{"id":592,"date":"2023-10-19T18:05:45","date_gmt":"2024-03-03T15:01:55","guid":{"rendered":"https:\/\/www.silicloud.com\/zh\/blog\/index.php\/2023\/11\/30\/%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8beautiful-soup%e7%88%ac%e5%8f%96%e4%ba%9a%e9%a9%ac%e9%80%8a%e4%ba%a7%e5%93%81%e4%bf%a1%e6%81%af\/"},"modified":"2025-08-02T21:38:07","modified_gmt":"2025-08-02T13:38:07","slug":"%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8beautiful-soup%e7%88%ac%e5%8f%96%e4%ba%9a%e9%a9%ac%e9%80%8a%e4%ba%a7%e5%93%81%e4%bf%a1%e6%81%af","status":"publish","type":"post","link":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8beautiful-soup%e7%88%ac%e5%8f%96%e4%ba%9a%e9%a9%ac%e9%80%8a%e4%ba%a7%e5%93%81%e4%bf%a1%e6%81%af\/","title":{"rendered":"Python\u5b9e\u6218\u6559\u7a0b\uff1a\u4f7f\u7528Beautiful Soup\u722c\u53d6\u4e9a\u9a6c\u900a\u4ea7\u54c1\u4fe1\u606f\u4e0e\u4ef7\u683c"},"content":{"rendered":"<p>\u7f51\u7edc\u722c\u866b\u662f\u4e00\u79cd\u57fa\u4e8e\u7f16\u7a0b\u7684\u6280\u672f\uff0c\u7528\u4e8e\u4ece\u7f51\u7ad9\u4e2d\u63d0\u53d6\u76f8\u5173\u4fe1\u606f\u5e76\u5b58\u50a8\u5728\u672c\u5730\u7cfb\u7edf\u4e2d\u4ee5\u4f9b\u8fdb\u4e00\u6b65\u4f7f\u7528\u3002<\/p>\n<p>\u5728\u73b0\u4ee3\uff0c\u7f51\u7edc\u6293\u53d6\u5728\u6570\u636e\u79d1\u5b66\u548c\u8425\u9500\u9886\u57df\u6709\u5f88\u591a\u5e94\u7528\u3002\u5168\u7403\u8303\u56f4\u7684\u7f51\u7edc\u722c\u866b\u4e3a\u4e2a\u4eba\u6216\u4e13\u4e1a\u7528\u9014\u6536\u96c6\u4e86\u5927\u91cf\u4fe1\u606f\u3002\u6b64\u5916\uff0c\u5f53\u4eca\u7684\u79d1\u6280\u5de8\u5934\u4f9d\u8d56\u8fd9\u79cd\u7f51\u7edc\u722c\u53d6\u65b9\u6cd5\u6765\u6ee1\u8db3\u4ed6\u4eec\u7684\u6d88\u8d39\u8005\u9700\u6c42\u3002<\/p>\n<p>\u5728\u672c\u6587\u4e2d\uff0c\u6211\u4eec\u5c06\u4ece\u4e9a\u9a6c\u900a\u7f51\u7ad9\u4e0a\u83b7\u53d6\u4ea7\u54c1\u4fe1\u606f\u3002\u56e0\u6b64\uff0c\u6211\u4eec\u5c06\u4ee5&#8221;Playstation 4&#8243;\u4f5c\u4e3a\u76ee\u6807\u4ea7\u54c1\u52a0\u4ee5\u8003\u8651\u3002<\/p>\n<blockquote><p>\u8bf7\u6ce8\u610f\uff1a\u7f51\u7ad9\u7684\u5e03\u5c40\u548c\u6807\u7b7e\u53ef\u80fd\u4f1a\u968f\u65f6\u95f4\u53d8\u5316\u3002\u56e0\u6b64\uff0c\u5efa\u8bae\u8bfb\u8005\u4e86\u89e3\u7f51\u9875\u6293\u53d6\u7684\u6982\u5ff5\uff0c\u4ee5\u514d\u81ea\u884c\u5b9e\u65bd\u65f6\u51fa\u73b0\u95ee\u9898\u3002<\/p><\/blockquote>\n<h2>\u7f51\u7edc\u722c\u866b\u670d\u52a1<\/h2>\n<p>\u5982\u679c\u4f60\u60f3\u4f7f\u7528\u7f51\u7edc\u722c\u866b\u6784\u5efa\u4e00\u4e2a\u670d\u52a1\uff0c\u4f60\u53ef\u80fd\u9700\u8981\u7ecf\u5386IP\u963b\u585e\u548c\u4ee3\u7406\u7ba1\u7406\u3002\u4e86\u89e3\u5e95\u5c42\u6280\u672f\u548c\u6d41\u7a0b\u662f\u597d\u7684\uff0c\u4f46\u5bf9\u4e8e\u5927\u89c4\u6a21\u722c\u53d6\u6765\u8bf4\uff0c\u6700\u597d\u4e0e\u50cfZenscrape\u8fd9\u6837\u7684\u7f51\u7edc\u722c\u866bAPI\u63d0\u4f9b\u5546\u5408\u4f5c\u3002\u4ed6\u4eec\u751a\u81f3\u8d1f\u8d23\u5904\u7406\u52a8\u6001\u9875\u9762\u7684Ajax\u8bf7\u6c42\u548cJavaScript\u3002\u4ed6\u4eec\u7684\u4e00\u4e2a\u53d7\u6b22\u8fce\u7684\u670d\u52a1\u662f\u4f4f\u5b85\u4ee3\u7406\u670d\u52a1\u3002<\/p>\n<h2>\u4e00\u4e9b\u57fa\u672c\u8981\u6c42\uff1a<\/h2>\n<p>\u4e3a\u4e86\u505a\u6c64\uff0c\u6211\u4eec\u9700\u8981\u9002\u5f53\u7684\u98df\u6750\u3002\u540c\u6837\u5730\uff0c\u6211\u4eec\u7684\u65b0\u9c9c\u7f51\u7edc\u722c\u866b\u4e5f\u9700\u8981\u7279\u5b9a\u7684\u7ec4\u4ef6\u3002<\/p>\n<ul class=\"post-ul\">\n<li>Python &#8211; Python\u7684\u6613\u7528\u6027\u548c\u4e30\u5bcc\u7684\u5e93\u96c6\u5408\u4f7f\u5176\u6210\u4e3a\u7f51\u7ad9\u722c\u53d6\u7684\u9996\u9009\u3002\u4f46\u662f\uff0c\u5982\u679c\u7528\u6237\u6ca1\u6709\u9884\u5b89\u88c5Python\uff0c\u8bf7\u53c2\u8003\u6b64\u5904\u7684\u5b89\u88c5\u6307\u5357\u3002<\/li>\n<li>Beautiful Soup &#8211; Python\u4f17\u591a\u7f51\u9875\u722c\u53d6\u5e93\u4e4b\u4e00\u3002\u8be5\u5e93\u7684\u7b80\u4fbf\u548c\u6e05\u6d01\u4f7f\u7528\u4f7f\u5176\u6210\u4e3a\u7f51\u9875\u722c\u53d6\u7684\u9876\u7ea7\u7ade\u4e89\u8005\u3002\u6210\u529f\u5b89\u88c5Python\u540e\uff0c\u7528\u6237\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u65b9\u5f0f\u5b89\u88c5Beautiful Soup\uff1a<\/li>\n<\/ul>\n<pre class=\"post-pre\"><code>pip install bs4\r\n<\/code><\/pre>\n<ul class=\"post-ul\">\n<li>HTML\u6807\u7b7e\u7684\u57fa\u672c\u7406\u89e3 &#8211; \u8bf7\u53c2\u8003\u672c\u6559\u7a0b\u83b7\u53d6\u6709\u5173HTML\u6807\u7b7e\u7684\u5fc5\u8981\u4fe1\u606f\u3002<\/li>\n<li>\u7f51\u9875\u6d4f\u89c8\u5668 &#8211; \u7531\u4e8e\u6211\u4eec\u5fc5\u987b\u4ece\u7f51\u7ad9\u4e2d\u7b5b\u9009\u6389\u5927\u91cf\u4e0d\u5fc5\u8981\u7684\u4fe1\u606f\uff0c\u6211\u4eec\u9700\u8981\u7279\u5b9a\u7684ID\u548c\u6807\u7b7e\u8fdb\u884c\u8fc7\u6ee4\u3002\u56e0\u6b64\uff0c\u50cfGoogle Chrome\u6216Mozilla Firefox\u8fd9\u6837\u7684\u7f51\u9875\u6d4f\u89c8\u5668\u53ef\u4ee5\u7528\u4e8e\u53d1\u73b0\u8fd9\u4e9b\u6807\u7b7e\u3002<\/li>\n<\/ul>\n<h2>\u521b\u5efa\u4e00\u4e2a\u7528\u6237\u4ee3\u7406<\/h2>\n<p>\u8bb8\u591a\u7f51\u7ad9\u6709\u7279\u5b9a\u7684\u534f\u8bae\u6765\u963b\u6b62\u673a\u5668\u4eba\u8bbf\u95ee\u6570\u636e\u3002\u56e0\u6b64\uff0c\u4e3a\u4e86\u4ece\u811a\u672c\u4e2d\u63d0\u53d6\u6570\u636e\uff0c\u6211\u4eec\u9700\u8981\u521b\u5efa\u4e00\u4e2a\u7528\u6237\u4ee3\u7406\u3002\u7528\u6237\u4ee3\u7406\u57fa\u672c\u4e0a\u662f\u4e00\u4e2a\u5b57\u7b26\u4e32\uff0c\u544a\u8bc9\u670d\u52a1\u5668\u53d1\u9001\u8bf7\u6c42\u7684\u4e3b\u673a\u7c7b\u578b\u3002<\/p>\n<p>\u8fd9\u4e2a\u7f51\u7ad9\u6709\u5f88\u591a\u7528\u6237\u4ee3\u7406\u4f9b\u8bfb\u8005\u9009\u62e9\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2aUser-Agent\u5728\u5934\u90e8\u503c\u4e2d\u7684\u793a\u4f8b\u3002<\/p>\n<pre class=\"post-pre\"><code>HEADERS <span class=\"token operator\">=<\/span> <span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">{<\/span><span class=\"token string\">'User-Agent'<\/span><span class=\"token punctuation\">:<\/span>\r\n            <span class=\"token string\">'Mozilla\/5.0 (X11; Linux x86_64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/44.0.2403.157 Safari\/537.36'<\/span><span class=\"token punctuation\">,<\/span>\r\n            <span class=\"token string\">'Accept-Language'<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">'en-US, en;q=0.5'<\/span><span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span>\r\n<\/code><\/pre>\n<p>\u5982\u679c\u9700\u8981\u7684\u8bdd\uff0cHEADERS \u4e2d\u6709\u4e00\u4e2a\u540d\u4e3a&#8221;Accept-Language&#8221;\u7684\u989d\u5916\u5b57\u6bb5\uff0c\u53ef\u4ee5\u5c06\u7f51\u9875\u7ffb\u8bd1\u6210\u7f8e\u5f0f\u82f1\u8bed\u3002<\/p>\n<h2>\u5411\u4e00\u4e2aURL\u53d1\u9001\u4e00\u4e2a\u8bf7\u6c42<\/h2>\n<p>\u4e00\u4e2a\u7f51\u9875\u662f\u901a\u8fc7\u5b83\u7684URL\uff08\u7edf\u4e00\u8d44\u6e90\u5b9a\u4f4d\u7b26\uff09\u8fdb\u884c\u8bbf\u95ee\u7684\u3002\u501f\u52a9URL\uff0c\u6211\u4eec\u5c06\u5411\u7f51\u9875\u53d1\u9001\u8bf7\u6c42\u4ee5\u8bbf\u95ee\u5176\u6570\u636e\u3002<\/p>\n<pre class=\"post-pre\"><code>URL <span class=\"token operator\">=<\/span> <span class=\"token string\">\"https:\/\/www.amazon.com\/Sony-PlayStation-Pro-1TB-Console-4\/dp\/B07K14XKZH\/\"<\/span>\r\nwebpage <span class=\"token operator\">=<\/span> requests<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span>URL<span class=\"token punctuation\">,<\/span> headers<span class=\"token operator\">=<\/span>HEADERS<span class=\"token punctuation\">)<\/span>\r\n<\/code><\/pre>\n<p>\u6240\u8bf7\u6c42\u7684\u7f51\u9875\u4e0a\u5c55\u793a\u4e86\u4e00\u4e2a\u4e9a\u9a6c\u900a\u4ea7\u54c1\u3002\u56e0\u6b64\uff0c\u6211\u4eec\u7684Python\u811a\u672c\u4e13\u6ce8\u4e8e\u63d0\u53d6\u4ea7\u54c1\u7ec6\u8282\uff0c\u5982&#8221;\u4ea7\u54c1\u540d\u79f0&#8221;\u3001&#8221;\u5f53\u524d\u4ef7\u683c&#8221;\u7b49\u7b49\u3002<\/p>\n<blockquote><p>\u6ce8\u610f\uff1a\u4f7f\u7528&#8221;requests&#8221;\u5e93\u53d1\u9001\u5bf9URL\u7684\u8bf7\u6c42\u3002\u5982\u679c\u7528\u6237\u9047\u5230&#8221;\u627e\u4e0d\u5230\u6a21\u5757\u540d\u4e3arequests&#8221;\u7684\u9519\u8bef\uff0c\u53ef\u4ee5\u901a\u8fc7&#8221;pip install requests&#8221;\u6765\u5b89\u88c5\u5b83\u3002<\/p><\/blockquote>\n<h2>\u521b\u9020\u4e00\u4e2a\u4fe1\u606f\u7684\u6c64<\/h2>\n<p>\u7f51\u9875\u7684\u53d8\u91cf\u5305\u542b\u4e86\u7f51\u7ad9\u63a5\u6536\u5230\u7684\u54cd\u5e94\u3002\u6211\u4eec\u5c06\u8be5\u54cd\u5e94\u7684\u5185\u5bb9\u548c\u89e3\u6790\u5668\u7684\u7c7b\u578b\u4f20\u9012\u7ed9Beautiful Soup\u51fd\u6570\u3002<\/p>\n<pre class=\"post-pre\"><code>soup <span class=\"token operator\">=<\/span> BeautifulSoup<span class=\"token punctuation\">(<\/span>webpage<span class=\"token punctuation\">.