{ "openapi": "3.0.1", "info": { "title": "Web Scraping API", "description": "Web Scraping API that quickly and reliably scrapes any website—no selectors required. Premium proxies, CAPTCHA solving, JavaScript rendering, and automated structured data extraction are all included. It’s just $2 per 1,000 web pages scraped, with no minimum spend.", "version": "4.3", "x-build-id": "gneO6PV3xbu8XBV8y" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/zeeb0t~web-scraping-api---scrape-any-website/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-zeeb0t-web-scraping-api---scrape-any-website", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/zeeb0t~web-scraping-api---scrape-any-website/runs": { "post": { "operationId": "runs-sync-zeeb0t-web-scraping-api---scrape-any-website", "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/zeeb0t~web-scraping-api---scrape-any-website/run-sync": { "post": { "operationId": "run-sync-zeeb0t-web-scraping-api---scrape-any-website", "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": { "endpoint": { "title": "Endpoint Name", "enum": [ "scrape", "links", "next", "search" ], "type": "string", "description": "Which API endpoint to call. Choose from 'scrape', 'links', 'next', or 'search'. Defaults to 'scrape' if not provided." }, "output_preference": { "title": "Output Preference", "enum": [ "json", "tabular", "meta" ], "type": "string", "description": "What is your output preference? For programmatic integrations choose 'json'. To view the data in a table or for CSV export, choose 'tabular'. Defaults to 'meta', which means the API will return the data as either 'json' or 'tabular' depending on the origin of the request." }, "url": { "title": "URL of the page", "type": "string", "description": "The URL of the webpage you want to extract data from. (Used by endpoints: 'scrape', 'links', 'next'.)" }, "fields": { "title": "Data Extraction Fields", "type": "object", "description": "A JSON object describing the data you want extracted. (Used by endpoint: 'scrape'.)" }, "description": { "title": "Description of Links", "type": "string", "description": "A short text indicating the type of links to extract, e.g. 'individual product urls'. (Used by endpoint: 'links'.)" }, "google_domain": { "title": "Google Search Domain", "type": "string", "description": "Domain for Google search, e.g., 'www.google.com', 'www.google.com.au', etc. (Used by endpoint: 'search'.)" }, "query": { "title": "Search Query", "type": "string", "description": "The search phrase you'd like to search for in Google. (Used by endpoint: 'search'.)" }, "page": { "title": "Google Search Page", "type": "integer", "description": "Which page of Google search results to fetch. (Used by endpoint: 'search'.)" }, "method": { "title": "(Deprecated) API Method Name", "type": "string", "description": "Legacy name for the API method; no longer required or used." }, "output": { "title": "(Deprecated) API Output Structure", "type": "string", "description": "Previously used for specifying the /scrape output JSON. Replaced by 'fields'." }, "proxy_country": { "title": "(Deprecated) Proxy Country", "type": "string", "description": "Previously used for specifying a premium proxy geolocation. No longer supported." } } }, "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 } } } } } } } } } }