{"id":202052,"date":"2025-05-10T14:24:51","date_gmt":"2025-05-10T06:24:51","guid":{"rendered":"https:\/\/server.hk\/cnblog\/202052\/"},"modified":"2025-05-10T14:24:51","modified_gmt":"2025-05-10T06:24:51","slug":"%e5%88%a9%e7%94%a8redis%e5%92%8cjavascript%e6%9e%84%e5%bb%ba%e7%ae%80%e5%8d%95%e7%9a%84%e7%bd%91%e7%bb%9c%e7%88%ac%e8%99%ab%ef%bc%9a%e5%a6%82%e4%bd%95%e5%bf%ab%e9%80%9f%e6%8a%93%e5%8f%96%e6%95%b0","status":"publish","type":"post","link":"https:\/\/server.hk\/cnblog\/202052\/","title":{"rendered":"\u5229\u7528Redis\u548cJavaScript\u6784\u5efa\u7b80\u5355\u7684\u7f51\u7edc\u722c\u866b\uff1a\u5982\u4f55\u5feb\u901f\u6293\u53d6\u6570\u636e"},"content":{"rendered":"<p><b><\/b> <\/p>\n<h1>\u5229\u7528Redis\u548cJavaScript\u6784\u5efa\u7b80\u5355\u7684\u7f51\u7edc\u722c\u866b\uff1a\u5982\u4f55\u5feb\u901f\u6293\u53d6\u6570\u636e<\/h1>\n<p>\u5b66\u4e60<span style=\"color: #FF6600;, Helvetica, Arial, sans-serif;font-size: 14px;background-color: #FFFFFF\">\u6570\u636e\u5e93<\/span>\u8981\u52aa\u529b\uff0c\u4f46\u662f\u4e0d\u8981\u6025\uff01\u4eca\u5929\u7684\u8fd9\u7bc7\u6587\u7ae0<span style=\"color: #FF6600;, Helvetica, Arial, sans-serif;font-size: 14px;background-color: #FFFFFF\">\u300a\u5229\u7528Redis\u548cJavaScript\u6784\u5efa\u7b80\u5355\u7684\u7f51\u7edc\u722c\u866b\uff1a\u5982\u4f55\u5feb\u901f\u6293\u53d6\u6570\u636e\u300b<\/span>\u5c06\u4f1a\u4ecb\u7ecd\u5230<span style=\"color: #FF6600;, Helvetica, Arial, sans-serif;font-size: 14px;background-color: #FFFFFF\"><\/span>\u7b49\u7b49\u77e5\u8bc6\u70b9\uff0c\u5982\u679c\u4f60\u60f3\u6df1\u5165\u5b66\u4e60<span style=\"color: #FF6600;, Helvetica, Arial, sans-serif;font-size: 14px;background-color: #FFFFFF\">\u6570\u636e\u5e93<\/span>\uff0c\u53ef\u4ee5\u5173\u6ce8\u6211\uff01\u6211\u4f1a\u6301\u7eed\u66f4\u65b0\u76f8\u5173\u6587\u7ae0\u7684\uff0c\u5e0c\u671b\u5bf9\u5927\u5bb6\u90fd\u80fd\u6709\u6240\u5e2e\u52a9\uff01<\/p>\n<p>\u5229\u7528Redis\u548cJavaScript\u6784\u5efa\u7b80\u5355\u7684\u7f51\u7edc\u722c\u866b\uff1a\u5982\u4f55\u5feb\u901f\u6293\u53d6\u6570\u636e<\/p>\n<p>\u5f15\u8a00\uff1a<br \/>\u7f51\u7edc\u722c\u866b\u662f\u4e00\u79cd\u4ece\u4e92\u8054\u7f51\u4e0a\u83b7\u53d6\u4fe1\u606f\u7684\u7a0b\u5e8f\u5de5\u5177\uff0c\u5b83\u53ef\u4ee5\u81ea\u52a8\u8bbf\u95ee\u7f51\u9875\u5e76\u89e3\u6790\u5176\u4e2d\u7684\u6570\u636e\u3002\u5229\u7528\u7f51\u7edc\u722c\u866b\uff0c\u6211\u4eec\u53ef\u4ee5\u5feb\u901f\u6293\u53d6\u5927\u91cf\u7684\u6570\u636e\uff0c\u4e3a\u6570\u636e\u5206\u6790\u548c\u4e1a\u52a1\u51b3\u7b56\u63d0\u4f9b\u652f\u6301\u3002\u672c\u6587\u5c06\u4ecb\u7ecd\u5982\u4f55\u4f7f\u7528Redis\u548cJavaScript\u6784\u5efa\u4e00\u4e2a\u7b80\u5355\u7684\u7f51\u7edc\u722c\u866b\uff0c\u5e76\u6f14\u793a\u5982\u4f55\u5feb\u901f\u6293\u53d6\u6570\u636e\u3002<\/p>\n<ol>\n<li>\u73af\u5883\u51c6\u5907<br \/>\u5728\u5f00\u59cb\u4e4b\u524d\uff0c\u6211\u4eec\u9700\u8981\u51c6\u5907\u4ee5\u4e0b\u73af\u5883\uff1a<\/li>\n<li>Redis\uff1a\u7528\u4f5c\u722c\u866b\u7684\u4efb\u52a1\u8c03\u5ea6\u5668\u548c\u6570\u636e\u5b58\u50a8\u5668\u3002<\/li>\n<li>Node.js\uff1a\u8fd0\u884cJavaScript\u4ee3\u7801\u3002<\/li>\n<li>Cheerio\uff1a\u7528\u4e8e\u89e3\u6790HTML\u9875\u9762\u7684\u5e93\u3002<\/li>\n<li>\u722c\u866b\u67b6\u6784\u8bbe\u8ba1<br \/>\u6211\u4eec\u7684\u722c\u866b\u5c06\u91c7\u7528\u5206\u5e03\u5f0f\u67b6\u6784\uff0c\u5206\u4e3a\u4e24\u4e2a\u90e8\u5206\uff1a\u4efb\u52a1\u8c03\u5ea6\u5668\u548c\u722c\u866b\u8282\u70b9\u3002<\/li>\n<\/ol>\n<ul>\n<li>\u4efb\u52a1\u8c03\u5ea6\u5668\uff1a\u8d1f\u8d23\u5c06\u5f85\u6293\u53d6\u7684URL\u6dfb\u52a0\u5230Redis\u961f\u5217\u4e2d\uff0c\u5e76\u6839\u636e\u9700\u8981\u8fdb\u884c\u53bb\u91cd\u548c\u4f18\u5148\u7ea7\u8bbe\u7f6e\u3002<\/li>\n<li>\u722c\u866b\u8282\u70b9\uff1a\u8d1f\u8d23\u4eceRedis\u961f\u5217\u4e2d\u83b7\u53d6\u5f85\u6293\u53d6\u7684URL\uff0c\u5e76\u8fdb\u884c\u9875\u9762\u89e3\u6790\uff0c\u63d0\u53d6\u6570\u636e\u5e76\u5b58\u50a8\u5230Redis\u4e2d\u3002<\/li>\n<\/ul>\n<ol>\n<li>\u4efb\u52a1\u8c03\u5ea6\u5668\u4ee3\u7801\u793a\u4f8b<br \/>\u4efb\u52a1\u8c03\u5ea6\u5668\u7684\u4ee3\u7801\u793a\u4f8b\u5982\u4e0b\uff1a<\/li>\n<\/ol>\n<pre>const redis = require('redis');\nconst client = redis.createClient();\n\n\/\/ \u6dfb\u52a0\u5f85\u6293\u53d6\u7684URL\u5230\u961f\u5217\nconst enqueueUrl = (url, priority = 0) =&gt; {\n  client.zadd('urls', priority, url);\n}\n\n\/\/ \u4ece\u961f\u5217\u4e2d\u83b7\u53d6\u5f85\u6293\u53d6\u7684URL\nconst dequeueUrl = () =&gt; {\n  return new Promise((resolve, reject) =&gt; {\n    client.zrange('urls', 0, 0, (err, urls) =&gt; {\n      if (err) reject(err);\n      else resolve(urls[0]);\n    })\n  })\n}\n\n\/\/ \u5224\u65adURL\u662f\u5426\u5df2\u7ecf\u88ab\u6293\u53d6\u8fc7\nconst isUrlVisited = (url) =&gt; {\n  