{"id":7047,"date":"2024-10-11T14:07:20","date_gmt":"2024-10-11T06:07:20","guid":{"rendered":"https:\/\/www.aisharenet.com\/?p=7047"},"modified":"2024-11-09T22:27:00","modified_gmt":"2024-11-09T14:27:00","slug":"crawl4ai","status":"publish","type":"post","link":"https:\/\/www.kdjingpai.com\/pt\/crawl4ai\/","title":{"rendered":"Crawl4AI\uff1a\u5f00\u6e90\u7684\u5f02\u6b65\u7f51\u9875\u722c\u866b\u5de5\u5177\uff0c\u65e0\u9700LLM\u63d0\u53d6\u7ed3\u6784\u5316\u6570\u636e"},"content":{"rendered":"<p>Crawl4AI \u662f\u4e00\u4e2a\u5f00\u6e90\u7684\u5f02\u6b65\u7f51\u9875\u722c\u866b\u5de5\u5177\uff0c\u4e13\u4e3a\u5927\u578b\u8bed\u8a00\u6a21\u578b\uff08LLMs\uff09\u548c\u4eba\u5de5\u667a\u80fd\uff08AI\uff09\u5e94\u7528\u8bbe\u8ba1\u3002\u5b83\u7b80\u5316\u4e86\u7f51\u7edc\u722c\u866b\u548c\u6570\u636e\u63d0\u53d6\u6d41\u7a0b\uff0c\u652f\u6301\u9ad8\u6548\u7684\u7f51\u9875\u722c\u53d6\uff0c\u5e76\u63d0\u4f9b\u5bf9 LLM \u53cb\u597d\u7684\u8f93\u51fa\u683c\u5f0f\uff0c\u5982 JSON\u3001\u6e05\u7406\u8fc7\u7684 HTML \u548c Markdown\u3002Crawl4AI \u652f\u6301\u540c\u65f6\u722c\u53d6\u591a\u4e2a URL\uff0c\u5b8c\u5168\u514d\u8d39\u4e14\u5f00\u6e90\uff0c\u9002\u5408\u5404\u79cd\u6570\u636e\u6293\u53d6\u9700\u6c42\u3002<\/p>\n<p><a href=\"https:\/\/crawl4ai.com\/mkdocs\/\">\u5b98\u65b9\u5e2e\u52a9\u6587\u6863<\/a><\/p>\n<p><a href=\"https:\/\/colab.research.google.com\/drive\/1REChY6fXQf-EaVYLv0eHEWvzlYxGm0pd?usp=sharing\">\u5728\u7ebf\u4f53\u9a8c<\/a><\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-13135\" src=\"https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2024\/10\/1df36102919b678.png\" alt=\"\" width=\"800\" height=\"450\" srcset=\"https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2024\/10\/1df36102919b678.png 800w, https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2024\/10\/1df36102919b678-300x169.png 300w, https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2024\/10\/1df36102919b678-768x432.png 768w, https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2024\/10\/1df36102919b678-18x10.png 18w\" sizes=\"auto, (max-width: 800px) 100vw, 800px\" \/><\/p>\n<p>&nbsp;<\/p>\n<h2>\u529f\u80fd\u5217\u8868<\/h2>\n<ul>\n<li>\u5f02\u6b65\u67b6\u6784\uff1a\u9ad8\u6548\u5904\u7406\u591a\u4e2a\u7f51\u9875\uff0c\u5feb\u901f\u6293\u53d6\u6570\u636e<\/li>\n<li>\u591a\u79cd\u8f93\u51fa\u683c\u5f0f\uff1a\u652f\u6301 JSON\u3001HTML\u3001Markdown<\/li>\n<li>\u591a URL \u722c\u53d6\uff1a\u540c\u65f6\u722c\u53d6\u591a\u4e2a\u7f51\u9875<\/li>\n<li>\u5a92\u4f53\u6807\u7b7e\u63d0\u53d6\uff1a\u63d0\u53d6\u56fe\u7247\u3001\u97f3\u9891\u548c\u89c6\u9891\u6807\u7b7e<\/li>\n<li>\u94fe\u63a5\u63d0\u53d6\uff1a\u63d0\u53d6\u6240\u6709\u5916\u90e8\u548c\u5185\u90e8\u94fe\u63a5<\/li>\n<li>\u5143\u6570\u636e\u63d0\u53d6\uff1a\u4ece\u9875\u9762\u4e2d\u63d0\u53d6\u5143\u6570\u636e<\/li>\n<li>\u81ea\u5b9a\u4e49\u94a9\u5b50\uff1a\u652f\u6301\u8eab\u4efd\u9a8c\u8bc1\u3001\u8bf7\u6c42\u5934\u548c\u9875\u9762\u4fee\u6539<\/li>\n<li>\u7528\u6237\u4ee3\u7406\u5b9a\u5236\uff1a\u81ea\u5b9a\u4e49\u7528\u6237\u4ee3\u7406<\/li>\n<li>\u9875\u9762\u622a\u56fe\uff1a\u6293\u53d6\u9875\u9762\u622a\u56fe<\/li>\n<li>\u6267\u884c\u81ea\u5b9a\u4e49 