<\/span>content<span class=\"token punctuation\">,<\/span> <span class=\"token string\">\"lxml\"<\/span><span class=\"token punctuation\">)<\/span>\r\n<\/code><\/pre>\n<p>lxml\u662fBeautiful Soup\u4f7f\u7528\u7684\u9ad8\u901f\u89e3\u6790\u5668\uff0c\u7528\u4e8e\u5c06HTML\u9875\u9762\u5206\u89e3\u6210\u590d\u6742\u7684Python\u5bf9\u8c61\u3002\u4e00\u822c\u6765\u8bf4\uff0c\u4f1a\u83b7\u5f97\u56db\u79cd\u7c7b\u578b\u7684Python\u5bf9\u8c61\u3002<\/p>\n<ul class=\"post-ul\">\n<li>\u6807\u7b7e &#8211; \u5bf9\u5e94\u4e8eHTML\u6216XML\u6807\u7b7e\uff0c\u5305\u62ec\u540d\u79f0\u548c\u5c5e\u6027\u3002<\/li>\n<li>\u53ef\u5bfc\u822a\u5b57\u7b26\u4e32 &#8211; \u5bf9\u5e94\u4e8e\u5b58\u50a8\u5728\u6807\u7b7e\u5185\u7684\u6587\u672c\u3002<\/li>\n<li>BeautifulSoup &#8211; \u5b9e\u9645\u4e0a\u662f\u6574\u4e2a\u89e3\u6790\u540e\u7684\u6587\u6863\u3002<\/li>\n<li>\u6ce8\u91ca &#8211; \u6700\u540e\uff0c\u662f\u4e0d\u5c5e\u4e8e\u4e0a\u8ff0\u4e09\u4e2a\u7c7b\u522b\u7684HTML\u9875\u9762\u7684\u5269\u4f59\u90e8\u5206\u3002<\/li>\n<\/ul>\n<h2>\u53d1\u73b0\u7528\u4e8e\u7269\u4f53\u63d0\u53d6\u7684\u786e\u5207\u6807\u7b7e<\/h2>\n<p>\u8fd9\u4e2a\u9879\u76ee\u4e2d\u6700\u7e41\u5fd9\u7684\u90e8\u5206\u4e4b\u4e00\u662f\u6316\u6398\u5b58\u50a8\u76f8\u5173\u4fe1\u606f\u7684ID\u548c\u6807\u7b7e\u3002\u5982\u524d\u6240\u8ff0\uff0c\u6211\u4eec\u4f7f\u7528\u7f51\u7edc\u6d4f\u89c8\u5668\u6765\u5b8c\u6210\u8fd9\u9879\u4efb\u52a1\u3002<\/p>\n<p>\u6211\u4eec\u5728\u6d4f\u89c8\u5668\u4e2d\u6253\u5f00\u7f51\u9875\uff0c\u5e76\u901a\u8fc7\u53f3\u952e\u5355\u51fb\u6765\u68c0\u67e5\u76f8\u5173\u5143\u7d20\u3002<\/p>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/65647613a4b2f92e6c72a7dc\/29-0.png\" alt=\"Amazon Web Scraper Inspect\" \/><\/div>\n<p>\u56e0\u6b64\uff0c\u5c4f\u5e55\u7684\u53f3\u4fa7\u4f1a\u51fa\u73b0\u5982\u4e0b\u56fe\u6240\u793a\u7684\u9762\u677f\u3002<\/p>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/65647613a4b2f92e6c72a7dc\/31-0.png\" alt=\"Amazon Web Scraper Extractions Edited\" \/><\/div>\n<p>\u4e00\u65e6\u6211\u4eec\u83b7\u5f97\u6807\u7b7e\u6570\u503c\uff0c\u63d0\u53d6\u4fe1\u606f\u5219\u53d8\u5f97\u975e\u5e38\u7b80\u5355\u3002\u7136\u800c\uff0c\u6211\u4eec\u5fc5\u987b\u5b66\u4e60\u4e3aBeautiful Soup\u5bf9\u8c61\u5b9a\u4e49\u7684\u67d0\u4e9b\u51fd\u6570\u3002<\/p>\n<h2>\u63d0\u53d6\u4ea7\u54c1\u6807\u9898<\/h2>\n<p>\u901a\u8fc7\u4f7f\u7528find()\u51fd\u6570\uff0c\u6211\u4eec\u53ef\u4ee5\u641c\u7d22\u7279\u5b9a\u7684HTML\u6807\u7b7e\u53ca\u5176\u5c5e\u6027\uff0c\u4ece\u800c\u627e\u5230\u5305\u542b\u4ea7\u54c1\u6807\u9898\u7684\u6807\u7b7e\u5bf9\u8c61\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"token comment\"># \u5916\u90e8\u6807\u7b7e\u5bf9\u8c61<\/span>\r\ntitle <span class=\"token operator\">=<\/span> soup<span class=\"token punctuation\">.<\/span>find<span class=\"token punctuation\">(<\/span><span class=\"token string\">\"span\"<\/span><span class=\"token punctuation\">,<\/span> attrs<span class=\"token operator\">=<\/span><span class=\"token punctuation\">{<\/span><span class=\"token string\">\"id\"<\/span><span class=\"token punctuation\">:<\/span><span class=\"token string\">'productTitle'<\/span><span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span>\r\n<\/code><\/pre>\n<p>\u7136\u540e\uff0c\u6211\u4eec\u53d6\u51fa\u53ef\u5bfc\u822a\u5b57\u7b26\u4e32\u5bf9\u8c61\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"token comment\"># \u5185\u90e8\u53ef\u5bfc\u822a\u5b57\u7b26\u4e32\u5bf9\u8c61<\/span>\r\ntitle_value <span class=\"token operator\">=<\/span> title<span class=\"token punctuation\">.<\/span>string\r\n<\/code><\/pre>\n<p>\u6700\u540e\uff0c\u6211\u4eec\u53bb\u6389\u591a\u4f59\u7684\u7a7a\u683c\u5e76\u5c06\u5bf9\u8c61\u8f6c\u6362\u4e3a\u5b57\u7b26\u4e32\u503c\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"token comment\"># \u8f6c\u6362\u4e3a\u5b57\u7b26\u4e32\u503c<\/span>\r\ntitle_string <span class=\"token operator\">=<\/span> title_value<span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span>\r\n<\/code><\/pre>\n<p>\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528type()\u51fd\u6570\u6765\u67e5\u770b\u6bcf\u4e2a\u53d8\u91cf\u7684\u6570\u636e\u7c7b\u578b\uff0c\u4ee5\u4fbf\u66f4\u597d\u5730\u7406\u89e3\u4ee3\u7801\u6267\u884c\u8fc7\u7a0b\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"token comment\"># \u6253\u5370\u5404\u503c\u7684\u6570\u636e\u7c7b\u578b\u4ee5\u4fbf\u4e8e\u7406\u89e3<\/span>\r\n<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token builtin\">type<\/span><span class=\"token punctuation\">(<\/span>title<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span>\r\n<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token builtin\">type<\/span><span class=\"token punctuation\">(<\/span>title_value<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span>\r\n<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token builtin\">type<\/span><span class=\"token punctuation\">(<\/span>title_string<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span>\r\n<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n<span class=\"token comment\"># \u6253\u5370\u4ea7\u54c1\u6807\u9898<\/span>\r\n<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">\"\u4ea7\u54c1\u6807\u9898 = \"<\/span><span class=\"token punctuation\">,<\/span> title_string<span class=\"token punctuation\">)<\/span>\r\n<\/code><\/pre>\n<p>\u7ed3\u679c\uff1a<\/p>\n<pre class=\"post-pre\"><code><span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>class<\/span> <span class=\"token attr-name\">'bs4.element.Tag'<\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\r\n<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>class<\/span> <span class=\"token attr-name\">'bs4.element.NavigableString'<\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\r\n<span class=\"token tag\"><span class=\"token tag\"><span class=\"token punctuation\">&lt;<\/span>class<\/span> <span class=\"token attr-name\">'str'<\/span><span class=\"token punctuation\">&gt;<\/span><\/span>\r\n\r\n\u4ea7\u54c1\u6807\u9898 =  Sony PlayStation 4 Pro 1TB Console - Black (PS4 Pro)\r\n<\/code><\/pre>\n<p>\u540c\u6837\u5730\uff0c\u6211\u4eec\u9700\u8981\u786e\u5b9a\u5176\u4ed6\u4ea7\u54c1\u7ec6\u8282\u7684\u6807\u7b7e\u503c\uff0c\u4f8b\u5982&#8221;\u4ea7\u54c1\u4ef7\u683c&#8221;\u548c&#8221;\u6d88\u8d39\u8005\u8bc4\u7ea7&#8221;\u3002<\/p>\n<h2>\u63d0\u53d6\u4ea7\u54c1\u4fe1\u606f\u7684Python\u811a\u672c<\/h2>\n<p>\u4ee5\u4e0bPython\u811a\u672c\u5c55\u793a\u4e86\u4e00\u4e2a\u4ea7\u54c1\u7684\u4ee5\u4e0b\u7ec6\u8282:<\/p>\n<ul class=\"post-ul\">\n<li>\u4ea7\u54c1\u6807\u9898<\/li>\n<li>\u4ea7\u54c1\u4ef7\u683c<\/li>\n<li>\u4ea7\u54c1\u8bc4\u5206<\/li>\n<li>\u5ba2\u6237\u8bc4\u8bba\u6570\u91cf<\/li>\n<li>\u4ea7\u54c1\u53ef\u7528\u6027<\/li>\n<\/ul>\n<pre class=\"post-pre\"><code><span class=\"token keyword\">from<\/span> bs4 <span class=\"token keyword\">import<\/span> BeautifulSoup\r\n<span class=\"token keyword\">import<\/span> requests\r\n\r\n<span class=\"token comment\"># \u63d0\u53d6\u4ea7\u54c1\u6807\u9898\u7684\u51fd\u6570<\/span>\r\n<span class=\"token keyword\">def<\/span> <span class=\"token function\">get_title<\/span><span class=\"token punctuation\">(<\/span>soup<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span>\r\n\t\r\n\t<span class=\"token keyword\">try<\/span><span class=\"token punctuation\">:<\/span>\r\n\t\t<span class=\"token comment\"># \u5916\u90e8\u6807\u7b7e\u5bf9\u8c61<\/span>\r\n\t\ttitle <span class=\"token operator\">=<\/span> soup<span class=\"token punctuation\">.