{ "openapi": "3.0.1", "info": { "title": "Torrent / BitTorrent DHT corpus search & crawl statistics", "description": "Search a live BitTorrent DHT metadata corpus and see how fast it is growing. Two endpoints: /search with category filters and relevance ranking, and /stats with a per-minute capture rate you can verify. No endpoint or key needed — the corpus is crawled and hosted by this Actor's operator.", "version": "1.1", "x-build-id": "1opd8r0gKYaj9Up8z" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/apricot_inference~fast-tracker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-apricot_inference-fast-tracker", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/apricot_inference~fast-tracker/runs": { "post": { "operationId": "runs-sync-apricot_inference-fast-tracker", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/apricot_inference~fast-tracker/run-sync": { "post": { "operationId": "run-sync-apricot_inference-fast-tracker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "query": { "title": "Query", "type": "string", "description": "Free text, up to 200 characters. Separators are normalised, so \"ubuntu 24 04\" matches \"ubuntu-24.04-desktop-amd64.iso\". Leave empty to browse with filters only. This is a DHT crawl rather than a curated catalogue, so a specific title may genuinely not be present — run the Crawl statistics action to see what the corpus does contain." }, "category": { "title": "Category", "enum": [ "", "video", "audio", "software", "archive", "document", "image" ], "type": "string", "description": "Restrict to one category. These describe file content, not intent: a Linux or game ISO is \"archive\", while \"software\" means installers and packages (.exe, .msi, .deb, .rpm, .apk). Leave unset unless you are sure which one you want — the filter is exact, so the wrong guess returns nothing rather than less.", "default": "" }, "sort": { "title": "Sort order", "enum": [ "seeders", "newest", "relevance", "size" ], "type": "string", "description": "Seeders, Newest and Size are the corpus server's own orderings, forwarded untouched. Relevance has no server-side equivalent — that API sorts by seeders, size or capture time only — so it is computed by this Actor over a candidate window drawn in seeder order. That makes it a re-ranking of candidates rather than of the whole corpus, and it needs a query.", "default": "seeders" }, "minSeeders": { "title": "Minimum seeders", "minimum": 0, "type": "integer", "description": "Drop records below this seeder count. Falls back to the DHT peer count for records the tracker scrape has not reached yet.", "default": 0 }, "year": { "title": "Year", "type": "string", "description": "Release year parsed from the name, for example 2024. Only matches records the parse job has processed." }, "resolution": { "title": "Resolution", "type": "string", "description": "Resolution parsed from the name, for example 1080p." }, "maxItems": { "title": "Maximum records", "minimum": 1, "maximum": 100200, "type": "integer", "description": "Stop after this many records. Paging is capped at offset 100000, so roughly 100200 records are reachable for any single query — narrow the query rather than paging deeper.", "default": 1000 }, "pageSize": { "title": "Records per request", "minimum": 1, "maximum": 200, "type": "integer", "description": "The API caps this at 200. Lower it only to be gentler on the corpus host.", "default": 200 }, "action": { "title": "Action", "enum": [ "search", "stats" ], "type": "string", "description": "Search returns records to the dataset. Crawl statistics measures how fast the corpus is growing and publishes the evidence.", "default": "search" }, "statsWindowMinutes": { "title": "Measurement window", "minimum": 1, "maximum": 1440, "type": "integer", "description": "How far back to count captures. At roughly 150 records per minute, 60 minutes costs about 45 requests against the corpus host.", "default": 60 }, "statsMaxPages": { "title": "Page budget", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Hard ceiling on requests for the measurement. If the budget runs out before the window is covered, the result reports the shorter window it actually measured rather than extrapolating.", "default": 200 }, "crossCheckSeconds": { "title": "Cross-check dwell", "minimum": 0, "maximum": 900, "type": "integer", "description": "The row count is read before and after the measurement; the delta is an independent estimate of the same rate. Set a dwell to widen that interval — below 10 seconds the batch writer's commit boundaries dominate and the figure is noise. 0 uses however long the measurement took.", "default": 0 }, "relevancePoolMultiplier": { "title": "Candidate pool multiplier", "minimum": 1, "maximum": 50, "type": "integer", "description": "Candidates to collect per requested record. 5 means a 200-record page is chosen from 1000 candidates.", "default": 5 }, "relevanceMaxCandidates": { "title": "Maximum candidates", "minimum": 200, "maximum": 20000, "type": "integer", "description": "Hard ceiling on the candidate window, whatever the multiplier works out to. Every 200 candidates is one request against a deployment that is also crawling.", "default": 2000 }, "standbyStatsCacheSecs": { "title": "Statistics cache", "minimum": 0, "maximum": 3600, "type": "integer", "description": "How long a computed /stats report is reused. 0 recomputes on every request.", "default": 60 }, "standbyStatsMaxPages": { "title": "Statistics page budget", "minimum": 1, "maximum": 500, "type": "integer", "description": "Request ceiling for one /stats measurement. Lower than the batch budget because an HTTP caller is waiting for the response.", "default": 60 }, "includeStats": { "title": "Attach corpus statistics to every run", "type": "boolean", "description": "Store a corpus snapshot under CRAWL_STATS in the key-value store, so a dataset can be dated against the corpus it came from. Costs one request.", "default": true }, "requestTimeoutSecs": { "title": "Request timeout", "minimum": 5, "maximum": 300, "type": "integer", "description": "Per-attempt timeout for a single API request.", "default": 60 }, "maxRequestRetries": { "title": "Retries per request", "minimum": 0, "maximum": 10, "type": "integer", "description": "Retries after the first attempt, for timeouts, 5xx and rate limiting. Backoff is exponential with jitter and honours Retry-After.", "default": 4 } } }, "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 } } } } } } } } } }