{ "openapi": "3.0.1", "info": { "title": "Hugging Face Scraper: Models, Datasets & Spaces", "description": "Scrape Hugging Face Hub models, datasets and Spaces by keyword, author or task: downloads, likes, trending score, gated status, plus license, parameter count and file lists. Export CSV, Excel, JSON, XML. No login or API key. Pay per record from $0.015.", "version": "0.1", "x-build-id": "bYdgujhHL8PXwWH6b" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/recordsdata~huggingface-hub-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-recordsdata-huggingface-hub-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/recordsdata~huggingface-hub-scraper/runs": { "post": { "operationId": "runs-sync-recordsdata-huggingface-hub-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/recordsdata~huggingface-hub-scraper/run-sync": { "post": { "operationId": "run-sync-recordsdata-huggingface-hub-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": { "searchTerms": { "title": "Search terms", "type": "array", "description": "Keywords to search on the Hugging Face Hub, one search per term (for example \"llama\", \"sentiment analysis\", \"stable diffusion\"). Applies to models, datasets, Spaces, papers (full-text paper search, up to 100 per term) and collections. Leave empty to browse by author, task or filters only; with no terms and no author the Hub's top results for the chosen sort order are returned.", "items": { "type": "string" } }, "author": { "title": "Author / organization", "type": "string", "description": "Only return records published by this Hugging Face author or organization, for example meta-llama, google or mistralai. For collections it is the collection owner. Leave empty for all authors.", "default": "" }, "maxItems": { "title": "Max Items", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Maximum number of records to return across all surfaces. Surfaces are read in the order Models, Datasets, Spaces, Papers, Collections until this limit is reached. Free users are limited to 10 records (preview); paid users can go up to 1,000,000. Each record is billed per event, so this also caps your cost.", "default": 10 }, "includeModels": { "title": "Models", "type": "boolean", "description": "Scrape model records (downloads, likes, trending score, pipeline task, tags).", "default": true }, "includeDatasets": { "title": "Datasets", "type": "boolean", "description": "Scrape dataset records for the same search terms.", "default": false }, "includeSpaces": { "title": "Spaces", "type": "boolean", "description": "Scrape Space records (demo apps) for the same search terms.", "default": false }, "includePapers": { "title": "Papers", "type": "boolean", "description": "Scrape Hugging Face papers: title, abstract, authors, upvotes, comments, GitHub repository and stars, project page, organization and AI summary. With search terms it searches all papers; otherwise it reads the daily papers feed (set the date range below for a period).", "default": false }, "includeCollections": { "title": "Collections", "type": "boolean", "description": "Scrape Hugging Face collections (curated lists of models, datasets, Spaces and papers): title, owner, upvotes, last update and the first items. Search terms match collection titles and descriptions; Author / organization selects the owner.", "default": false }, "pipelineTag": { "title": "Task (pipeline tag)", "enum": [ "", "text-generation", "text-classification", "token-classification", "question-answering", "zero-shot-classification", "translation", "summarization", "feature-extraction", "text2text-generation", "fill-mask", "sentence-similarity", "text-to-speech", "text-to-audio", "automatic-speech-recognition", "audio-to-audio", "audio-classification", "text-to-image", "image-to-text", "image-to-image", "image-text-to-text", "text-to-video", "image-classification", "object-detection", "image-segmentation", "depth-estimation", "video-classification", "visual-question-answering", "document-question-answering", "zero-shot-image-classification", "mask-generation", "text-ranking", "reinforcement-learning", "robotics", "tabular-classification", "tabular-regression", "time-series-forecasting", "any-to-any" ], "type": "string", "description": "Only return models for this Hugging Face task (pipeline tag), such as text-generation or text-to-image. Applies to models only. Leave on Any task for no filter.", "default": "" }, "library": { "title": "Library", "type": "string", "description": "Only models (or datasets) tagged with this library or file format, for example transformers, diffusers, gguf, peft, sentence-transformers or llama.cpp. It is an exact Hub tag; a name that does not exist returns no records. Does not apply to Spaces.", "default": "" }, "language": { "title": "Language", "type": "string", "description": "Only models (or datasets) tagged with this language code, for example en, fr, es, de, zh or pt. Use the ISO 639 code the Hub uses as a tag. Does not apply to Spaces.", "default": "" }, "license": { "title": "License", "type": "string", "description": "Only models (or datasets) with this license id, for example apache-2.0, mit, cc-by-4.0, openrail or llama3. Use the id the Hub shows on the license badge. Does not apply to Spaces.", "default": "" }, "filterTags": { "title": "Tags (all must match)", "type": "array", "description": "Extra Hub tags every record must carry, one per line, for example text-generation, gguf, license:mit, task_categories:text-classification, size_categories:1K