{ "openapi": "3.0.1", "info": { "title": "HuggingFace Hub Scraper", "description": "Scrape Hugging Face Hub, search and fetch models, datasets, and spaces with full metadata: downloads, likes, license, pipeline tag, library, tags, files, and more. Pure HTTP, no auth required.", "version": "1.0", "x-build-id": "AQLTOZVthiw6aG2tP" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/crawlerbros~huggingface-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-crawlerbros-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/crawlerbros~huggingface-scraper/runs": { "post": { "operationId": "runs-sync-crawlerbros-huggingface-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/crawlerbros~huggingface-scraper/run-sync": { "post": { "operationId": "run-sync-crawlerbros-huggingface-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Mode", "enum": [ "search", "byModel", "byDataset", "bySpace", "byUser", "trending", "byUrl" ], "type": "string", "description": "What to fetch from the Hub. Use `search` for free-text discovery, `byModel`/`byDataset`/`bySpace` for specific repos, or `byUrl` to auto-detect from a Hugging Face URL.", "default": "search" }, "entityType": { "title": "Entity type (mode=search / trending)", "enum": [ "models", "datasets", "spaces" ], "type": "string", "description": "Which Hub catalog to search or browse: models, datasets, or spaces.", "default": "models" }, "searchQuery": { "title": "Search query (mode=search)", "type": "string", "description": "Free-text search; matches repo name, description, and tags.", "default": "bert" }, "repoIds": { "title": "Repo IDs (mode=byModel / byDataset / bySpace)", "type": "array", "description": "Hub repo IDs like `bert-base-uncased`, `google-bert/bert-base-uncased`, or full URLs.", "default": [], "items": { "type": "string" } }, "username": { "title": "Username (mode=byUser)", "type": "string", "description": "Hugging Face username (or organization name)." }, "startUrls": { "title": "Start URLs (mode=byUrl)", "type": "array", "description": "Full huggingface.co URLs (model, dataset, space, or user pages).", "default": [], "items": { "type": "string" } }, "pipelineTag": { "title": "Pipeline tag (models only)", "enum": [ "", "text-generation", "text-classification", "token-classification", "fill-mask", "question-answering", "summarization", "translation", "text2text-generation", "feature-extraction", "sentence-similarity", "zero-shot-classification", "table-question-answering", "automatic-speech-recognition", "audio-classification", "text-to-speech", "text-to-audio", "audio-to-audio", "voice-activity-detection", "image-classification", "image-segmentation", "image-to-image", "image-to-text", "object-detection", "depth-estimation", "video-classification", "text-to-video", "text-to-image", "image-to-video", "image-text-to-text", "visual-question-answering", "document-question-answering", "any-to-any", "tabular-classification", "tabular-regression", "time-series-forecasting", "reinforcement-learning", "robotics", "graph-ml", "mask-generation", "zero-shot-image-classification", "zero-shot-object-detection", "unconditional-image-generation" ], "type": "string", "description": "Filter models by their primary task tag (e.g. text-generation, image-classification). Applied as a server-side filter on `mode=search`/`trending`; otherwise post-filter.", "default": "" }, "libraryName": { "title": "Library (models only)", "enum": [ "", "transformers", "diffusers", "sentence-transformers", "timm", "spacy", "stable-baselines3", "ml-agents", "keras", "fastai", "tensorflow", "pytorch", "jax", "onnx", "safetensors", "gguf", "peft", "adapters" ], "type": "string", "description": "Filter models by their primary library / framework.", "default": "" }, "authorFilter": { "title": "Author / organization", "type": "string", "description": "Constrain results to a specific author / org slug (e.g. `google`, `meta-llama`)." }, "license": { "title": "License filter", "enum": [ "", "apache-2.0", "mit", "cc-by-4.0", "cc-by-sa-4.0", "cc-by-nc-4.0", "cc-by-nc-sa-4.0", "cc-by-nd-4.0", "cc0-1.0", "openrail", "openrail++", "creativeml-openrail-m", "bigscience-openrail-m", "bigscience-bloom-rail-1.0", "bigcode-openrail-m", "llama2", "llama3", "llama3.1", "llama3.2", "llama3.3", "gemma", "afl-3.0", "gpl-3.0", "lgpl-3.0", "agpl-3.0", "bsd-3-clause", "bsd-2-clause", "wtfpl", "unlicense", "other" ], "type": "string", "description": "Filter to a specific license (post-fetch filter).", "default": "" }, "language": { "title": "Language filter", "type": "string", "description": "Filter records whose tags contain this 2-letter language code (e.g. `en`, `fr`, `zh`)." }, "sort": { "title": "Sort by (mode=search)", "enum": [ "", "trendingScore", "downloads", "likes", "lastModified", "createdAt" ], "type": "string", "description": "Server-side sort key. Leave blank for relevance-based sort.", "default": "" }, "direction": { "title": "Sort direction", "enum": [ "desc", "asc" ], "type": "string", "description": "Direction for the `sort` key.", "default": "desc" }, "minDownloads": { "title": "Min downloads (post-filter)", "minimum": 0, "maximum": 1000000000, "type": "integer", "description": "Drop records with fewer downloads than this." }, "minLikes": { "title": "Min likes (post-filter)", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "Drop records with fewer likes than this." }, "includeFullDetails": { "title": "Include full repo details", "type": "boolean", "description": "Request `?full=true` from the Hub API to include sibling files, cardData, config, and tags. Heavier payloads but richer records.", "default": false }, "maxItems": { "title": "Max items", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Hard cap on emitted records.", "default": 50 } } }, "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 } } } } } } } } } }