{"id":201768,"date":"2025-05-10T13:18:48","date_gmt":"2025-05-10T05:18:48","guid":{"rendered":"https:\/\/server.hk\/cnblog\/201768\/"},"modified":"2025-05-10T13:18:48","modified_gmt":"2025-05-10T05:18:48","slug":"redis%e5%ae%9e%e7%8e%b0%e5%88%86%e5%b8%83%e5%bc%8f%e7%88%ac%e8%99%ab%e7%9a%84%e6%96%b9%e6%b3%95%e4%b8%8e%e5%ba%94%e7%94%a8%e5%ae%9e%e4%be%8b","status":"publish","type":"post","link":"https:\/\/server.hk\/cnblog\/201768\/","title":{"rendered":"Redis\u5b9e\u73b0\u5206\u5e03\u5f0f\u722c\u866b\u7684\u65b9\u6cd5\u4e0e\u5e94\u7528\u5b9e\u4f8b"},"content":{"rendered":"<p><b><\/b> <\/p>\n<h1>Redis\u5b9e\u73b0\u5206\u5e03\u5f0f\u722c\u866b\u7684\u65b9\u6cd5\u4e0e\u5e94\u7528\u5b9e\u4f8b<\/h1>\n<p>\u5927\u5bb6\u597d\uff0c\u6211\u4eec\u53c8\u89c1\u9762\u4e86\u554a~\u672c\u6587<span style=\"color: #FF6600;, Helvetica, Arial, sans-serif;font-size: 14px;background-color: #FFFFFF\">\u300aRedis\u5b9e\u73b0\u5206\u5e03\u5f0f\u722c\u866b\u7684\u65b9\u6cd5\u4e0e\u5e94\u7528\u5b9e\u4f8b\u300b<\/span>\u7684\u5185\u5bb9\u4e2d\u5c06\u4f1a\u6d89\u53ca\u5230<span style=\"color: #FF6600;, Helvetica, Arial, sans-serif;font-size: 14px;background-color: #FFFFFF\"><\/span>\u7b49\u7b49\u3002\u5982\u679c\u4f60\u6b63\u5728\u5b66\u4e60<span style=\"color: #FF6600;, Helvetica, Arial, sans-serif;font-size: 14px;background-color: #FFFFFF\">\u6570\u636e\u5e93<\/span>\u76f8\u5173\u77e5\u8bc6\uff0c\u6b22\u8fce\u5173\u6ce8\u6211\uff0c\u4ee5\u540e\u4f1a\u7ed9\u5927\u5bb6\u5e26\u6765\u66f4\u591a<span style=\"color: #FF6600;, Helvetica, Arial, sans-serif;font-size: 14px;background-color: #FFFFFF\">\u6570\u636e\u5e93<\/span>\u76f8\u5173\u6587\u7ae0\uff0c\u5e0c\u671b\u6211\u4eec\u80fd\u4e00\u8d77\u8fdb\u6b65\uff01\u4e0b\u9762\u5c31\u5f00\u59cb\u672c\u6587\u7684\u6b63\u5f0f\u5185\u5bb9~<\/p>\n<p>\u968f\u7740\u4e92\u8054\u7f51\u7684\u666e\u53ca\u548c\u6570\u636e\u89c4\u6a21\u7684\u4e0d\u65ad\u589e\u5927\uff0c\u722c\u866b\u6280\u672f\u7684\u5e94\u7528\u8d8a\u6765\u8d8a\u5e7f\u6cdb\u3002\u7136\u800c\uff0c\u968f\u7740\u6570\u636e\u91cf\u7684\u4e0d\u65ad\u81a8\u80c0\uff0c\u5355\u673a\u722c\u866b\u5df2\u7ecf\u96be\u4ee5\u6ee1\u8db3\u5b9e\u9645\u9700\u6c42\u3002\u5206\u5e03\u5f0f\u722c\u866b\u6280\u672f\u5e94\u8fd0\u800c\u751f\uff0c\u5176\u4e2dRedis\u662f\u4e00\u79cd\u975e\u5e38\u4f18\u79c0\u7684\u5206\u5e03