JavaScript\uff1a\u5728\u722c\u53d6\u524d\u6267\u884c\u591a\u4e2a\u81ea\u5b9a\u4e49 JavaScript<\/li>\n<li>\u4ee3\u7406\u652f\u6301\uff1a\u589e\u5f3a\u9690\u79c1\u548c\u8bbf\u95ee<\/li>\n<li>\u4f1a\u8bdd\u7ba1\u7406\uff1a\u5904\u7406\u590d\u6742\u7684\u591a\u9875\u9762\u722c\u53d6\u573a\u666f<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<h2>\u4f7f\u7528\u5e2e\u52a9<\/h2>\n<h3>\u5b89\u88c5\u6d41\u7a0b<\/h3>\n<p>Crawl4AI \u63d0\u4f9b\u7075\u6d3b\u7684\u5b89\u88c5\u9009\u9879\uff0c\u9002\u7528\u4e8e\u5404\u79cd\u4f7f\u7528\u573a\u666f\u3002\u60a8\u53ef\u4ee5\u5c06\u5176\u4f5c\u4e3a Python \u5305\u5b89\u88c5\u6216\u4f7f\u7528 Docker\u3002<\/p>\n<h4>\u4f7f\u7528 pip \u5b89\u88c5<\/h4>\n<ol>\n<li>\u57fa\u672c\u5b89\u88c5\n<pre><code class=\"language-bash\">pip install crawl4ai\r\n<\/code><\/pre>\n<p>\u8fd9\u5c06\u9ed8\u8ba4\u5b89\u88c5 Crawl4AI \u7684\u5f02\u6b65\u7248\u672c\uff0c\u4f7f\u7528 Playwright \u8fdb\u884c\u7f51\u9875\u722c\u53d6\u3002<\/li>\n<li>\u624b\u52a8\u5b89\u88c5 Playwright\uff08\u5982\u679c\u9700\u8981\uff09\n<pre><code class=\"language-bash\">playwright install\r\n<\/code><\/pre>\n<p>\u6216\u8005<\/p>\n<pre><code class=\"language-bash\">python -m playwright install chromium\r\n<\/code><\/pre>\n<\/li>\n<\/ol>\n<h4>\u4f7f\u7528 Docker \u5b89\u88c5<\/h4>\n<ol>\n<li>\u62c9\u53d6 Docker \u955c\u50cf\n<pre><code class=\"language-bash\">docker pull unclecode\/crawl4ai\r\n<\/code><\/pre>\n<\/li>\n<li>\u8fd0\u884c Docker \u5bb9\u5668\n<pre><code class=\"language-bash\">docker run -it unclecode\/crawl4ai\r\n<\/code><\/pre>\n<\/li>\n<\/ol>\n<h3>\u4f7f\u7528\u6307\u5357<\/h3>\n<ol>\n<li><strong>\u57fa\u672c\u4f7f\u7528<\/strong>\n<pre><code class=\"language-python\"><span class=\"hljs-keyword\">from<\/span> crawl4ai <span class=\"hljs-keyword\">import<\/span> AsyncWebCrawler\r\n\r\ncrawler = AsyncWebCrawler()\r\nresults = crawler.crawl([<span class=\"hljs-string\">\"https:\/\/example.com\"<\/span>])\r\n<span class=\"hljs-built_in\">print<\/span>(results)\r\n<\/code><\/pre>\n<\/li>\n<li><strong>\u81ea\u5b9a\u4e49\u8bbe\u7f6e<\/strong>\n<pre><code class=\"language-python\"><span class=\"hljs-keyword\">from<\/span> crawl4ai <span class=\"hljs-keyword\">import<\/span> AsyncWebCrawler\r\n\r\ncrawler = AsyncWebCrawler(\r\n    user_agent=<span class=\"hljs-string\">\"CustomUserAgent\"<\/span>,\r\n    headers={<span class=\"hljs-string\">\"Authorization\"<\/span>: <span class=\"hljs-string\">\"Bearer <a href=\"https:\/\/www.kdjingpai.com\/en\/tokenization\/\">token<\/a>\"<\/span>},\r\n    custom_js=[<span class=\"hljs-string\">\"console.log('Hello, world!')