{"id":219753,"date":"2024-05-11T18:03:32","date_gmt":"2024-05-11T10:03:32","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/219753.html"},"modified":"2024-05-11T18:03:37","modified_gmt":"2024-05-11T10:03:37","slug":"go%e8%af%ad%e8%a8%80%e7%bd%91%e7%bb%9c%e5%86%85%e5%ae%b9%e7%88%ac%e8%99%ab%e5%a6%82%e4%bd%95%e5%86%99-2","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/219753.html","title":{"rendered":"go\u8bed\u8a00\u7f51\u7edc\u5185\u5bb9\u722c\u866b\u5982\u4f55\u5199"},"content":{"rendered":"<p style=\"text-align:center\"><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/25140159\/fd6e0106-3007-47c5-aaf2-3a5470b11688.webp\" alt=\"go\u8bed\u8a00\u7f51\u7edc\u5185\u5bb9\u722c\u866b\u5982\u4f55\u5199\" \/><\/p>\n<p><p>Go\u8bed\u8a00\u7f51\u7edc\u5185\u5bb9\u722c\u866b\u901a\u5e38\u6d89\u53ca\u4f7f\u7528<code>net\/http<\/code>\u5305\u6765\u53d1\u9001\u8bf7\u6c42\u3001<code>html<\/code>\u5305\u6765\u89e3\u6790HTML\u6587\u6863\u4ee5\u53ca\u4f7f\u7528<code>goquery<\/code>\u6216<code>colly<\/code>\u7b49\u7b2c\u4e09\u65b9\u5e93\u6765\u63d0\u9ad8\u5f00\u53d1\u6548\u7387\u3002<strong>\u6838\u5fc3\u8981\u70b9\u6db5\u76d6\u4e86\u81ea\u5b9a\u4e49HTTP\u8bf7\u6c42\u3001\u89e3\u6790\u6536\u5230\u7684\u5185\u5bb9\u3001\u5904\u7406\u7f51\u9875\u5143\u7d20\u4ee5\u53ca\u4fdd\u5b58\u6216\u8fdb\u4e00\u6b65\u5904\u7406\u6570\u636e<\/strong>\u3002\u5728\u8fd9\u91cc\uff0c\u4f1a\u91cd\u70b9\u63cf\u8ff0<strong>\u4f7f\u7528<code>colly<\/code>\u8fd9\u4e00\u7b2c\u4e09\u65b9\u5e93\u6765\u7b80\u5316\u722c\u866b\u5f00\u53d1<\/strong>\u7684\u65b9\u6cd5\u3002<\/p>\n<\/p>\n<p><p>\u4e00\u3001\u8bbe\u7f6eHTTP\u8bf7\u6c42<\/p>\n<\/p>\n<p><p>\u5728\u7f16\u5199Go\u8bed\u8a00\u722c\u866b\u65f6\uff0c\u9996\u5148\u9700\u8981\u8bbe\u7f6eHTTP\u8bf7\u6c42\u3002Go\u6807\u51c6\u5e93\u4e2d\u7684<code>net\/http<\/code>\u5305\u975e\u5e38\u9002\u5408\u8fdb\u884c\u8fd9\u4e00\u4efb\u52a1\u3002\u901a\u8fc7\u521b\u5efa\u4e00\u4e2a<code>http.Client<\/code>\u5bf9\u8c61\uff0c\u5f00\u53d1\u8005\u53ef\u4ee5\u53d1\u9001GET\u3001POST\u8bf7\u6c42\uff0c\u5e76\u63a5\u6536\u54cd\u5e94\u3002<\/p>\n<\/p>\n<p><p>\u9996\u5148\u9700\u8981\u5bfc\u5165<code>net\/http<\/code>\u5305\uff0c\u5e76\u521b\u5efa\u4e00\u4e2a\u5ba2\u6237\u7aef\u5b9e\u4f8b\u3002\u53ef\u4ee5\u901a\u8fc7<code>http.NewRequest<\/code>\u65b9\u6cd5\u6765\u6784\u9020\u8bf7\u6c42\uff0c\u5e76\u901