{"id":5560,"date":"2025-03-29T23:33:10","date_gmt":"2025-03-29T15:33:10","guid":{"rendered":"https:\/\/www.aisharenet.com\/?p=5560"},"modified":"2025-08-25T00:03:10","modified_gmt":"2025-08-24T16:03:10","slug":"gpt-crawler","status":"publish","type":"post","link":"https:\/\/www.kdjingpai.com\/en\/gpt-crawler\/","title":{"rendered":"GPT-Crawler\uff1a\u81ea\u52a8\u722c\u53d6\u7f51\u7ad9\u5185\u5bb9\u751f\u6210\u77e5\u8bc6\u5e93\u6587\u4ef6"},"content":{"rendered":"<p>GPT-Crawler \u662f\u7531 BuilderIO \u56e2\u961f\u5f00\u53d1\u7684\u4e00\u4e2a\u5f00\u6e90\u5de5\u5177\uff0c\u6258\u7ba1\u5728 GitHub \u4e0a\u3002\u5b83\u901a\u8fc7\u8f93\u5165\u4e00\u4e2a\u6216\u591a\u4e2a\u7f51\u7ad9 URL\uff0c\u722c\u53d6\u9875\u9762\u5185\u5bb9\uff0c\u751f\u6210\u7ed3\u6784\u5316\u7684\u77e5\u8bc6\u6587\u4ef6\uff08<code>output.json<\/code>\uff09\uff0c\u7528\u4e8e\u521b\u5efa\u81ea\u5b9a\u4e49 GPT \u6216 AI \u52a9\u624b\u3002\u7528\u6237\u53ef\u4ee5\u914d\u7f6e\u722c\u53d6\u89c4\u5219\uff0c\u6bd4\u5982\u6307\u5b9a\u8d77\u59cb URL \u548c\u5185\u5bb9\u9009\u62e9\u5668\uff0c\u5de5\u5177\u4f1a\u81ea\u52a8\u63d0\u53d6\u6587\u672c\u5e76\u6574\u7406\u6210\u6587\u4ef6\u3002\u8fd9\u4e2a\u5de5\u5177\u7b80\u5355\u6613\u7528\uff0c\u652f\u6301\u672c\u5730\u8fd0\u884c\u3001Docker \u5bb9\u5668\u90e8\u7f72\u548c API \u8c03\u7528\uff0c\u9002\u5408\u5f00\u53d1\u8005\u5feb\u901f\u4ece\u7f51\u7ad9\u5185\u5bb9\u6784\u5efa\u4e13\u5c5e AI \u52a9\u624b\u3002\u622a\u81f3\u76ee\u524d\uff0c\u5b83\u5728\u6280\u672f\u793e\u533a\u4e2d\u53d7\u5230\u5173\u6ce8\uff0c\u56e0\u5176\u9ad8\u6548\u6027\u548c\u5f00\u6e90\u7279\u6027\u5e7f\u53d7\u6b22\u8fce\u3002<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"\" title=\"GPT Crawler\uff1a\u4ece\u7f51\u7ad9\u6293\u53d6\u77e5\u8bc6\u6587\u4ef6\uff0c\u521b\u5efa\u5b9a\u5236GPTs-1\" src=\"https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2024\/08\/9893e7723745627.jpg\" alt=\"GPT Crawler\uff1a\u4ece\u7f51\u7ad9\u6293\u53d6\u77e5\u8bc6\u6587\u4ef6\uff0c\u521b\u5efa\u5b9a\u5236GPTs-1\" width=\"776\" height=\"493\" \/><\/p>\n<p>&nbsp;<\/p>\n<h2>\u529f\u80fd\u5217\u8868<\/h2>\n<ul>\n<li>\u4ece\u4e00\u4e2a\u6216\u591a\u4e2a URL \u722c\u53d6\u7f51\u7ad9\u5185\u5bb9\uff0c\u751f\u6210\u00a0<code>output.json<\/code>\u00a0\u6587\u4ef6\u3002<\/li>\n<li>\u652f\u6301\u81ea\u5b9a\u4e49\u722c\u53d6\u89c4\u5219\uff0c\u5305\u62ec\u8d77\u59cb URL\u3001\u94fe\u63a5\u5339\u914d\u6a21\u5f0f\u548c CSS \u9009\u62e9\u5668\u3002<\/li>\n<li>\u80fd\u5904\u7406\u52a8\u6001\u7f51\u9875\uff0c\u4f7f\u7528\u65e0\u5934\u6d4f\u89c8\u5668\u6293\u53d6\u5ba2\u6237\u7aef\u6e32\u67d3\u5185\u5bb9\u3002<\/li>\n<li>\u63d0\u4f9b API \u63a5\u53e3\uff0c\u901a\u8fc7 