\"<\/span>]\r\n)\r\nresults = crawler.crawl([<span class=\"hljs-string\">\"https:\/\/example.com\"<\/span>])\r\n<span class=\"hljs-built_in\">print<\/span>(results)\r\n<\/code><\/pre>\n<\/li>\n<li><strong>\u63d0\u53d6\u7279\u5b9a\u6570\u636e<\/strong>\n<pre><code class=\"language-python\"><span class=\"hljs-keyword\">from<\/span> crawl4ai <span class=\"hljs-keyword\">import<\/span> AsyncWebCrawler\r\n\r\ncrawler = AsyncWebCrawler()\r\nresults = crawler.crawl([<span class=\"hljs-string\">\"https:\/\/example.com\"<\/span>], extract_media=<span class=\"hljs-literal\">True<\/span>, extract_links=<span class=\"hljs-literal\">True<\/span>)\r\n<span class=\"hljs-built_in\">print<\/span>(results)\r\n<\/code><\/pre>\n<\/li>\n<li><strong>\u4f1a\u8bdd\u7ba1\u7406<\/strong>\n<pre><code class=\"language-python\"><span class=\"hljs-keyword\">from<\/span> crawl4ai <span class=\"hljs-keyword\">import<\/span> AsyncWebCrawler\r\n\r\ncrawler = AsyncWebCrawler()\r\nsession = crawler.create_session()\r\nsession_results = session.crawl([<span class=\"hljs-string\">\"https:\/\/example.com\"<\/span>])\r\n<span class=\"hljs-built_in\">print<\/span>(session_results)\r\n<\/code><\/pre>\n<\/li>\n<\/ol>\n<p>Crawl4AI \u63d0\u4f9b\u4e86\u4e30\u5bcc\u7684\u529f\u80fd\u548c\u7075\u6d3b\u7684\u914d\u7f6e\u9009\u9879\uff0c\u9002\u7528\u4e8e\u5404\u79cd\u7f51\u9875\u722c\u53d6\u548c\u6570\u636e\u6293\u53d6\u9700\u6c42\u3002\u901a\u8fc7\u8be6\u7ec6\u7684\u5b89\u88c5\u548c\u4f7f\u7528\u6307\u5357\uff0c\u7528\u6237\u53ef\u4ee5\u8f7b\u677e\u4e0a\u624b\u5e76\u5145\u5206\u5229\u7528\u8be5\u5de5\u5177\u7684\u5f3a\u5927\u529f\u80fd\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Crawl4AI \u662f\u4e00\u4e2a\u5f00\u6e90\u7684\u5f02\u6b65\u7f51\u9875\u722c\u866b\u5de5\u5177\uff0c\u4e13\u4e3a\u5927\u578b\u8bed\u8a00\u6a21\u578b\uff08LLMs\uff09\u548c\u4eba\u5de5\u667a\u80fd\uff08AI\uff09\u5e94\u7528\u8bbe\u8ba1\u3002\u5b83\u7b80\u5316\u4e86\u7f51\u7edc\u722c\u866b\u548c\u6570\u636e\u63d0\u53d6\u6d41\u7a0b\uff0c\u652f\u6301\u9ad8\u6548\u7684\u7f51\u9875\u722c\u53d6\uff0c\u5e76\u63d0\u4f9b\u5bf9 LLM \u53cb\u597d\u7684\u8f93\u51fa\u683c\u5f0f\uff0c\u5982 JSON\u3001\u6e05\u7406\u8fc7\u7684 HTML \u548c Markdo&#8230;<\/p>\n","protected":false},"author":1,"featured_media":61091,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[230],"class_list":["post-7047","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-tool","tag-aikaiyuanxiangmu"],"_links":{"self":[{"href":"https:\/\/www.kdjingpai.com\/pt\/wp-json\/wp\/v2\/posts\/7047","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.kdjingpai.com\/pt\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.kdjingpai.com\/pt\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/pt\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/pt\/wp-json\/wp\/v2\/comments?post=7047"}],"version-history":[{"count":0,"href":"https:\/\/www.kdjingpai.com\/pt\/wp-json\/wp\/v2\/posts\/7047\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/pt\/wp-json\/wp\/v2\/media\/61091"}],"wp:attachment":[{"href":"https:\/\/www.kdjingpai.com\/pt\/wp-json\/wp\/v2\/media?parent=7047"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.kdjingpai.com\/pt\/wp-json\/wp\/v2\/categories?post=7047"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.kdjingpai.com\/pt\/wp-json\/wp\/v2\/tags?post=7047"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}