a\u8fc7\u5ba2\u6237\u7aef\u7684<code>Do<\/code>\u65b9\u6cd5\u53d1\u9001\u3002\u53ef\u4ee5\u8bbe\u7f6e\u8bf7\u6c42\u5934\u4ee5\u6a21\u62df\u5e38\u89c1\u7684\u6d4f\u89c8\u5668\u884c\u4e3a\uff0c\u5305\u62ecUser-Agent\u3001Cookies\u7b49\uff0c\u4ee5\u9002\u5e94\u670d\u52a1\u5668\u7684\u4e0d\u540c\u8981\u6c42\u3002<\/p>\n<\/p>\n<p><p>\u4e8c\u3001\u89e3\u6790HTML\u6587\u6863<\/p>\n<\/p>\n<p><p>\u6536\u5230\u54cd\u5e94\u540e\uff0c\u63a5\u4e0b\u6765\u662f\u89e3\u6790HTML\u6587\u6863\u3002Go\u8bed\u8a00\u7684<code>html<\/code>\u5305\u53ef\u4ee5\u5bf9HTML\u8fdb\u884c\u8bcd\u6cd5\u89e3\u6790\uff0c\u4f46\u662f\u5904\u7406\u8d77\u6765\u8f83\u4e3a\u7e41\u7410\u3002\u56e0\u6b64\uff0c\u4f7f\u7528\u7b2c\u4e09\u65b9\u5e93\u5982<code>goquery<\/code>\u53ef\u4ee5\u5927\u5927\u7b80\u5316\u89e3\u6790\u8fc7\u7a0b\u3002<\/p>\n<\/p>\n<p><p><strong><code>goquery<\/code><\/strong> \u662f\u53d7jQuery\u542f\u53d1\u7684Go\u8bed\u8a00\u5e93\uff0c\u4f7fHTML\u6587\u6863\u7684\u904d\u5386\u548c\u64cd\u4f5c\u53d8\u5f97\u66f4\u4e3a\u7b80\u4fbf\u3002\u53ef\u4ee5\u901a\u8fc7\u9009\u62e9\u5668\u6765\u67e5\u627e\u9700\u8981\u7684\u5143\u7d20\uff0c\u5e76\u62bd\u53d6\u4fe1\u606f\u3002\u8fd9\u5bf9\u5904\u7406\u590d\u6742\u7684HTML\u7ed3\u6784\u65f6\u7279\u522b\u6709\u7528\u3002<\/p>\n<\/p>\n<p><p>\u4e09\u3001\u4f7f\u7528Colly\u6846\u67b6<\/p>\n<\/p>\n<p><p><strong><code>colly<\/code><\/strong> \u662f\u4e00\u4e2a\u5feb\u901f\u4e14\u529f\u80fd\u4e30\u5bcc\u7684Go\u8bed\u8a00\u722c\u866b\u6846\u67b6\uff0c\u5141\u8bb8\u5feb\u901f\u5f00\u53d1\u590d\u6742\u7684\u722c\u866b\u5e94\u7528\u3002\u5b83\u63d0\u4f9b\u4e86\u6613\u4e8e\u4f7f\u7528\u7684API\u6765\u5904\u7406\u591a\u79cd\u7c7b\u578b\u7684\u8bf7\u6c42\u3001\u9650\u5236\u3001\u5e76\u53d1\u4ee5\u53ca\u6570\u636e\u63d0\u53d6\u3002<\/p>\n<\/p>\n<p><p>\u4f7f\u7528<code>colly<\/code>\u5f00\u59cb\u4e00\u4e2a\u9879\u76ee\uff0c\u9996\u5148\u9700\u8981\u5b89\u88c5\u6b64\u5e93\uff0c\u5e76\u5728\u4ee3\u7801\u4e2d\u5bfc\u5165\u3002\u4e4b\u540e\uff0c\u521b\u5efa\u4e00\u4e2a\u65b0\u7684<code>colly.Collector<\/code>\u5b9e\u4f8b\u662f\u5f00\u59cb\u722c\u53d6\u5de5\u4f5c\u7684\u7b2c\u4e00\u6b65\u3002Collector\u5141\u8bb8\u8bbe\u7f6e\u4e0d\u540c\u7684\u914d\u7f6e\uff0c\u5982\u6700\u5927\u6df1\u5ea6\u3001\u5e76\u53d1\u91cf\u7b49\u3002<\/p>\n<\/p>\n<p><p>\u56db\u3001\u6267\u884c\u722c\u53d6\u4e0e\u6570\u636e\u62bd\u53d6