return new Promise((resolve, reject) =&gt; {\n    client.sismember('visited_urls', url, (err, result) =&gt; {\n      if (err) reject(err);\n      else resolve(!!result);\n    })\n  })\n}\n\n\/\/ \u5c06URL\u6807\u8bb0\u4e3a\u5df2\u7ecf\u88ab\u6293\u53d6\u8fc7\nconst markUrlVisited = (url) =&gt; {\n  client.sadd('visited_urls', url);\n}<\/pre>\n<p>\u5728\u4e0a\u9762\u7684\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528\u4e86Redis\u7684\u6709\u5e8f\u96c6\u5408\u548c\u96c6\u5408\u6570\u636e\u7ed3\u6784\uff0c\u6709\u5e8f\u96c6\u5408<code>urls<\/code>\u7528\u4e8e\u5b58\u50a8\u5f85\u6293\u53d6\u7684URL\uff0c\u96c6\u5408<code>visited_urls<\/code>\u7528\u4e8e\u5b58\u50a8\u5df2\u7ecf\u88ab\u6293\u53d6\u8fc7\u7684URL\u3002<\/p>\n<ol>\n<li>\u722c\u866b\u8282\u70b9\u4ee3\u7801\u793a\u4f8b<br \/>\u722c\u866b\u8282\u70b9\u7684\u4ee3\u7801\u793a\u4f8b\u5982\u4e0b\uff1a<\/li>\n<\/ol>\n<pre>const request = require('request');\nconst cheerio = require('cheerio');\n\n\/\/ \u4ece\u6307\u5b9a\u7684URL\u4e2d\u89e3\u6790\u6570\u636e\nconst parseData = (url) =&gt; {\n  return new Promise((resolve, reject) =&gt; {\n    request(url, (error, response, body) =&gt; {\n      if (error) reject(error);\n      else {\n        const $ = cheerio.load(body);\n        \/\/ \u5728\u8fd9\u91cc\u5bf9\u9875\u9762\u8fdb\u884c\u89e3\u6790\uff0c\u5e76\u63d0\u53d6\u6570\u636e\n        \/\/ ...\n\n        resolve(data);\n      }\n    })\n  })\n}\n\n\/\/ \u722c\u866b\u8282\u70b9\u7684\u4e3b\u903b\u8f91\nconst crawler = async () =&gt; {\n  while (true) {\n    const url = await dequeueUrl();\n    if (!url) break;\n\n    if (await isUrlVisited(url)) continue;\n\n    try {\n      const data = await parseData(url);\n\n      \/\/ \u5728\u8fd9\u91cc\u5c06\u6570\u636e\u5b58\u50a8\u5230Redis\u4e2d\n      \/\/ ...\n\n      markUrlVisited(url);\n    } catch (error) {\n      console.error(`Failed to parse data from ${url}`, error);\n    }\n  }\n}\n\ncrawler();<\/pre>\n<p>\u5728\u4e0a\u9762\u7684\u4ee3\u7801\u4e2d\uff0c\u6211\u4eec\u4f7f\u7528\u4e86<code>request<\/code>\u5e93\u53d1\u9001HTTP\u8bf7\u6c42\uff0c\u4f7f\u7528<code>cheerio<\/code>\u5e93\u89e3\u6790\u9875\u9762\u3002\u5728<code>parseData<\/code>\u51fd\u6570\u4e2d\uff0c\u6211\u4eec\u53ef\u4ee5\u6839\u636e\u5177\u4f53\u7684\u9875\u9762\u7ed3\u6784\u548c\u6570\u636e\u63d0\u53d6\u9700\u6c42\uff0c\u4f7f\u7528<code