{"id":4112,"date":"2018-10-10T20:18:50","date_gmt":"2018-10-10T12:18:50","guid":{"rendered":"https:\/\/ixyzero.com\/blog\/?p=4112"},"modified":"2018-10-10T20:18:50","modified_gmt":"2018-10-10T12:18:50","slug":"elasticsearch%e7%9a%84scroll%e6%8e%a5%e5%8f%a3%e6%90%9c%e7%b4%a2%e7%a4%ba%e4%be%8b","status":"publish","type":"post","link":"https:\/\/ixyzero.com\/blog\/archives\/4112.html","title":{"rendered":"ElasticSearch\u7684scroll\u63a5\u53e3\u641c\u7d22\u793a\u4f8b"},"content":{"rendered":"<p>=Start=<\/p>\n<h4 id=\"id-\u6a21\u677f-\u7f18\u7531\uff1a\">\u7f18\u7531\uff1a<\/h4>\n<p>\u4e4b\u524d\u6574\u7406\u8fc7\u4e00\u7bc7\u300c<a href=\"https:\/\/ixyzero.com\/blog\/archives\/4076.html\" target=\"_blank\" rel=\"noopener prev\">ElasticSearch\u7684\u641c\u7d22API\u5b66\u4e60\u6574\u7406<\/a>\u300d\u7684\u6587\u7ae0\uff0c\u4f46\u91cc\u9762\u4ecb\u7ecd\u7684\u4e3b\u8981\u662f\u4e00\u4e9b\u641c\u7d22\u8bed\u6cd5\u3001\u9650\u5236\u6761\u4ef6\uff0c\u5e76\u6ca1\u6709\u5b9e\u9645\u641e\u5b9a\u6700\u7ec8\u5339\u914d\u6570\u91cf\u8d85\u8fc710000\u7684\u6570\u636e\u83b7\u53d6\u529e\u6cd5\uff0c\u5176\u5b9e\u65b9\u6cd5\u4e5f\u5f88\u7b80\u5355\u2014\u2014\u4f7f\u7528scroll\u63a5\u53e3\u5206\u6279\u6b21\u53d6\uff0c\u8fd9\u91cc\u7b80\u5355\u8bb0\u5f55\u4e00\u4e0b\uff0c\u65b9\u4fbf\u4ee5\u540e\u53c2\u8003\u3002<\/p>\n<h4 id=\"id-\u6a21\u677f-\u6b63\u6587\uff1a\">\u6b63\u6587\uff1a<\/h4>\n<h5 id=\"id-\u6a21\u677f-\u53c2\u8003\u89e3\u7b54\uff1a\">\u53c2\u8003\u89e3\u7b54\uff1a<\/h5>\n<h6># \u65b9\u6cd5\u4e00\uff1aHTTP\u8bf7\u6c42 scroll \u63a5\u53e3<\/h6>\n<p><strong>scroll\u662f\u5148\u505a\u4e00\u6b21\u521d\u59cb\u5316\u641c\u7d22\u628a\u6240\u6709\u7b26\u5408\u641c\u7d22\u6761\u4ef6\u7684\u7ed3\u679c\u7f13\u5b58\u8d77\u6765\u751f\u6210\u4e00\u4e2a<span style=\"color: #ff0000;\">\u5feb\u7167<\/span>\uff0c\u7136\u540e\u6301\u7eed\u5730\u3001\u6279\u91cf\u5730\u4ece\u5feb\u7167\u91cc\u62c9\u53d6\u6570\u636e\u76f4\u5230\u6ca1\u6709\u6570\u636e\u5269\u4e0b\u3002<\/strong>\u800c\u8fd9\u65f6\u5bf9\u7d22\u5f15\u6570\u636e\u7684\u63d2\u5165\u3001\u5220\u9664\u3001\u66f4\u65b0\u90fd\u4e0d\u4f1a\u5f71\u54cd\u904d\u5386\u7ed3\u679c\uff0c\u56e0\u6b64<span style=\"color: #ff0000;\"><strong>scroll\u5e76\u4e0d\u9002\u5408\u7528\u6765\u505a\u5b9e\u65f6\u641c\u7d22\u3002<\/strong><\/span><\/p>\n<p>\u9700\u8981\u5148\u6267\u884c\u4e00\u4e2a\u521d\u59cb\u5316\u641c\u7d22\u8bf7\u6c42\uff0c\u4f20\u9012\u4e00\u4e2ascroll\u53c2\u6570\u6765\u544a\u8bc9\u00a0Elasticsearch\u7f13\u5b58\u5e94\u8be5\u6301\u7eed\u591a\u957f\u65f6\u95f4\uff0c\u5728\u7f13\u5b58\u6301\u7eed\u65f6\u95f4\u5185\u521d\u59cb\u5316\u641c\u7d22\u8bf7\u6c42\u540e\u5bf9\u7d22\u5f15\u7684\u4fee\u6539\u4e0d\u4f1a\u53cd\u5e94\u5230\u5feb\u7167\u4e2d\u3002\u6bcf\u6b21\u641c\u7d22\u8bf7\u6c42\u540e\u90fd\u4f1a\u8fd4\u56de\u4e00\u4e2ascrollId\uff0c\u662f\u4e00\u4e2a 64 \u4f4d\u7684\u5b57\u7b26\u4e32\u7f16\u7801\uff0c\u540e\u7eed\u4f1a\u4f7f\u7528\u6b64scrollId\u6765\u83b7\u53d6\u6570\u636e\u3002scroll\u65f6\u95f4\u6307\u7684\u662f\u672c\u6b21\u6570\u636e\u5904\u7406\u6240\u9700\u8981\u7684\u65f6\u95f4\uff0c\u5982\u679c\u8d85\u8fc7\u6b64\u65f6\u95f4\uff0c\u7ee7\u7eed\u4f7f\u7528\u8be5scrollId\u641c\u7d22\u6570\u636e\u5219\u4f1a\u62a5\u9519\u3002<\/p>\n<pre class=\"lang:default decode:true \">#!\/usr\/bin\/env python\r\n# coding=utf-8\r\n\r\nimport sys, time\r\nimport json\r\nimport requests\r\n\r\ndef main():\r\n    elastic_url = 'http:\/\/localhost:9200\/index_name\/_search?scroll=2m'\r\n    payload = {\r\n        \"size\": 10,\r\n        \"query\": {\r\n            \"bool\" : {\r\n                \"must\": {\r\n                    \"query_string\": {\r\n                       \"query\": \"spend_time:&gt;=1000\",\r\n                    }\r\n                },\r\n                \"filter\": {\r\n                    \"range\" : {\r\n                        \"es_timestamp\" : {\r\n                            \"gte\": \"2018\/08\/30 00:00:32 +0800\",\r\n                            \"lte\": \"2018\/08\/31 00:00:32 +0800\",\r\n                        }\r\n                    }\r\n                }\r\n            }\r\n        }\r\n    }\r\n\r\n    r = requests.post(elastic_url, data=json.dumps(payload))\r\n    resp_json = r.json()\r\n    hits = resp_json['hits']['hits']\r\n    _scroll_id = resp_json['_scroll_id']\r\n\r\n    # \u6ce8\u610f\uff0c\u8fd9\u91cc\u7684URL\u548c\u4e0a\u9762\u7684\u4e0d\u4e00\u6837\uff0c\u5e76\u6ca1\u6709 index_name \u4fe1\u606f\uff0c\u5bf9\u4e8e\u65b0\u624b\u6765\u8bf4\u5343\u4e07\u6ce8\u610f\uff01\r\n    # scroll_api_url = 'http:\/\/localhost:9200\/_search\/scroll'\r\n    scroll_api_url = 'http:\/\/localhost:9200\/_search\/scroll?filter_path=_shards,_scroll_id,hits.total,hits.hits._source'\r\n    \r\n    while hits:\r\n        print \"hits: {}\".format(len(hits))\r\n        print \"_scroll_id: {}\".format(_scroll_id)\r\n\r\n        scroll_payload = {\r\n            'scroll': '2m',\r\n            'scroll_id': _scroll_id\r\n        }\r\n        scroll_r = requests.post(scroll_api_url, data=json.dumps(scroll_payload))\r\n        resp_json = scroll_r.json()\r\n        # print resp_json\r\n        hits = resp_json['hits']['hits']\r\n        _scroll_id = resp_json['_scroll_id']\r\n\r\n\r\nif __name__ == '__main__':\r\n    time_start = time.time()\r\n    try:\r\n        main()\r\n    except KeyboardInterrupt:\r\n        print 'Killed by user'\r\n        sys.exit(0)\r\n    print \"Spend {0} seconds.