<\/p>\n<\/p>\n<p><p>\u6267\u884c\u722c\u53d6\u5de5\u4f5c\u6d89\u53ca\u5230\u5177\u4f53\u7684URL\u8bbf\u95ee\u548c\u6570\u636e\u62bd\u53d6\u3002\u4f7f\u7528<code>colly<\/code>\u65f6\uff0c\u53ef\u4ee5\u4e3a\u7279\u5b9a\u57df\u540d\u6ce8\u518c\u4e8b\u4ef6\uff0c\u6bcf\u5f53\u8bbf\u95ee\u8be5\u57df\u540d\u7684\u9875\u9762\u65f6\u5c31\u4f1a\u89e6\u53d1\u8fd9\u4e9b\u4e8b\u4ef6\u3002<\/p>\n<\/p>\n<p><p>\u6570\u636e\u62bd\u53d6\u901a\u5e38\u662f\u901a\u8fc7\u9009\u62e9\u5668\u6765\u5b8c\u6210\u7684\u3002<code>colly<\/code>\u63d0\u4f9b\u7c7b\u4f3c\u4e8ejQuery\u7684\u9009\u62e9\u5668\uff0c\u53ef\u4ee5\u5f88\u65b9\u4fbf\u5730\u6293\u53d6\u5143\u7d20\u7684\u6587\u672c\u503c\u3001\u5c5e\u6027\u7b49\u3002\u9664\u4e86\u9759\u6001\u5185\u5bb9\uff0c<code>colly<\/code>\u8fd8\u652f\u6301\u5904\u7406JavaScript\u751f\u6210\u7684\u52a8\u6001\u5185\u5bb9\u3002<\/p>\n<\/p>\n<p><p>\u4e94\u3001\u722c\u866b\u7684\u4f18\u5316\u4e0e\u6269\u5c55<\/p>\n<\/p>\n<p><p>\u4e00\u4e2a\u57fa\u672c\u7684\u722c\u866b\u7f16\u5199\u5b8c\u6210\u540e\uff0c\u5e38\u5e38\u9700\u8981\u8fdb\u884c\u4f18\u5316\u548c\u6269\u5c55\u3002\u4f18\u5316\u53ef\u80fd\u5305\u62ec\u8bf7\u6c42\u901f\u5ea6\u7684\u63a7\u5236\u3001\u9519\u8bef\u5904\u7406\u3001\u91cd\u8bd5\u7b56\u7565\u7b49\u3002\u6269\u5c55\u5219\u53ef\u80fd\u5305\u62ec\u6dfb\u52a0\u4ee3\u7406\u652f\u6301\u3001\u5206\u5e03\u5f0f\u722c\u53d6\u7b49\u3002<\/p>\n<\/p>\n<p><p>\u5728\u7f16\u5199Go\u8bed\u8a00\u722c\u866b\u65f6\uff0c\u8981\u8003\u8651\u5982\u4f55\u6709\u6548\u5730\u7ba1\u7406\u8d44\u6e90\uff0c\u6bd4\u5982\u901a\u8fc7\u8bbe\u7f6e\u5408\u7406\u7684\u8d85\u65f6\u3001\u907f\u514d\u4e0d\u5fc5\u8981\u7684\u5185\u5b58\u5206\u914d\u7b49\u3002\u6b64\u5916\uff0c\u786e\u4fdd\u4ee3\u7801\u6613\u4e8e\u7ef4\u62a4\u548c\u6269\u5c55\u4e5f\u662f\u91cd\u8981\u7684\uff0c\u8fd9\u53ef\u80fd\u6d89\u53ca\u5230\u4ee3\u7801\u7ed3\u6784\u7684\u8c03\u6574\u3001\u6a21\u5757\u5316\u7f16\u7a0b\u7b49\u3002<\/p>\n<\/p>\n<p><p>\u516d\u3001\u9075\u5b88\u722c\u866b\u9053\u5fb7\u4e0e\u6cd5\u5f8b<\/p>\n<\/p>\n<p><p>\u5728\u722c\u866b\u7684\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u5c24\u5176\u662f\u5728\u5546\u4e1a\u9879\u76ee\u4e2d\uff0c\u5fc5\u987b\u8003\u8651\u9075\u5b88\u6cd5\u5f8b\u6cd5\u89c4\u4ee5\u53ca\u9053\u5fb7\u89c4\u8303\u3002\u8fd9\u901a\u5e38\u610f\u5473\u7740\u8981\u5c0a\u91cd\u7f51\u7ad9\u7684robots.txt