{
"openapi": "3.0.1",
"info": {
"title": "Website Legal Entity Extractor: CIF, VAT & Audit",
"description": "Find the company behind any website: CIF/NIF, EU VAT ID and legal name, plus cookie-consent, security, SEO and social-profile audit in one run.",
"version": "0.0",
"x-build-id": "HsmbWg1dlkkxRFMJD"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/rastriq~legal-entity-extractor/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-rastriq-legal-entity-extractor",
"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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/rastriq~legal-entity-extractor/runs": {
"post": {
"operationId": "runs-sync-rastriq-legal-entity-extractor",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/rastriq~legal-entity-extractor/run-sync": {
"post": {
"operationId": "run-sync-rastriq-legal-entity-extractor",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": [
"startUrls"
],
"properties": {
"startUrls": {
"title": "Website URLs",
"type": "array",
"description": "Home pages (or any page) of the websites to analyze. Example: https://www.example.es. The actor looks for the tax ID on the page, then in the privacy policy and legal notice (aviso legal) linked from it.",
"items": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"title": "URL of a web page",
"format": "uri"
}
}
}
},
"maxPagesPerSite": {
"title": "Max pages per site",
"minimum": 1,
"maximum": 500,
"type": "integer",
"description": "Maximum number of pages audited per website (one billed result per page). Use 1 to only analyze the URL you provide; higher values also follow internal links.",
"default": 1
},
"consentStates": {
"title": "Consent states to test",
"type": "array",
"description": "baseline: no interaction with the banner. reject: rejects non-essential cookies. accept: accepts all. Selecting only baseline is about 3x faster. Example: [\"baseline\"].",
"items": {
"type": "string",
"enum": [
"baseline",
"reject",
"accept"
],
"enumTitles": [
"Baseline (no interaction)",
"Reject all",
"Accept all"
]
},
"default": [
"baseline",
"reject",
"accept"
]
},
"locales": {
"title": "Browser language",
"type": "array",
"description": "Browser locale used for the audit. It affects the language of the consent banner and the page. The first value is used. Example: es-ES, en-GB, de-DE.",
"items": {
"type": "string"
},
"default": [
"es-ES"
]
},
"captureRawCookieValues": {
"title": "Store raw cookie values",
"type": "boolean",
"description": "When off, cookie values and tracking identifiers are masked before saving. Turn on only if you need real values for forensic analysis.",
"default": false
},
"captureRequestPayloadValues": {
"title": "Store request payloads",
"type": "boolean",
"description": "When off, HTTP request bodies are redacted. Turn on to inspect what data trackers send.",
"default": false
},
"includeUrlGlobs": {
"title": "Include URL patterns",
"type": "array",
"description": "Only internal links matching these globs are followed. Example: https://example.com/legal/**",
"items": {
"type": "object",
"required": [
"glob"
],
"properties": {
"glob": {
"type": "string",
"title": "Glob of a web page"
}
}
}
},
"excludeUrlGlobs": {
"title": "Exclude URL patterns",
"type": "array",
"description": "Internal links matching these globs are skipped. Example: https://example.com/blog/**",
"items": {
"type": "object",
"required": [
"glob"
],
"properties": {
"glob": {
"type": "string",
"title": "Glob of a web page"
}
}
}
},
"respectRobotsTxt": {
"title": "Respect robots.txt",
"type": "boolean",
"description": "Skip pages disallowed by robots.txt when discovering internal links.",
"default": true
},
"proxyConfiguration": {
"title": "Proxy configuration",
"type": "object",
"description": "Proxy used for the audit. Consent banners are often geo-targeted: set the country to where your audience is (for example ES, DE, FR) to see the EU banner. Not every country is available on datacenter proxies.",
"default": {
"useApifyProxy": true,
"apifyProxyCountry": "US"
}
},
"saveDetailedDatasets": {
"title": "Save detailed raw datasets",
"type": "boolean",
"description": "Also write 8 raw named datasets per run (pcs-RUNID-pages, -network-requests, -detections, -storage-items, -consent-audit, -tracking-ids, -social-profiles, -sites). Named datasets are kept in your storage until you delete them. Leave off unless you need raw request-level evidence.",
"default": false
},
"maxConcurrency": {
"title": "Max concurrency",
"minimum": 1,
"maximum": 20,
"type": "integer",
"description": "Pages processed in parallel. Higher is faster but needs more memory (4 GB is enough for the default).",
"default": 4
},
"maxRequestsPerCrawl": {
"title": "Max requests per run",
"minimum": 1,
"maximum": 10000,
"type": "integer",
"description": "Hard cap on total pages requested in the whole run.",
"default": 100
},
"pageTimeoutSeconds": {
"title": "Page timeout",
"minimum": 10,
"maximum": 120,
"type": "integer",
"description": "Navigation timeout for each page load, in seconds.",
"default": 45
},
"userAgent": {
"title": "Custom User-Agent",
"type": "string",
"description": "Leave empty to use the default Chromium user agent."
}
}
},
"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
}
}
}
}
}
}
}
}
}
}