{ "openapi": "3.0.1", "info": { "title": "Olostep Web Scraper", "description": "Automate web search, scraping and crawling with Apify Actors using Olostep — the API to search, extract and structure web data for your workflows.", "version": "1.0", "x-build-id": "b1gbE5hzTqNtwkdrz" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/olostep~olostep-web-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-olostep-olostep-web-scraper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/olostep~olostep-web-scraper/runs": { "post": { "operationId": "runs-sync-olostep-olostep-web-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/olostep~olostep-web-scraper/run-sync": { "post": { "operationId": "run-sync-olostep-olostep-web-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "operation", "apiKey" ], "properties": { "operation": { "title": "Operation Type", "enum": [ "scrape", "batch", "crawl", "map", "answers" ], "type": "string", "description": "Select which Olostep operation to perform", "default": "scrape" }, "apiKey": { "title": "Olostep API Key", "type": "string", "description": "Your Olostep API key. Get it from https://olostep.com/dashboard" }, "url_to_scrape": { "title": "URL to Scrape", "type": "string", "description": "The URL of the website to scrape (required for 'scrape' operation)" }, "formats": { "title": "Output Format", "enum": [ "html", "markdown", "json", "text" ], "type": "string", "description": "Format for the scraped content output", "default": "markdown" }, "country": { "title": "Country Code", "type": "string", "description": "Optional country code (e.g., US, GB, CA) for location-specific scraping" }, "wait_before_scraping": { "title": "Wait Before Scraping (milliseconds)", "type": "integer", "description": "Wait time in milliseconds before scraping (useful for dynamic content)", "default": 0 }, "parser": { "title": "Parser ID", "type": "string", "description": "Optional parser ID for specialized content extraction (e.g., @olostep/amazon-product)" }, "batch_array": { "title": "Batch URLs Array", "type": "string", "description": "JSON array of objects with 'url' and optional 'custom_id' fields (required for 'batch' operation). Example: [{\"url\":\"https://example.com\",\"custom_id\":\"site1\"}]" }, "start_url": { "title": "Start URL", "type": "string", "description": "The starting URL for the crawl (required for 'crawl' operation)" }, "max_pages": { "title": "Maximum Pages", "type": "integer", "description": "Maximum number of pages to crawl", "default": 10 }, "follow_links": { "title": "Follow Links", "type": "boolean", "description": "Whether to follow links found on pages", "default": true }, "website_url": { "title": "Website URL", "type": "string", "description": "Website URL to extract links from (required for 'map' operation)" }, "search_query": { "title": "Search Query", "type": "string", "description": "Optional search query to filter URLs" }, "top_n": { "title": "Top N URLs", "type": "integer", "description": "Limit the number of URLs returned" }, "include_patterns": { "title": "Include URL Patterns", "type": "string", "description": "Glob patterns to include specific paths (e.g., /blog/**)" }, "exclude_patterns": { "title": "Exclude URL Patterns", "type": "string", "description": "Glob patterns to exclude specific paths (e.g., /admin/**)" }, "task": { "title": "Answers Task", "type": "string", "description": "Question or task to answer using web data (required for 'answers' operation)." }, "json": { "title": "Desired JSON Shape", "type": "string", "description": "Optional JSON schema/object or short description of the desired output. Example: {\"company\":\"\",\"round\":\"\",\"date\":\"\",\"amount\":\"\"}" } } }, "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 } } }, "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 } } } } } } } } } }