<\/span>find<span class=\"token punctuation\">(<\/span><span class=\"token string\">\"span\"<\/span><span class=\"token punctuation\">,<\/span> attrs<span class=\"token operator\">=<\/span><span class=\"token punctuation\">{<\/span><span class=\"token string\">\"id\"<\/span><span class=\"token punctuation\">:<\/span><span class=\"token string\">'productTitle'<\/span><span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n\t\t<span class=\"token comment\"># \u5185\u90e8\u53ef\u5bfc\u822a\u5b57\u7b26\u4e32\u5bf9\u8c61<\/span>\r\n\t\ttitle_value <span class=\"token operator\">=<\/span> title<span class=\"token punctuation\">.<\/span>string\r\n\r\n\t\t<span class=\"token comment\"># \u4f5c\u4e3a\u5b57\u7b26\u4e32\u503c\u7684\u6807\u9898<\/span>\r\n\t\ttitle_string <span class=\"token operator\">=<\/span> title_value<span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n\t\t<span class=\"token comment\"># # \u6253\u5370\u503c\u7684\u7c7b\u578b\u4ee5\u4fbf\u9ad8\u6548\u7406\u89e3<\/span>\r\n\t\t<span class=\"token comment\"># print(type(title))<\/span>\r\n\t\t<span class=\"token comment\"># print(type(title_value))<\/span>\r\n\t\t<span class=\"token comment\"># print(type(title_string))<\/span>\r\n\t\t<span class=\"token comment\"># print()<\/span>\r\n\r\n\t<span class=\"token keyword\">except<\/span> AttributeError<span class=\"token punctuation\">:<\/span>\r\n\t\ttitle_string <span class=\"token operator\">=<\/span> <span class=\"token string\">\"\"<\/span>\t\r\n\r\n\t<span class=\"token keyword\">return<\/span> title_string\r\n\r\n<span class=\"token comment\"># \u63d0\u53d6\u4ea7\u54c1\u4ef7\u683c\u7684\u51fd\u6570<\/span>\r\n<span class=\"token keyword\">def<\/span> <span class=\"token function\">get_price<\/span><span class=\"token punctuation\">(<\/span>soup<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span>\r\n\r\n\t<span class=\"token keyword\">try<\/span><span class=\"token punctuation\">:<\/span>\r\n\t\tprice <span class=\"token operator\">=<\/span> soup<span class=\"token punctuation\">.<\/span>find<span class=\"token punctuation\">(<\/span><span class=\"token string\">\"span\"<\/span><span class=\"token punctuation\">,<\/span> attrs<span class=\"token operator\">=<\/span><span class=\"token punctuation\">{<\/span><span class=\"token string\">'id'<\/span><span class=\"token punctuation\">:<\/span><span class=\"token string\">'priceblock_ourprice'<\/span><span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>string<span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n\t<span class=\"token keyword\">except<\/span> AttributeError<span class=\"token punctuation\">:<\/span>\r\n\t\tprice <span class=\"token operator\">=<\/span> <span class=\"token string\">\"\"<\/span>\t\r\n\r\n\t<span class=\"token keyword\">return<\/span> price\r\n\r\n<span class=\"token comment\"># \u63d0\u53d6\u4ea7\u54c1\u8bc4\u5206\u7684\u51fd\u6570<\/span>\r\n<span class=\"token keyword\">def<\/span> <span class=\"token function\">get_rating<\/span><span class=\"token punctuation\">(<\/span>soup<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span>\r\n\r\n\t<span class=\"token keyword\">try<\/span><span class=\"token punctuation\">:<\/span>\r\n\t\trating <span class=\"token operator\">=<\/span> soup<span class=\"token punctuation\">.<\/span>find<span class=\"token punctuation\">(<\/span><span class=\"token string\">\"i\"<\/span><span class=\"token punctuation\">,<\/span> attrs<span class=\"token operator\">=<\/span><span class=\"token punctuation\">{<\/span><span class=\"token string\">'class'<\/span><span class=\"token punctuation\">:<\/span><span class=\"token string\">'a-icon a-icon-star a-star-4-5'<\/span><span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>string<span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span>\r\n\t\t\r\n\t<span class=\"token keyword\">except<\/span> AttributeError<span class=\"token punctuation\">:<\/span>\r\n\t\t\r\n\t\t<span class=\"token keyword\">try<\/span><span class=\"token punctuation\">:<\/span>\r\n\t\t\trating <span class=\"token operator\">=<\/span> soup<span class=\"token punctuation\">.<\/span>find<span class=\"token punctuation\">(<\/span><span class=\"token string\">\"span\"<\/span><span class=\"token punctuation\">,<\/span> attrs<span class=\"token operator\">=<\/span><span class=\"token punctuation\">{<\/span><span class=\"token string\">'class'<\/span><span class=\"token punctuation\">:<\/span><span class=\"token string\">'a-icon-alt'<\/span><span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>string<span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span>\r\n\t\t<span class=\"token keyword\">except<\/span><span class=\"token punctuation\">:<\/span>\r\n\t\t\trating <span class=\"token operator\">=<\/span> <span class=\"token string\">\"\"<\/span>\t\r\n\r\n\t<span class=\"token keyword\">return<\/span> rating\r\n\r\n<span class=\"token comment\"># \u63d0\u53d6\u7528\u6237\u8bc4\u8bba\u6570\u91cf\u7684\u51fd\u6570<\/span>\r\n<span class=\"token keyword\">def<\/span> <span class=\"token function\">get_review_count<\/span><span class=\"token punctuation\">(<\/span>soup<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span>\r\n\t<span class=\"token keyword\">try<\/span><span class=\"token punctuation\">:<\/span>\r\n\t\treview_count <span class=\"token operator\">=<\/span> soup<span class=\"token punctuation\">.<\/span>find<span class=\"token punctuation\">(<\/span><span class=\"token string\">\"span\"<\/span><span class=\"token punctuation\">,<\/span> attrs<span class=\"token operator\">=<\/span><span class=\"token punctuation\">{<\/span><span class=\"token string\">'id'<\/span><span class=\"token punctuation\">:<\/span><span class=\"token string\">'acrCustomerReviewText'<\/span><span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>string<span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span>\r\n\t\t\r\n\t<span class=\"token keyword\">except<\/span> AttributeError<span class=\"token punctuation\">:<\/span>\r\n\t\treview_count <span class=\"token operator\">=<\/span> <span class=\"token string\">\"\"<\/span>\t\r\n\r\n\t<span class=\"token keyword\">return<\/span> review_count\r\n\r\n<span class=\"token comment\"># \u63d0\u53d6\u53ef\u7528\u6027\u72b6\u6001\u7684\u51fd\u6570<\/span>\r\n<span class=\"token keyword\">def<\/span> <span class=\"token function\">get_availability<\/span><span class=\"token punctuation\">(<\/span>soup<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span>\r\n\t<span class=\"token keyword\">try<\/span><span class=\"token punctuation\">:<\/span>\r\n\t\tavailable <span class=\"token operator\">=<\/span> soup<span class=\"token punctuation\">.<\/span>find<span class=\"token punctuation\">(<\/span><span class=\"token string\">\"div\"<\/span><span class=\"token punctuation\">,<\/span> attrs<span class=\"token operator\">=<\/span><span class=\"token punctuation\">{<\/span><span class=\"token string\">'id'<\/span><span class=\"token punctuation\">:<\/span><span class=\"token string\">'availability'<\/span><span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span>\r\n\t\tavailable <span class=\"token operator\">=<\/span> available<span class=\"token punctuation\">.