Spark を使用して saveAsTextFile を S3 に保存した後、Hadoop のようにフォーマットします。そのようなバケット内のファイルの形式。
形式は YEAR/MONTH/DATE/TIMESTAMP で、データは part-0000 ファイルは json 形式です。
ドリルを構成し、バケット名を指定します
{
"type": "file",
"enabled": true,
"connection": "s3://com.giaosudau.win-bid",
"workspaces": {
"root": {
"location": "/",
"writable": false,
"defaultInputFormat": "json"
},
"tmp": {
"location": "/tmp",
"writable": true,
"defaultInputFormat": null
}
},
"formats": {
"psv": {
"type": "text",
"extensions": [
"tbl"
],
"delimiter": "|"
},
"csv": {
"type": "text",
"extensions": [
"csv"
],
"delimiter": ","
},
"tsv": {
"type": "text",
"extensions": [
"tsv"
],
"delimiter": "\t"
},
"parquet": {
"type": "parquet"
},
"json": {
"type": "json"
},
"avro": {
"type": "avro"
}
}
}
ストレージは問題ありません。しかし、日付、時間、またはファイルのデータを選択して取得する方法がわかりません。
私はまた、ファイルを選択するようなことを試みますが、成功しません:
ファイルサンプルはこちら
{"auctionId":"xx","bidRequestString":{"id":"xx","timestamp":"2015-07-29T08:31:00.413Z","isTest":false,"url":"http://www.222.3232.com/","userAgent":"Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.8.1.7pre) Gecko/20070815 Firefox/2.0.0.6 Navigator/9.0b3","protocolVersion":"Google Protocol Buffer","exchange":"adx","provider":"Google","location":{"dma":-1,"metro":-1,"timezoneOffsetMinutes":-1},"segments":{"AdxDetectedVerticals":["23:0.571243","355:0.409098","380:0.339647","474:0.415936","540:0.079871"]},"userIds":{"prov":"bGZqaWdsa2dmbmRubWxtamdoaGs","xchg":"bGZqaWdsa2dmbmRubWxtamdoaGs"},"imp":[{"id":"99","banner":{"w":[220,300],"h":[600,450],"id":"99","pos":0,"topframe":0},"pmp":{"ext":{"adgroup_id":"17490739393"}},"formats":["220x600","300x450"],"position":0},{"id":"199","banner":{"w":120,"h":600,"id":"199","pos":0,"topframe":0},"pmp":{"ext":{"adgroup_id":"17490739393"}},"formats":["120x600"],"position":0}],"spots":[{"id":"99","banner":{"w":[220,300],"h":[600,450],"id":"99","pos":0,"topframe":0},"pmp":{"ext":{"adgroup_id":"17490739393"}},"formats":["220x600","300x450"],"position":0},{"id":"199","banner":{"w":120,"h":600,"id":"199","pos":0,"topframe":0},"pmp":{"ext":{"adgroup_id":"17490739393"}},"formats":["120x600"],"position":0}],"site":{"id":"502","publisher":{"id":"502"},"page":"http://www.blog.34343.com/"},"device":{"ua":"Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.8.1.7pre) Gecko/20070815 Firefox/2.0.0.6 Navigator/9.0b3","ip":"109.103.101.0","geo":{"zip":" 2600"},"language":"en","ext":{"geo_criteria_id":1000142}},"user":{"id":"bGZqaWdsa2dmbmRubWxtamdoaGs","ext":{"cookie_age_seconds":2080089}}},"bidResponseCreative":{"itemId":"fsknxfwe34235235","campaignId":"332","htmlSnippet":"\u003ciframe frameborder=0 scrolling=no width=\"300\" height=\"250\" src=\"//sv.brand-display.com/adedge/api/bd/serving/simple/frame?aukey=34343\u0026_=%CACHEBUSTER%\u0026winning_price=%WINNING_PRICE%\u0026google_click_url=%CLICK_URL_ESC%\u0026encrypt_value=%ENCRYPT_VALUE%\"\u003e\u003c/iframe\u003e","name":"Expandable Web","formatCode":"billboard","bd":"","status":1,"deleted":false,"destinationUrl":"https://ex.sg","tagging":[1,2,3],"expandingDirection":14,"bdUrl":"","format":{"code":"billboard","name":"Billboard","publisher":"default","type":"standard","width":120,"height":600,"expanded_width":0,"expanded_height":0,"collapsed_width":0,"collapsed_height":0,"aspratio":3.76,"expandable":true,"expand_first":true}},"bidResponseCreativeId":"1","bidResponseCreativeName":"","bidResponseData":{"bids":[{"creative":0,"ext":null,"price":"6071USD/1M","priority":1.0,"spotIndex":0},{"creative":1,"ext":null,"price":"6071USD/1M","priority":1.0,"spotIndex":1}]},"bidResponseMeta":"null","bidWinMeta":"null","biddingAgentName":"iface.http","biddingFullAccount":"23848834:strategy","biddingMainAccount":"1212312","biddingMaxPrice":"6071USD/1M","biddingRequestFormatType":"datacratic","biddingSubAccount":"strategy","impIndex":"1","impressionId":"199","pricePriority":"1.000000","rawWinPrice":"100USD/1M","timestamp":"2015-Jul-29 08:31:00.53899","userIds":{"prov":"123232","xchg":"9849839"},"winPrice":"100USD/1M"}