\u5f0f\u722c\u866b\u5de5\u5177\u3002\u672c\u6587\u5c06\u4ecb\u7ecdRedis\u5b9e\u73b0\u5206\u5e03\u5f0f\u722c\u866b\u7684\u65b9\u6cd5\u548c\u5e94\u7528\u5b9e\u4f8b\u3002<\/p>\n<p>\u4e00\u3001Redis\u5206\u5e03\u5f0f\u722c\u866b\u7684\u539f\u7406<\/p>\n<p>Redis\u662f\u4e00\u4e2a\u975e\u5173\u7cfb\u578b\u6570\u636e\u5e93\uff0c\u5728\u5206\u5e03\u5f0f\u722c\u866b\u4e2d\uff0c\u5b83\u88ab\u7528\u4f5c\u6570\u636e\u7684\u7f13\u5b58\u548c\u961f\u5217\uff0c\u5b9e\u73b0\u5206\u5e03\u5f0f\u7684\u91cd\u8981\u624b\u6bb5\u662f\u901a\u8fc7\u5b9e\u73b0\u5148\u8fdb\u5148\u51fa\uff08FIFO\uff09\u961f\u5217\u7684\u5f62\u5f0f\uff0c\u8fdb\u884c\u4efb\u52a1\u5206\u914d\u3002<\/p>\n<p>\u5728Redis\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528List\u7c7b\u578b\u6765\u5b9e\u73b0\u961f\u5217\u3002Redis\u63d0\u4f9b\u4e86LPUSH\u548cRPUSH\u547d\u4ee4\u6765\u5b9e\u73b0\u5c06\u6570\u636e\u63d2\u5165\u961f\u5217\u5934\u548c\u961f\u5217\u5c3e\u3002\u540c\u65f6\uff0c\u8fd8\u63d0\u4f9b\u4e86LPOP\u548cRPOP\u547d\u4ee4\u6765\u5f39\u51fa\u961f\u5217\u4e2d\u7684\u6570\u636e\uff0c\u5e76\u5220\u9664\u5f39\u51fa\u7684\u6570\u636e\u3002<\/p>\n<p>\u901a\u8fc7Redis\uff0c\u53ef\u4ee5\u5b9e\u73b0\u591a\u4e2a\u722c\u866b\u8fdb\u7a0b\u7684\u4efb\u52a1\u5206\u914d\uff0c\u63d0\u9ad8\u722c\u866b\u6548\u7387\u548c\u901f\u5ea6\u3002<\/p>\n<p>\u4e8c\u3001Redis\u5206\u5e03\u5f0f\u722c\u866b\u7684\u5177\u4f53\u5b9e\u73b0<\/p>\n<ol>\n<li>\u5229\u7528Redis\u5b58\u50a8\u5f85\u6293\u53d6\u7684URL<\/li>\n<\/ol>\n<p>\u5728\u6293\u53d6\u7f51\u9875\u6570\u636e\u65f6\uff0c\u9996\u5148\u8981\u786e\u5b9a\u5f85\u6293\u53d6\u7684URL\u961f\u5217\u3002\u4f7f\u7528Redis\u65f6\uff0c\u6211\u4eec\u53ef\u4ee5\u901a\u8fc7RPUSH\u5c06\u5f85\u6293\u53d6\u7684URL\u52a0\u5165\u5230\u961f\u5217\u672b\u5c3e\u3002\u540c\u65f6\uff0c\u901a\u8fc7LPOP\u547d\u4ee4\u5b9e\u73b0\u4ece\u5934\u90e8\u5f39\u51fa\u961f\u5217\uff0c\u83b7\u53d6\u5f85\u6293\u53d6\u7684URL\u3002<\/p>\n<p>\u5177\u4f53\u4ee3\u7801\u5982\u4e0b\uff1a<\/p>\n<pre>import redis\n\n# \u521d\u59cb\u5316Redis\u6570\u636e\u5e93\nclient = redis.Redis(host='localhost', port=6379, db=0)\n\n# \u5c06\u5f85\u6293\u53d6\u7684URL\u52a0\u5165\u5230\u961f\u5217\u672b\u5c3e\nclient.rpush('url_queue', 'http:\/\/www.example.com')\n\n# \u4ece\u961f\u5217\u5934\u90e8\u5f39\u51faURL\nurl = client.lpop('url_queue')<\/pre>\n<ol>\n<li>\u722c\u866b\u8fdb\u7a0b\u4e0e\u4efb\u52a1\u5206\u914d<\/li>\n<\/ol>\n<p>\u5728\u5206\u5e03\u5f0f\u722c\u866b\u4e2d\uff0c\u9700\u8981\u5c06\u4efb\u52a1\u5206\u914d\u7ed9\u591a\u4e2a\u722c\u866b\u8fdb\u7a0b\u3002\u4e3a\u4e86\u5b9e\u73b0\u5206\u5e03\u5f0f\u4efb\u52a1\u5206\u914d\uff0c\u53ef\u4ee5\u5728Redis\u4e2d\u521b\u5efa\u591a\u4e2a\u961f\u5217\uff0c\u6bcf\u4e2a\u722c\u866b\u8fdb\u7a0b\u4ece\u4e0d\u540c\u7684\u961f\u5217\u4e2d\u83b7\u53d6\u4efb\u52a1\u3002\u5728\u8fdb\u884c\u4efb\u52a1\u5206\u914d\u65f6\uff0c\u901a\u8fc7Round-robin\u7b97\u6cd5\u5b9e\u73b0\u4efb\u52a1\u7684\u5e73\u5747\u5206\u914d\u3002<\/p>\n<p>\u5177\u4f53\u4ee3\u7801\u5982\u4e0b\uff1a<\/p>\n<pre>import redis\n\n# \u521d\u59cb\u5316Redis\u6570\u636e\u5e93\nclient = redis.Redis(host='localhost', port=6379, db=0)\n\n# \u5b9a\u4e49\u722c\u866b\u8fdb\u7a0b\u4e2a\u6570\nnum_spiders = 3\n\n# \u5c06\u4efb\u52a1\u5206\u914d\u7ed9\u722c\u866b\u8fdb\u7a0b\nfor i in range(num_spiders):\n    url = client.lpop('url_queue_%d' % i)\n    if url:\n        # \u542f\u52a8\u722c\u866b\u8fdb\u7a0b\u8fdb\u884c\u4efb\u52a1\u5904\u7406\n        process_url(url)<\/pre>\n<ol>\n<li>\u722c\u866b\u6570\u636e\u7684\u5b58\u50a8<\/li>\n<\/ol>\n<p>\u5728\u5206\u5e03\u5f0f\u722c\u866b\u4e2d\uff0c\u9700\u8981\u5c06\u722c\u866b\u6570\u636e\u5b58\u50a8\u5230\u540c\u4e00\u4e2a\u6570\u636e\u5e93\u4e2d\uff0c\u4ee5\u4fbf\u5b9e\u73b0\u6570\u636e\u7684\u6c47\u603b\u548c\u5206\u6790\u3002\u6b64\u65f6\uff0cRedis\u7684Hash\u6570\u636e\u7c7b\u578b\u53ef\u4ee5\u53d1\u6325\u91cd\u8981\u4f5c\u7528\u3002\u4f7f\u7528Redis\u7684Hash\u6570\u7ec4\uff0c\u5b58\u50a8\u722c\u866b\u6570\u636e\u7684\u7f16\u53f7\u548c\u5185\u5bb9\uff0c\u4fbf\u4e8e\u540e\u7eed\u7684\u6570\u636e\u5904\u7406\u548c\u7edf\u8ba1\u3002<\/p>\n<p>\u5177\u4f53\u4ee3\u7801\u5982\u4e0b\uff1a<\/p>\n<pre>import redis\n\n# \u521d\u59cb\u5316Redis\u6570\u636e\u5e93\nclient = redis.Redis(host='localhost', port=6379, db=0)\n\n# \u5b58\u50a8\u722c\u866b\u6570\u636e\ndef save_data(data):\n    