{ "openapi": "3.0.1", "info": { "title": "Universal Data Harvester", "description": "Harvest data from anywhere - Web, Maps, Business, Social", "version": "2.2", "x-build-id": "VBcid2K3lMMs9cqY8" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/caring_dizi~universal-data-harvester/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-caring_dizi-universal-data-harvester", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/caring_dizi~universal-data-harvester/runs": { "post": { "operationId": "runs-sync-caring_dizi-universal-data-harvester", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/caring_dizi~universal-data-harvester/run-sync": { "post": { "operationId": "run-sync-caring_dizi-universal-data-harvester", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "queries", "engines" ], "properties": { "queries": { "title": "Search queries", "type": "array", "description": "Keywords to search. One query per line.", "items": { "type": "string" } }, "quoteHandles": { "title": "Quote handle-like tokens", "type": "boolean", "description": "Wraps tokens with _ or - in quotes so Google cannot rewrite asiaaa___princess into Princess Asia. nfpr=1 alone is not enough.", "default": true }, "engines": { "title": "Search engines", "minItems": 1, "uniqueItems": true, "type": "array", "description": "Run the same queries across these engines. Default is Brave + Bing. Google 429s on residential; leave it off unless you want to burn retries. Yandex is optional and often captchas.", "items": { "type": "string", "enum": [ "google", "bing", "duckduckgo", "yandex", "brave" ], "enumTitles": [ "Google", "Bing", "DuckDuckGo", "Yandex", "Brave" ] }, "default": [ "brave", "bing" ] }, "resultsPerEngine": { "title": "Results per engine", "minimum": 1, "maximum": 50, "type": "integer", "description": "Organic results to keep for each query on each engine.", "default": 10 }, "proxyCountries": { "title": "Residential proxy countries", "minItems": 1, "uniqueItems": true, "type": "array", "description": "Each country gets its own RESIDENTIAL exit plus matching Accept-Language, timezone, and GPS. Datacenter IPs are refused. Pick more than one to catch geo-fenced / split-index results.", "items": { "type": "string", "enum": [ "US", "IT", "VN", "NL", "DE", "GB", "FR", "CA", "AU", "JP", "BR", "IN", "RU" ], "enumTitles": [ "United States", "Italy", "Vietnam", "Netherlands", "Germany", "United Kingdom", "France", "Canada", "Australia", "Japan", "Brazil", "India", "Russia (used automatically for Yandex)" ] }, "default": [ "US", "NL" ] }, "usSubdivisions": { "title": "US states (optional)", "uniqueItems": true, "type": "array", "description": "Only used when United States is selected. Targets a state residential pool (AZ vs NY) instead of a generic US exit.", "items": { "type": "string", "enum": [ "AZ", "NY", "CA", "TX", "FL", "WA", "IL" ], "enumTitles": [ "Arizona", "New York", "California", "Texas", "Florida", "Washington", "Illinois" ] } }, "forceResidential": { "title": "Refuse datacenter proxies", "type": "boolean", "description": "Search engines block AWS/DigitalOcean ranges. Keep this on. Actor will error if you pick a non-RESIDENTIAL Apify group or disable proxy with no residential URLs.", "default": true }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Apify Proxy. Country/state above override the widget. Do not pick datacenter groups." }, "language": { "title": "Language override (legacy)", "type": "string", "description": "Ignored when proxy countries are set. Locale is taken from the residential country so IP and headers match.", "default": "en-US" }, "country": { "title": "Country fallback (legacy)", "type": "string", "description": "Used only if no residential countries are selected.", "default": "us" }, "saveEvidence": { "title": "Save screenshots + HTML", "type": "boolean", "description": "Writes full-page PNG and raw HTML into the key-value store so a fake takedown page cannot hide behind a 200 status.", "default": true }, "evidenceMode": { "title": "When to save evidence", "enum": [ "blocked", "empty", "always" ], "type": "string", "description": "blocked = failures and empty SERPs. empty = anything that is not a clean hit list. always = every search (burns residential GB).", "default": "blocked" }, "uncloakHidden": { "title": "Force-reveal hidden results", "type": "boolean", "description": "Un-hide display:none / visibility:hidden players, galleries, and result cards some sites cloak by locale.", "default": true }, "blockHeavyAssets": { "title": "Block images / fonts / media", "type": "boolean", "description": "Saves residential GB. Leave on for search pages. Turn off if you need pretty screenshots.", "default": true }, "sessionRotation": { "title": "Rotate browser session", "type": "boolean", "description": "New cookie jar / fingerprint session when a page looks blocked.", "default": true }, "stealth": { "title": "Stealth + telemetry spoof", "type": "boolean", "description": "Hide webdriver, spoof navigator.language, pin timezone to the proxy country, and log geo-IP API calls (ipapi, maxmind, ipify).", "default": true }, "minDelayMs": { "title": "Min delay between searches (ms)", "minimum": 0, "type": "integer", "description": "Jittered wait before each SERP. Slows blocks.", "default": 1200 }, "maxDelayMs": { "title": "Max delay between searches (ms)", "minimum": 0, "type": "integer", "description": "Upper bound of the jittered wait before each SERP.", "default": 3200 }, "maxConcurrency": { "title": "Concurrency", "minimum": 1, "maximum": 4, "type": "integer", "description": "Keep this low. Search engines punish parallel tabs. Residential RTT is also slower.", "default": 1 }, "maxRequestRetries": { "title": "Retries on block / fail", "minimum": 0, "maximum": 8, "type": "integer", "description": "Retries after a captcha, empty SERP, or navigation fail.", "default": 3 }, "navigationTimeoutSecs": { "title": "Navigation timeout (sec)", "minimum": 15, "type": "integer", "description": "How long to wait for a search page to load before failing the request.", "default": 60 }, "headless": { "title": "Headless browser", "type": "boolean", "description": "Run Chromium without a visible window. Leave on for Apify cloud.", "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 } } } } } } } } } }