{"id":53767,"date":"2025-02-16T08:40:18","date_gmt":"2025-02-16T00:40:18","guid":{"rendered":"https:\/\/fwq.ai\/blog\/53767\/"},"modified":"2025-02-16T08:40:18","modified_gmt":"2025-02-16T00:40:18","slug":"crawl4ai%e6%95%b0%e6%8d%ae%e9%9b%86%e5%88%b6%e4%bd%9c%e5%bf%85%e5%a4%87%e7%88%ac%e8%99%ab%e5%ba%93","status":"publish","type":"post","link":"https:\/\/fwq.ai\/blog\/53767\/","title":{"rendered":"Crawl4AI\u6570\u636e\u96c6\u5236\u4f5c\u5fc5\u5907\u722c\u866b\u5e93"},"content":{"rendered":"<p>\u5728\u5f53\u4eca\u6570\u636e\u9a71\u52a8\u7684\u4e16\u754c\u4e2d\uff0c\u9ad8\u6548\u6536\u96c6\u548c\u5904\u7406\u4fe1\u606f\u7684\u80fd\u529b\u5bf9\u4e8e\u4eba\u5de5\u667a\u80fd (AI) \u5e94\u7528\u7a0b\u5e8f\u7684\u6210\u529f\u81f3\u5173\u91cd\u8981\u3002\u968f\u7740\u4eba\u5de5\u667a\u80fd\u7684\u4e0d\u65ad\u53d1\u5c55\uff0c\u5bf9\u7528\u4e8e\u8bad\u7ec3\u5927\u578b\u8bed\u8a00\u6a21\u578b (LLM) \u7684\u7ed3\u6784\u5316\u6570\u636e\u7684\u9700\u6c42\u4ece\u672a\u5982\u6b64\u9ad8\u6da8\u3002<\/p>\n<p>\u662f\u4e00\u4e2a\u521b\u65b0\u7684\u5f00\u6e90 Python \u5e93\uff0c\u65e8\u5728\u7b80\u5316\u7f51\u7edc\u722c\u866b\u548c\u6570\u636e\u63d0\u53d6\uff0c\u4f7f\u5176\u6210\u4e3a\u5f00\u53d1\u4eba\u5458\u548c\u4eba\u5de5\u667a\u80fd\u7231\u597d\u8005\u7684\u5fc5\u5907\u5de5\u5177\u3002\u672c\u535a\u5ba2\u5c06\u63a2\u8ba8 Crawl4AI \u7684\u7279\u6027\u3001\u529f\u80fd\u548c\u7528\u4f8b\uff0c\u91cd\u70b9\u4ecb\u7ecd\u5b83\u5982\u4f55\u5e2e\u52a9\u7528\u6237\u5229\u7528\u7f51\u7edc\u7684\u529b\u91cf\u8fdb\u884c\u4eba\u5de5\u667a\u80fd\u8bad\u7ec3\u3002<\/p>\n<h2>1\u3001Crawl4AI\u7b80\u4ecb<\/h2>\n<p>Crawl4AI \u662f\u4e00\u4e2a\u5f00\u6e90\u7f51\u7edc\u722c\u866b\u548c\u6293\u53d6\u6846\u67b6\uff0c\u65e8\u5728\u81ea\u52a8\u4ece\u7f51\u7ad9\u6536\u96c6\u6570\u636e\u3002\u5b83\u5141\u8bb8\u7528\u6237\u540c\u65f6\u6293\u53d6\u591a\u4e2a URL\uff0c\u4f7f\u5176\u6210\u4e3a\u9700\u8981\u5927\u89c4\u6a21\u6570\u636e\u6536\u96c6\u7684\u9879\u76ee\u7684\u7406\u60f3\u9009\u62e9\u3002\u51ed\u501f\u9488\u5bf9\u4eba\u5de5\u667a\u80fd\u5e94\u7528\u7a0b\u5e8f\u91cf\u8eab\u5b9a\u5236\u7684\u529f\u80fd\uff0cCrawl4AI \u7b80\u5316\u4e86\u5c06\u539f\u59cb\u7f51\u7edc\u6570\u636e\u8f6c\u6362\u4e3a\u7ed3\u6784\u5316\u683c\u5f0f\u7684\u8fc7\u7a0b\u3002<\/p>\n<p>Crawl4AI \u7684\u4e3b\u8981\u7279\u70b9\uff1a<\/p>\n<ul>\n<li>\u5f00\u6e90\u3002\u5176\u5f00\u6e90\u7279\u6027\u786e\u4fdd\u7528\u6237\u53ef\u4ee5\u5b8c\u5168\u8bbf\u95ee\u4ee3\u7801\uff0c\u4ece\u800c\u5b9e\u73b0\u81ea\u5b9a\u4e49\u548c\u53ef\u6269\u5c55\u6027\u3002\u6b64\u5916\uff0c\u5f3a\u5927\u7684\u793e\u533a\u652f\u6301\u548c\u4e30\u5bcc\u7684\u6587\u6863\u4f7f\u65b0\u7528\u6237\u66f4\u5bb9\u6613\u4e0a\u624b\u3002<\/li>\n<li>\u8d85\u5feb\u7684\u6027\u80fd\u3002Crawl4AI \u7684\u7a81\u51fa\u7279\u70b9\u4e4b\u4e00\u662f\u5176\u975e\u51e1\u7684\u901f\u5ea6\u3002\u8be5\u6846\u67b6\u7ecf\u8fc7\u4f18\u5316\uff0c\u6027\u80fd\u4f18\u4e8e\u8bb8\u591a\u4ed8\u8d39\u670d\u52a1\uff0c\u4f7f\u7528\u6237\u80fd\u591f\u5feb\u901f\u9ad8\u6548\u5730\u63d0\u53d6\u6570\u636e\u3002<\/li>\n<li>\u5f02\u6b65\u67b6\u6784\u3002\u652f\u6301\u5e76\u53d1\u6293\u53d6\u591a\u4e2a URL\uff0c\u5927\u5927\u51cf\u5c11\u4e86\u5927\u89c4\u6a21\u6570\u636e\u6536\u96c6\u6240\u9700\u7684\u65f6\u95f4\u3002<\/li>\n<li>LLM \u53cb\u597d\u7684\u8f93\u51fa\u683c\u5f0f\u3002\u652f\u6301\u5404\u79cd\u8f93\u51fa\u683c\u5f0f\uff0c\u5305\u62ec JSON\u3001\u6e05\u7406\u7684 HTML \u548c Markdown\uff0c\u786e\u4fdd\u8f7b\u677e\u96c6\u6210\u5230 