POST \u8bf7\u6c42\u542f\u52a8\u722c\u53d6\u4efb\u52a1\u3002<\/li>\n<li>\u652f\u6301\u8bbe\u7f6e\u6700\u5927\u9875\u9762\u6570\uff08<code>maxPagesToCrawl<\/code>\uff09\u3001\u6587\u4ef6\u5927\u5c0f\uff08<code>maxFileSize<\/code>\uff09\u548c\u4ee4\u724c\u6570\uff08<code>maxTokens<\/code>\uff09\u3002<\/li>\n<li>\u751f\u6210\u7684\u6587\u4ef6\u53ef\u76f4\u63a5\u4e0a\u4f20\u5230 OpenAI\uff0c\u7528\u4e8e\u521b\u5efa\u81ea\u5b9a\u4e49 GPT \u6216 AI \u52a9\u624b\u3002<\/li>\n<li>\u652f\u6301 Docker \u5bb9\u5668\u8fd0\u884c\uff0c\u65b9\u4fbf\u5728\u4e0d\u540c\u73af\u5883\u4e2d\u90e8\u7f72\u3002<\/li>\n<li>\u53ef\u6392\u9664\u7279\u5b9a\u8d44\u6e90\u7c7b\u578b\uff08\u5982\u56fe\u7247\u3001\u89c6\u9891\u7b49\uff09\uff0c\u4f18\u5316\u722c\u53d6\u6548\u7387\u3002<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<h2>\u4f7f\u7528\u5e2e\u52a9<\/h2>\n<h3>\u5b89\u88c5\u4e0e\u8fd0\u884c\uff08\u672c\u5730\u65b9\u5f0f\uff09<\/h3>\n<p>GPT-Crawler \u57fa\u4e8e Node.js \u5f00\u53d1\uff0c\u9700\u8981\u5b89\u88c5\u76f8\u5173\u73af\u5883\u624d\u80fd\u8fd0\u884c\u3002\u4ee5\u4e0b\u662f\u8be6\u7ec6\u6b65\u9aa4\uff1a<\/p>\n<ol>\n<li><strong>\u68c0\u67e5\u73af\u5883<\/strong><br \/>\n\u786e\u4fdd\u7535\u8111\u5df2\u5b89\u88c5 Node.js\uff08\u7248\u672c 16 \u6216\u66f4\u9ad8\uff09\u548c npm\u3002\u8fd0\u884c\u4ee5\u4e0b\u547d\u4ee4\u786e\u8ba4\uff1a<\/li>\n<\/ol>\n<pre><code>node -v\r\nnpm -v\r\n<\/code><\/pre>\n<p>\u5982\u679c\u6ca1\u6709\uff0c\u8bf7\u4ece\u00a0Node.js \u5b98\u7f51\u00a0\u4e0b\u8f7d\u5b89\u88c5\u3002<\/p>\n<ol start=\"2\">\n<li><strong>\u514b\u9686\u9879\u76ee<\/strong><br \/>\n\u5728\u7ec8\u7aef\u8f93\u5165\u547d\u4ee4\uff0c\u5c06\u9879\u76ee\u4e0b\u8f7d\u5230\u672c\u5730\uff1a<\/li>\n<\/ol>\n<pre><code>git clone https:\/\/github.com\/BuilderIO\/gpt-crawler.git\r\n<\/code><\/pre>\n<ol start=\"3\">\n<li><strong>\u8fdb\u5165\u76ee\u5f55<\/strong><br \/>\n\u4e0b\u8f7d\u5b8c\u6210\u540e\uff0c\u8fdb\u5165\u9879\u76ee\u6587\u4ef6\u5939\uff1a<\/li>\n<\/ol>\n<pre><code>cd gpt-crawler\r\n<\/code><\/pre>\n<ol start=\"4\">\n<li><strong>\u5b89\u88c5\u4f9d\u8d56<\/strong><br \/>\n\u8fd0\u884c\u4ee5\u4e0b\u547d\u4ee4\u5b89\u88c5\u6240\u9700\u8f6f\u4ef6\u5305\uff1a<\/li>\n<\/ol>\n<pre><code>npm install\r\n<\/code><\/pre>\n<ol start=\"5\">\n<li><strong>\u914d\u7f6e\u722c\u866b<\/strong><br \/>\n\u6253\u5f00\u00a0<code>config.ts<\/code>\u00a0\u6587\u4ef6\uff0c\u4fee\u6539\u722c\u53d6\u53c2\u6570\u3002\u4f8b\u5982\uff0c\u722c\u53d6 Builder.io \u6587\u6863\uff1a<\/li>\n<\/ol>\n<pre><code>export const defaultConfig: Config = {\r\nurl: \"https:\/\/www.builder.io\/c\/docs\/developers\",\r\nmatch: \"https:\/\/www.builder.io\/c\/docs\/**\",\r\nselector: \".docs-builder-container\",\r\nmaxPagesToCrawl: 50,\r\noutputFileName: \"output.json\"\r\n};\r\n<\/code><\/pre>\n<ul>\n<li><code>url<\/code>\uff1a\u8d77\u59cb\u722c\u53d6\u5730\u5740\u3002<\/li>\n<li><code>match<\/code>\uff1a\u94fe\u63a5\u5339\u914d\u6a21\u5f0f\uff0c\u652f\u6301\u901a\u914d\u7b26\u3002<\/li>\n<li><code>selector<\/code>\uff1a\u63d0\u53d6\u5185\u5bb9\u7684 CSS \u9009\u62e9\u5668\u3002<\/li>\n<li><code>maxPagesToCrawl<\/code>\uff1a\u6700\u5927\u722c\u53d6\u9875\u9762\u6570\u3002<\/li>\n<li><code>outputFileName<\/code>\uff1a\u8f93\u51fa\u6587\u4ef6\u540d\u3002<\/li>\n<\/ul>\n<ol start=\"6\">\n<li><strong>\u8fd0\u884c\u722c\u866b<\/strong><br \/>\n\u914d\u7f6e\u5b8c\u6210\u540e\uff0c\u8fd0\u884c\u4ee5\u4e0b\u547d\u4ee4\u542f\u52a8\u722c\u53d6\uff1a<\/li>\n<\/ol>\n<pre><code>npm start\r\n<\/code><\/pre>\n<p>\u5b8c\u6210\u540e\uff0c<code>output.json<\/code>\u00a0\u6587\u4ef6\u4f1a\u751f\u6210\u5728\u9879\u76ee\u6839\u76ee\u5f55\u3002<\/p>\n<h3>\u66ff\u4ee3\u8fd0\u884c\u65b9\u5f0f<\/h3>\n<h4>\u4f7f\u7528 Docker \u5bb9\u5668<\/h4>\n<ol>\n<li>\u786e\u4fdd\u5df2\u5b89\u88c5 Docker\uff08\u4ece\u00a0Docker \u5b98\u7f51\u00a0\u4e0b\u8f7d\uff09\u3002<\/li>\n<li>\u8fdb\u5165\u00a0<code>containerapp<\/code>\u00a0\u6587\u4ef6\u5939\uff0c\u7f16\u8f91\u00a0<code>config.ts<\/code>\u3002<\/li>\n<li>\u8fd0\u884c\u4ee5\u4e0b\u547d\u4ee4\u6784\u5efa\u5e76\u542f\u52a8\u5bb9\u5668\uff1a<\/li>\n<\/ol>\n<pre><code>docker build -t gpt-crawler .\r\ndocker run -v $(pwd)\/data:\/app\/data gpt-crawler\r\n<\/code><\/pre>\n<ol start=\"4\">\n<li>\u8f93\u51fa\u6587\u4ef6\u4f1a\u751f\u6210\u5728\u00a0<code>data<\/code>\u00a0\u6587\u4ef6\u5939\u4e2d\u3002<\/li>\n<\/ol>\n<h4>\u4f7f\u7528 API \u8fd0\u884c<\/h4>\n<ol>\n<li>\u5b89\u88c5\u4f9d\u8d56\u540e\uff0c\u542f\u52a8 API \u670d\u52a1\uff1a<\/li>\n<\/ol>\n<pre><code>npm run start:server\r\n<\/code><\/pre>\n<ol start=\"2\">\n<li>\u670d\u52a1\u9ed8\u8ba4\u8fd0\u884c\u5728\u00a0<code>http:\/\/localhost:3000<\/code>\u3002<\/li>\n<li>\u53d1\u9001 POST \u8bf7\u6c42\u5230\u00a0<code>\/crawl<\/code>\uff0c\u793a\u4f8b\uff1a<\/li>\n<\/ol>\n<pre><code>curl -X POST http:\/\/localhost:3000\/crawl -H \"Content-Type: application\/json\" -d '{\"url\":\"https:\/\/example.com\",\"match\":\"https:\/\/example.com\/**\",\"selector\":\"body\",\"maxPagesToCrawl\":10,\"outputFileName\":\"output.json\"}'\r\n<\/code><\/pre>\n<ol start=\"4\">\n<li>\u53ef\u8bbf\u95ee\u00a0<code>\/api-docs<\/code>\u00a0\u67e5\u770b API \u6587\u6863\uff08\u57fa\u4e8e Swagger\uff09\u3002<\/li>\n<\/ol>\n<h3>\u4e0a\u4f20\u5230 OpenAI<\/h3>\n<ol>\n<li><strong>\u521b\u5efa\u81ea\u5b9a\u4e49 