<\/span>find<span class=\"token punctuation\">(<\/span><span class=\"token string\">\"span\"<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>string<span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n\t<span class=\"token keyword\">except<\/span> AttributeError<span class=\"token punctuation\">:<\/span>\r\n\t\tavailable <span class=\"token operator\">=<\/span> <span class=\"token string\">\"\"<\/span>\t\r\n\r\n\t<span class=\"token keyword\">return<\/span> available\t\r\n\r\n<span class=\"token keyword\">if<\/span> __name__ <span class=\"token operator\">==<\/span> <span class=\"token string\">'__main__'<\/span><span class=\"token punctuation\">:<\/span>\r\n\r\n\t<span class=\"token comment\"># \u8bf7\u6c42\u5934<\/span>\r\n\tHEADERS <span class=\"token operator\">=<\/span> <span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">{<\/span><span class=\"token string\">'User-Agent'<\/span><span class=\"token punctuation\">:<\/span>\r\n\t            <span class=\"token string\">'Mozilla\/5.0 (X11; Linux x86_64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/44.0.2403.157 Safari\/537.36'<\/span><span class=\"token punctuation\">,<\/span>\r\n\t            <span class=\"token string\">'Accept-Language'<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">'en-US, en;q=0.5'<\/span><span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n\t<span class=\"token comment\"># \u7f51\u9875URL<\/span>\r\n\tURL <span class=\"token operator\">=<\/span> <span class=\"token string\">\"https:\/\/www.amazon.com\/Sony-PlayStation-Pro-1TB-Console-4\/dp\/B07K14XKZH\/\"<\/span>\r\n\r\n\t<span class=\"token comment\"># HTTP\u8bf7\u6c42<\/span>\r\n\twebpage <span class=\"token operator\">=<\/span> requests<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span>URL<span class=\"token punctuation\">,<\/span> headers<span class=\"token operator\">=<\/span>HEADERS<span class=\"token punctuation\">)<\/span>\r\n\r\n\t<span class=\"token comment\"># \u5305\u542b\u6240\u6709\u6570\u636e\u7684Soup\u5bf9\u8c61<\/span>\r\n\tsoup <span class=\"token operator\">=<\/span> BeautifulSoup<span class=\"token punctuation\">(<\/span>webpage<span class=\"token punctuation\">.<\/span>content<span class=\"token punctuation\">,<\/span> <span class=\"token string\">\"lxml\"<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n\t<span class=\"token comment\"># \u8c03\u7528\u51fd\u6570\u4ee5\u663e\u793a\u6240\u6709\u5fc5\u8981\u7684\u4ea7\u54c1\u4fe1\u606f<\/span>\r\n\t<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">\"\u4ea7\u54c1\u6807\u9898 =\"<\/span><span class=\"token punctuation\">,<\/span> get_title<span class=\"token punctuation\">(<\/span>soup<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span>\r\n\t<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">\"\u4ea7\u54c1\u4ef7\u683c =\"<\/span><span class=\"token punctuation\">,<\/span> get_price<span class=\"token punctuation\">(<\/span>soup<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span>\r\n\t<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">\"\u4ea7\u54c1\u8bc4\u5206 =\"<\/span><span class=\"token punctuation\">,<\/span> get_rating<span class=\"token punctuation\">(<\/span>soup<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span>\r\n\t<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">\"\u4ea7\u54c1\u8bc4\u8bba\u6570\u91cf =\"<\/span><span class=\"token punctuation\">,<\/span> get_review_count<span class=\"token punctuation\">(<\/span>soup<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span>\r\n\t<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">\"\u53ef\u7528\u6027 =\"<\/span><span class=\"token punctuation\">,<\/span> get_availability<span class=\"token punctuation\">(<\/span>soup<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span>\r\n\t<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span>\r\n\t<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n\r\n<\/code><\/pre>\n<p>\u8f93\u51fa\uff1a<\/p>\n<pre class=\"post-pre\"><code>\u4ea7\u54c1\u6807\u9898 = Sony PlayStation 4 Pro 1TB Console - Black (PS4 Pro)\r\n\u4ea7\u54c1\u4ef7\u683c = $473.99\r\n\u4ea7\u54c1\u8bc4\u5206 = 4.7 out of 5 stars\r\n\u4ea7\u54c1\u8bc4\u8bba\u6570\u91cf = 1,311 ratings\r\n\u53ef\u7528\u6027 = In Stock.\r\n<\/code><\/pre>\n<p>\u73b0\u5728\u6211\u4eec\u77e5\u9053\u4e86\u5982\u4f55\u4ece\u5355\u4e2a\u4e9a\u9a6c\u900a\u7f51\u9875\u4e2d\u63d0\u53d6\u4fe1\u606f\uff0c\u6211\u4eec\u53ef\u4ee5\u901a\u8fc7\u7b80\u5355\u66f4\u6539URL\u5c06\u76f8\u540c\u7684\u811a\u672c\u5e94\u7528\u4e8e\u591a\u4e2a\u7f51\u9875\u3002<\/p>\n<p>\u6b64\u5916\uff0c\u8ba9\u6211\u4eec\u73b0\u5728\u5c1d\u8bd5\u4ece\u4e9a\u9a6c\u900a\u7684\u641c\u7d22\u7ed3\u679c\u7f51\u9875\u4e2d\u83b7\u53d6\u94fe\u63a5\u3002<\/p>\n<h2>\u4ece\u4e9a\u9a6c\u900a\u641c\u7d22\u7ed3\u679c\u9875\u9762\u63d0\u53d6\u94fe\u63a5<\/h2>\n<p>\u4e4b\u524d\uff0c\u6211\u4eec\u83b7\u53d6\u4e86\u4e00\u53f0\u968f\u673aPlayStation 4\u7684\u4fe1\u606f\u3002\u4e3a\u4e86\u6bd4\u8f83\u4ef7\u683c\u548c\u8bc4\u5206\uff0c\u63d0\u53d6\u591a\u53f0PlayStation\u7684\u4fe1\u606f\u662f\u4e2a\u5f88\u597d\u7684\u65b9\u6cd5\u3002<\/p>\n<p>\u6211\u4eec\u53ef\u4ee5\u4ece&lt;a&gt;\u6807\u7b7e\u7684href\u5c5e\u6027\u4e2d\u627e\u5230\u94fe\u63a5\u3002<\/p>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/65647613a4b2f92e6c72a7dc\/56-0.png\" alt=\"Amazon Web Scraper Links\" \/><\/div>\n<p>\u4e0d\u53ea\u662f\u83b7\u53d6\u5355\u4e2a\u94fe\u63a5\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528find_all()\u51fd\u6570\u6765\u63d0\u53d6\u6240\u6709\u7c7b\u4f3c\u7684\u94fe\u63a5\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"token comment\"># \u5c06\u94fe\u63a5\u4f5c\u4e3a\u6807\u7b7e\u5bf9\u8c61\u5217\u8868\u83b7\u53d6<\/span>\r\nlinks <span class=\"token operator\">=<\/span> soup<span class=\"token punctuation\">.<\/span>find_all<span class=\"token punctuation\">(<\/span><span class=\"token string\">\"a\"<\/span><span class=\"token punctuation\">,<\/span> attrs<span class=\"token operator\">=<\/span><span class=\"token punctuation\">{<\/span><span class=\"token string\">'class'<\/span><span class=\"token punctuation\">:<\/span><span class=\"token string\">'a-link-normal s-no-outline'<\/span><span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span>\r\n<\/code><\/pre>\n<p>find_all()\u51fd\u6570\u8fd4\u56de\u4e00\u4e2a\u5305\u542b\u591a\u4e2aTag\u5bf9\u8c61\u7684\u53ef\u8fed\u4ee3\u96c6\u5408\u3002\u56e0\u6b64\uff0c\u6211\u4eec\u9010\u4e2a\u9009\u62e9Tag\u5bf9\u8c61\uff0c\u5e76\u63d0\u53d6\u5b58\u50a8\u5728href\u5c5e\u6027\u4e2d\u7684\u94fe\u63a5\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"token comment\"># \u5b58\u50a8\u94fe\u63a5<\/span>\r\nlinks_list <span class=\"token operator\">=<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span>\r\n\r\n<span class=\"token comment\"># \u5faa\u73af\u4eceTag\u5bf9\u8c61\u4e2d\u63d0\u53d6\u94fe\u63a5<\/span>\r\n<span class=\"token keyword\">for<\/span> link <span class=\"token keyword\">in<\/span> links<span class=\"token punctuation\">:<\/span>\r\n\tlinks_list<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span>link<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">'href'<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span>\r\n<\/code><\/pre>\n<p>\u6211\u4eec\u5c06\u94fe\u63a5\u5b58\u50a8\u5728\u5217\u8868\u4e2d\uff0c\u4ee5\u4fbf\u904d\u5386\u6bcf\u4e2a\u94fe\u63a5\u5e76\u63d0\u53d6\u4ea7\u54c1\u8be6\u60c5\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"token comment\"># \u5faa\u73af\u4ece\u6bcf\u4e2a\u94fe\u63a5\u4e2d\u63d0\u53d6\u4ea7\u54c1\u8be6\u60c5<\/span>\r\n\t<span class=\"token keyword\">for<\/span> link <span class=\"token keyword\">in<\/span> links_list<span class=\"token punctuation\">:<\/span>\r\n\t\t\r\n\t\tnew_webpage <span class=\"token operator\">=<\/span> requests<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">\"https:\/\/www.amazon.com\"<\/span> <span class=\"token operator\">+<\/span> link<span class=\"token punctuation\">,<\/span> headers<span class=\"token operator\">=<\/span>HEADERS<span class=\"token punctuation\">)<\/span>\r\n\t\tnew_soup <span class=\"token operator\">=<\/span> BeautifulSoup<span class=\"token punctuation\">(<\/span>new_webpage<span class=\"token punctuation\">.