{"auctionId":"343","bidRequestString":{"id":"344","timestamp":"2015-07-28T08:31:00.413Z","isTest":false,"url":"http://www.xx.xx.com/","userAgent":"Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.8.1.7pre) Gecko/20070815 Firefox/2.0.0.6 Navigator/9.0b3","protocolVersion":"Google Protocol Buffer","exchange":"adx","provider":"Google","location":{"dma":-1,"metro":-1,"timezoneOffsetMinutes":-1},"segments":{"AdxDetectedVerticals":["23:0.571243","355:0.409098","380:0.339647","474:0.415936","540:0.079871"]},"userIds":{"prov":"bGZqaWdsa2dmbmRubWxtamdoaGs","xchg":"bGZqaWdsa2dmbmRubWxtamdoaGs"},"imp":[{"id":"99","banner":{"w":[220,300],"h":[600,450],"id":"99","pos":0,"topframe":0},"pmp":{"ext":{"adgroup_id":"17490739393"}},"formats":["220x600","300x450"],"position":0},{"id":"199","banner":{"w":120,"h":600,"id":"199","pos":0,"topframe":0},"pmp":{"ext":{"adgroup_id":"17490739393"}},"formats":["120x600"],"position":0}],"spots":[{"id":"99","banner":{"w":[220,300],"h":[600,450],"id":"99","pos":0,"topframe":0},"pmp":{"ext":{"adgroup_id":"17490739393"}},"formats":["220x600","300x450"],"position":0},{"id":"199","banner":{"w":120,"h":600,"id":"199","pos":0,"topframe":0},"pmp":{"ext":{"adgroup_id":"17490739393"}},"formats":["120x600"],"position":0}],"site":{"id":"502","publisher":{"id":"502"},"page":"http://www.blog.343.com/"},"device":{"ua":"Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.8.1.7pre) Gecko/20070815 Firefox/2.0.0.6 Navigator/9.0b3","ip":"109.103.101.0","geo":{"zip":" 2600"},"language":"en","ext":{"geo_criteria_id":1000142}},"user":{"id":"bGZqaWdsa2dmbmRubWxtamdoaGs","ext":{"cookie_age_seconds":2080089}}},"bidResponseCreative":{"itemId":"fsknxfwe34235235","campaignId":"342342342","htmlSnippet":"\u003ciframe frameborder=0 scrolling=no width=\"300\" height=\"250\" src=\"//sv.brand-display.com/adedge/api/bd/serving/simple/frame?aukey=xxx\u0026_=%CACHEBUSTER%\u0026winning_price=%WINNING_PRICE%\u0026google_click_url=%CLICK_URL_ESC%\u0026encrypt_value=%ENCRYPT_VALUE%\"\u003e\u003c/iframe\u003e","name":"Expandable Web","formatCode":"billboard","bd":"","status":1,"deleted":false,"destinationUrl":"https://ex.sg","tagging":[1,2,3],"expandingDirection":14,"bdUrl":"","format":{"code":"billboard","name":"Billboard","publisher":"default","type":"standard","width":120,"height":600,"expanded_width":0,"expanded_height":0,"collapsed_width":0,"collapsed_height":0,"aspratio":3.76,"expandable":true,"expand_first":true}},"bidResponseCreativeId":"1","bidResponseCreativeName":"","bidResponseData":{"bids":[{"creative":0,"ext":null,"price":"6071USD/1M","priority":1.0,"spotIndex":0},{"creative":1,"ext":null,"price":"6071USD/1M","priority":1.0,"spotIndex":1}]},"bidResponseMeta":"null","bidWinMeta":"null","biddingAgentName":"iface.http","biddingFullAccount":"829838828928932:strategy","biddingMainAccount":"3434","biddingMaxPrice":"6071USD/1M","biddingRequestFormatType":"datacratic","biddingSubAccount":"strategy","impIndex":"1","impressionId":"199","pricePriority":"1.000000","rawWinPrice":"100USD/1M","timestamp":"2015-Jul-29 08:31:00.53899","userIds":{"prov":"cc","xchg":"cc"},"winPrice":"100USD/1M"}
そこからデータを取得する方法は？