GPT<\/strong><\/li>\n<\/ol>\n<ul>\n<li>\u6253\u5f00\u00a0ChatGPT\u3002<\/li>\n<li>\u70b9\u51fb\u5de6\u4e0b\u89d2\u59d3\u540d\uff0c\u9009\u62e9\u201cMy GPTs\u201d\u3002<\/li>\n<li>\u70b9\u51fb\u201cCreate a GPT\u201d &gt; \u201cConfigure\u201d &gt; \u201cKnowledge\u201d\u3002<\/li>\n<li>\u4e0a\u4f20\u00a0<code>output.json<\/code>\u00a0\u6587\u4ef6\u3002<\/li>\n<li>\u5982\u679c\u6587\u4ef6\u8fc7\u5927\uff0c\u53ef\u5728\u00a0<code>config.ts<\/code>\u00a0\u8bbe\u7f6e\u00a0<code>maxFileSize<\/code>\u00a0\u6216\u00a0<code>maxTokens<\/code>\u00a0\u62c6\u5206\u6587\u4ef6\u3002<\/li>\n<\/ul>\n<ol start=\"2\">\n<li><strong>\u521b\u5efa\u81ea\u5b9a\u4e49\u52a9\u624b<\/strong><\/li>\n<\/ol>\n<ul>\n<li>\u6253\u5f00\u00a0OpenAI \u5e73\u53f0\u3002<\/li>\n<li>\u70b9\u51fb\u201c+ Create\u201d &gt; \u201cUpload\u201d\u3002<\/li>\n<li>\u4e0a\u4f20\u00a0<code>output.json<\/code>\u00a0\u6587\u4ef6\u3002<\/li>\n<\/ul>\n<h3>\u529f\u80fd\u64cd\u4f5c\u8be6\u89e3<\/h3>\n<ul>\n<li><strong>\u722c\u53d6\u5185\u5bb9<\/strong><br \/>\n\u6307\u5b9a\u00a0<code>url<\/code>\u00a0\u548c\u00a0<code>selector<\/code>\u00a0\u540e\uff0c\u5de5\u5177\u4f1a\u63d0\u53d6\u9875\u9762\u6587\u672c\u3002\u6bd4\u5982\uff0c<code>.docs-builder-container<\/code>\u00a0\u53ea\u6293\u53d6\u8be5\u533a\u57df\u5185\u5bb9\u3002<\/li>\n<li><strong>\u751f\u6210\u6587\u4ef6<\/strong><br \/>\n\u8f93\u51fa\u6587\u4ef6\u683c\u5f0f\u4e3a\uff1a<\/li>\n<\/ul>\n<pre><code>[{\"title\": \"\u9875\u9762\u6807\u9898\", \"url\": \"https:\/\/example.com\/page\", \"html\": \"\u63d0\u53d6\u7684\u6587\u672c\"}, ...]\r\n<\/code><\/pre>\n<ul>\n<li><strong>\u4f18\u5316\u8f93\u51fa<\/strong><br \/>\n\u4f7f\u7528\u00a0<code>resourceExclusions<\/code>\u00a0\u6392\u9664\u65e0\u5173\u8d44\u6e90\uff08\u5982\u00a0<code>png<\/code>\u3001<code>jpg<\/code>\uff09\uff0c\u51cf\u5c11\u6587\u4ef6\u4f53\u79ef\u3002<\/li>\n<\/ul>\n<h3>\u6ce8\u610f\u4e8b\u9879<\/h3>\n<ul>\n<li>\u9700\u8981 OpenAI \u4ed8\u8d39\u8d26\u6237\u624d\u80fd\u521b\u5efa\u81ea\u5b9a\u4e49 GPT\u3002<\/li>\n<li>\u52a8\u6001\u7f51\u9875\u722c\u53d6\u4f9d\u8d56\u65e0\u5934\u6d4f\u89c8\u5668\uff0c\u786e\u4fdd\u4f9d\u8d56\u5b8c\u6574\u3002<\/li>\n<li>\u6587\u4ef6\u8fc7\u5927\u65f6\uff0c\u53ef\u8c03\u6574\u914d\u7f6e\u62c6\u5206\u4e0a\u4f20\u3002<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<h2>\u5e94\u7528\u573a\u666f<\/h2>\n<ol>\n<li><strong>\u6280\u672f\u652f\u6301\u52a9\u624b<\/strong><br \/>\n\u722c\u53d6\u4ea7\u54c1\u6587\u6863\u7f51\u7ad9\uff0c\u751f\u6210 AI \u52a9\u624b\uff0c\u5e2e\u52a9\u7528\u6237\u89e3\u7b54\u6280\u672f\u95ee\u9898\u3002<\/li>\n<li><strong>\u5185\u5bb9\u6574\u7406\u5de5\u5177<\/strong><br \/>\n\u4ece\u535a\u5ba2\u6216\u65b0\u95fb\u7f51\u7ad9\u6293\u53d6\u6587\u7ae0\uff0c\u5236\u4f5c\u77e5\u8bc6\u5e93\u6216\u95ee\u7b54\u52a9\u624b\u3002<\/li>\n<li><strong>\u6559\u80b2\u57f9\u8bad\u52a9\u624b<\/strong><br \/>\n\u722c\u53d6\u5728\u7ebf\u8bfe\u7a0b\u9875\u9762\uff0c\u751f\u6210\u5b66\u4e60\u52a9\u624b\uff0c\u63d0\u4f9b\u8bfe\u7a0b\u76f8\u5173\u89e3\u7b54\u3002<\/li>\n<\/ol>\n<p>&nbsp;<\/p>\n<h2>QA<\/h2>\n<ol>\n<li><strong>\u53ef\u4ee5\u722c\u53d6\u591a\u4e2a\u7f51\u7ad9\u5417\uff1f<\/strong><br \/>\n\u53ef\u4ee5\u3002\u5728\u00a0<code>config.ts<\/code>\u00a0\u4e2d\u8bbe\u7f6e\u591a\u4e2a URL \u548c\u5339\u914d\u89c4\u5219\u5373\u53ef\u3002<\/li>\n<li><strong>\u6587\u4ef6\u592a\u5927\u65e0\u6cd5\u4e0a\u4f20\u600e\u4e48\u529e\uff1f<\/strong><br \/>\n\u8bbe\u7f6e\u00a0<code>maxFileSize<\/code>\u00a0\u6216\u00a0<code>maxTokens<\/code>\uff0c\u5c06\u6587\u4ef6\u62c6\u5206\u4e3a\u591a\u4e2a\u5c0f\u6587\u4ef6\u3002<\/li>\n<li><strong>\u652f\u6301\u4e2d\u6587\u7f51\u7ad9\u5417\uff1f<\/strong><br \/>\n\u652f\u6301\u3002\u53ea\u8981\u7f51\u7ad9\u5185\u5bb9\u53ef\u88ab\u65e0\u5934\u6d4f\u89c8\u5668\u89e3\u6790\uff0c\u5c31\u80fd\u6b63\u5e38\u722c\u53d6\u3002<\/li>\n<\/ol>\n","protected":false},"excerpt":{"rendered":"<p>GPT-Crawler \u662f\u7531 BuilderIO \u56e2\u961f\u5f00\u53d1\u7684\u4e00\u4e2a\u5f00\u6e90\u5de5\u5177\uff0c\u6258\u7ba1\u5728 GitHub \u4e0a\u3002\u5b83\u901a\u8fc7\u8f93\u5165\u4e00\u4e2a\u6216\u591a\u4e2a\u7f51\u7ad9 URL\uff0c\u722c\u53d6\u9875\u9762\u5185\u5bb9\uff0c\u751f\u6210\u7ed3\u6784\u5316\u7684\u77e5\u8bc6\u6587\u4ef6\uff08output.json\uff09\uff0c\u7528\u4e8e\u521b\u5efa\u81ea\u5b9a\u4e49 GPT \u6216 AI \u52a9\u624b\u3002\u7528\u6237&#8230;<\/p>\n","protected":false},"author":1,"featured_media":32782,"comment_status":"open","ping_status":"closed","sticky":true,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20,499],"tags":[230,252],"class_list":["post-5560","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-tool","category-document-extraction","tag-aikaiyuanxiangmu","tag-markdown"],"_links":{"self":[{"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/posts\/5560","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/comments?post=5560"}],"version-history":[{"count":0,"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/posts\/5560\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/media\/32782"}],"wp:attachment":[{"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/media?parent=5560"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/categories?post=5560"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.kdjingpai.com\/en\/wp-json\/wp\/v2\/tags?post=5560"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}