{ "openapi": "3.0.1", "info": { "title": "Facebook Page Extractor", "description": "Facebook Page Extractor: Extract Facebook page names, usernames, categories, descriptions, locations, follower counts, websites, contact details, and page URLs. Build structured datasets for business research, lead generation, competitor analysis, and social media intelligence.", "version": "1.0", "x-build-id": "PLsb4XFuOLjSoXe7E" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapier~facebook-page-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapier-facebook-page-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapier~facebook-page-scraper/runs": { "post": { "operationId": "runs-sync-scrapier-facebook-page-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapier~facebook-page-scraper/run-sync": { "post": { "operationId": "run-sync-scrapier-facebook-page-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "startUrls" ], "properties": { "startUrls": { "title": "🔗 Facebook Page URLs or Usernames", "type": "array", "description": "📌 Pages to extract. Use a full URL (https://www.facebook.com/pagename) or just the username (pagename). Add as many as you need — one per line.", "items": { "type": "string" } }, "maxPages": { "title": "📊 Maximum Pages to Scrape", "minimum": 1, "maximum": 100000, "type": "integer", "description": "🎯 Cap how many pages from your list are processed in this run (1–100,000). Handy for testing before a full bulk extract.", "default": 10 }, "delaySeconds": { "title": "⏱️ Delay Between Pages (seconds)", "minimum": 0, "maximum": 30, "type": "integer", "description": "⏳ Wait this many seconds after each page before fetching the next one. Helps avoid Facebook rate limits. 0 = no wait.", "default": 2 }, "onlyWithContacts": { "title": "📇 Only Pages With Contacts", "type": "boolean", "description": "Keep only pages that publicly show an email or website. Pages with no contact are skipped.", "default": false }, "minFollowers": { "title": "👥 Minimum Followers", "minimum": 0, "type": "integer", "description": "Keep only pages with at least this many followers. Leave empty to keep all. Uses the public follower count already extracted from the page." }, "minLikes": { "title": "👍 Minimum Likes", "minimum": 0, "type": "integer", "description": "Keep only pages with at least this many likes. Leave empty to keep all. Uses the public likes count already extracted from the page." }, "onlyBusinessPages": { "title": "🏢 Only Business Pages", "type": "boolean", "description": "Keep only business pages. Matches Facebook's Ads active-business flag, plus local/commercial pages (restaurant, shop, salon, hotel, etc.) and pages with About cards like address, phone, or hours. Community/interest pages without those signals are skipped.", "default": false }, "proxyConfiguration": { "title": "🛡️ Proxy configuration", "type": "object", "description": "⚙️ Optional. Start with no proxy. If Facebook blocks the request, the actor automatically switches to datacenter proxy, then residential proxy, and retries up to 3 times." } } }, "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 } } } } } } } } } }