\u89c4\u5219\u3001\u4e0d\u8fdb\u884c\u8fc7\u5ea6\u8bf7\u6c42\u4ee5\u53ca\u5408\u7406\u4f7f\u7528\u722c\u53d6\u5230\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n<p><p>\u722c\u866b\u53ef\u80fd\u88ab\u4e00\u4e9b\u7f51\u7ad9\u770b\u4f5c\u662f\u4e0d\u53d7\u6b22\u8fce\u7684\u8bbf\u5ba2\uff0c\u56e0\u6b64\uff0c\u7f16\u5199\u722c\u866b\u65f6\u8fd8\u9700\u8981\u8003\u8651\u5982\u4f55\u907f\u514d\u88ab\u7f51\u7ad9\u8bc6\u522b\u548c\u5c4f\u853d\u3002\u8fd9\u53ef\u80fd\u4f1a\u6d89\u53ca\u5230\u6a21\u4eff\u4eba\u7c7b\u7528\u6237\u884c\u4e3a\u3001\u52a8\u6001\u66f4\u6539\u8bf7\u6c42\u5934\u3001\u4f7f\u7528\u4ee3\u7406\u670d\u52a1\u5668\u7b49\u7b56\u7565\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p><strong>1. \u5982\u4f55\u7528Go\u8bed\u8a00\u7f16\u5199\u4e00\u4e2a\u7f51\u7edc\u5185\u5bb9\u722c\u866b\uff1f<\/strong><\/p>\n<p>\u7f16\u5199\u4e00\u4e2a\u7f51\u7edc\u5185\u5bb9\u722c\u866b\u53ef\u4ee5\u4f7f\u7528Go\u8bed\u8a00\u4e2d\u7684\u4e00\u4e9b\u5e93\u548c\u6a21\u5757\u6765\u5b8c\u6210\u3002\u9996\u5148\uff0c\u9700\u8981\u4f7f\u7528Go\u8bed\u8a00\u7684http\u5305\u6765\u53d1\u9001HTTP\u8bf7\u6c42\u5e76\u83b7\u53d6\u7f51\u9875\u7684\u5185\u5bb9\u3002\u5176\u6b21\uff0c\u53ef\u4ee5\u4f7f\u7528Go\u8bed\u8a00\u4e2d\u7684\u6b63\u5219\u8868\u8fbe\u5f0f\u6216\u8005\u7b2c\u4e09\u65b9\u5305\u6765\u89e3\u6790\u548c\u63d0\u53d6\u6240\u9700\u7684\u5185\u5bb9\u3002\u6700\u540e\uff0c\u53ef\u4ee5\u4f7f\u7528Go\u8bed\u8a00\u4e2d\u7684\u6587\u4ef6\u64cd\u4f5c\u6765\u5c06\u5185\u5bb9\u4fdd\u5b58\u5230\u672c\u5730\u6216\u8005\u8fdb\u884c\u5176\u4ed6\u5904\u7406\u3002<\/p>\n<p><strong>2. \u6709\u54ea\u4e9b\u5173\u952e\u6280\u5de7\u53ef\u4ee5\u63d0\u9ad8Go\u8bed\u8a00\u7f51\u7edc\u5185\u5bb9\u722c\u866b\u7684\u6548\u7387\uff1f<\/strong><\/p>\n<p>\u8981\u63d0\u9ad8Go\u8bed\u8a00\u7f51\u7edc\u5185\u5bb9\u722c\u866b\u7684\u6548\u7387\uff0c\u53ef\u4ee5\u91c7\u53d6\u4ee5\u4e0b\u5173\u952e\u6280\u5de7\uff1a\u9996\u5148\uff0c\u4f7f\u7528\u5e76\u53d1\u7684\u65b9\u5f0f\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u53ef\u4ee5\u4f7f\u7528Go\u8bed\u8a00\u4e2d\u7684goroutine\u548cchannel\u6765\u5b9e\u73b0\u3002\u5176\u6b21\uff0c\u9002\u5f53\u8bbe\u7f6e\u8d85\u65f6\u65f6\u95f4\uff0c\u4ee5\u514d\u963b\u585e\u6216\u957f\u65f6\u95f4\u7b49\u5f85\u54cd\u5e94\u3002\u6b64\u5916\uff0c\u53ef\u4ee5\u4f7f\u7528\u8fde\u63a5\u6c60\u6765\u63