\u53d6\u7684\u6587\u672c\u6bb5\u786e\u5b9e\u88ab\u5305\u88f9\u5728&lt;a&gt;\u6807\u7b7e\u5185\u3002\u7136\u540e\u4fee\u6539xpath\u8def\u5f84\u4ee5\u83b7\u53d6\u6240\u6709&lt;p&gt;\u6807\u7b7e\u4e0b\u7684\u6240\u6709\u8282\u70b9\uff0c\u5176\u4e2d\u5305\u62ec\u6587\u672c\u548c\u6807\u7b7e\uff1a<\/p>\n<pre>content = html.xpath('\/\/div[@class=\"f14 l24 news_content mt25 zoom\"]\/p\/\/node()')<\/pre>\n<p>\u4e4b\u540e\uff0c\u5728\u5904\u7406\u5185\u5bb9\u65f6\uff0c\u5bf9\u4e8e\u6bcf\u4e2a\u8282\u70b9\u5224\u65ad\u5176\u7c7b\u578b\uff1a\u5982\u679c\u662f\u6587\u672c\u8282\u70b9\uff0c\u5219\u4fdd\u7559\u5e76\u8ffd\u52a0\u5230\u7ed3\u679c\u4e2d\uff1b\u5982\u679c\u662f&lt;a&gt;\u6807\u7b7e\uff0c\u5219\u53ea\u4fdd\u7559\u5176\u6587\u672c\u90e8\u5206\u5e76\u8ffd\u52a0\u5230\u7ed3\u679c\u4e2d\uff1a<\/p>\n<pre>import requests\nfrom lxml import etree\n\n# \u722c\u53d6\u5e76\u8f6c\u5316\u4e3ahtml\u683c\u5f0f\nbase_url = \"https:\/\/www.solidwaste.com.cn\/news\/342864.html\"\nresp = requests.get(url=base_url)\nhtml = etree.HTML(resp.text)\n\n# \u66f4\u6362\u7f16\u7801\u65b9\u5f0f\u4e3a\u7f51\u9875\u5bf9\u5e94\u7684\u7f16\u7801\nencod = html.xpath('\/\/meta[1]\/@content')\nif encod != []:\n    encod = encod[0].split(\"=\")[-1]\n    resp.encoding = encod\n    html = etree.HTML(resp.text)\n\n# \u83b7\u53d6\u7f51\u9875\u6b63\u6587\ncontent = html.xpath('\/\/div[@class=\"f14 l24 news_content mt25 zoom\"]\/p\/\/node()')\n\ncontent_deal = \"\"\nfor node in content:\n    if isinstance(node, etree._ElementUnicodeResult):\n        content_deal += node.strip() + \"\\n\"\n    elif isinstance(node, etree._Element) and node.tag == 'a':\n        content_deal += node.text.strip() + \"\\n\"\n\nprint(content_deal)<\/pre>\n<p>\u901a\u8fc7\u8fd9\u4e9b\u4fee\u6539\uff0c\u60a8\u5e94\u8be5\u53ef\u4ee5\u6210\u529f\u722c\u53d6\u5e26\u6709\u8d85\u94fe\u63a5\u7684\u6587\u672c\u5b57\u6bb5\u3002<\/p>\n<p>\u5230\u8fd9\u91cc\uff0c\u6211\u4eec\u4e5f\u5c31\u8bb2\u5b8c\u4e86\u300a\u5982\u4f55\u4f7f\u7528 Python \u722c\u866b\u6293\u53d6\u5e26\u6709\u8d85\u94fe\u63a5\u7684\u6587\u672c\u5b57\u6bb5\uff1f\u300b\u7684\u5185\u5bb9\u4e86\u3002\u4e2a\u4eba\u8ba4\u4e3a\uff0c\u57fa\u7840\u77e5\u8bc6\u7684\u5b66\u4e60\u548c\u5de9\u56fa\uff0c\u662f\u4e3a\u4e86\u66f4\u597d\u7684\u5c06\u5176\u8fd0\u7528\u5230\u9879\u76ee\u4e2d\uff0c\u6b22\u8fce\u5173\u6ce8\u516c\u4f17\u53f7\uff0c\u5e26\u4f60\u4e86\u89e3\u66f4\u591a\u5173\u4e8e\u7684\u77e5\u8bc6\u70b9\uff01<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u5982\u4f55\u4f7f\u7528 Python \u722c\u866b\u6293\u53d6&#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-204762","post","type-post","status-publish","format-standard","hentry","category-4925"],"_links":{"self":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/204762","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=204762"}],"version-history":[{"count":0,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/204762\/revisions"}],"wp:attachment":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/media?parent=204762"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/categories?post=204762"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/tags?post=204762"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}