{ "openapi": "3.0.1", "info": { "title": "Hugging Face Scraper | Hub Models & Authors", "description": "Scrape the Hugging Face Hub: models, datasets, Spaces, papers and collections. Rows include author names, socials, and the Hugging Face org press email when published. No phones or street address. Guest Hub REST — no API token, no weight download. Export CSV, Excel or JSON.", "version": "0.1", "x-build-id": "sYhYEwdGSA5jDNkM8" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/lentic_clockss~huggingface-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-lentic_clockss-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/lentic_clockss~huggingface-scraper/runs": { "post": { "operationId": "runs-sync-lentic_clockss-huggingface-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/lentic_clockss~huggingface-scraper/run-sync": { "post": { "operationId": "run-sync-lentic_clockss-huggingface-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "query": { "title": "Search query", "type": "string", "description": "Hub search string for models/datasets/spaces. Empty lists the default Hub catalog (not a hardcoded bert canary).", "default": "" }, "searchType": { "title": "Search type", "enum": [ "models", "datasets", "spaces", "papers", "collections", "model", "dataset", "space", "paper", "collection", "files", "enterprise", "community", "home", "login", "inference" ], "type": "string", "description": "Opened: models, datasets, spaces, papers, collections, model, dataset, space, paper, collection, files. enterprise/community/home/login/inference are 未验证. Papers/collections keyword search is ignored by Hub REST.", "default": "models" }, "repoId": { "title": "Repo id", "type": "string", "description": "org/name. Required for searchType=model|dataset|space|files unless owner+name is set.", "default": "" }, "owner": { "title": "Owner / org", "type": "string", "description": "Optional. Combined with name when repoId is empty.", "default": "" }, "name": { "title": "Repo name", "type": "string", "description": "Optional. Combined with owner when repoId is empty.", "default": "" }, "repoKind": { "title": "Repo kind", "enum": [ "", "models", "datasets", "spaces" ], "type": "string", "description": "For files/detail when the URL is ambiguous. models (default), datasets, or spaces.", "default": "" }, "pipelineTag": { "title": "Pipeline tag", "type": "string", "description": "Models filter. Same key as HTML pipeline_tag= (e.g. text-generation, text-classification, fill-mask).", "default": "" }, "modality": { "title": "Dataset modality", "type": "string", "description": "Datasets filter sent as filter=modality:{value} (e.g. text, audio, image). The Hub modality= query key is ignored for audio/image.", "default": "" }, "spaceFilter": { "title": "Space filter", "type": "string", "description": "Spaces list filter. Hub API filter= (e.g. gradio, docker, streamlit, static).", "default": "" }, "filterTags": { "title": "Hub filter tags", "type": "array", "description": "Extra filter= tags such as license:mit, diffusers, safetensors, task_categories:question-answering. text-classification is remapped to pipelineTag (Hub 400).", "items": { "type": "string" } }, "language": { "title": "Dataset language", "type": "string", "description": "Datasets only. Sent as filter=language:{code} (zh, en, ja, ar). Not a country market. Ignored on models.", "default": "" }, "author": { "title": "Author", "type": "string", "description": "Optional Hub author= filter.", "default": "" }, "sort": { "title": "Sort", "type": "string", "description": "downloads, likes, createdAt, lastModified. HTML trending is default Hub order (API sort=trending is 400).", "default": "" }, "maxResults": { "title": "Max results", "minimum": 1, "maximum": 200, "type": "integer", "description": "Cap emitted rows.", "default": 1 }, "maxPages": { "title": "Max pages", "minimum": 1, "maximum": 20, "type": "integer", "description": "Hub REST pages via Link cursor. Hard cap 20. Do not try to exhaust the catalog.", "default": 1 }, "detailUrls": { "title": "Detail URLs", "type": "array", "description": "Optional huggingface.co model / dataset / space / tree URLs. /resolve blobs and /inference/models are rejected.", "items": { "type": "string" } }, "enrichDetails": { "title": "Enrich author / org leads", "type": "boolean", "description": "Fetch public /{author} profile HTML (name, socials, mailto). Default on. Does not invent phones or street addresses. Does not stamp press@huggingface.co onto every model row.", "default": true }, "workerBaseUrl": { "title": "Worker base URL override", "type": "string", "description": "HTTPS only. Production source of truth is Actor env WORKER_BASE_URL." } } }, "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 } } } } } } } } } }