{ "openapi": "3.0.1", "info": { "title": "Hugging Face Scraper - Models, Datasets, Papers", "description": "Hugging Face data export tool: scrape models, datasets & daily papers without a token. Export to CSV/JSON. A no-login Hugging Face API alternative.", "version": "1.0", "x-build-id": "ueStgZeCvxSKkynTj" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/logiover~huggingface-hub-intelligence-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-logiover-huggingface-hub-intelligence-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/logiover~huggingface-hub-intelligence-scraper/runs": { "post": { "operationId": "runs-sync-logiover-huggingface-hub-intelligence-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/logiover~huggingface-hub-intelligence-scraper/run-sync": { "post": { "operationId": "run-sync-logiover-huggingface-hub-intelligence-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "entityType": { "title": "Entity Type", "enum": [ "models", "datasets", "spaces", "papers", "collections" ], "type": "string", "description": "Which entity to enumerate from the Hugging Face Hub. 'models' = ML models (~1M+), 'datasets' = training/evaluation datasets (~200k+), 'spaces' = hosted demo apps, 'papers' = daily curated research papers, 'collections' = curated lists of models/datasets/spaces.", "default": "models" }, "search": { "title": "Search Query", "type": "string", "description": "Free-text search over name + description. Examples: 'llama', 'whisper', 'mistral', 'phi', 'instruct'. Leave empty to enumerate all entities matching filters.", "default": "" }, "author": { "title": "Author / Organization Filter", "type": "string", "description": "Restrict to a single author or organization (e.g. 'mistralai', 'meta-llama', 'openai-community', 'stabilityai'). Substring match.", "default": "" }, "pipelineTag": { "title": "Task / Pipeline Tag (models only)", "enum": [ "", "text-generation", "text-classification", "token-classification", "feature-extraction", "sentence-similarity", "fill-mask", "translation", "summarization", "question-answering", "table-question-answering", "zero-shot-classification", "text2text-generation", "text-to-image", "image-to-text", "image-to-image", "image-classification", "image-segmentation", "object-detection", "depth-estimation", "zero-shot-image-classification", "text-to-speech", "text-to-audio", "automatic-speech-recognition", "audio-classification", "audio-to-audio", "voice-activity-detection", "video-classification", "text-to-video", "image-text-to-text", "visual-question-answering", "document-question-answering", "reinforcement-learning", "robotics", "tabular-classification", "tabular-regression", "time-series-forecasting" ], "type": "string", "description": "Filter models by primary task (pipeline tag). Leave as 'Any task' for no task filter.", "default": "" }, "library": { "title": "Library Filter (models / datasets)", "enum": [ "", "transformers", "diffusers", "sentence-transformers", "peft", "gguf", "mlx", "onnx", "safetensors", "pytorch", "jax", "tensorflow", "keras", "timm", "adapter-transformers", "transformers.js", "sample-factory", "stable-baselines3", "ml-agents", "spacy", "espnet", "fastai", "flair", "nemo", "open_clip", "paddlepaddle", "setfit" ], "type": "string", "description": "Filter by framework / library. Leave as 'Any library' for no library filter.", "default": "" }, "language": { "title": "Language Tag (models / datasets)", "enum": [ "", "en", "multilingual", "zh", "es", "fr", "de", "ru", "ja", "ar", "pt", "it", "ko", "hi", "tr", "nl", "pl", "sv", "vi", "id", "fa", "th", "uk", "he", "cs", "ro", "el", "fi", "da", "hu", "no", "bn" ], "type": "string", "description": "Filter models / datasets by primary language tag. Leave as 'Any language' for no filter.", "default": "" }, "tags": { "title": "Additional Tags Filter", "type": "array", "description": "Restrict to items whose tag list contains all of these. Examples: ['safetensors','region:us'], ['license:apache-2.0','llama'], ['gated:false']. Hugging Face supports complex tag filters at the API level.", "default": [], "items": { "type": "string" } }, "sort": { "title": "Sort By", "enum": [ "downloads", "likes", "lastModified", "createdAt", "trendingScore" ], "type": "string", "description": "Field to sort by. 'downloads' = most downloaded, 'likes' = community favorites, 'lastModified' = recently updated, 'createdAt' = newest creations, 'trendingScore' = HF's trending algorithm.", "default": "downloads" }, "sortDirection": { "title": "Sort Direction", "enum": [ "-1", "1" ], "type": "string", "description": "Sort direction: '-1' = descending (highest first), '1' = ascending.", "default": "-1" }, "maxResults": { "title": "Maximum Results", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Hard cap on records returned. Set to 0 for unlimited (auto-paginates). Be aware: the full models catalog is ~1M+ items.", "default": 500 }, "fetchDetails": { "title": "Fetch Full Details Per Item", "type": "boolean", "description": "When enabled, for every model / dataset / space / paper, the actor makes an additional call to `/api/{type}/{id}` to fetch richer fields: full README content, sibling file list, model card data, dataset card data, config files, gated status, license, citation. Adds 1 HTTP request per item.", "default": false }, "fetchReadme": { "title": "Fetch README Content", "type": "boolean", "description": "When enabled (requires 'Fetch Full Details'), the actor also pulls the raw model/dataset card (README.md) for each item. Useful for AI training datasets, model documentation indexing, and RAG over the Hub.", "default": false }, "minDownloads": { "title": "Minimum Downloads (client-side filter)", "minimum": 0, "type": "integer", "description": "Drop entities with fewer than this many downloads. Useful for filtering out abandoned or experimental items.", "default": 0 }, "minLikes": { "title": "Minimum Likes (client-side filter)", "minimum": 0, "type": "integer", "description": "Drop entities with fewer than this many likes.", "default": 0 }, "modifiedFrom": { "title": "Modified From (ISO date)", "type": "string", "description": "Drop items last-modified before this date (YYYY-MM-DD). Useful for tracking what's new this week / month.", "default": null }, "papersStartDate": { "title": "Daily Papers — Start Date", "type": "string", "description": "For entityType='papers' only. Pull papers from the daily-papers archive starting at this date (YYYY-MM-DD). Defaults to last 30 days.", "default": null }, "papersEndDate": { "title": "Daily Papers — End Date", "type": "string", "description": "For entityType='papers' only. Pull papers up to this date (YYYY-MM-DD). Defaults to today.", "default": null }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Proxy for the public Hugging Face API requests. Defaults to Apify Proxy (automatic pool). The Actor also falls back to a direct connection on the final retry, so it works without proxy too.", "default": { "useApifyProxy": 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 } } }, "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 } } } } } } } } } }