<\/span>content<span class=\"token punctuation\">,<\/span> <span class=\"token string\">\"lxml\"<\/span><span class=\"token punctuation\">)<\/span>\r\n\t\t\r\n\t\t<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">\"\u4ea7\u54c1\u6807\u9898 =\"<\/span><span class=\"token punctuation\">,<\/span> get_title<span class=\"token punctuation\">(<\/span>new_soup<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span>\r\n\t\t<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">\"\u4ea7\u54c1\u4ef7\u683c =\"<\/span><span class=\"token punctuation\">,<\/span> get_price<span class=\"token punctuation\">(<\/span>new_soup<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span>\r\n\t\t<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">\"\u4ea7\u54c1\u8bc4\u5206 =\"<\/span><span class=\"token punctuation\">,<\/span> get_rating<span class=\"token punctuation\">(<\/span>new_soup<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span>\r\n\t\t<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">\"\u4ea7\u54c1\u8bc4\u8bba\u6570 =\"<\/span><span class=\"token punctuation\">,<\/span> get_review_count<span class=\"token punctuation\">(<\/span>new_soup<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span>\r\n\t\t<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">\"\u53ef\u7528\u6027 =\"<\/span><span class=\"token punctuation\">,<\/span> get_availability<span class=\"token punctuation\">(<\/span>new_soup<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span>\r\n<\/code><\/pre>\n<p>\u6211\u4eec\u590d\u7528\u4e4b\u524d\u521b\u5efa\u7684\u51fd\u6570\u6765\u63d0\u53d6\u4ea7\u54c1\u4fe1\u606f\u3002\u867d\u7136\u5904\u7406\u591a\u4e2a\u4ea7\u54c1\u7684\u6d41\u7a0b\u4f1a\u4f7f\u4ee3\u7801\u8fd0\u884c\u53d8\u6162\uff0c\u4f46\u5b83\u80fd\u591f\u63d0\u4f9b\u4e0d\u540c\u578b\u53f7\u548c\u4ea4\u6613\u4e4b\u95f4\u7684\u4ef7\u683c\u6bd4\u8f83\u3002<\/p>\n<h2>\u63d0\u53d6\u591a\u4e2a\u7f51\u9875\u4e0a\u4ea7\u54c1\u8be6\u7ec6\u4fe1\u606f\u7684Python\u811a\u672c<\/h2>\n<p>\u4ee5\u4e0b\u662f\u7528\u4e8e\u5217\u51fa\u591a\u4e2aPlayStation\u4ea4\u6613\u7684\u5b8c\u6574\u5de5\u4f5cPython\u811a\u672c\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"token keyword\">from<\/span> bs4 <span class=\"token keyword\">import<\/span> BeautifulSoup\r\n<span class=\"token keyword\">import<\/span> requests\r\n\r\n<span class=\"token comment\"># Function to extract Product Title<\/span>\r\n<span class=\"token keyword\">def<\/span> <span class=\"token function\">get_title<\/span><span class=\"token punctuation\">(<\/span>soup<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span>\r\n\t\r\n\t<span class=\"token keyword\">try<\/span><span class=\"token punctuation\">:<\/span>\r\n\t\t<span class=\"token comment\"># Outer Tag Object<\/span>\r\n\t\ttitle <span class=\"token operator\">=<\/span> soup<span class=\"token punctuation\">.<\/span>find<span class=\"token punctuation\">(<\/span><span class=\"token string\">\"span\"<\/span><span class=\"token punctuation\">,<\/span> attrs<span class=\"token operator\">=<\/span><span class=\"token punctuation\">{<\/span><span class=\"token string\">\"id\"<\/span><span class=\"token punctuation\">:<\/span><span class=\"token string\">'productTitle'<\/span><span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n\t\t<span class=\"token comment\"># Inner NavigatableString Object<\/span>\r\n\t\ttitle_value <span class=\"token operator\">=<\/span> title<span class=\"token punctuation\">.<\/span>string\r\n\r\n\t\t<span class=\"token comment\"># Title as a string value<\/span>\r\n\t\ttitle_string <span class=\"token operator\">=<\/span> title_value<span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n\t\t<span class=\"token comment\"># # Printing types of values for efficient understanding<\/span>\r\n\t\t<span class=\"token comment\"># print(type(title))<\/span>\r\n\t\t<span class=\"token comment\"># print(type(title_value))<\/span>\r\n\t\t<span class=\"token comment\"># print(type(title_string))<\/span>\r\n\t\t<span class=\"token comment\"># print()<\/span>\r\n\r\n\t<span class=\"token keyword\">except<\/span> AttributeError<span class=\"token punctuation\">:<\/span>\r\n\t\ttitle_string <span class=\"token operator\">=<\/span> <span class=\"token string\">\"\"<\/span>\t\r\n\r\n\t<span class=\"token keyword\">return<\/span> title_string\r\n\r\n<span class=\"token comment\"># Function to extract Product Price<\/span>\r\n<span class=\"token keyword\">def<\/span> <span class=\"token function\">get_price<\/span><span class=\"token punctuation\">(<\/span>soup<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span>\r\n\r\n\t<span class=\"token keyword\">try<\/span><span class=\"token punctuation\">:<\/span>\r\n\t\tprice <span class=\"token operator\">=<\/span> soup<span class=\"token punctuation\">.<\/span>find<span class=\"token punctuation\">(<\/span><span class=\"token string\">\"span\"<\/span><span class=\"token punctuation\">,<\/span> attrs<span class=\"token operator\">=<\/span><span class=\"token punctuation\">{<\/span><span class=\"token string\">'id'<\/span><span class=\"token punctuation\">:<\/span><span class=\"token string\">'priceblock_ourprice'<\/span><span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>string<span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n\t<span class=\"token keyword\">except<\/span> AttributeError<span class=\"token punctuation\">:<\/span>\r\n\r\n\t\t<span class=\"token keyword\">try<\/span><span class=\"token punctuation\">:<\/span>\r\n\t\t\t<span class=\"token comment\"># If there is some deal price<\/span>\r\n\t\t\tprice <span class=\"token operator\">=<\/span> soup<span class=\"token punctuation\">.<\/span>find<span class=\"token punctuation\">(<\/span><span class=\"token string\">\"span\"<\/span><span class=\"token punctuation\">,<\/span> attrs<span class=\"token operator\">=<\/span><span class=\"token punctuation\">{<\/span><span class=\"token string\">'id'<\/span><span class=\"token punctuation\">:<\/span><span class=\"token string\">'priceblock_dealprice'<\/span><span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>string<span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n\t\t<span class=\"token keyword\">except<\/span><span class=\"token punctuation\">:<\/span>\t\t\r\n\t\t\tprice <span class=\"token operator\">=<\/span> <span class=\"token string\">\"\"<\/span>\t\r\n\r\n\t<span class=\"token keyword\">return<\/span> price\r\n\r\n<span class=\"token comment\"># Function to extract Product Rating<\/span>\r\n<span class=\"token keyword\">def<\/span> <span class=\"token function\">get_rating<\/span><span class=\"token punctuation\">(<\/span>soup<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span>\r\n\r\n\t<span class=\"token keyword\">try<\/span><span class=\"token punctuation\">:<\/span>\r\n\t\trating <span class=\"token operator\">=<\/span> soup<span class=\"token punctuation\">.<\/span>find<span class=\"token punctuation\">(<\/span><span class=\"token string\">\"i\"<\/span><span class=\"token punctuation\">,<\/span> attrs<span class=\"token operator\">=<\/span><span class=\"token punctuation\">{<\/span><span class=\"token string\">'class'<\/span><span class=\"token punctuation\">:<\/span><span class=\"token string\">'a-icon a-icon-star a-star-4-5'<\/span><span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>string<span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span>\r\n\t\t\r\n\t<span class=\"token keyword\">except<\/span> AttributeError<span class=\"token punctuation\">:<\/span>\r\n\t\t\r\n\t\t<span class=\"token keyword\">try<\/span><span class=\"token punctuation\">:<\/span>\r\n\t\t\trating <span class=\"token operator\">=<\/span> soup<span class=\"token punctuation\">.