{ "openapi": "3.0.1", "info": { "title": "HuggingFace Hub Scraper - Models, Datasets, Spaces & Authors", "description": "Scrape HuggingFace Hub: models, datasets, spaces. 30+ fields per record, trending filters, author profiles, parsed tags, web enrichment for emails & websites.", "version": "1.0", "x-build-id": "CFVDfFZcVJP2gK96Y" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/makework36~huggingface-hub-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-makework36-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/makework36~huggingface-hub-scraper/runs": { "post": { "operationId": "runs-sync-makework36-huggingface-hub-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/makework36~huggingface-hub-scraper/run-sync": { "post": { "operationId": "run-sync-makework36-huggingface-hub-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "searchType": { "title": "What to scrape", "enum": [ "models", "datasets", "spaces", "papers", "byIds" ], "type": "string", "description": "Which HuggingFace resource to search.", "default": "models" }, "ids": { "title": "Item IDs (one per line)", "type": "array", "description": "Used only with searchType = byIds. Format: 'author/name' for models/datasets/spaces.", "items": { "type": "string" } }, "searchQuery": { "title": "Search query (full-text)", "type": "string", "description": "Free-text search across IDs and tags." }, "author": { "title": "Author / Organization filter", "type": "string", "description": "Filter by author (e.g. 'meta-llama', 'google', 'mistralai')." }, "pipelineTag": { "title": "Pipeline tag (task)", "type": "string", "description": "Filter by task: text-generation, text-classification, automatic-speech-recognition, image-classification, sentence-similarity, embeddings, etc." }, "library": { "title": "Library", "type": "string", "description": "Filter by library: transformers, diffusers, sentence-transformers, gguf, llama.cpp, etc." }, "language": { "title": "Language", "type": "string", "description": "ISO code (en, es, multilingual, ja, ...)." }, "license": { "title": "License", "type": "string", "description": "Filter by license: apache-2.0, mit, llama3.1, openrail, cc-by-nc-4.0, etc." }, "sdk": { "title": "Space SDK (for spaces only)", "type": "string", "description": "Filter spaces by SDK: docker, gradio, streamlit, static." }, "minDownloads": { "title": "Min downloads", "minimum": 0, "type": "integer", "description": "Skip records below this download count." }, "minLikes": { "title": "Min likes", "minimum": 0, "type": "integer", "description": "Skip records below this likes count." }, "sort": { "title": "Sort by", "enum": [ "trendingScore", "downloads", "likes", "lastModified", "createdAt" ], "type": "string", "description": "Sort criterion for the result list.", "default": "trendingScore" }, "maxResults": { "title": "Max results", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Hard cap on records to return.", "default": 100 }, "parseTagsStructured": { "title": "Parse tags into structured fields", "type": "boolean", "description": "If true, splits the flat tags array into: license, languages, datasetsUsed, arxivPapers, region, hardwareCompatible, frameworks.", "default": true }, "includeAuthorProfile": { "title": "Include author profile", "type": "boolean", "description": "For each record, fetch the author/org overview (followers, isPro, numModels, orgs).", "default": false }, "enrichWithGoogle": { "title": "Enrich author with web search", "type": "boolean", "description": "For each unique author, find their personal/company website, LinkedIn, Facebook, and secondary emails using a web search (no API key required).", "default": false }, "enrichLimit": { "title": "Enrich limit", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Max number of UNIQUE authors to enrich (not records).", "default": 50 }, "proxyConfig": { "title": "Proxy", "type": "object", "description": "Apify proxy. Used for enrichment only.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "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 } } } } } } } } } }