AI \u6a21\u578b\u4e2d\u3002<\/li>\n<li>\u63d0\u53d6\u5e76\u8fd4\u56de\u6240\u6709\u5a92\u4f53\u6807\u7b7e\u3002\u4f7f\u7528 Crawl4AI\uff0c\u7528\u6237\u53ef\u4ee5\u63d0\u53d6\u5404\u79cd\u5a92\u4f53\u7c7b\u578b\uff0c\u5305\u62ec\u56fe\u50cf\u3001\u97f3\u9891\u548c\u89c6\u9891\u3002\u6b64\u529f\u80fd\u5bf9\u4e8e\u4f9d\u8d56\u591a\u5a92\u4f53\u5185\u5bb9\u7684\u5e94\u7528\u7a0b\u5e8f\uff08\u4f8b\u5982\u793e\u4ea4\u5a92\u4f53\u5206\u6790\u6216\u5185\u5bb9\u521b\u5efa\uff09\u7279\u522b\u6709\u7528\u3002<\/li>\n<li>JavaScript \u6267\u884c\u3002\u5141\u8bb8\u6293\u53d6\u52a8\u6001\u5185\u5bb9\uff0c\u786e\u4fdd\u5176\u4ed6\u6293\u53d6\u5de5\u5177\u53ef\u80fd\u9519\u8fc7\u7684\u5168\u9762\u6570\u636e\u6536\u96c6\u3002<\/li>\n<li>\u5404\u79cd\u5206\u5757\u7b56\u7565\u3002Crawl4AI \u652f\u6301\u591a\u79cd\u5206\u5757\u7b56\u7565\uff0c\u4f8b\u5982\u57fa\u4e8e\u4e3b\u9898\u3001\u6b63\u5219\u8868\u8fbe\u5f0f\u548c\u57fa\u4e8e\u53e5\u5b50\u7684\u5206\u5757\u3002\u8fd9\u79cd\u7075\u6d3b\u6027\u5141\u8bb8\u7528\u6237\u6839\u636e\u7279\u5b9a\u8981\u6c42\u5b9a\u5236\u6570\u636e\u63d0\u53d6\uff0c\u786e\u4fdd\u4e3a\u5404\u79cd\u5e94\u7528\u7a0b\u5e8f\u63d0\u4f9b\u6700\u4f73\u7ed3\u679c\u3002<\/li>\n<li> \u9ad8\u7ea7\u63d0\u53d6\u6280\u672f\u3002\u5229\u7528 XPath \u548c\u6b63\u5219\u8868\u8fbe\u5f0f\u7b49\u5f3a\u5927\u7684\u65b9\u6cd5\uff0c\u8ba9\u7528\u6237\u80fd\u591f\u4ece\u7f51\u9875\u4e2d\u7cbe\u786e\u5b9a\u4f4d\u6240\u9700\u7684\u6570\u636e\u3002<\/li>\n<li>\u5143\u6570\u636e\u63d0\u53d6\u3002\u6536\u96c6\u4e3b\u8981\u5185\u5bb9\u4ee5\u53ca\u5fc5\u8981\u7684\u5143\u6570\u636e\uff0c\u4e30\u5bcc AI \u8bad\u7ec3\u7684\u6570\u636e\u96c6\u3002<\/li>\n<li>\u81ea\u5b9a\u4e49\u94a9\u5b50\u548c\u7528\u6237\u4ee3\u7406\u652f\u6301\u3002\u7528\u6237\u53ef\u4ee5\u4e3a\u8eab\u4efd\u9a8c\u8bc1\u548c\u6807\u5934\u5b9a\u4e49\u81ea\u5b9a\u4e49\u94a9\u5b50\uff0c\u4ee5\u53ca\u4e3a HTTP \u8bf7\u6c42\u81ea\u5b9a\u4e49\u7528\u6237\u4ee3\u7406\uff0c\u4ece\u800c\u66f4\u597d\u5730\u63a7\u5236\u6293\u53d6\u8fc7\u7a0b\u3002<\/li>\n<li>\u9519\u8bef\u5904\u7406\u548c\u91cd\u8bd5\u673a\u5236\u3002\u7ed3\u5408\u5f3a\u5927\u7684\u9519\u8bef\u5904\u7406\u548c\u91cd\u8bd5\u7b56\u7565\uff0c\u5373\u4f7f\u9047\u5230\u7f51\u7edc\u95ee\u9898\u6216\u9875\u9762\u52a0\u8f7d\u5931\u8d25\u4e5f\u80fd\u786e\u4fdd\u6570\u636e\u5b8c\u6574\u6027\u3002<\/li>\n<li>\u901f\u7387\u9650\u5236\u548c\u8282\u6d41\u3002\u6709\u52a9\u4e8e\u907f\u514d\u76ee\u6807\u670d\u52a1\u5668\u4e0d\u582a\u91cd\u8d1f\uff0c\u5e76\u786e\u4fdd\u7b26\u5408\u7f51\u7edc\u6293\u53d6\u6700\u4f73\u5b9e\u8df5\u3002<\/li>\n<\/ul>\n<p>Crawl4AI \u4e0d\u4ec5\u4ec5\u662f\u4e00\u4e2a\u7f51\u7edc\u6293\u53d6\u5de5\u5177\uff1b\u5b83\u662f\u4e00\u4e2a\u7528\u4e8e\u9ad8\u7ea7\u5f02\u6b65\u7f51\u7edc\u6293\u53d6\u548c\u6570\u636e\u63d0\u53d6\u7684\u7efc\u5408\u89e3\u51b3\u65b9\u6848\uff0c\u4e13\u4e3a\u6ee1\u8db3\u5f00\u53d1\u4eba\u5458\u548c\u6570\u636e\u5206\u6790\u5e08\u7684\u9700\u6c42\u800c\u8bbe\u8ba1\u3002<\/p>\n<p>\u73b0\u5728\uff0c\u6211\u4eec\u5c06\u6df1\u5165\u7814\u7a76 Crawl4AI \u7684\u4e00\u4e9b\u6838\u5fc3\u7279\u6027\u548c\u529f\u80fd\uff0c\u5c55\u793a\u4ee3\u7801\u793a\u4f8b\u4ee5\u8bf4\u660e\u5982\u4f55\u5b9e\u73b0\u8fd9\u4e9b\u7279\u6027\u548c\u529f\u80fd\u4ee5\u4f18\u5316\u7f51\u7edc\u6570\u636e\u63d0\u53d6\u3002<\/p>\n<h2>2\u3001\u5b89\u88c5Crawl4AI<\/h2>\n<p>\u6709\u51e0\u79cd\u5b89\u88c5 Crawl4AI \u7684\u9009\u9879 &#8211; \u4f60\u53ef\u4ee5\u5c06\u5176\u5b89\u88c5\u4e3a