{ "openapi": "3.0.1", "info": { "title": "Stealth Web Scraper", "description": "General-purpose stealth collection helper for public pages when a dedicated source Actor is not available. Prefer specialized Actors for jobs, ads, maps, and e-commerce.", "version": "0.2", "x-build-id": "iW4SBgeu9Dyq9YUYo" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/lentic_clockss~stealth-web-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-lentic_clockss-stealth-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/lentic_clockss~stealth-web-scraper/runs": { "post": { "operationId": "runs-sync-lentic_clockss-stealth-web-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/lentic_clockss~stealth-web-scraper/run-sync": { "post": { "operationId": "run-sync-lentic_clockss-stealth-web-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "urls": { "title": "URLs to scrape", "minItems": 1, "maxItems": 40, "type": "array", "description": "List of absolute http(s) URLs to scrape. Localhost, direct private, loopback, link-local, multicast, reserved IP, ambiguous numeric, and whitespace/control-character targets are rejected. Only pages successfully written to the default dataset are billed.", "items": { "type": "string" }, "default": [ "https://example.com" ] }, "extractSelectors": { "title": "CSS selectors to extract", "type": "object", "description": "Optional key-value pairs of CSS selectors. Example: {\"title\": \"h1\", \"price\": \".product-price\", \"cta\": \"a[href]\"}. Leave empty to get the page content only.", "default": {} }, "outputFormat": { "title": "Output format", "enum": [ "html", "text", "both" ], "type": "string", "description": "Choose whether to return rendered HTML, plain text, or both.", "default": "text" }, "waitForSelector": { "title": "Wait for selector", "type": "string", "description": "Optional CSS selector expected on the final page before extraction. If it never appears, the page is moved to the failures dataset and is not billed as a successful page." }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 4, "type": "integer", "description": "Pages scraped in parallel. Higher values cut run time and platform cost; the worker retries a few pages if its slots are busy.", "default": 3 }, "pageTimeout": { "title": "Page timeout (seconds)", "minimum": 30, "maximum": 120, "type": "integer", "description": "Maximum time to wait for each page to load and pass anti-bot checks.", "default": 45 }, "proxyGroup": { "title": "Proxy group hint", "enum": [ "auto", "RESIDENTIAL", "BUYPROXIES94952" ], "type": "string", "description": "Optional hint for the scrape worker. Residential egress is provided by the worker (not minted in this Actor). Prefer leaving the default.", "default": "RESIDENTIAL" }, "proxyCountry": { "title": "Proxy country", "type": "string", "description": "Optional ISO country for residential egress (e.g. us, gb, de, kr). When omitted, the worker infers country from the first URL (host map / TLD, e.g. .co.uk→gb, coupang.com→kr)." }, "provider": { "title": "Engine provider", "type": "string", "description": "Optional force: unlocker_only, brightdata_unlocker, patchright, camoufox, orchestrator. Leave empty for automatic ladder." }, "cookies": { "title": "Cookies", "type": "array", "description": "Optional cookies forwarded to the worker browser (Playwright cookie objects).", "items": { "type": "object" } }, "headers": { "title": "Extra HTTP headers", "type": "object", "description": "Optional request headers forwarded to Unlocker / browser (string map)." }, "gotoWaitUntil": { "title": "Navigation wait until", "enum": [ "commit", "domcontentloaded", "load", "networkidle" ], "type": "string", "description": "Browser navigation waitUntil strategy.", "default": "domcontentloaded" }, "blockResources": { "title": "Block heavy resources", "type": "boolean", "description": "When true, worker blocks images/fonts/media to cut proxy bandwidth (default true).", "default": true } } }, "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 } } } } } } } } } }