Created
September 23, 2020 06:46
-
-
Save DhyanRathore/e24943df181048dd13103107a8765498 to your computer and use it in GitHub Desktop.
Using Azure Data Factory to copy multiple files based on URL pattern over HTTP
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| { | |
| "name": "pl_autoCopyCsvFiles", | |
| "properties": { | |
| "activities": [ | |
| { | |
| "name": "ac_checkAllAvailableFiles", | |
| "type": "GetMetadata", | |
| "dependsOn": [], | |
| "policy": { | |
| "timeout": "7.00:00:00", | |
| "retry": 0, | |
| "retryIntervalInSeconds": 30, | |
| "secureOutput": false, | |
| "secureInput": false | |
| }, | |
| "userProperties": [], | |
| "typeProperties": { | |
| "dataset": { | |
| "referenceName": "ds_csvStgAccDest", | |
| "type": "DatasetReference" | |
| }, | |
| "fieldList": [ | |
| "childItems" | |
| ], | |
| "storeSettings": { | |
| "type": "AzureBlobFSReadSettings", | |
| "recursive": true | |
| }, | |
| "formatSettings": { | |
| "type": "DelimitedTextReadSettings" | |
| } | |
| } | |
| }, | |
| { | |
| "name": "ac_setStartingFileName", | |
| "type": "SetVariable", | |
| "dependsOn": [ | |
| { | |
| "activity": "ac_checkAllAvailableFiles", | |
| "dependencyConditions": [ | |
| "Succeeded" | |
| ] | |
| } | |
| ], | |
| "userProperties": [], | |
| "typeProperties": { | |
| "variableName": "i", | |
| "value": { | |
| "value": "@if(empty(last(activity('ac_checkAllAvailableFiles').output.childItems)),variables('j'),formatDateTime(addDays(formatDateTime(replace(last(activity('ac_checkAllavailableFiles').output.childItems).name,'.csv',''),'MM-dd-yyyy'),1),'MM-dd-yyyy'))", | |
| "type": "Expression" | |
| } | |
| } | |
| }, | |
| { | |
| "name": "ac_getCsvFiles", | |
| "type": "Until", | |
| "dependsOn": [ | |
| { | |
| "activity": "ac_setStartingFileName", | |
| "dependencyConditions": [ | |
| "Succeeded" | |
| ] | |
| } | |
| ], | |
| "userProperties": [], | |
| "typeProperties": { | |
| "expression": { | |
| "value": "@greater(dayOfYear(formatDateTime(variables('i'),'MM-dd-yyyy')),dayOfYear(subtractFromTime(utcnow(),1,'Day')))", | |
| "type": "Expression" | |
| }, | |
| "activities": [ | |
| { | |
| "name": "ac_copyCsvFile", | |
| "type": "Copy", | |
| "dependsOn": [], | |
| "policy": { | |
| "timeout": "7.00:00:00", | |
| "retry": 0, | |
| "retryIntervalInSeconds": 30, | |
| "secureOutput": false, | |
| "secureInput": false | |
| }, | |
| "userProperties": [], | |
| "typeProperties": { | |
| "source": { | |
| "type": "DelimitedTextSource", | |
| "storeSettings": { | |
| "type": "HttpReadSettings", | |
| "requestMethod": "GET" | |
| }, | |
| "formatSettings": { | |
| "type": "DelimitedTextReadSettings" | |
| } | |
| }, | |
| "sink": { | |
| "type": "DelimitedTextSink", | |
| "storeSettings": { | |
| "type": "AzureBlobFSWriteSettings" | |
| }, | |
| "formatSettings": { | |
| "type": "DelimitedTextWriteSettings", | |
| "quoteAllText": true, | |
| "fileExtension": ".txt" | |
| } | |
| }, | |
| "enableStaging": false, | |
| "translator": { | |
| "type": "TabularTranslator", | |
| "typeConversion": true, | |
| "typeConversionSettings": { | |
| "allowDataTruncation": true, | |
| "treatBooleanAsNumber": false | |
| } | |
| } | |
| }, | |
| "inputs": [ | |
| { | |
| "referenceName": "ds_csvWebSrc", | |
| "type": "DatasetReference", | |
| "parameters": { | |
| "fileName": { | |
| "value": "@concat(formatDateTime(variables('i'),'MM-dd-yyyy'),'.csv')", | |
| "type": "Expression" | |
| } | |
| } | |
| } | |
| ], | |
| "outputs": [ | |
| { | |
| "referenceName": "ds_csvStgAccDest", | |
| "type": "DatasetReference" | |
| } | |
| ] | |
| }, | |
| { | |
| "name": "ac_incrementDateP1", | |
| "type": "SetVariable", | |
| "dependsOn": [ | |
| { | |
| "activity": "ac_copyCsvFile", | |
| "dependencyConditions": [ | |
| "Succeeded" | |
| ] | |
| } | |
| ], | |
| "userProperties": [], | |
| "typeProperties": { | |
| "variableName": "j", | |
| "value": { | |
| "value": "@addDays(formatDateTime(variables('i'),'MM-dd-yyyy'),1)", | |
| "type": "Expression" | |
| } | |
| } | |
| }, | |
| { | |
| "name": "ac_incrementDateP2", | |
| "type": "SetVariable", | |
| "dependsOn": [ | |
| { | |
| "activity": "ac_incrementDateP1", | |
| "dependencyConditions": [ | |
| "Succeeded" | |
| ] | |
| } | |
| ], | |
| "userProperties": [], | |
| "typeProperties": { | |
| "variableName": "i", | |
| "value": { | |
| "value": "@variables('j')", | |
| "type": "Expression" | |
| } | |
| } | |
| } | |
| ], | |
| "timeout": "7.00:00:00" | |
| } | |
| } | |
| ], | |
| "variables": { | |
| "i": { | |
| "type": "String", | |
| "defaultValue": "01-22-2020" | |
| }, | |
| "j": { | |
| "type": "String", | |
| "defaultValue": "01-22-2020" | |
| } | |
| }, | |
| "annotations": [], | |
| "lastPublishTime": "2020-09-18T17:38:57Z" | |
| }, | |
| "type": "Microsoft.DataFactory/factories/pipelines" | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment