{"id":3848,"date":"2021-11-13T16:08:55","date_gmt":"2021-11-13T07:08:55","guid":{"rendered":"https:\/\/www.skyer9.pe.kr\/wordpress\/?p=3848"},"modified":"2022-12-20T16:03:44","modified_gmt":"2022-12-20T07:03:44","slug":"elasticsearch-import-csv","status":"publish","type":"post","link":"https:\/\/www.skyer9.pe.kr\/wordpress\/?p=3848","title":{"rendered":"Elasticsearch import CSV"},"content":{"rendered":"

Elasticsearch import CSV<\/h1>\n

\ucc38\uc870<\/a><\/p>\n

CSV \ub97c \uc784\ud3ec\ud2b8 \ud558\ub294 \ubc29\ubc95\uc740 \uc5ec\ub7ec\uac00\uc9c0\uac00 \uc788\uc9c0\ub9cc,
\n\uc5ec\uae30\uc11c\ub294 python \uc744 \uc774\uc6a9\ud558\ub294 \ubc29\ubc95\uc744 \uc815\ub9ac\ud55c\ub2e4.<\/p>\n

import using python<\/h2>\n
pip3 install elasticsearch<\/code><\/pre>\n
vi import_csv.py\n---------------------------\nfrom elasticsearch import helpers, Elasticsearch\nimport csv\n\ndocument = {\n  "mappings":{\n    "dynamic": False,\n    "properties":{\n      "Time":{\n        "type": "date"\n      },\n      "Year":{\n        "type": "text",\n        "fields": {\n          "keyword":{\n            "type": "keyword",\n            "ignore_above": 256\n          }\n        }\n      },\n      "Month":{\n        "type": "text",\n        "fields": {\n          "keyword":{\n            "type": "keyword",\n            "ignore_above": 256\n          }\n        }\n      },\n      "Hour":{\n        "type": "text",\n        "fields": {\n          "keyword":{\n            "type": "keyword",\n            "ignore_above": 256\n          }\n        }\n      },\n      "Type":{\n        "type": "text",\n        "fields": {\n          "keyword":{\n            "type": "keyword",\n            "ignore_above": 256\n          }\n        }\n      },\n      "Data":{\n        "type": "integer"\n      },\n      "Latitude":{\n        "type": "double"\n      },\n      "Longitude":{\n        "type": "double"\n      },\n    }\n  }\n}\n\n# itemid,item_name,item_option_name,brand,category,price,image_url\n\n# sed -i '1s\/^\\xEF\\xBB\\xBF\/\/' item_info.csv\n# cp item_info_header.csv item_info_full.csv\n# head -1000000 item_info.csv >> item_info_full.csv\n# vi item_info_full.csv\n\nes = Elasticsearch(['192.168.1.16:9200'], port=9200)\n\nif es.indices.exists(index="mydata"):\n  pass\nelse:\n  es.indices.create(index="mydata", body=document)\n\nwith open('\/home\/renesys\/work\/defined_data.csv') as f:\n  reader = csv.DictReader(f)\n  helpers.bulk(es, reader, index="mydata", raise_on_error=False)\n---------------------------<\/code><\/pre>\n
python3 import_csv.py<\/code><\/pre>\n
\ubcc0\uacbd\uc0ac\ud56d<\/h2>\n
API \uac00 \uc57d\uac04 \ubcc0\uacbd\ub41c \ub4ef \ud558\ub2e4.(2022-12-20 \uae30\uc900)<\/p>\n
from elasticsearch import helpers, Elasticsearch\nimport csv\n\n# search_string, sort\n\nes = Elasticsearch("http:\/\/testconfig.10x10.co.kr:9200")\n\nwith open('autocomplete.csv', 'rt', encoding='UTF8') as f:\n  fieldnames = ['search_string', 'sort']\n  reader = csv.DictReader(f, fieldnames=fieldnames, delimiter='\\t')\n  helpers.bulk(es, reader, index="auto_complete", raise_on_error=False)<\/code><\/pre>\n","protected":false},"excerpt":{"rendered":"
Elasticsearch import CSV \ucc38\uc870 CSV \ub97c \uc784\ud3ec\ud2b8 \ud558\ub294 \ubc29\ubc95\uc740 \uc5ec\ub7ec\uac00\uc9c0\uac00 \uc788\uc9c0\ub9cc, \uc5ec\uae30\uc11c\ub294 python \uc744 \uc774\uc6a9\ud558\ub294 \ubc29\ubc95\uc744 \uc815\ub9ac\ud55c\ub2e4. import using python pip3 install elasticsearch vi import_csv.py ————————— from elasticsearch import helpers, Elasticsearch import csv document = { "mappings":{ "dynamic": False, "properties":{ "Time":{ "type": "date" }, "Year":{ "type": "text", "fields": { "keyword":{ "type": "keyword", "ignore_above": 256 }\u2026 Read More »<\/a><\/span><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[],"class_list":["post-3848","post","type-post","status-publish","format-standard","hentry","category-elasticsearch"],"_links":{"self":[{"href":"https:\/\/www.skyer9.pe.kr\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3848","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.skyer9.pe.kr\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.skyer9.pe.kr\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.skyer9.pe.kr\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.skyer9.pe.kr\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=3848"}],"version-history":[{"count":5,"href":"https:\/\/www.skyer9.pe.kr\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3848\/revisions"}],"predecessor-version":[{"id":7260,"href":"https:\/\/www.skyer9.pe.kr\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3848\/revisions\/7260"}],"wp:attachment":[{"href":"https:\/\/www.skyer9.pe.kr\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3848"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.skyer9.pe.kr\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3848"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.skyer9.pe.kr\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3848"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}