{ "openapi": "3.0.1", "info": { "title": "Stealth Web Scraper - HTML, Text & Contact Data", "description": "Extract text, HTML, CSS-selected fields and public contact details from supplied web pages across countries. Pay per successful page row plus a small start fee.", "version": "0.3", "x-build-id": "uqo5gFvvSiflqfI9x" }, "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": "Input URLs (one row per URL)", "minItems": 1, "maxItems": 40, "type": "array", "description": "Enter 1 to 40 full public HTTP or HTTPS URLs. Each unique URL produces at most one successful row; duplicates are removed. Empty input uses three example pages at normal prices. Private-network and localhost URLs are rejected.", "items": { "type": "string" } }, "maxResults": { "title": "Max results per URL", "minimum": 1, "type": "integer", "description": "Maximum rows per input URL, default 70. Each URL produces at most one page row, so any value of 1 or more gives the same limit; reduce the number of URLs to make the whole run smaller.", "default": 70 }, "extractSelectors": { "title": "CSS selectors to extract", "type": "object", "description": "Map your field names to CSS selectors, for example {\"heading\":\"h1\",\"price\":\".price\"}. Values appear in extracted; matching several elements returns a list. Leave empty for page content and available contact attributes.", "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 that must appear before extraction. If it is not found, the page goes to the failures dataset without a successful-row charge." }, "maxConcurrency": { "title": "Pages processed together", "minimum": 1, "maximum": 4, "type": "integer", "description": "Requested number of pages to process at the same time, from 1 to 4. The Actor may reduce this number when capacity is limited.", "default": 3 }, "pageTimeout": { "title": "Page timeout (seconds)", "minimum": 30, "maximum": 120, "type": "integer", "description": "Page-loading allowance in seconds, from 30 to 120. This is separate from the overall run timeout, which defaults to 900 seconds.", "default": 45 }, "proxyGroup": { "title": "Connection preference", "enum": [ "auto", "RESIDENTIAL", "BUYPROXIES94952" ], "type": "string", "description": "Optional connection preference. Leave the default unchanged for normal use; a preference does not guarantee availability.", "default": "RESIDENTIAL" }, "proxyCountry": { "title": "Country hint", "pattern": "^[A-Za-z]{2}$", "type": "string", "description": "Optional two-letter country hint, such as us, gb or de. Leave empty to use the default location; availability varies by page." }, "provider": { "title": "Developer testing option", "type": "string", "description": "Leave empty. Used only by the developer for testing." }, "cookies": { "title": "Cookies", "type": "array", "description": "Optional cookie objects with name and value, plus applicable URL or domain and path fields. Use only cookies you are authorized to supply; leave empty for normal public-page runs.", "items": { "type": "object" } }, "headers": { "title": "Extra HTTP headers", "type": "object", "description": "Optional object mapping request header names to string values. Leave empty unless a public page needs a specific header." }, "gotoWaitUntil": { "title": "Page loading milestone", "enum": [ "commit", "domcontentloaded", "load", "networkidle" ], "type": "string", "description": "Choose when navigation is considered ready: commit, domcontentloaded, load or networkidle. The default is domcontentloaded; waitForSelector can require a specific element.", "default": "domcontentloaded" }, "blockResources": { "title": "Block heavy resources", "type": "boolean", "description": "Skip images, fonts and media where supported. This can reduce page loading, but may affect completeness on pages that depend on those resources.", "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 }, "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 } } } } } } } } } }