Python \u5305\uff0c\u4f7f\u7528 Docker \u8bbe\u7f6e\u5b83\uff0c\u6216\u8005\u5728\u672c\u5730\u8fd0\u884c\u5b83\u3002\u4ee5\u4e0b\u662f Python \u5305\u5b89\u88c5\u6b65\u9aa4\uff1a<\/p>\n<pre><code># To install all available features\n!pip3 install \"crawl4ai[all]\"\n\n# After installation, download the necessary models for better performance:\n!crawl4ai-download-models\n\n# Lastly, install Playwright dependencies\n!playwright install <\/code><\/pre>\n<p>\u6709\u5173\u4e0d\u540c\u7684\u5b89\u88c5\u65b9\u6cd5\uff0c\u8bf7\u53c2\u9605 \u3002<\/p>\n<h2>3\u3001Crawl4AI\u57fa\u672c\u7528\u6cd5<\/h2>\n<p>\u8981\u5f00\u59cb\u4f7f\u7528 Crawl4AI\uff0c\u6211\u4eec\u9996\u5148\u9700\u8981\u521b\u5efa\u4e00\u4e2a <code>AsyncWebCrawler<\/code> \u5b9e\u4f8b\u3002\u8fd9\u662f\u6838\u5fc3\u7ec4\u4ef6\uff0c\u5b83\u5c06\u4f7f\u7528\u5f02\u6b65\u4e0a\u4e0b\u6587\u7ba1\u7406\u5668\u6709\u6548\u5730\u7ba1\u7406\u6293\u53d6\u751f\u547d\u5468\u671f\u3002\u9ed8\u8ba4\u60c5\u51b5\u4e0b\uff0c\u5b83\u5c06\u7f13\u5b58\u6293\u53d6\u7ed3\u679c\uff0c\u8fd9\u610f\u5473\u7740\u5bf9\u540c\u4e00 URL \u7684\u540e\u7eed\u6293\u53d6\u5c06\u66f4\u5feb\uff01\uff01<\/p>\n<pre><code>from crawl4ai import AsyncWebCrawler\nfrom crawl4ai.chunking_strategy import RegexChunking\n\nasync with AsyncWebCrawler(verbose=True) as crawler:\n    result = await crawler.arun(url=\"https:\/\/en.wikipedia.org\/wiki\/3_Idiots\", bypass_cache=False) \n    print(f\"Extracted content: {result.extracted_content}\")<\/code><\/pre>\n<p>  \u9ad8\u6267\u884c\u901f\u5ea6 <\/p>\n<p>\u5728\u4e0a\u9762\u7684\u4ee3\u7801\u7247\u6bb5\u4e2d\uff1a<\/p>\n<ul>\n<li><code>url<\/code>\uff1a\u6307\u5b9a\u8981\u6293\u53d6\u7684\u7f51\u9875\u3002<\/li>\n<li><code>bypass_cache<\/code>\uff1a\u662f\u5426\u5f3a\u5236\u8fdb\u884c\u5168\u65b0\u6293\u53d6<\/li>\n<\/ul>\n<p>\u63d0\u53d6\u7684\u5185\u5bb9\u6709\u591a\u79cd\u683c\u5f0f\uff0c\u5982 <code>markdown<\/code> \u548c <code>cleaned_html<\/code>\uff0c\u53ef\u6839\u636e\u4f60\u7684\u9700\u6c42\u63d0\u4f9b\u7075\u6d3b\u6027\u3002<\/p>\n<pre><code>print(result.markdown)\nprint(result.cleaned_html)<\/code><\/pre>\n<h2>4\u3001Crawl4AI\u622a\u5c4f<\/h2>\n<p>Crawl4AI\u8fd8\u5141\u8bb8\u4f60\u6355\u83b7\u6b63\u5728\u6293\u53d6\u7684\u9875\u9762\u7684\u5c4f\u5e55\u622a\u56fe\u3002<\/p>\n<pre><code>import base64\nfrom crawl4ai import AsyncWebCrawler\n\nasync with AsyncWebCrawler(verbose=True) as crawler:\n    result = await crawler.arun(url=\"https:\/\/www.cricbuzz.com\/\", screenshot=True)\n    with open(\"cricbuzz_screenshot.png\", \"wb\") as f:\n        f.write(base64.b64decode(result.screenshot))\n    print(\"Screenshot saved to 'screenshot.png'!\")<\/code><\/pre>\n<h2>5\u3001\u4e3aCrawl4AI\u6dfb\u52a0\u5206\u5757\u7b56\u7565<\/h2>\n<p>\u73b0\u5728\u6211\u4eec\u5c06\u6839\u636e\u7ed9\u5b9a\u7684\u6b63\u5219\u8868\u8fbe\u5f0f\u6a21\u5f0f\u62c6\u5206\u6587\u672c\u3002<\/p>\n<ul>\n<li><code>word_count_threshold<\/code>\uff1a\u8bbe\u7f6e\u6709\u610f\u4e49\u7684\u5185\u5bb9\u5757\u7684\u6700\u5c0f\u5b57\u6570\u3002<\/li>\n<li><code>chunking_strategy<\/code>\uff1a\u5b9a\u4e49\u7528\u4e8e\u62c6\u5206\u6587\u672c\u7684\u5206\u5757\u7b56\u7565<\/li>\n<\/ul>\n<pre><code>from crawl4ai import AsyncWebCrawler\nfrom crawl4ai.chunking_strategy import RegexChunking\n\nasync with AsyncWebCrawler(verbose=True) as crawler:\n    result = await crawler.arun(url=\"https:\/\/en.wikipedia.org\/wiki\/3_Idiots\", chunking_strategy=RegexChunking(patterns=[\"\\n\\n\"]), word_count_threshold=10) \n    