{ "openapi": "3.0.1", "info": { "title": "Hugging Face Scraper — Models, Datasets & Spaces with Stats", "description": "Hugging Face Hub models, datasets and Spaces: downloads, likes, trending score, task, library, license, tags, gated flag, dates and a card summary. By search, author, task or repo link.", "version": "0.1", "x-build-id": "xWJezFANllJBjGYaT" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/highbrow_fame~hugging-face-hub/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-highbrow_fame-hugging-face-hub", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/highbrow_fame~hugging-face-hub/runs": { "post": { "operationId": "runs-sync-highbrow_fame-hugging-face-hub", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/highbrow_fame~hugging-face-hub/run-sync": { "post": { "operationId": "run-sync-highbrow_fame-hugging-face-hub", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "searchUrls": { "title": "Search links", "type": "array", "description": "Set up a search on huggingface.co/models, /datasets or /spaces with the filters you want (task, library, language, license, sort…) and paste the address. One per line.", "items": { "type": "string" } }, "repos": { "title": "Repos", "type": "array", "description": "Or single repos, one record each: a link (https://huggingface.co/meta-llama/Llama-3.1-8B, …/datasets/openai/gsm8k, …/spaces/…) or an id (meta-llama/Llama-3.1-8B, datasets/openai/gsm8k). A profile link (https://huggingface.co/TheBloke) gives all of that account's models.", "items": { "type": "string" } }, "searchTerms": { "title": "Search terms", "type": "array", "description": "Or search here without a link: words in the repo name (llama, whisper, bert). Each is one search; the type and filters below apply.", "items": { "type": "string" } }, "maxItemsPerSearch": { "title": "Max results per search", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stops each search after this many repos.", "default": 200 }, "authors": { "title": "Authors / organizations", "type": "array", "description": "Accounts whose repos you want (meta-llama, Qwen, HuggingFaceFW). Each is one search; with search terms, every term is searched in every account.", "items": { "type": "string" } }, "repoType": { "title": "Models, datasets or Spaces", "enum": [ "model", "dataset", "space" ], "type": "string", "description": "For the search terms, authors and filters here.", "default": "model" }, "task": { "title": "Task", "type": "string", "description": "Optional, as Hugging Face names it: text-generation, text-to-image, automatic-speech-recognition, image-text-to-text, feature-extraction, text-classification… For models the pipeline tag, for datasets the task category; Spaces have none." }, "library": { "title": "Library", "type": "string", "description": "Optional, for models and datasets: transformers, gguf, diffusers, sentence-transformers, mlx, peft, onnx… (datasets: datasets, pandas, polars…)." }, "tags": { "title": "Tags", "type": "array", "description": "Optional: any Hub tags, all of which must match — license:mit, en, conversational, modality:image, language:hu, size_categories:1K