{ "openapi": "3.0.1", "info": { "title": "Facebook Groups Search Scraper With AI Relevance Filter", "description": "📘 Facebook Groups Search Scraper collects group names, URLs, member count, privacy, niche & activity from Facebook search results. 🔎 Perfect for market research, lead gen & community growth. ⚡ Fast, accurate CSV/JSON exports. ✅ Ideal for marketers, analysts & founders.", "version": "0.1", "x-build-id": "rbJ33eKNK9pkJKIwc" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapier~facebook-groups-search-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapier-facebook-groups-search-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapier~facebook-groups-search-scraper/runs": { "post": { "operationId": "runs-sync-scrapier-facebook-groups-search-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapier~facebook-groups-search-scraper/run-sync": { "post": { "operationId": "run-sync-scrapier-facebook-groups-search-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "groupSearchKeywords": { "title": "🔗 Keywords or Facebook Group URLs", "type": "array", "description": "✨ Add one or more search keywords (e.g. \"tesla\", \"bmw\") to discover related groups via search, or paste full Facebook group URLs to scrape them directly. Mix and match in one run. Also accepts the base 'startUrls'/'urls' field for backward compatibility.\n\nExample: [\"tesla\", \"https://www.facebook.com/groups/1234567890/\"]", "items": { "type": "string" } }, "maxGroupsPerKeyword": { "title": "📊 Max Groups Per Keyword", "minimum": 1, "maximum": 500, "type": "integer", "description": "🎯 When you use a keyword, how many groups do you want per search? Choose between 1 and 500. Does not apply to direct group URLs (all of those are always scraped). Default 100. (Also accepts the base 'maxItems' key.)" }, "enableRelevanceClassification": { "title": "🎯 Enable AI Topical-Relevance Classification", "type": "boolean", "description": "When ON, each keyword-discovered group is classified by an LLM as genuinely on-topic or a likely DuckDuckGo search false-positive, using its name + groupDescription. Adds isOnTopic / relevanceConfidence / relevanceReason columns. Default OFF.", "default": false }, "dropOffTopicGroups": { "title": "🚫 Drop Off-Topic Groups From Output", "type": "boolean", "description": "Only takes effect when the relevance classifier above is ON and a key is available. When ON, groups classified off-topic are excluded from the output table instead of just flagged. Default OFF (flag only - every discovered group stays in the output, which is the superset-safe / recommended setting).", "default": false }, "enableDuplicateClustering": { "title": "🧬 Enable AI Near-Duplicate / Rebrand Clustering", "type": "boolean", "description": "When ON, groups discovered in the SAME run are semantically compared by name + groupDescription to detect the same real-world community listed under different names or a rebrand (e.g. \"Tesla Owners Club\" vs \"Tesla Owners Worldwide\"). Matches share a clusterId / clusterConfidence / clusterReason. Default OFF.", "default": false }, "aiModel": { "title": "🧠 AI Model / Provider", "enum": [ "claude-haiku-4-5", "claude-sonnet-5", "claude-opus-4-8", "claude-fable-5", "gpt-4o-mini", "gpt-4o", "gpt-4.1-mini", "gpt-4.1", "o3-mini", "o1", "gemini-2.0-flash-lite", "gemini-2.0-flash", "gemini-1.5-pro", "gemini-2.5-flash", "gemini-2.5-pro", "grok-2-latest", "grok-3-mini", "grok-3", "grok-beta", "deepseek-chat", "deepseek-reasoner", "sonar", "sonar-pro", "sonar-reasoning", "mistral-small-latest", "mistral-large-latest" ], "type": "string", "description": "Provider auto-detected from the name: claude-*=Anthropic, gpt-*/o1/o3=OpenAI, gemini-*=Google, grok-*=xAI, deepseek-*=DeepSeek, sonar*=Perplexity, mistral-*=Mistral. Cheaper mini/flash/haiku/lite models are recommended for classification. Only used when a feature above is enabled.", "default": "claude-haiku-4-5" }, "aiApiKey": { "title": "🔑 AI API Key", "type": "string", "description": "API key for the selected provider. Kept secret. If left empty, the actor falls back to the provider's environment variable (e.g. ANTHROPIC_API_KEY, OPENAI_API_KEY, GEMINI_API_KEY, XAI_API_KEY, DEEPSEEK_API_KEY, PERPLEXITY_API_KEY, MISTRAL_API_KEY). Only used when a feature above is enabled." }, "proxyConfiguration": { "title": "🌐 Connection / Proxy Settings", "type": "object", "description": "⚙️ Optional. Leave default for best compatibility. You can enable your own Apify Proxy config here if you prefer; the actor auto-escalates to a backup connection (then residential) if it detects a block." } } }, "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 } } } } } } } } } }