{ "openapi": "3.0.1", "info": { "title": "Hugging Face Scraper: Models, Datasets & Spaces", "description": "Export Hugging Face Hub models, datasets and Spaces with downloads, likes, trending score, licence, base model and task tags parsed into their own fields. Official Hub API, no login needed for public repos.", "version": "0.0", "x-build-id": "d1gsSC1f0y9NCccVh" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/winterlock~huggingface-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-winterlock-huggingface-scraper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/winterlock~huggingface-scraper/runs": { "post": { "operationId": "runs-sync-winterlock-huggingface-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/winterlock~huggingface-scraper/run-sync": { "post": { "operationId": "run-sync-winterlock-huggingface-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "What to scrape", "enum": [ "models", "datasets", "spaces", "repoDetails" ], "type": "string", "description": "Browse models, datasets or Spaces, or pull the full record for specific repositories.", "default": "models" }, "searchTerms": { "title": "Search terms", "type": "array", "description": "Free-text search over repository names. Leave empty to list everything sorted by the field below.", "items": { "type": "string" } }, "authors": { "title": "Authors or organisations", "type": "array", "description": "Limit results to these owners, for example meta-llama, google, openai-community.", "items": { "type": "string" } }, "filterTag": { "title": "Filter tag", "type": "string", "description": "A single Hub tag, for example text-generation, pytorch, license:mit or en." }, "sortBy": { "title": "Sort by", "enum": [ "downloads", "likes", "trendingScore", "lastModified", "createdAt" ], "type": "string", "description": "For Models, Datasets and Spaces. How the Hub orders the listing before the cap is applied.", "default": "downloads" }, "maxResults": { "title": "Max results per search", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Counted per combination of author and search term.", "default": 100 }, "repositories": { "title": "Repositories", "type": "array", "description": "For Specific repositories. Use owner/name (openai-community/gpt2) or a huggingface.co link.", "items": { "type": "string" } }, "repoType": { "title": "Repository type", "enum": [ "models", "datasets", "spaces" ], "type": "string", "description": "Which kind of repository the list above refers to.", "default": "models" }, "hfToken": { "title": "Hugging Face token (optional)", "type": "string", "description": "Not needed for public repositories. A free read token raises the rate limit and lets the Actor read gated repositories you have been granted access to. Create one at huggingface.co/settings/tokens. Stored encrypted, never written to the dataset." }, "maxItems": { "title": "Max items in total", "minimum": 1, "type": "integer", "description": "Stop the run after saving this many items. Leave empty for no limit." }, "maxConcurrency": { "title": "Max parallel requests", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many requests run at once. The Hub API is generous; raise it for large detail runs.", "default": 4 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Not needed for most runs. Consider it for very large crawls.", "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 } } } } } } } } } }