d0\u9ad8\u8fde\u63a5\u7684\u590d\u7528\u548c\u6027\u80fd\u3002\u6700\u540e\uff0c\u5408\u7406\u4f7f\u7528\u7f13\u5b58\uff0c\u907f\u514d\u91cd\u590d\u8bf7\u6c42\u76f8\u540c\u7684\u5185\u5bb9\u3002<\/p>\n<p><strong>3. \u5982\u4f55\u907f\u514d\u88ab\u7f51\u7ad9\u5c4f\u853d\u6216\u5c01\u7981\u7684\u98ce\u9669\uff0c\u4fdd\u62a4Go\u8bed\u8a00\u7f51\u7edc\u5185\u5bb9\u722c\u866b\u7684\u5408\u6cd5\u6027\uff1f<\/strong><\/p>\n<p>\u4e3a\u4e86\u4fdd\u62a4Go\u8bed\u8a00\u7f51\u7edc\u5185\u5bb9\u722c\u866b\u7684\u5408\u6cd5\u6027\uff0c\u9700\u8981\u9075\u5b88\u4e00\u4e9b\u89c4\u5219\u548c\u6ce8\u610f\u4e8b\u9879\u3002\u9996\u5148\uff0c\u5e94\u8be5\u5c0a\u91cd\u7f51\u7ad9\u7684robots.txt\u6587\u4ef6\uff0c\u4e0d\u722c\u53d6\u4e0d\u5141\u8bb8\u7684\u5185\u5bb9\u3002\u5176\u6b21\uff0c\u53ef\u4ee5\u9002\u5f53\u8bbe\u7f6e\u722c\u53d6\u901f\u5ea6\uff0c\u5e76\u4f7f\u7528\u5408\u7406\u7684User-Agent\u6765\u6a21\u62df\u771f\u5b9e\u7684\u6d4f\u89c8\u5668\u884c\u4e3a\u3002\u6b64\u5916\uff0c\u5e94\u8be5\u907f\u514d\u722c\u53d6\u654f\u611f\u4fe1\u606f\u548c\u5927\u91cf\u7684\u6570\u636e\uff0c\u4ee5\u514d\u5bf9\u7f51\u7ad9\u9020\u6210\u5f71\u54cd\u3002\u6700\u540e\uff0c\u53ef\u4ee5\u5728\u722c\u866b\u4ee3\u7801\u4e2d\u52a0\u5165\u9002\u5f53\u7684\u5ef6\u8fdf\uff0c\u4ee5\u514d\u5bf9\u76ee\u6807\u7f51\u7ad9\u7684\u670d\u52a1\u5668\u9020\u6210\u8fc7\u5927\u7684\u8d1f\u8f7d\u538b\u529b\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Go\u8bed\u8a00\u7f51\u7edc\u5185\u5bb9\u722c\u866b\u901a\u5e38\u6d89\u53ca\u4f7f\u7528net\/http\u5305\u6765\u53d1\u9001\u8bf7\u6c42\u3001html\u5305\u6765\u89e3\u6790HTML\u6587\u6863\u4ee5\u53ca\u4f7f\u7528goquer [&hellip;]","protected":false},"author":3,"featured_media":219761,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[37],"tags":[],"acf":[],"_links":{"self":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/219753"}],"collection":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/comments?post=219753"}],"version-history":[{"count":0,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/219753\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/219761"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=219753"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=219753"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=219753"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}