<\/span>find<span class=\"token punctuation\">(<\/span><span class=\"token string\">\"span\"<\/span><span class=\"token punctuation\">,<\/span> attrs<span class=\"token operator\">=<\/span><span class=\"token punctuation\">{<\/span><span class=\"token string\">'class'<\/span><span class=\"token punctuation\">:<\/span><span class=\"token string\">'a-icon-alt'<\/span><span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>string<span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span>\r\n\t\t<span class=\"token keyword\">except<\/span><span class=\"token punctuation\">:<\/span>\r\n\t\t\trating <span class=\"token operator\">=<\/span> <span class=\"token string\">\"\"<\/span>\t\r\n\r\n\t<span class=\"token keyword\">return<\/span> rating\r\n\r\n<span class=\"token comment\"># Function to extract Number of User Reviews<\/span>\r\n<span class=\"token keyword\">def<\/span> <span class=\"token function\">get_review_count<\/span><span class=\"token punctuation\">(<\/span>soup<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span>\r\n\t<span class=\"token keyword\">try<\/span><span class=\"token punctuation\">:<\/span>\r\n\t\treview_count <span class=\"token operator\">=<\/span> soup<span class=\"token punctuation\">.<\/span>find<span class=\"token punctuation\">(<\/span><span class=\"token string\">\"span\"<\/span><span class=\"token punctuation\">,<\/span> attrs<span class=\"token operator\">=<\/span><span class=\"token punctuation\">{<\/span><span class=\"token string\">'id'<\/span><span class=\"token punctuation\">:<\/span><span class=\"token string\">'acrCustomerReviewText'<\/span><span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>string<span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span>\r\n\t\t\r\n\t<span class=\"token keyword\">except<\/span> AttributeError<span class=\"token punctuation\">:<\/span>\r\n\t\treview_count <span class=\"token operator\">=<\/span> <span class=\"token string\">\"\"<\/span>\t\r\n\r\n\t<span class=\"token keyword\">return<\/span> review_count\r\n\r\n<span class=\"token comment\"># Function to extract Availability Status<\/span>\r\n<span class=\"token keyword\">def<\/span> <span class=\"token function\">get_availability<\/span><span class=\"token punctuation\">(<\/span>soup<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">:<\/span>\r\n\t<span class=\"token keyword\">try<\/span><span class=\"token punctuation\">:<\/span>\r\n\t\tavailable <span class=\"token operator\">=<\/span> soup<span class=\"token punctuation\">.<\/span>find<span class=\"token punctuation\">(<\/span><span class=\"token string\">\"div\"<\/span><span class=\"token punctuation\">,<\/span> attrs<span class=\"token operator\">=<\/span><span class=\"token punctuation\">{<\/span><span class=\"token string\">'id'<\/span><span class=\"token punctuation\">:<\/span><span class=\"token string\">'availability'<\/span><span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span>\r\n\t\tavailable <span class=\"token operator\">=<\/span> available<span class=\"token punctuation\">.<\/span>find<span class=\"token punctuation\">(<\/span><span class=\"token string\">\"span\"<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">.<\/span>string<span class=\"token punctuation\">.<\/span>strip<span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n\t<span class=\"token keyword\">except<\/span> AttributeError<span class=\"token punctuation\">:<\/span>\r\n\t\tavailable <span class=\"token operator\">=<\/span> <span class=\"token string\">\"Not Available\"<\/span>\t\r\n\r\n\t<span class=\"token keyword\">return<\/span> available\t\r\n\r\n\r\n<span class=\"token keyword\">if<\/span> __name__ <span class=\"token operator\">==<\/span> <span class=\"token string\">'__main__'<\/span><span class=\"token punctuation\">:<\/span>\r\n\r\n\t<span class=\"token comment\"># Headers for request<\/span>\r\n\tHEADERS <span class=\"token operator\">=<\/span> <span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">{<\/span><span class=\"token string\">'User-Agent'<\/span><span class=\"token punctuation\">:<\/span>\r\n\t            <span class=\"token string\">'Mozilla\/5.0 (X11; Linux x86_64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/44.0.2403.157 Safari\/537.36'<\/span><span class=\"token punctuation\">,<\/span>\r\n\t            <span class=\"token string\">'Accept-Language'<\/span><span class=\"token punctuation\">:<\/span> <span class=\"token string\">'en-US'<\/span><span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n\t<span class=\"token comment\"># The webpage URL<\/span>\r\n\tURL <span class=\"token operator\">=<\/span> <span class=\"token string\">\"https:\/\/www.amazon.com\/s?k=playstation+4&amp;ref=nb_sb_noss_2\"<\/span>\r\n\t\r\n\t<span class=\"token comment\"># HTTP Request<\/span>\r\n\twebpage <span class=\"token operator\">=<\/span> requests<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span>URL<span class=\"token punctuation\">,<\/span> headers<span class=\"token operator\">=<\/span>HEADERS<span class=\"token punctuation\">)<\/span>\r\n\r\n\t<span class=\"token comment\"># Soup Object containing all data<\/span>\r\n\tsoup <span class=\"token operator\">=<\/span> BeautifulSoup<span class=\"token punctuation\">(<\/span>webpage<span class=\"token punctuation\">.<\/span>content<span class=\"token punctuation\">,<\/span> <span class=\"token string\">\"lxml\"<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n\t<span class=\"token comment\"># Fetch links as List of Tag Objects<\/span>\r\n\tlinks <span class=\"token operator\">=<\/span> soup<span class=\"token punctuation\">.<\/span>find_all<span class=\"token punctuation\">(<\/span><span class=\"token string\">\"a\"<\/span><span class=\"token punctuation\">,<\/span> attrs<span class=\"token operator\">=<\/span><span class=\"token punctuation\">{<\/span><span class=\"token string\">'class'<\/span><span class=\"token punctuation\">:<\/span><span class=\"token string\">'a-link-normal s-no-outline'<\/span><span class=\"token punctuation\">}<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n\t<span class=\"token comment\"># Store the links<\/span>\r\n\tlinks_list <span class=\"token operator\">=<\/span> <span class=\"token punctuation\">[<\/span><span class=\"token punctuation\">]<\/span>\r\n\r\n\t<span class=\"token comment\"># Loop for extracting links from Tag Objects<\/span>\r\n\t<span class=\"token keyword\">for<\/span> link <span class=\"token keyword\">in<\/span> links<span class=\"token punctuation\">:<\/span>\r\n\t\tlinks_list<span class=\"token punctuation\">.<\/span>append<span class=\"token punctuation\">(<\/span>link<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">'href'<\/span><span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span>\r\n\r\n\r\n\t<span class=\"token comment\"># Loop for extracting product details from each link <\/span>\r\n\t<span class=\"token keyword\">for<\/span> link <span class=\"token keyword\">in<\/span> links_list<span class=\"token punctuation\">:<\/span>\r\n\r\n\t\tnew_webpage <span class=\"token operator\">=<\/span> requests<span class=\"token punctuation\">.<\/span>get<span class=\"token punctuation\">(<\/span><span class=\"token string\">\"https:\/\/www.amazon.com\"<\/span> <span class=\"token operator\">+<\/span> link<span class=\"token punctuation\">,<\/span> headers<span class=\"token operator\">=<\/span>HEADERS<span class=\"token punctuation\">)<\/span>\r\n\r\n\t\tnew_soup <span class=\"token operator\">=<\/span> BeautifulSoup<span class=\"token punctuation\">(<\/span>new_webpage<span class=\"token punctuation\">.