{ "openapi": "3.0.1", "info": { "title": "🤖 Facebook Group Sentiment & Lead Analysis Scraper", "description": "Extract data from public Facebook groups including posts, comments, reactions, and member insights. This Apify scraper helps you track discussions, analyze engagement, monitor trends, and gather valuable data for research, marketing, and community intelligence", "version": "0.1", "x-build-id": "hxDqc3IzDJL1kZwTD" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapeengine~facebook-groups-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapeengine-facebook-groups-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapeengine~facebook-groups-scraper/runs": { "post": { "operationId": "runs-sync-scrapeengine-facebook-groups-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapeengine~facebook-groups-scraper/run-sync": { "post": { "operationId": "run-sync-scrapeengine-facebook-groups-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "groupUrlsToAnalyze": { "title": "🔗 Group URLs to Analyze", "type": "array", "description": "Public Facebook group URLs whose posts you want to analyze for sentiment and lead intent. Add multiple groups in one run. Only public groups are supported without a session cookie.\n\nExample: [\"https://www.facebook.com/groups/cheapmealideas/\"]", "items": { "type": "string" } }, "postsToAnalyze": { "title": "📊 Posts to Analyze", "minimum": 1, "type": "integer", "description": "Maximum number of posts to pull into the analysis across all groups. Leave empty to analyze as many as possible (slower). Recommended: start with 20-50 to test. Default is 10." }, "feedScanOrder": { "title": "🔄 Feed Scan Order", "enum": [ "CHRONOLOGICAL", "RECENT_ACTIVITY", "TOP_POSTS", "CHRONOLOGICAL_LISTINGS" ], "type": "string", "description": "Order in which posts are pulled from each group before analysis:\n- Chronological: oldest → newest\n- Recent Activity: most recently active discussions\n- Top Posts: most popular/engaging content\n- Chronological Listings: for Buy/Sell groups" }, "intentKeywordFilter": { "title": "🔍 Intent Keyword Filter", "type": "string", "description": "Client-side substring filter applied to each post's text (not a full Facebook search). Only matching posts are kept and analyzed. Without login, single letters or short fragments work best. Leave empty to analyze all posts.\n\nExample: \"buy\" or \"recommend\"" }, "analysisYear": { "title": "📅 Analysis Year", "type": "string", "description": "Keep only posts from a specific year (e.g. 2024) for analysis. Works together with the Intent Keyword Filter above." }, "analyzePostsNewerThan": { "title": "📅 Analyze Posts Newer Than", "pattern": "^$|^(\\d{4})-(0[1-9]|1[0-2])-(0[1-9]|[12]\\d|3[01])$|^(\\d+)\\s*(day|week|month|year)s?$", "type": "string", "description": "Only analyze posts newer than this date/time.\nFormats:\n- Absolute: YYYY-MM-DD (e.g. 2024-01-15)\n- Relative: \"30 days\", \"2 weeks\", \"1 month\", \"1 year\"" }, "enableAI": { "title": "🤖 Enable AI Enrichment", "type": "boolean", "description": "Turn on AI analysis of each post's text. Needs a valid API key for the selected provider. Default is off.", "default": false }, "aiModel": { "title": "🧠 AI Model / Provider", "enum": [ "claude-haiku-4-5", "claude-sonnet-5", "claude-opus-4-8", "gpt-4o-mini", "gpt-4o", "gpt-4.1-mini", "o3-mini", "gemini-2.0-flash-lite", "gemini-2.0-flash", "gemini-2.5-flash", "grok-3-mini", "deepseek-chat", "sonar", "mistral-small-latest" ], "type": "string", "description": "Provider is auto-detected from the model 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 AI enrichment 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 AI enrichment is enabled." }, "proxyConfiguration": { "title": "🌐 Proxy Configuration", "type": "object", "description": "Proxy settings. This actor uses Apify Residential proxies for reliable access to Facebook and rotates IPs automatically on retries." }, "facebookSessionCookie": { "title": "🍪 Facebook Cookie String", "type": "string", "description": "Optional Facebook session cookie header (must include at least c_user and xs). Leave empty to analyze public groups logged-out. Use a dedicated/secondary account — cookies grant access to that account.\n\nFormat: c_user=100000...; xs=12%3A...; datr=...; fr=..." } } }, "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 } } } } } } } } } }