client.hset('data', data['id'], json.dumps(data))<\/pre>\n<p>\u4e09\u3001Redis\u5206\u5e03\u5f0f\u722c\u866b\u7684\u5e94\u7528\u5b9e\u4f8b<\/p>\n<p>Redis\u5206\u5e03\u5f0f\u722c\u866b\u6280\u672f\u7684\u5e94\u7528\u975e\u5e38\u5e7f\u6cdb\uff0c\u5305\u62ec\u6570\u636e\u6316\u6398\u3001\u641c\u7d22\u5f15\u64ce\u3001\u91d1\u878d\u5206\u6790\u7b49\u9886\u57df\u3002\u4e0b\u9762\u4ee5\u57fa\u4e8eRedis\u7684\u5206\u5e03\u5f0f\u722c\u866b\u6846\u67b6Scrapy-Redis\u4e3a\u4f8b\uff0c\u4ecb\u7ecd\u5206\u5e03\u5f0f\u722c\u866b\u7684\u5b9e\u73b0\u65b9\u5f0f\u3002<\/p>\n<ol>\n<li>\u5b89\u88c5Scrapy-Redis<\/li>\n<\/ol>\n<p>Scrapy-Redis\u662f\u57fa\u4e8eScrapy\u6846\u67b6\u5f00\u53d1\u7684\u5206\u5e03\u5f0f\u722c\u866b\u5de5\u5177\uff0c\u53ef\u4ee5\u5b9e\u73b0\u591a\u722c\u866b\u8fdb\u7a0b\u4e4b\u95f4\u7684\u6570\u636e\u5171\u4eab\u548c\u4efb\u52a1\u5206\u914d\u3002\u5728\u8fdb\u884c\u5206\u5e03\u5f0f\u722c\u866b\u65f6\uff0c\u9700\u8981\u5b89\u88c5Scrapy-Redis\u3002<\/p>\n<pre>pip install scrapy-redis<\/pre>\n<ol>\n<li>\u914d\u7f6eScrapy-Redis\u548cRedis<\/li>\n<\/ol>\n<p>\u5728\u8fdb\u884cScrapy-Redis\u722c\u866b\u65f6\uff0c\u9700\u8981\u914d\u7f6eScrapy-Redis\u548cRedis\u3002Scrapy-Redis\u7684\u8bbe\u7f6e\u548cScrapy\u6846\u67b6\u7c7b\u4f3c\uff0c\u53ef\u4ee5\u901a\u8fc7\u5728settings.py\u6587\u4ef6\u4e2d\u8bbe\u7f6e\u5b9e\u73b0\u3002Scrapy-Redis\u9700\u8981\u5229\u7528Redis\u5b9e\u73b0\u4efb\u52a1\u961f\u5217\u548c\u6570\u636e\u5171\u4eab\uff0c\u56e0\u6b64\u9700\u8981\u914d\u7f6eRedis\u6570\u636e\u5e93\u7684\u76f8\u5173\u4fe1\u606f\u3002<\/p>\n<pre># Scrapy-Redis\u914d\u7f6e\nSCHEDULER = \"scrapy_redis.scheduler.Scheduler\"  # \u4f7f\u7528Redis\u8c03\u5ea6\uff08Scheduler\uff09\nDUPEFILTER_CLASS = \"scrapy_redis.dupefilter.RFPDupeFilter\"  # \u4f7f\u7528Redis\u53bb\u91cd\uff08Dupefilter\uff09\n\n# Redis\u6570\u636e\u5e93\u914d\u7f6e\nREDIS_URL = 'redis:\/\/user:password@localhost:6379'<\/pre>\n<ol>\n<li>\u7f16\u5199Scrapy-Redis\u722c\u866b\u4ee3\u7801<\/li>\n<\/ol>\n<p>\u5728\u8fdb\u884cScrapy-Redis\u722c\u866b\u65f6\uff0c\u4e3b\u8981\u7684\u4ee3\u7801\u5b9e\u73b0\u548cScrapy\u6846\u67b6\u7c7b\u4f3c\u3002\u552f\u4e00\u7684\u533a\u522b\u662f\u9700\u8981\u5229\u7528Scrapy-Redis\u63d0\u4f9b\u7684RedisSpider\u7c7b\u4ee3\u66ff\u539f\u6765\u7684Spider\u7c7b\uff0c\u5b9e\u73b0\u5bf9Redis\u6570\u636e\u5e93\u7684\u64cd\u4f5c\u548c\u4efb\u52a1\u5206\u914d\u3002<\/p>\n<pre>import scrapy\nfrom scrapy_redis.spiders import RedisSpider\n\n\nclass MySpider(RedisSpider):\n    \"\"\"Spider that reads urls from redis queue (myspider:start_urls).