<\/span>content<span class=\"token punctuation\">,<\/span> <span class=\"token string\">\"lxml\"<\/span><span class=\"token punctuation\">)<\/span>\r\n\t\t\r\n\t\t<span class=\"token comment\"># Function calls to display all necessary product information<\/span>\r\n\t\t<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">\"Product Title =\"<\/span><span class=\"token punctuation\">,<\/span> get_title<span class=\"token punctuation\">(<\/span>new_soup<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span>\r\n\t\t<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">\"Product Price =\"<\/span><span class=\"token punctuation\">,<\/span> get_price<span class=\"token punctuation\">(<\/span>new_soup<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span>\r\n\t\t<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">\"Product Rating =\"<\/span><span class=\"token punctuation\">,<\/span> get_rating<span class=\"token punctuation\">(<\/span>new_soup<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span>\r\n\t\t<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">\"Number of Product Reviews =\"<\/span><span class=\"token punctuation\">,<\/span> get_review_count<span class=\"token punctuation\">(<\/span>new_soup<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span>\r\n\t\t<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token string\">\"Availability =\"<\/span><span class=\"token punctuation\">,<\/span> get_availability<span class=\"token punctuation\">(<\/span>new_soup<span class=\"token punctuation\">)<\/span><span class=\"token punctuation\">)<\/span>\r\n\t\t<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span>\r\n\t\t<span class=\"token keyword\">print<\/span><span class=\"token punctuation\">(<\/span><span class=\"token punctuation\">)<\/span>\r\n<\/code><\/pre>\n<p>\u8f93\u51fa\uff1a\u8bf7\u5c06\u4ee5\u4e0b\u5185\u5bb9\u7528\u4e2d\u6587\u7b80\u6d01\u5730\u8868\u8fbe\u51fa\u6765\u3002\u53ea\u9700\u8981\u4e00\u4e2a\u9009\u9879\uff1a<\/p>\n<pre class=\"post-pre\"><code>Product Title = SONY PlayStation 4 Slim 1TB Console, Light &amp; Slim PS4 System, 1TB Hard Drive, All the Greatest Games, TV, Music &amp; More\r\nProduct Price = $357.00\r\nProduct Rating = 4.4 out of 5 stars\r\nNumber of Product Reviews = 32 ratings\r\nAvailability = In stock on September 8, 2020.\r\n\r\n\r\nProduct Title = Newest Sony Playstation 4 PS4 1TB HDD Gaming Console Bundle with Three Games: The Last of Us, God of War, Horizon Zero Dawn, Included Dualshock 4 Wireless Controller\r\nProduct Price = $469.00\r\nProduct Rating = 4.6 out of 5 stars\r\nNumber of Product Reviews = 211 ratings\r\nAvailability = Only 14 left in stock - order soon.\r\n\r\n\r\nProduct Title = PlayStation 4 Slim 1TB Console - Fortnite Bundle\r\nProduct Price = \r\nProduct Rating = 4.8 out of 5 stars\r\nNumber of Product Reviews = 2,715 ratings\r\nAvailability = Not Available\r\n\r\n\r\nProduct Title = PlayStation 4 Slim 1TB Console - Only On PlayStation Bundle\r\nProduct Price = $444.00\r\nProduct Rating = 4.7 out of 5 stars\r\nNumber of Product Reviews = 5,190 ratings\r\nAvailability = Only 1 left in stock - order soon.\r\n<\/code><\/pre>\n<p>\u4ee5\u4e0a\u7684Python\u811a\u672c\u5e76\u4e0d\u9650\u5236\u53ea\u9488\u5bf9PlayStation\u8bbe\u5907\u3002\u6211\u4eec\u53ef\u4ee5\u5c06\u7f51\u5740\u5207\u6362\u4e3a\u5176\u4ed6\u94fe\u63a5\uff0c\u4f8b\u5982\u4e9a\u9a6c\u900a\u4e0a\u7684\u8033\u673a\u6216\u542c\u7b52\u7684\u641c\u7d22\u7ed3\u679c\u3002<\/p>\n<p>\u5982\u524d\u6240\u8ff0\uff0cHTML\u9875\u9762\u7684\u5e03\u5c40\u548c\u6807\u7b7e\u53ef\u80fd\u968f\u65f6\u95f4\u800c\u53d8\u5316\uff0c\u4f7f\u4e0a\u8ff0\u4ee3\u7801\u5728\u8fd9\u65b9\u9762\u53d8\u5f97\u6beb\u65e0\u4ef7\u503c\u3002\u7136\u800c\uff0c\u8bfb\u8005\u5fc5\u987b\u7262\u8bb0\u7f51\u7edc\u722c\u866b\u7684\u6982\u5ff5\u548c\u672c\u6587\u4e2d\u5b66\u5230\u7684\u6280\u5de7\u3002<\/p>\n<h2>\u7ed3\u8bba \u7ed3\u675f<\/p>\n<p>\u4ece<strong>\u6bd4\u8f83\u4ea7\u54c1\u4ef7\u683c<\/strong>\u5230<strong>\u5206\u6790\u6d88\u8d39\u8005\u503e\u5411<\/strong>\uff0c<strong>\u7f51\u9875\u6293\u53d6<\/strong>\u53ef\u4ee5\u5e26\u6765\u5404\u79cd\u597d\u5904\u3002\u7531\u4e8e\u4e92\u8054\u7f51\u5bf9\u6bcf\u4e2a\u4eba\u90fd\u53ef\u8bbf\u95ee\uff0c\u800c<strong>Python<\/strong>\u662f\u4e00\u79cd\u975e\u5e38\u6613\u5b66\u7684\u8bed\u8a00\uff0c\u4efb\u4f55\u4eba\u90fd\u53ef\u4ee5\u8fdb\u884c<strong>\u7f51\u9875\u6293\u53d6<\/strong>\u4ee5\u6ee1\u8db3\u81ea\u5df1\u7684\u9700\u6c42\u3002<\/p>\n<p>\u5e0c\u671b\u672c\u7bc7\u5173\u4e8e<strong>Beautiful Soup<\/strong>\u7684\u6587\u7ae0\u5bb9\u6613\u7406\u89e3\u3002\u5982\u6709\u4efb\u4f55\u95ee\u9898\u6216\u53cd\u9988\uff0c\u8bf7\u968f\u610f\u5728\u4e0b\u65b9\u7559\u8a00\u3002\u795d\u60a8\u6109\u5feb\u5730\u6536\u96c6\u6570\u636e\uff01<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u7f51\u7edc\u722c\u866b\u662f\u4e00\u79cd\u57fa\u4e8e\u7f16\u7a0b\u7684\u6280\u672f\uff0c\u7528\u4e8e\u4ece\u7f51\u7ad9\u4e2d\u63d0\u53d6\u76f8\u5173\u4fe1\u606f\u5e76\u5b58\u50a8\u5728\u672c\u5730\u7cfb\u7edf\u4e2d\u4ee5\u4f9b\u8fdb\u4e00\u6b65\u4f7f\u7528\u3002 \u5728\u73b0\u4ee3\uff0c\u7f51\u7edc\u6293\u53d6\u5728\u6570 [&hellip;]<\/p>\n","protected":false},"author":6,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[1702,1701,1703,165,1704],"class_list":["post-592","post","type-post","status-publish","format-standard","hentry","category-uncategorized","tag-beautiful-soup","tag-python","tag-1703","tag-165","tag-1704"],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v21.5 (Yoast SEO v21.5) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Python\u5b9e\u6218\u6559\u7a0b\uff1a\u4f7f\u7528Beautiful Soup\u722c\u53d6\u4e9a\u9a6c\u900a\u4ea7\u54c1\u4fe1\u606f\u4e0e\u4ef7\u683c - Blog - Silicon Cloud<\/title>\n<meta name=\"description\" content=\"\u672c\u6559\u7a0b\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u4f7f\u7528Python\u7684Beautiful Soup\u5e93\u722c\u53d6\u4e9a\u9a6c\u900a\u4ea7\u54c1\u4fe1\u606f\uff0c\u5305\u62ec\u4ef7\u683c\u3001\u8bc4\u8bba\u7b49\u6570\u636e\u3002\u901a\u8fc7\u5b9e\u4f8b\u4ee3\u7801\u548c\u5206\u6b65\u8bb2\u89e3\uff0c\u5373\u4f7f\u662f\u521d\u5b66\u8005\u4e5f\u80fd\u5feb\u901f\u638c\u63e1\u7f51\u7edc\u722c\u866b\u6280\u672f\uff0c\u8f7b\u677e\u83b7\u53d6\u6240\u9700\u7684\u7535\u5546\u6570\u636e\u3002\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.silicloud.com\/zh\/blog\/\u5982\u4f55\u4f7f\u7528beautiful-soup\u722c\u53d6\u4e9a\u9a6c\u900a\u4ea7\u54c1\u4fe1\u606f\/\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Python\u5b9e\u6218\u6559\u7a0b\uff1a\u4f7f\u7528Beautiful Soup\u722c\u53d6\u4e9a\u9a6c\u900a\u4ea7\u54c1\u4fe1\u606f\u4e0e\u4ef7\u683c\" \/>\n<meta property=\"og:description\" content=\"\u672c\u6559\u7a0b\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u4f7f\u7528Python\u7684Beautiful Soup\u5e93\u722c\u53d6\u4e9a\u9a6c\u900a\u4ea7\u54c1\u4fe1\u606f\uff0c\u5305\u62ec\u4ef7\u683c\u3001\u8bc4\u8bba\u7b49\u6570\u636e\u3002\u901a\u8fc7\u5b9e\u4f8b\u4ee3\u7801\u548c\u5206\u6b65\u8bb2\u89e3\uff0c\u5373\u4f7f\u662f\u521d\u5b66\u8005\u4e5f\u80fd\u5feb\u901f\u638c\u63e1\u7f51\u7edc\u722c\u866b\u6280\u672f\uff0c\u8f7b\u677e\u83b7\u53d6\u6240\u9700\u7684\u7535\u5546\u6570\u636e\u3002\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.silicloud.com\/zh\/blog\/\u5982\u4f55\u4f7f\u7528beautiful-soup\u722c\u53d6\u4e9a\u9a6c\u900a\u4ea7\u54c1\u4fe1\u606f\/\" \/>\n<meta property=\"og:site_name\" content=\"Blog - Silicon Cloud\" \/>\n<meta property=\"article:published_time\" content=\"2024-03-03T15:01:55+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-08-02T13:38:07+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/65647613a4b2f92e6c72a7dc\/29-0.png\" \/>\n<meta name=\"author\" content=\"\u6587, \u7fd4\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"\u6587, \u7fd4\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 \u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8beautiful-soup%e7%88%ac%e5%8f%96%e4%ba%9a%e9%a9%ac%e9%80%8a%e4%ba%a7%e5%93%81%e4%bf%a1%e6%81%af\/\",\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8beautiful-soup%e7%88%ac%e5%8f%96%e4%ba%9a%e9%a9%ac%e9%80%8a%e4%ba%a7%e5%93%81%e4%bf%a1%e6%81%af\/\",\"name\":\"Python\u5b9e\u6218\u6559\u7a0b\uff1a\u4f7f\u7528Beautiful Soup\u722c\u53d6\u4e9a\u9a6c\u900a\u4ea7\u54c1\u4fe1\u606f\u4e0e\u4ef7\u683c - Blog - Silicon Cloud\",\"isPartOf\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#website\"},\"datePublished\":\"2024-03-03T15:01:55+00:00\",\"dateModified\":\"2025-08-02T13:38:07+00:00\",\"author\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/64d5cc7727fffbff2f9a2a8da1de3e5c\"},\"description\":\"\u672c\u6559\u7a0b\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u4f7f\u7528Python\u7684Beautiful