\\n\".format(time.time() - time_start)<\/pre>\n<p>&nbsp;<\/p>\n<h6># \u65b9\u6cd5\u4e8c\uff1a\u4f7f\u7528\u5b98\u65b9\u63d0\u4f9b\u7684\u5e93<\/h6>\n<p>\u7565<\/p>\n<p>&nbsp;<\/p>\n<h5 id=\"id-\u6a21\u677f-\u53c2\u8003\u94fe\u63a5\uff1a\">\u53c2\u8003\u94fe\u63a5\uff1a<\/h5>\n<ul>\n<li><a href=\"https:\/\/stackoverflow.com\/questions\/24997251\/elasticsearch-scrolling-using-python-client\">elasticsearch scrolling using python client<\/a><\/li>\n<li><a href=\"https:\/\/www.elastic.co\/guide\/en\/elasticsearch\/reference\/current\/search-request-scroll.html#search-request-scroll\">https:\/\/www.elastic.co\/guide\/en\/elasticsearch\/reference\/current\/search-request-scroll.html#search-request-scroll<\/a><\/li>\n<li><a href=\"https:\/\/blog.csdn.net\/xsdxs\/article\/details\/72876703\">ElasticSearch scan\u548cscroll\u529f\u80fd python \u5b9e\u73b0<\/a><\/li>\n<li><a href=\"http:\/\/www.linuxyw.com\/790.html\">python \u4f7f\u7528elasticsearch\u6a21\u5757\u83b7\u53d6ELK\u7cfb\u7edf\u4e0a\u7684\u7d22\u5f15\u6570\u636e<\/a><\/li>\n<li><a href=\"https:\/\/blog.csdn.net\/peterwanghao\/article\/details\/75037600\">Elasticsearch\u4f7f\u7528Scroll-Scan\u5b9e\u73b0\u6570\u636e\u904d\u5386<\/a><\/li>\n<\/ul>\n<p>=END=<\/p>\n","protected":false},"excerpt":{"rendered":"<p>=Start= \u7f18\u7531\uff1a \u4e4b\u524d\u6574\u7406\u8fc7\u4e00\u7bc7\u300cElasticSearch\u7684\u641c\u7d22API\u5b66\u4e60\u6574\u7406\u300d\u7684\u6587\u7ae0\uff0c\u4f46\u91cc\u9762\u4ecb\u7ecd\u7684\u4e3b [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[23,7,12],"tags":[1207,8,1224],"class_list":["post-4112","post","type-post","status-publish","format-standard","hentry","category-knowledgebase-2","category-programing","category-tools","tag-elasticsearch","tag-python","tag-scroll"],"views":4118,"_links":{"self":[{"href":"https:\/\/ixyzero.com\/blog\/wp-json\/wp\/v2\/posts\/4112","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ixyzero.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/ixyzero.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/ixyzero.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/ixyzero.com\/blog\/wp-json\/wp\/v2\/comments?post=4112"}],"version-history":[{"count":1,"href":"https:\/\/ixyzero.com\/blog\/wp-json\/wp\/v2\/posts\/4112\/revisions"}],"predecessor-version":[{"id":4113,"href":"https:\/\/ixyzero.com\/blog\/wp-json\/wp\/v2\/posts\/4112\/revisions\/4113"}],"wp:attachment":[{"href":"https:\/\/ixyzero.com\/blog\/wp-json\/wp\/v2\/media?parent=4112"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/ixyzero.com\/blog\/wp-json\/wp\/v2\/categories?post=4112"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/ixyzero.com\/blog\/wp-json\/wp\/v2\/tags?post=4112"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}