print(f\"Extracted content: {result.extracted_content}\")<\/code><\/pre>\n<h2>6\u3001\u4e3aCrawl4AI\u6dfb\u52a0\u9ad8\u7ea7\u63d0\u53d6\u7b56\u7565<\/h2>\n<p>\u73b0\u5728\uff0c\u8ba9\u6211\u4eec\u5728\u722c\u53d6\u4e2d\u6dfb\u52a0\u4e00\u4e2a\u667a\u80fd\u63d0\u53d6\u7b56\u7565 \u2014 <code>JsonCssExtractionStrategy<\/code>\u3002<\/p>\n<p><code>JsonCssExtractionStrategy<\/code> \u901a\u8fc7\u5b9a\u4e49\u5177\u6709\u57fa\u672c\u9009\u62e9\u5668\u7684\u67b6\u6784\u6765\u5b9e\u73b0\u7cbe\u786e\u7684\u7ed3\u6784\u5316\u6570\u636e\u63d0\u53d6\uff0c\u8fd9\u4e9b\u9009\u62e9\u5668\u7528\u4e8e\u9875\u9762\u4e0a\u7684\u91cd\u590d\u5143\u7d20\u3002\u67b6\u6784\u4e2d\u7684\u6bcf\u4e2a\u5b57\u6bb5\u90fd\u6709\u81ea\u5df1\u7684\u9009\u62e9\u5668\uff0c\u5141\u8bb8\u63d0\u53d6\u5d4c\u5957\u7ed3\u6784\u6216\u5217\u8868\u3002\u6b64\u65b9\u6cd5\u975e\u5e38\u9002\u5408\u5c06 Web \u5185\u5bb9\uff08\u5982\u4ea7\u54c1\u5217\u8868\u3001\u6587\u7ae0\u6216\u641c\u7d22\u7ed3\u679c\uff09\u8f6c\u6362\u4e3a\u5e72\u51c0\u7684 JSON \u683c\u5f0f\uff0c\u4ece\u800c\u4e3a Web \u6570\u636e\u63d0\u53d6\u63d0\u4f9b\u7075\u6d3b\u6027\u548c\u51c6\u786e\u6027\u3002<\/p>\n<pre><code>from crawl4ai import AsyncWebCrawler\nfrom crawl4ai.extraction_strategy import JsonCssExtractionStrategy\nimport json\nimport nest_asyncio\nnest_asyncio.apply()\n\n\nasync def extract_news_teasers():\n    schema = {\n        \"name\": \"News Teaser Extractor\",\n        \"baseSelector\": \".wide-tease-item__wrapper\",\n        \"fields\": [\n            {\n                \"name\": \"category\",\n                \"selector\": \".unibrow span[data-testid='unibrow-text']\",\n                \"type\": \"text\",\n            },\n            {\n                \"name\": \"headline\",\n                \"selector\": \".wide-tease-item__headline\",\n                \"type\": \"text\",\n            },\n            {\n                \"name\": \"summary\",\n                \"selector\": \".wide-tease-item__description\",\n                \"type\": \"text\",\n            },\n            {\n                \"name\": \"time\",\n                \"selector\": \"[data-testid='wide-tease-date']\",\n                \"type\": \"text\",\n            },\n            {\n                \"name\": \"image\",\n                \"type\": \"nested\",\n                \"selector\": \"picture.teasePicture img\",\n                \"fields\": [\n                    {\"name\": \"src\", \"type\": \"attribute\", \"attribute\": \"src\"},\n                    {\"name\": \"alt\", \"type\": \"attribute\", \"attribute\": \"alt\"},\n                ],\n            },\n            {\n                \"name\": \"link\",\n                \"selector\": \"a[href]\",\n                \"type\": \"attribute\",\n                \"attribute\": \"href\",\n            },\n        ],\n    }\n\n    extraction_strategy = JsonCssExtractionStrategy(schema, verbose=True)\n\n    async with AsyncWebCrawler(verbose=True) as crawler:\n        result = await crawler.arun(\n            url=\"https:\/\/www.nbcnews.com\/business\",\n            extraction_strategy=extraction_strategy,\n            bypass_cache=True,\n        )\n\n        assert result.success, \"Failed to crawl the page\"\n\n        news_teasers = json.loads(result.extracted_content)\n        print(f\"Successfully extracted {len(news_teasers)} news teasers\")\n        print(json.dumps(news_teasers[0], indent=2))\n\nawait