>cheerio<\/code>\u5e93\u6765\u89e3\u6790\u9875\u9762\u5e76\u63d0\u53d6\u6570\u636e\u3002\u5728\u722c\u866b\u8282\u70b9\u7684\u4e3b\u903b\u8f91\u4e2d\uff0c\u6211\u4eec\u5faa\u73af\u4eceRedis\u961f\u5217\u4e2d\u83b7\u53d6\u5f85\u6293\u53d6\u7684URL\uff0c\u5e76\u8fdb\u884c\u9875\u9762\u89e3\u6790\u548c\u6570\u636e\u5b58\u50a8\u3002<\/p>\n<p>\u603b\u7ed3\uff1a<br \/>\u901a\u8fc7\u5229\u7528Redis\u548cJavaScript\uff0c\u6211\u4eec\u53ef\u4ee5\u6784\u5efa\u4e00\u4e2a\u7b80\u5355\u4f46\u529f\u80fd\u5f3a\u5927\u7684\u7f51\u7edc\u722c\u866b\uff0c\u5b9e\u73b0\u5feb\u901f\u6293\u53d6\u5927\u91cf\u6570\u636e\u7684\u76ee\u7684\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528\u4efb\u52a1\u8c03\u5ea6\u5668\u5c06\u5f85\u6293\u53d6\u7684URL\u6dfb\u52a0\u5230Redis\u961f\u5217\uff0c\u5e76\u5728\u722c\u866b\u8282\u70b9\u4e2d\u4ece\u961f\u5217\u4e2d\u83b7\u53d6URL\u5e76\u8fdb\u884c\u9875\u9762\u89e3\u6790\u548c\u6570\u636e\u5b58\u50a8\u3002\u8fd9\u79cd\u5206\u5e03\u5f0f\u67b6\u6784\u53ef\u4ee5\u63d0\u9ad8\u722c\u53d6\u6548\u7387\uff0c\u5e76\u4e14\u901a\u8fc7Redis\u7684\u6570\u636e\u5b58\u50a8\u548c\u9ad8\u6027\u80fd\u7279\u6027\uff0c\u53ef\u4ee5\u8f7b\u677e\u5904\u7406\u5927\u91cf\u6570\u636e\u3002<\/p>\n<dl>\n<dt>\n <\/dt>\n<dd>\n   \u5982\u4f55\u5229\u7528MySQL\u5728Java\u4e2d\u5b9e\u73b0\u6570\u636e\u63d2\u5165\u529f\u80fd\n <\/dd>\n<\/dl>\n<dl>\n<dt>\n <\/dt>\n<dd>\n   \u5982\u4f55\u4f7f\u7528Go\u8bed\u8a00\u4e2d\u7684\u7f51\u7edc\u7f16\u7a0b\u51fd\u6570\u5b9e\u73b0UDP\u5e7f\u64ad\u901a\u4fe1\uff1f\n <\/dd>\n<\/dl>\n","protected":false},"excerpt":{"rendered":"<p>\u5229\u7528Redis\u548cJavaScri&#46;&#46;&#46;<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[101],"tags":[],"class_list":["post-202052","post","type-post","status-publish","format-standard","hentry","category-database"],"_links":{"self":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/202052","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/comments?post=202052"}],"version-history":[{"count":0,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/202052\/revisions"}],"wp:attachment":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/media?parent=202052"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/categories?post=202052"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/tags?post=202052"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}