{ "openapi": "3.0.1", "info": { "title": "Web Scraping Extractor Data API - Import.io Crawl Runs, Reports", "description": "Export the output of your own Import.io web data extractors: every extracted row of the latest finished or any crawl run, crawl run history and stats, data and change report rows, extractors, inputs, plan and usage. Read only: nothing is started or changed. Bring your own key.", "version": "0.1", "x-build-id": "7QxtCK76PgRCkulGq" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/nabeelbaghoor~web-scraping-extractor-data-api/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-nabeelbaghoor-web-scraping-extractor-data-api", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/nabeelbaghoor~web-scraping-extractor-data-api/runs": { "post": { "operationId": "runs-sync-nabeelbaghoor-web-scraping-extractor-data-api", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/nabeelbaghoor~web-scraping-extractor-data-api/run-sync": { "post": { "operationId": "run-sync-nabeelbaghoor-web-scraping-extractor-data-api", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "service": { "title": "What to read", "enum": [ "extractors", "latestResult", "crawlRuns", "crawlRunResult", "crawlRunDetails", "extractorDetails", "extractorInputs", "reports", "reportRuns", "reportRunResult", "reportRunDetails", "subscription" ], "type": "string", "description": "Extractors lists every extractor in the account and needs nothing else, so it is the default; it is where extractor ids come from. Latest result returns every extracted row of an extractor's newest finished crawl run. Crawl runs lists run history, which is where crawl run ids come from. Reports and report runs list data and change reports, which is where report run ids come from.", "default": "extractors" }, "identifiers": { "title": "Ids", "type": "array", "description": "One per line. Extractor ids for latest result, extractor details and inputs, and optionally to narrow crawl runs. Crawl run ids for result and details of a crawl run. Report run ids for rows and details of a report run, and optionally report ids to narrow report runs. Extractors, reports and plan and usage read none.", "items": { "type": "string" } }, "crawlRunState": { "title": "Crawl run state", "enum": [ "any", "FINISHED", "STARTED", "PENDING", "CANCELLED", "FAILED" ], "type": "string", "description": "Crawl runs only: keep only runs in this state. Any keeps every run.", "default": "any" }, "sortDirection": { "title": "Order", "enum": [ "DESC", "ASC" ], "type": "string", "description": "Lists only (extractors, crawl runs, reports, report runs): sort by creation time, newest first by default.", "default": "DESC" }, "reportFileType": { "title": "Report file", "enum": [ "csv", "json" ], "type": "string", "description": "Rows of a report run only: the results file read. CSV works for every report; JSON exists for change reports only.", "default": "csv" }, "maxResults": { "title": "Maximum results", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stop after this many rows. One crawl run can hold many thousands of extracted rows.", "default": 1000 }, "requestsPerMinute": { "title": "Requests per minute", "minimum": 1, "maximum": 300, "type": "integer", "description": "Pacing ceiling for calls to the provider. Rate limited answers are retried after a pause.", "default": 60 }, "apiKey": { "title": "API key", "type": "string", "description": "Your own API key, copied from account settings in your Import.io dashboard. This actor is bring-your-own-key and never ships one. Leave blank to use the DATA_API_KEY environment secret. The key is never written to a row or logged." }, "baseUrl": { "title": "API base URL", "type": "string", "description": "Override the host the actor calls. Only useful for testing against a different environment." } } }, "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 } } } } } } } } } }