{ "openapi": "3.0.1", "info": { "title": "AI Scraper Builder Selextract: describe the data, get a scraper", "description": "Describe the data you want in plain English. The Actor builds a scraper, checks that it returns that data, and saves the rows to your dataset. Re-run saved scrapers by ID without building again.", "version": "0.1", "x-build-id": "gxmdHWP20yYFSjHxc" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/stefanie-rink~ai-scraper-builder/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-stefanie-rink-ai-scraper-builder", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/stefanie-rink~ai-scraper-builder/runs": { "post": { "operationId": "runs-sync-stefanie-rink-ai-scraper-builder", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/stefanie-rink~ai-scraper-builder/run-sync": { "post": { "operationId": "run-sync-stefanie-rink-ai-scraper-builder", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "prompt": { "title": "What data do you want?", "type": "string", "description": "Describe the data in plain English, including the fields you need. Example: \"All fiction books on books.toscrape.com with title, price, rating and stock status\". Required unless you give a scraper ID." }, "url": { "title": "Start URL (optional)", "type": "string", "description": "A page to start from. Leave empty to let the Actor find the right site." }, "scraperId": { "title": "Scraper ID or run ID (optional)", "type": "string", "description": "Re-run a scraper you built before, without building again. Enter its scraper ID, or the run ID of an earlier run of this Actor that built or ran it. You'll find the scraper ID in that run's status message, Log and Output tab." }, "scraperInput": { "title": "Scraper inputs (optional)", "type": "object", "description": "Values for the scraper's own inputs, such as a search term, as JSON. Example: {\"query\": \"running shoes\"}. Used when an existing scraper runs (a re-run or a reused scraper), not on a new build. After a build, the Log and the Output tab list the inputs that scraper takes." }, "mode": { "title": "Mode", "enum": [ "auto", "build", "rerun" ], "type": "string", "description": "Auto reuses your scraper when you give a scraper ID or run ID, or repeat one of your earlier requests word for word; otherwise it builds a new one. Build always builds: a new scraper, or a new version of the one you already have for this request. Re-run only runs a saved scraper and never builds; use it for scheduled Tasks.", "default": "auto" }, "rebuildMethod": { "title": "How to build again", "enum": [ "fresh", "repair" ], "type": "string", "description": "Used when the Actor rebuilds a scraper you already have. Fresh build starts from scratch. Repair starts from your current scraper and fixes what stopped working, which can help after a website change. Either way the result is a new version with the same scraper ID, so your Tasks keep working. If the new version fails the check, the current one stays and nothing is charged.", "default": "fresh" }, "maxResults": { "title": "Maximum results", "minimum": 1, "maximum": 1000, "type": "integer", "description": "The most rows to save. Each saved row is charged as one result.", "default": 100 } } }, "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 } } } } } } } } } }