{ "openapi": "3.0.1", "info": { "title": "Tor Hidden Service Crawler & Contact Extractor", "description": "Crawl Tor .onion sites by URL or keyword search and pull emails, phone numbers, crypto wallet addresses, social handles, and exposed API keys from each page.", "version": "1.0", "x-build-id": "UYaXoEvdhfwElKP1q" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/xyrelith-data~tor-hidden-service-crawler-and-contact-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-xyrelith-data-tor-hidden-service-crawler-and-contact-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/xyrelith-data~tor-hidden-service-crawler-and-contact-extractor/runs": { "post": { "operationId": "runs-sync-xyrelith-data-tor-hidden-service-crawler-and-contact-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/xyrelith-data~tor-hidden-service-crawler-and-contact-extractor/run-sync": { "post": { "operationId": "run-sync-xyrelith-data-tor-hidden-service-crawler-and-contact-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "mode" ], "properties": { "mode": { "title": "Mode", "enum": [ "directories", "search", "byUrls", "crawl", "searchAndCrawl" ], "type": "string", "description": "What to collect. `directories` aggregates public onion directory entries; `search` returns Ahmia index-result metadata; `byUrls` reads directory pages you supply. Legacy `crawl` and `searchAndCrawl` values are accepted and mapped in code.", "default": "directories" }, "source": { "title": "Directory source", "enum": [ "all", "onionTree", "darkFail", "torTaxi" ], "type": "string", "description": "Directory aggregation source (mode=directories). `all` merges OnionTree, dark.fail and tor.taxi.", "default": "onionTree" }, "categories": { "title": "OnionTree categories", "type": "array", "description": "Keep OnionTree entries matching any selected category (mode=directories). Allowed values: archive, blockchain, blog, chat, dead, defcon, ebook, etherpad, forum, git, hacking, hosting, imageboard, jabber, journalism, keyserver, leaks, library, link-list, linux, mail, news, operating-system, pastebin, pgp, publishing, riseup, search, securedrop, security, social-media, tor, upload, video, vpn, vps, whistleblowing, wiki, xmpp. Empty means all neutral categories. This filter is ignored for dark.fail and tor.taxi rows because they carry no tags.", "default": [], "items": { "type": "string" } }, "searchQueries": { "title": "Ahmia search queries", "type": "array", "description": "One or more keywords to query against the Ahmia index (mode=search). Each query is one request; result pages are never opened.", "default": [], "items": { "type": "string" } }, "maxResultsPerQuery": { "title": "Max results per query", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Cap on Ahmia rows per query (mode=search). The global maxItems cap still applies.", "default": 20 }, "startUrls": { "title": "Directory page URLs", "type": "array", "description": "Clearnet or v3 onion directory/index pages to read (mode=byUrls). Only entry links and adjacent structured contact links are parsed; linked onion pages are not opened.", "items": { "type": "object", "properties": { "url": { "type": "string", "title": "Directory page URL", "description": "Clearnet URL or valid v3 .onion directory/index page." } } }, "default": [] }, "maxItems": { "title": "Max output items", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Hard cap on records emitted to the dataset.", "default": 100 }, "maxPages": { "title": "Max directory pages", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum directory pages fetched in mode=byUrls.", "default": 5 }, "verifyLiveness": { "title": "Verify onion liveness through Tor", "type": "boolean", "description": "Fetch each unique onion domain once through Tor and fill measured status, HTTP code, page title and check time. Applies to directories and byUrls; search mode never opens result pages.", "default": true }, "livenessTimeoutSecs": { "title": "Liveness timeout (seconds)", "minimum": 5, "maximum": 60, "type": "integer", "description": "Per-domain timeout for the optional Tor liveness check.", "default": 12 }, "includeUnreachable": { "title": "Include unreachable entries", "type": "boolean", "description": "When liveness is enabled, keep entries measured as timeout or unreachable. Applies only when verifyLiveness is true.", "default": true }, "extractEmails": { "title": "Include contact emails", "type": "boolean", "description": "Include structured emails from OnionTree PGP user IDs and explicit mailto: links on directory pages. No free-text email mining.", "default": true }, "extractPhones": { "title": "Include phone numbers", "type": "boolean", "description": "Include phone numbers from explicit tel: links on directory pages only. No free-text phone mining.", "default": true }, "extractSocialHandles": { "title": "Include social profiles", "type": "boolean", "description": "Include handles from explicit X/Twitter, Instagram and Telegram profile links on directory pages only.", "default": true }, "extractPgpContacts": { "title": "Include PGP contact metadata", "type": "boolean", "description": "Include OnionTree PGP fingerprint, key ID and contact email. The public key block itself is never stored.", "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 } } } } } } } } } }