{ "openapi": "3.0.1", "info": { "title": "Job Dedupe & Merge — Remove Duplicate Jobs Across Boards", "description": "Merge job data from several scrapers and remove duplicate jobs: the same opening on LinkedIn, Indeed and a company's Greenhouse page becomes one row, with every URL and source kept. Optional memory returns only jobs that are new since the last run. Nothing is scraped.", "version": "0.1", "x-build-id": "ZIkapXpyc5f24zzwX" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/northbell~job-dedupe-merge/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-northbell-job-dedupe-merge", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/northbell~job-dedupe-merge/runs": { "post": { "operationId": "runs-sync-northbell-job-dedupe-merge", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/northbell~job-dedupe-merge/run-sync": { "post": { "operationId": "run-sync-northbell-job-dedupe-merge", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "jobs": { "title": "Jobs", "type": "array", "description": "Rows from any job scraper, as they are. Read from the usual field names: title / jobTitle / positionName, company / companyName / hiringOrganization, location / jobLocation, url / jobUrl / applyUrl, postedAt / datePosted / postedOn. Summary and error rows are skipped. Up to 100,000 rows per run, together with the datasets below." }, "datasetIds": { "title": "Datasets to merge", "type": "array", "description": "Datasets from your other Actor runs: pick them here, or pass their IDs (defaultDatasetId) through the API. The Actor gets read access to the datasets you pick and nothing else. Each is read in full and merged with the rows above, so you do not have to copy anything." }, "outputMode": { "title": "Output", "enum": [ "merged", "annotated" ], "type": "string", "description": "One row per job keeps the fullest row of each group and adds every URL and source. Every row returns all your rows with the group key, so you can check what was merged.", "default": "merged" }, "rememberAcrossRuns": { "title": "Remember jobs between runs", "type": "boolean", "description": "Keep the jobs seen so far (in your key-value store job-dedupe-history, for 120 days) and mark each job as new or already seen. Turn on for a daily feed.", "default": false }, "onlyNew": { "title": "Return only new jobs", "type": "boolean", "description": "With memory on: return only jobs not seen in an earlier run. Turn off to get all jobs with a newSinceLastRun flag.", "default": true }, "historyName": { "title": "Memory name", "type": "string", "description": "Separate memories for separate feeds (for example \"us-engineering\" and \"uk-sales\"). Letters, numbers and dashes.", "default": "default" } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }