{
"openapi": "3.0.1",
"info": {
"title": "Public Document Finder — Domain & Company Files",
"description": "Find public PDFs and files for a company, domain, or keyword — no logins, no API keys. Search, Google Drive, cloud shares, Wayback, GitHub, sitemaps, and site crawls. Deduped URLs with type, host, and channel for lead gen and recon.",
"version": "0.1",
"x-build-id": "7LNUNTDn3naCdXJxr"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/bakos_bence~public-document-finder/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-bakos_bence-public-document-finder",
"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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/bakos_bence~public-document-finder/runs": {
"post": {
"operationId": "runs-sync-bakos_bence-public-document-finder",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/bakos_bence~public-document-finder/run-sync": {
"post": {
"operationId": "run-sync-bakos_bence-public-document-finder",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"queries": {
"title": "Domains or keywords",
"type": "array",
"description": "One per line. Hostname (e.g. nasa.gov) runs site-scoped discovery; keywords run filetype search. Prefer apex domains over long marketing URLs. Examples: who.int, nasa.gov, mozilla.org, europa.eu, cdc.gov, un.org, worldbank.org, annual report, investor presentation, privacy policy pdf.",
"items": {
"type": "string"
},
"default": [
"who.int"
]
},
"keyword": {
"title": "Extra keyword",
"type": "string",
"description": "Narrows domain searches (e.g. transparency, pricing, annual report) — combined with filetype queries."
},
"includeSubdomains": {
"title": "Discover subdomains",
"type": "boolean",
"description": "Find public hosts under your apex (certificate transparency + host lists), then extend search, sitemaps, and crawls. www and apex are always prioritized.",
"default": true
},
"maxSubdomains": {
"title": "Subdomain cap",
"type": "integer",
"description": "Maximum extra hosts to expand after discovery (does not limit Wayback/Common Crawl domain-wide queries).",
"default": 25
},
"channels": {
"title": "Discovery channels",
"type": "array",
"description": "Leave empty to run all seven channels below. Only these ids work — any other value is dropped silently.",
"items": {
"type": "string",
"enum": [
"commonCrawl",
"wayback",
"search",
"sitemap",
"siteCrawl",
"cloudShares",
"wellKnown"
],
"enumTitles": [
"Common Crawl",
"Wayback Machine",
"DuckDuckGo search",
"Sitemap",
"Site crawl",
"Cloud shares",
"Well-known paths"
]
}
},
"fileTypes": {
"title": "File extensions",
"type": "array",
"description": "Extensions without dots. Leave empty for the full OSINT set (PDF, Office, CSV, JSON, archives, …). Examples: pdf, docx, xlsx, csv, pptx, json, zip, txt, md.",
"items": {
"type": "string"
}
},
"maxItems": {
"title": "Maximum documents",
"minimum": 1,
"type": "integer",
"description": "Stop after this many unique document URLs (minimum 1; 0 is not supported). Prefill 5 for a cheap first run.",
"default": 5
},
"query": {
"title": "Single query (API alias)",
"type": "string",
"description": "Optional one domain or keyword. For several targets, use Domains or keywords above."
},
"domains": {
"title": "Domains list (alias)",
"type": "array",
"description": "Same as queries when you only pass hostnames.",
"items": {
"type": "string"
}
},
"startUrls": {
"title": "Website URLs (alias)",
"type": "array",
"description": "Full URLs — only the hostname is used as the domain.",
"items": {
"type": "string"
}
},
"domain": {
"title": "Single domain (alias)",
"type": "string",
"description": "One hostname alias of the queries list."
},
"fileType": {
"title": "Single file type (alias)",
"type": "string",
"description": "One extension alias of File extensions."
},
"maxResults": {
"title": "Maximum documents (alias)",
"minimum": 1,
"type": "integer",
"description": "Alias of Maximum documents when maxItems is omitted (same cap). Minimum 1.",
"default": 5
},
"proxy": {
"title": "Proxy (alias)",
"type": "object",
"description": "Ignored at runtime — managed direct egress. Leave default."
},
"proxyConfiguration": {
"title": "Proxy configuration",
"type": "object",
"description": "Ignored at runtime — the Actor uses direct egress. Leave default.",
"default": {
"useApifyProxy": false
}
}
}
},
"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
}
}
}
}
}
}
}
}
}
}