extract_news_teasers()<\/code><\/pre>\n<h2>7\u3001Crawl4AI\u57fa\u4e8e\u4f1a\u8bdd\u7684\u52a8\u6001\u5185\u5bb9\u6293\u53d6<\/h2>\n<p>Crawl4AI \u57fa\u4e8e\u4f1a\u8bdd\u7684\u6293\u53d6\u5728\u5904\u7406 GitHub \u7b49\u5e73\u53f0\u4e0a\u7684\u52a8\u6001\u5185\u5bb9\u65f6\u7279\u522b\u6709\u7528\u3002\u5728\u6b64\u793a\u4f8b\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528\u5b83\u6765\u63d0\u53d6\u591a\u4e2a\u9875\u9762\u7684\u63d0\u4ea4\u5386\u53f2\u8bb0\u5f55\uff0c\u5e76\u5229\u7528\u81ea\u5b9a\u4e49\u94a9\u5b50\u786e\u4fdd\u6b63\u786e\u52a0\u8f7d\u65b0\u5185\u5bb9\u3002<\/p>\n<pre><code>import asyncio\nimport re\nfrom bs4 import BeautifulSoup\nfrom crawl4ai import AsyncWebCrawler\n\nasync def crawl_linux_commits():\n    first_commit = \"\"\n    async def on_execution_started(page):\n        nonlocal first_commit \n        try:\n            while True:\n                await page.wait_for_selector('li.Box-sc-g0xbh4-0 h4')\n                commit = await page.query_selector('li.Box-sc-g0xbh4-0 h4')\n                commit = await commit.evaluate('(element) =&gt; element.textContent')\n                commit = re.sub(r'\\s+', '', commit)\n                if commit and commit != first_commit:\n                    first_commit = commit\n                    break\n                await asyncio.sleep(0.5)\n        except Exception as e:\n            print(f\"Warning: New content didn't appear after JavaScript execution: {e}\")\n\n    async with AsyncWebCrawler(verbose=True) as crawler:\n        crawler.crawler_strategy.set_hook('on_execution_started', on_execution_started)\n\n        url = \"https:\/\/github.com\/torvalds\/linux\/commits\/master\"\n        session_id = \"linux_commits_session\"\n        all_commits = []\n\n        js_next_page = \"\"\"\n        const button = document.querySelector('a[data-testid=\"pagination-next-button\"]');\n        if (button) button.click();\n        \"\"\"\n\n        for page in range(3):  # Crawl 3 pages\n            result = await crawler.arun(\n                url=url,\n                session_id=session_id,\n                css_selector=\"li.Box-sc-g0xbh4-0\",\n                js=js_next_page if page &gt; 0 else None,\n                bypass_cache=True,\n                js_only=page &gt; 0\n            )\n\n            assert result.success, f\"Failed to crawl page {page + 1}\"\n\n            soup = BeautifulSoup(result.cleaned_html, 'html.parser')\n            commits = soup.select(\"li\")\n            all_commits.extend(commits)\n\n            print(f\"Page {page + 1}: Found {len(commits)} commits\")\n\n        await crawler.crawler_strategy.kill_session(session_id)\n        print(f\"Successfully crawled {len(all_commits)} commits across 3 pages\")\n\nasyncio.run(crawl_linux_commits())<\/code><\/pre>\n<ul>\n<li>\u57fa\u4e8e\u4f1a\u8bdd\u7684\u6293\u53d6\uff1a\u6211\u4eec\u7ef4\u62a4\u4e00\u4e2a\u4f1a\u8bdd\u6765\u5904\u7406\u52a8\u6001\u5185\u5bb9\u5e76\u52a0\u8f7d\u65b0\u9875\u9762\u3002<\/li>\n<li>JavaScript \u6267\u884c\uff1a\u81ea\u5b9a\u4e49 JavaScript \u5355\u51fb GitHub \u63d0\u4ea4\u9875\u9762\u4e0a\u7684\u201c\u4e0b\u4e00\u6b65\u201d\u6309\u94ae\u4ee5\u52a0\u8f7d\u66f4\u591a\u63d0\u4ea4\u3002<\/li>\n<li>\u81ea\u5b9a\u4e49\u94a9\u5b50\uff1a <code>on_execution_started<\/code> \u94a9\u5b50\u786e\u4fdd\u5728\u7ee7\u7eed\u4e4b\u524d\u52a0\u8f7d\u65b0\u63d0\u4ea4\u3002<br \/>\u6b64\u6280\u672f\u5141\u8bb8\u60a8\u4ece\u52a8\u6001\u9875\u9762\u4e2d\u63d0\u53d6\u5185\u5bb9\uff0c\u540c\u65f6\u7ba1\u7406\u8de8\u591a\u4e2a\u8bf7\u6c42\u7684\u72b6\u6001\u3002<\/li>\n<\/ul>\n<p>\u6709\u5173\u66f4\u591a\u8be6\u7ec6\u4fe1\u606f\u548c\u9ad8\u7ea7\u7528\u6cd5\uff0c\u8bf7\u67e5\u770b\u3002<\/p>\n<h2>8\u3001Crawl4AI\u7684\u5b9e\u9645\u5e94\u7528<\/h2>\n<p>Crawl4AI \u9002\u7528\u4e8e\u5e7f\u6cdb\u7684\u5e94\u7528\uff0c\u5305\u62ec\uff1a<\/p>\n<ul>\n<li>\u8bad\u7ec3\u5927\u578b\u8bed\u8a00\u6a21\u578b\uff1aCrawl4AI \u6536\u96c6\u7684\u7ed3\u6784\u5316\u6570\u636e\u975e\u5e38\u9002\u5408\u8bad\u7ec3 LLM\uff0c\u6709\u52a9\u4e8e\u63d0\u9ad8\u5176\u5728\u5404\u79cd\u5e94\u7528\u7a0b\u5e8f\u4e2d\u7684\u6027\u80fd\u3002<\/li>\n<li>\u5e02\u573a\u7814\u7a76\uff1a\u4f01\u4e1a\u53ef\u4ee5\u5229\u7528 Crawl4AI \u4ece\u7ade\u4e89\u5bf9\u624b\u7684\u7f51\u7ad9\u3001\u65b0\u95fb\u6587\u7ae0\u548c\u793e\u4ea4\u5a92\u4f53\u4e2d\u6536\u96c6\u89c1\u89e3\uff0c\u4ece\u800c\u5b9e\u73b0\u6570\u636e\u9a71\u52a8\u7684\u51b3\u7b56\u3002<\/li>\n<li>\u5185\u5bb9\u805a\u5408\uff1a\u5185\u5bb9\u521b\u5efa\u8005\u53ef\u4ee5\u4f7f\u7528 Crawl4AI \u4ece\u591a\u4e2a\u6765\u6e90\u6536\u96c6\u548c\u6574\u7406\u4fe1\u606f\uff0c\u4ece\u800c\u7b80\u5316\u5185\u5bb9\u521b\u5efa\u8fc7\u7a0b\u3002<\/li>\n<li>\u5b66\u672f\u7814\u7a76\uff1a\u7814\u7a76\u4eba\u5458\u53ef\u4ee5\u81ea\u52a8\u4ece\u5b66\u672f\u51fa\u7248\u7269\u548c\u5728\u7ebf\u6570\u636e\u5e93\u6536\u96c6\u6570\u636e\uff0c\u4ece\u800c\u4fc3\u8fdb\u6587\u732e\u7efc\u8ff0\u548c\u6570\u636e\u5206\u6790\u3002<\/li>\n<li>\u60c5\u7eea\u5206\u6790\uff1a\u901a\u8fc7\u6293\u53d6\u8bc4\u8bba\u548c\u793e\u4ea4\u5a92\u4f53\u5e16\u5b50\uff0c\u7528\u6237\u53ef\u4ee5\u5206\u6790\u516c\u4f17\u5bf9\u4ea7\u54c1\u6216\u670d\u52a1\u7684\u60c5\u7eea\u3002<\/li>\n<li>\u5b9e\u65f6\u6570\u636e\u68c0\u7d22\uff1aRAG \u7cfb\u7edf\u53ef\u4ee5\u5229\u7528 Crawl4AI \u4ece\u7f51\u7edc\u4e0a\u83b7\u53d6\u6700\u65b0\u4fe1\u606f\uff0c\u4ece\u800c\u63d0\u9ad8 AI \u751f\u6210\u5185\u5bb9\u7684\u51c6\u786e\u6027\u3002<\/li>\n<li>\u52a8\u6001\u51fd\u6570\u8c03\u7528\uff1aAI \u4ee3\u7406\u53ef\u4ee5\u5229\u7528 Crawl4AI \u6839\u636e\u5b9e\u65f6\u6570\u636e\u6267\u884c\u51fd\u6570\u8c03\u7528\uff0c\u4ece\u800c\u5b9e\u73b0\u66f4\u5177\u4ea4\u4e92\u6027\u548c\u54cd\u5e94\u6027\u7684\u5e94\u7528\u7a0b\u5e8f\u3002<\/li>\n<\/ul>\n<h2>9\u3001\u7ed3\u675f\u8bed<\/h2>\n<p>\u968f\u7740\u6570\u636e\u5728\u5404\u4e2a\u884c\u4e1a\u7684\u51b3\u7b56\u8fc7\u7a0b\u4e2d\u53d8\u5f97\u8d8a\u6765\u8d8a\u4e0d\u53ef\u6216\u7f3a\uff0cCrawl4AI \u7b49\u5de5\u5177\u5bf9\u4e8e\u5229\u7528\u7f51\u7edc\u6570\u636e\u81f3\u5173\u91cd\u8981\u3002\u5176\u5f3a\u5927\u7684\u81ea\u52a8\u5316\u529f\u80fd\u4e0d\u4ec5\u53ef\u4ee5\u8282\u7701\u65f6\u95f4\uff0c\u8fd8\u53ef\u4ee5\u4e3a\u5206\u6790\u548c\u6d1e\u5bdf\u751f\u6210\u5f00\u8f9f\u65b0\u7684\u9014\u5f84\u3002 Crawl4AI \u662f\u4e00\u6b3e\u529f\u80fd\u5f3a\u5927\u4e14\u9ad8\u6548\u7684\u7f51\u9875\u6293\u53d6\u5de5\u5177\uff0c\u5177\u6709\u591a URL \u6293\u53d6\u3001\u5a92\u4f53\u63d0\u53d6\u548c\u9ad8\u7ea7\u8f93\u51fa\u683c\u5f0f\u7b49\u529f\u80fd\uff0c\u53ef\u6ee1\u8db3\u73b0\u4ee3\u6570\u636e\u6536\u96c6\u9700\u6c42\u3002\u65e0\u8bba\u60a8\u662f\u5f00\u53d1\u4eba\u5458\u3001\u7814\u7a76\u4eba\u5458\u8fd8\u662f\u4f01\u4e1a\u4e3b\uff0c\u5b83\u90fd\u80fd\u63d0\u4f9b\u5fc5\u8981\u7684\u8d44\u6e90\u6765\u7b80\u5316\u6570\u636e\u63d0\u53d6\u6d41\u7a0b\u5e76\u6700\u5927\u9650\u5ea6\u5730\u53d1\u6325\u6d1e\u5bdf\u7684\u4ef7\u503c\u3002<\/p>\n<hr>\n<p>\n","protected":false},"excerpt":{"rendered":"<p>\u5728\u5f53\u4eca\u6570\u636e\u9a71\u52a8\u7684\u4e16\u754c\u4e2d\uff0c\u9ad8\u6548\u6536\u96c6\u548c\u5904\u7406\u4fe1\u606f\u7684\u80fd\u529b\u5bf9\u4e8e\u4eba\u5de5\u667a\u80fd (AI) \u5e94\u7528\u7a0b\u5e8f\u7684\u6210\u529f\u81f3\u5173\u91cd\u8981\u3002\u968f\u7740\u4eba\u5de5\u667a\u80fd\u7684\u4e0d\u65ad\u53d1\u5c55\uff0c\u5bf9\u7528\u4e8e\u8bad\u7ec3\u5927\u578b\u8bed\u8a00\u6a21\u578b (LLM) \u7684\u7ed3\u6784\u5316\u6570\u636e\u7684\u9700\u6c42\u4ece\u672a\u5982\u6b64\u9ad8\u6da8\u3002 \u662f\u4e00\u4e2a\u521b\u65b0\u7684\u5f00\u6e90 Python \u5e93\uff0c\u65e8\u5728\u7b80\u5316\u7f51\u7edc\u722c\u866b\u548c\u6570\u636e\u63d0\u53d6\uff0c\u4f7f\u5176\u6210\u4e3a\u5f00\u53d1\u4eba\u5458\u548c\u4eba\u5de5\u667a\u80fd\u7231\u597d\u8005\u7684\u5fc5\u5907\u5de5\u5177\u3002\u672c\u535a\u5ba2\u5c06\u63a2\u8ba8 Crawl4AI \u7684\u7279\u6027\u3001\u529f\u80fd\u548c\u7528\u4f8b\uff0c\u91cd\u70b9\u4ecb\u7ecd\u5b83\u5982\u4f55\u5e2e\u52a9\u7528\u6237\u5229\u7528\u7f51\u7edc\u7684\u529b\u91cf\u8fdb\u884c\u4eba\u5de5\u667a\u80fd\u8bad\u7ec3\u3002 1\u3001Crawl4AI\u7b80\u4ecb Crawl4AI \u662f\u4e00\u4e2a\u5f00\u6e90\u7f51\u7edc\u722c\u866b\u548c\u6293\u53d6\u6846\u67b6\uff0c\u65e8\u5728\u81ea\u52a8\u4ece\u7f51\u7ad9\u6536\u96c6\u6570\u636e\u3002\u5b83\u5141\u8bb8\u7528\u6237\u540c\u65f6\u6293\u53d6\u591a\u4e2a URL\uff0c\u4f7f\u5176\u6210\u4e3a\u9700\u8981\u5927\u89c4\u6a21\u6570\u636e\u6536\u96c6\u7684\u9879\u76ee\u7684\u7406\u60f3\u9009\u62e9\u3002\u51ed\u501f\u9488\u5bf9\u4eba\u5de5\u667a\u80fd\u5e94\u7528\u7a0b\u5e8f\u91cf\u8eab\u5b9a\u5236\u7684\u529f\u80fd\uff0cCrawl4AI \u7b80\u5316\u4e86\u5c06\u539f\u59cb\u7f51\u7edc\u6570\u636e\u8f6c\u6362\u4e3a\u7ed3\u6784\u5316\u683c\u5f0f\u7684\u8fc7\u7a0b\u3002 Crawl4AI \u7684\u4e3b\u8981\u7279\u70b9\uff1a \u5f00\u6e90\u3002\u5176\u5f00\u6e90\u7279\u6027\u786e\u4fdd\u7528\u6237\u53ef\u4ee5\u5b8c\u5168\u8bbf\u95ee\u4ee3\u7801\uff0c\u4ece\u800c\u5b9e\u73b0\u81ea\u5b9a\u4e49\u548c\u53ef\u6269\u5c55\u6027\u3002\u6b64\u5916\uff0c\u5f3a\u5927\u7684\u793e\u533a\u652f\u6301\u548c\u4e30\u5bcc\u7684\u6587\u6863\u4f7f\u65b0\u7528\u6237\u66f4\u5bb9\u6613\u4e0a\u624b\u3002 \u8d85\u5feb\u7684\u6027\u80fd\u3002Crawl4AI \u7684\u7a81\u51fa\u7279\u70b9\u4e4b\u4e00\u662f\u5176\u975e\u51e1\u7684\u901f\u5ea6\u3002\u8be5\u6846\u67b6\u7ecf\u8fc7\u4f18\u5316\uff0c\u6027\u80fd\u4f18\u4e8e\u8bb8\u591a\u4ed8\u8d39\u670d\u52a1\uff0c\u4f7f\u7528\u6237\u80fd\u591f\u5feb\u901f\u9ad8\u6548\u5730\u63d0\u53d6\u6570\u636e\u3002 \u5f02\u6b65\u67b6\u6784\u3002\u652f\u6301\u5e76\u53d1\u6293\u53d6\u591a\u4e2a URL\uff0c\u5927\u5927\u51cf\u5c11\u4e86\u5927\u89c4\u6a21\u6570\u636e\u6536\u96c6\u6240\u9700\u7684\u65f6\u95f4\u3002 LLM \u53cb\u597d\u7684\u8f93\u51fa\u683c\u5f0f\u3002\u652f\u6301\u5404\u79cd\u8f93\u51fa\u683c\u5f0f\uff0c\u5305\u62ec JSON\u3001\u6e05\u7406\u7684 HTML \u548c Markdown\uff0c\u786e\u4fdd\u8f7b\u677e\u96c6\u6210\u5230 AI \u6a21\u578b\u4e2d\u3002 \u63d0\u53d6\u5e76\u8fd4\u56de\u6240\u6709\u5a92\u4f53\u6807\u7b7e\u3002\u4f7f\u7528 Crawl4AI\uff0c\u7528\u6237\u53ef\u4ee5\u63d0\u53d6\u5404\u79cd\u5a92\u4f53\u7c7b\u578b\uff0c\u5305\u62ec\u56fe\u50cf\u3001\u97f3\u9891\u548c\u89c6\u9891\u3002\u6b64\u529f\u80fd\u5bf9\u4e8e\u4f9d\u8d56\u591a\u5a92\u4f53\u5185\u5bb9\u7684\u5e94\u7528\u7a0b\u5e8f\uff08\u4f8b\u5982\u793e\u4ea4\u5a92\u4f53\u5206\u6790\u6216\u5185\u5bb9\u521b\u5efa\uff09\u7279\u522b\u6709\u7528\u3002 JavaScript \u6267\u884c\u3002\u5141\u8bb8\u6293\u53d6\u52a8\u6001\u5185\u5bb9\uff0c\u786e\u4fdd\u5176\u4ed6\u6293\u53d6\u5de5\u5177\u53ef\u80fd\u9519\u8fc7\u7684\u5168\u9762\u6570\u636e\u6536\u96c6\u3002 \u5404\u79cd\u5206\u5757\u7b56\u7565\u3002Crawl4AI \u652f\u6301\u591a\u79cd\u5206\u5757\u7b56\u7565\uff0c\u4f8b\u5982\u57fa\u4e8e\u4e3b\u9898\u3001\u6b63\u5219\u8868\u8fbe\u5f0f\u548c\u57fa\u4e8e\u53e5\u5b50\u7684\u5206\u5757\u3002\u8fd9\u79cd\u7075\u6d3b\u6027\u5141\u8bb8\u7528\u6237\u6839\u636e\u7279\u5b9a\u8981\u6c42\u5b9a\u5236\u6570\u636e\u63d0\u53d6\uff0c\u786e\u4fdd\u4e3a\u5404\u79cd\u5e94\u7528\u7a0b\u5e8f\u63d0\u4f9b\u6700\u4f73\u7ed3\u679c\u3002 \u9ad8\u7ea7\u63d0\u53d6\u6280\u672f\u3002\u5229\u7528 XPath \u548c\u6b63\u5219\u8868\u8fbe\u5f0f\u7b49\u5f3a\u5927\u7684\u65b9\u6cd5\uff0c\u8ba9\u7528\u6237\u80fd\u591f\u4ece\u7f51\u9875\u4e2d\u7cbe\u786e\u5b9a\u4f4d\u6240\u9700\u7684\u6570\u636e\u3002 \u5143\u6570\u636e\u63d0\u53d6\u3002\u6536\u96c6\u4e3b\u8981\u5185\u5bb9\u4ee5\u53ca\u5fc5\u8981\u7684\u5143\u6570\u636e\uff0c\u4e30\u5bcc AI \u8bad\u7ec3\u7684\u6570\u636e\u96c6\u3002 \u81ea\u5b9a\u4e49\u94a9\u5b50\u548c\u7528\u6237\u4ee3\u7406\u652f\u6301\u3002\u7528\u6237\u53ef\u4ee5\u4e3a\u8eab\u4efd\u9a8c\u8bc1\u548c\u6807\u5934\u5b9a\u4e49\u81ea\u5b9a\u4e49\u94a9\u5b50\uff0c\u4ee5\u53ca\u4e3a HTTP \u8bf7\u6c42\u81ea\u5b9a\u4e49\u7528\u6237\u4ee3\u7406\uff0c\u4ece\u800c\u66f4\u597d\u5730\u63a7\u5236\u6293\u53d6\u8fc7\u7a0b\u3002 \u9519\u8bef\u5904\u7406\u548c\u91cd\u8bd5\u673a\u5236\u3002\u7ed3\u5408\u5f3a\u5927\u7684\u9519\u8bef\u5904\u7406\u548c\u91cd\u8bd5\u7b56\u7565\uff0c\u5373\u4f7f\u9047\u5230\u7f51\u7edc\u95ee\u9898\u6216\u9875\u9762\u52a0\u8f7d\u5931\u8d25\u4e5f\u80fd\u786e\u4fdd\u6570\u636e\u5b8c\u6574\u6027\u3002 \u901f\u7387\u9650\u5236\u548c\u8282\u6d41\u3002\u6709\u52a9\u4e8e\u907f\u514d\u76ee\u6807\u670d\u52a1\u5668\u4e0d\u582a\u91cd\u8d1f\uff0c\u5e76\u786e\u4fdd\u7b26\u5408\u7f51\u7edc\u6293\u53d6\u6700\u4f73\u5b9e\u8df5\u3002 Crawl4AI \u4e0d\u4ec5\u4ec5\u662f\u4e00\u4e2a\u7f51\u7edc\u6293\u53d6\u5de5\u5177\uff1b\u5b83\u662f\u4e00\u4e2a\u7528\u4e8e\u9ad8\u7ea7\u5f02\u6b65\u7f51\u7edc\u6293\u53d6\u548c\u6570\u636e\u63d0\u53d6\u7684\u7efc\u5408\u89e3\u51b3\u65b9\u6848\uff0c\u4e13\u4e3a\u6ee1\u8db3\u5f00\u53d1\u4eba\u5458\u548c\u6570\u636e\u5206\u6790\u5e08\u7684\u9700\u6c42\u800c\u8bbe\u8ba1\u3002 \u73b0\u5728\uff0c\u6211\u4eec\u5c06\u6df1\u5165\u7814\u7a76 Crawl4AI \u7684\u4e00\u4e9b\u6838\u5fc3\u7279\u6027\u548c\u529f\u80fd\uff0c\u5c55\u793a\u4ee3\u7801\u793a\u4f8b\u4ee5\u8bf4\u660e\u5982\u4f55\u5b9e\u73b0\u8fd9\u4e9b\u7279\u6027\u548c\u529f\u80fd\u4ee5\u4f18\u5316\u7f51\u7edc\u6570\u636e\u63d0\u53d6\u3002 2\u3001\u5b89\u88c5Crawl4AI \u6709\u51e0\u79cd\u5b89\u88c5 Crawl4AI [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[13],"tags":[],"class_list":["post-53767","post","type-post","status-publish","format-standard","hentry","category-ai"],"_links":{"self":[{"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/posts\/53767","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/comments?post=53767"}],"version-history":[{"count":0,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/posts\/53767\/revisions"}],"wp:attachment":[{"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/media?parent=53767"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/categories?post=53767"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/tags?post=53767"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}