\"\"\"\n    name = 'myspider_redis'\n    redis_key = 'myspider:start_urls'\n\n    def parse(self, response):\n        \"\"\"This function parses a sample response. Some contracts are mingled\n        with this docstring.\n\n        @url http:\/\/www.example.com\/\n        @returns items 1\n        @returns requests 1\n        \"\"\"\n        item = MyItem()\n        item['title'] = response.xpath('\/\/title\/text()').extract_first()\n        yield item<\/pre>\n<p>\u56db\u3001\u603b\u7ed3<\/p>\n<p>\u5b9e\u73b0\u5206\u5e03\u5f0f\u722c\u866b\uff0c\u4e0d\u4ec5\u53ef\u4ee5\u63d0\u9ad8\u722c\u866b\u7684\u6548\u7387\u548c\u901f\u5ea6\uff0c\u800c\u4e14\u8fd8\u53ef\u4ee5\u907f\u514d\u5355\u70b9\u6545\u969c\u7684\u98ce\u9669\u3002Redis\u4f5c\u4e3a\u4e00\u6b3e\u975e\u5e38\u4f18\u79c0\u7684\u6570\u636e\u7f13\u5b58\u548c\u961f\u5217\u5de5\u5177\uff0c\u5728\u5206\u5e03\u5f0f\u722c\u866b\u4e2d\u53ef\u4ee5\u53d1\u6325\u5f88\u597d\u7684\u4f5c\u7528\u3002\u901a\u8fc7\u4ee5\u4e0a\u4ecb\u7ecd\u7684Redis\u5b9e\u73b0\u5206\u5e03\u5f0f\u722c\u866b\u7684\u65b9\u6cd5\u548c\u5e94\u7528\u5b9e\u4f8b\uff0c\u53ef\u4ee5\u66f4\u597d\u5730\u4e86\u89e3\u5206\u5e03\u5f0f\u722c\u866b\u7684\u5b9e\u73b0\u65b9\u5f0f\u548cRedis\u7684\u4f18\u52bf\u3002<\/p>\n<dl>\n<dt>\n <\/dt>\n<dd>\n   Redis\u5b9e\u73b0\u5206\u5e03\u5f0f\u9501\u7684\u539f\u7406\u548c\u5b9e\u73b0\u65b9\u5f0f\n <\/dd>\n<\/dl>\n<dl>\n<dt>\n <\/dt>\n<dd>\n   mysql\u8e29\u5751\u4e4bcount&nbsp;distinct\u591a\u5217\u95ee\u9898\u600e\u4e48\u89e3\u51b3\n <\/dd>\n<\/dl>\n","protected":false},"excerpt":{"rendered":"<p>Redis\u5b9e\u73b0\u5206\u5e03\u5f0f\u722c\u866b\u7684\u65b9\u6cd5\u4e0e&#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-201768","post","type-post","status-publish","format-standard","hentry","category-database"],"_links":{"self":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/201768","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=201768"}],"version-history":[{"count":0,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/201768\/revisions"}],"wp:attachment":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/media?parent=201768"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/categories?post=201768"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/tags?post=201768"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}