Soup\u5e93\u722c\u53d6\u4e9a\u9a6c\u900a\u4ea7\u54c1\u4fe1\u606f\uff0c\u5305\u62ec\u4ef7\u683c\u3001\u8bc4\u8bba\u7b49\u6570\u636e\u3002\u901a\u8fc7\u5b9e\u4f8b\u4ee3\u7801\u548c\u5206\u6b65\u8bb2\u89e3\uff0c\u5373\u4f7f\u662f\u521d\u5b66\u8005\u4e5f\u80fd\u5feb\u901f\u638c\u63e1\u7f51\u7edc\u722c\u866b\u6280\u672f\uff0c\u8f7b\u677e\u83b7\u53d6\u6240\u9700\u7684\u7535\u5546\u6570\u636e\u3002\",\"breadcrumb\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8beautiful-soup%e7%88%ac%e5%8f%96%e4%ba%9a%e9%a9%ac%e9%80%8a%e4%ba%a7%e5%93%81%e4%bf%a1%e6%81%af\/#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.silicloud.com\/zh\/blog\/%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8beautiful-soup%e7%88%ac%e5%8f%96%e4%ba%9a%e9%a9%ac%e9%80%8a%e4%ba%a7%e5%93%81%e4%bf%a1%e6%81%af\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8beautiful-soup%e7%88%ac%e5%8f%96%e4%ba%9a%e9%a9%ac%e9%80%8a%e4%ba%a7%e5%93%81%e4%bf%a1%e6%81%af\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.silicloud.com\/zh\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Python\u5b9e\u6218\u6559\u7a0b\uff1a\u4f7f\u7528Beautiful Soup\u722c\u53d6\u4e9a\u9a6c\u900a\u4ea7\u54c1\u4fe1\u606f\u4e0e\u4ef7\u683c\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#website\",\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/\",\"name\":\"Blog - Silicon Cloud\",\"description\":\"\",\"inLanguage\":\"zh-Hans\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/64d5cc7727fffbff2f9a2a8da1de3e5c\",\"name\":\"\u6587, \u7fd4\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/920c3d673e0bccacc98e5e6b7149bb3c22edd8d39cb753e5d7d7e471498118a1?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/920c3d673e0bccacc98e5e6b7149bb3c22edd8d39cb753e5d7d7e471498118a1?s=96&d=mm&r=g\",\"caption\":\"\u6587, \u7fd4\"},\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/author\/wenxiang\/\"},{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8beautiful-soup%e7%88%ac%e5%8f%96%e4%ba%9a%e9%a9%ac%e9%80%8a%e4%ba%a7%e5%93%81%e4%bf%a1%e6%81%af\/#local-main-organization-logo\",\"url\":\"\",\"contentUrl\":\"\",\"caption\":\"Blog - Silicon Cloud\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Python\u5b9e\u6218\u6559\u7a0b\uff1a\u4f7f\u7528Beautiful Soup\u722c\u53d6\u4e9a\u9a6c\u900a\u4ea7\u54c1\u4fe1\u606f\u4e0e\u4ef7\u683c - Blog - Silicon Cloud","description":"\u672c\u6559\u7a0b\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u4f7f\u7528Python\u7684Beautiful Soup\u5e93\u722c\u53d6\u4e9a\u9a6c\u900a\u4ea7\u54c1\u4fe1\u606f\uff0c\u5305\u62ec\u4ef7\u683c\u3001\u8bc4\u8bba\u7b49\u6570\u636e\u3002\u901a\u8fc7\u5b9e\u4f8b\u4ee3\u7801\u548c\u5206\u6b65\u8bb2\u89e3\uff0c\u5373\u4f7f\u662f\u521d\u5b66\u8005\u4e5f\u80fd\u5feb\u901f\u638c\u63e1\u7f51\u7edc\u722c\u866b\u6280\u672f\uff0c\u8f7b\u677e\u83b7\u53d6\u6240\u9700\u7684\u7535\u5546\u6570\u636e\u3002","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.silicloud.com\/zh\/blog\/\u5982\u4f55\u4f7f\u7528beautiful-soup\u722c\u53d6\u4e9a\u9a6c\u900a\u4ea7\u54c1\u4fe1\u606f\/","og_locale":"zh_CN","og_type":"article","og_title":"Python\u5b9e\u6218\u6559\u7a0b\uff1a\u4f7f\u7528Beautiful Soup\u722c\u53d6\u4e9a\u9a6c\u900a\u4ea7\u54c1\u4fe1\u606f\u4e0e\u4ef7\u683c","og_description":"\u672c\u6559\u7a0b\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u4f7f\u7528Python\u7684Beautiful Soup\u5e93\u722c\u53d6\u4e9a\u9a6c\u900a\u4ea7\u54c1\u4fe1\u606f\uff0c\u5305\u62ec\u4ef7\u683c\u3001\u8bc4\u8bba\u7b49\u6570\u636e\u3002\u901a\u8fc7\u5b9e\u4f8b\u4ee3\u7801\u548c\u5206\u6b65\u8bb2\u89e3\uff0c\u5373\u4f7f\u662f\u521d\u5b66\u8005\u4e5f\u80fd\u5feb\u901f\u638c\u63e1\u7f51\u7edc\u722c\u866b\u6280\u672f\uff0c\u8f7b\u677e\u83b7\u53d6\u6240\u9700\u7684\u7535\u5546\u6570\u636e\u3002","og_url":"https:\/\/www.silicloud.com\/zh\/blog\/\u5982\u4f55\u4f7f\u7528beautiful-soup\u722c\u53d6\u4e9a\u9a6c\u900a\u4ea7\u54c1\u4fe1\u606f\/","og_site_name":"Blog - Silicon Cloud","article_published_time":"2024-03-03T15:01:55+00:00","article_modified_time":"2025-08-02T13:38:07+00:00","og_image":[{"url":"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/65647613a4b2f92e6c72a7dc\/29-0.png"}],"author":"\u6587, \u7fd4","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"\u6587, \u7fd4","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"2 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8beautiful-soup%e7%88%ac%e5%8f%96%e4%ba%9a%e9%a9%ac%e9%80%8a%e4%ba%a7%e5%93%81%e4%bf%a1%e6%81%af\/","url":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8beautiful-soup%e7%88%ac%e5%8f%96%e4%ba%9a%e9%a9%ac%e9%80%8a%e4%ba%a7%e5%93%81%e4%bf%a1%e6%81%af\/","name":"Python\u5b9e\u6218\u6559\u7a0b\uff1a\u4f7f\u7528Beautiful Soup\u722c\u53d6\u4e9a\u9a6c\u900a\u4ea7\u54c1\u4fe1\u606f\u4e0e\u4ef7\u683c - Blog - Silicon Cloud","isPartOf":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#website"},"datePublished":"2024-03-03T15:01:55+00:00","dateModified":"2025-08-02T13:38:07+00:00","author":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/64d5cc7727fffbff2f9a2a8da1de3e5c"},"description":"\u672c\u6559\u7a0b\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u4f7f\u7528Python\u7684Beautiful Soup\u5e93\u722c\u53d6\u4e9a\u9a6c\u900a\u4ea7\u54c1\u4fe1\u606f\uff0c\u5305\u62ec\u4ef7\u683c\u3001\u8bc4\u8bba\u7b49\u6570\u636e\u3002\u901a\u8fc7\u5b9e\u4f8b\u4ee3\u7801\u548c\u5206\u6b65\u8bb2\u89e3\uff0c\u5373\u4f7f\u662f\u521d\u5b66\u8005\u4e5f\u80fd\u5feb\u901f\u638c\u63e1\u7f51\u7edc\u722c\u866b\u6280\u672f\uff0c\u8f7b\u677e\u83b7\u53d6\u6240\u9700\u7684\u7535\u5546\u6570\u636e\u3002","breadcrumb":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8beautiful-soup%e7%88%ac%e5%8f%96%e4%ba%9a%e9%a9%ac%e9%80%8a%e4%ba%a7%e5%93%81%e4%bf%a1%e6%81%af\/#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.silicloud.com\/zh\/blog\/%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8beautiful-soup%e7%88%ac%e5%8f%96%e4%ba%9a%e9%a9%ac%e9%80%8a%e4%ba%a7%e5%93%81%e4%bf%a1%e6%81%af\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8beautiful-soup%e7%88%ac%e5%8f%96%e4%ba%9a%e9%a9%ac%e9%80%8a%e4%ba%a7%e5%93%81%e4%bf%a1%e6%81%af\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.silicloud.com\/zh\/blog\/"},{"@type":"ListItem","position":2,"name":"Python\u5b9e\u6218\u6559\u7a0b\uff1a\u4f7f\u7528Beautiful Soup\u722c\u53d6\u4e9a\u9a6c\u900a\u4ea7\u54c1\u4fe1\u606f\u4e0e\u4ef7\u683c"}]},{"@type":"WebSite","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#website","url":"https:\/\/www.silicloud.com\/zh\/blog\/","name":"Blog - Silicon Cloud","description":"","inLanguage":"zh-Hans"},{"@type":"Person","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/64d5cc7727fffbff2f9a2a8da1de3e5c","name":"\u6587, \u7fd4","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/920c3d673e0bccacc98e5e6b7149bb3c22edd8d39cb753e5d7d7e471498118a1?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/920c3d673e0bccacc98e5e6b7149bb3c22edd8d39cb753e5d7d7e471498118a1?s=96&d=mm&r=g","caption":"\u6587, \u7fd4"},"url":"https:\/\/www.silicloud.com\/zh\/blog\/author\/wenxiang\/"},{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e5%a6%82%e4%bd%95%e4%bd%bf%e7%94%a8beautiful-soup%e7%88%ac%e5%8f%96%e4%ba%9a%e9%a9%ac%e9%80%8a%e4%ba%a7%e5%93%81%e4%bf%a1%e6%81%af\/#local-main-organization-logo","url":"","contentUrl":"","caption":"Blog - Silicon Cloud"}]}},"_links":{"self":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/592","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/comments?post=592"}],"version-history":[{"count":4,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/592\/revisions"}],"predecessor-version":[{"id":110324,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/592\/revisions\/110324"}],"wp:attachment":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/media?parent=592"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/categories?post=592"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/tags?post=592"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}