{ "openapi": "3.0.1", "info": { "title": "Social Page Scraper (Facebook & Instagram)", "description": "Scrapes public Facebook and Instagram pages: page info, posts, images, captions, engagement metrics (reactions, shares, comments), and datetimes.", "version": "0.1", "x-build-id": "JGiQaVxZavaxuCsxb" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/xiphosuran_puzzle~social-page-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-xiphosuran_puzzle-social-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/xiphosuran_puzzle~social-page-scraper/runs": { "post": { "operationId": "runs-sync-xiphosuran_puzzle-social-page-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/xiphosuran_puzzle~social-page-scraper/run-sync": { "post": { "operationId": "run-sync-xiphosuran_puzzle-social-page-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "pageUrl" ], "properties": { "pageUrl": { "title": "Page URL", "pattern": "https?://(www\\.)?(facebook\\.com|instagram\\.com)/.+", "type": "string", "description": "URL of the Facebook or Instagram page to scrape. Examples: https://www.facebook.com/nasa or https://www.instagram.com/nasa" }, "maxPosts": { "title": "Max posts", "minimum": 0, "maximum": 500, "type": "integer", "description": "Maximum number of posts to scrape. Set to 0 for unlimited (not recommended — will scroll until end of feed).", "default": 20 }, "postTypes": { "title": "Post types to scrape", "uniqueItems": true, "type": "array", "description": "Filter which post types to include. Select one or more. Leave empty or select 'all' to scrape everything.", "items": { "type": "string", "enum": [ "all", "photo", "video", "reel", "album", "text", "link" ], "enumTitles": [ "All types", "Photos", "Videos", "Reels", "Albums (multiple images)", "Text-only posts", "Link shares" ] }, "default": [ "all" ] }, "scrapeComments": { "title": "Scrape comments", "type": "boolean", "description": "Whether to open each post and scrape its comments. Significantly increases run time.", "default": false }, "maxComments": { "title": "Max comments per post", "minimum": 1, "maximum": 200, "type": "integer", "description": "Maximum number of comments to scrape per post (only used when scrapeComments is enabled).", "default": 10 }, "cookies": { "title": "Session cookies", "type": "array", "description": "Provide your browser session cookies to unlock full feed access. Without cookies, Facebook/Instagram only show ~5-10 public posts.\n\n━━━ HOW TO GET YOUR COOKIES ━━━\n\n🔹 Step 1: Open Chrome and log into Facebook (or Instagram)\n\n🔹 Step 2: Press F12 to open Developer Tools\n\n🔹 Step 3: Click the 'Application' tab at the top of DevTools\n (If you don't see it, click the >> arrows to find it)\n\n🔹 Step 4: In the left sidebar, expand 'Cookies' and click on\n 'https://www.facebook.com' (or instagram.com)\n\n🔹 Step 5: You'll see a table of cookies. Find and copy these:\n\n FOR FACEBOOK — you need 2 cookies:\n • c_user → your Facebook user ID (a number like 100012345678)\n • xs → your session token (a long string)\n\n FOR INSTAGRAM — you need 1 cookie:\n • sessionid → your session token (a long string)\n\n🔹 Step 6: Paste them below in this format (see placeholder)\n\n━━━ EASY METHOD: Cookie Editor Extension ━━━\n\n🔹 Install 'Cookie-Editor' browser extension:\n Chrome: https://chromewebstore.google.com/detail/cookie-editor/hlkenndednhfkekhgcdicdfddnkalmdm\n Firefox: https://addons.mozilla.org/en-US/firefox/addon/cookie-editor/\n\n🔹 Log into Facebook/Instagram, click the extension icon,\n click 'Export' (JSON format), and paste the result here.\n The actor will automatically pick out the cookies it needs.\n\n━━━ IMPORTANT NOTES ━━━\n• Cookies expire after a few days/weeks — you may need to refresh them\n• Never share your cookies with anyone — they give full access to your account\n• We recommend using a secondary/dummy account for scraping" }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy settings. Residential proxies are strongly recommended for Facebook/Instagram — datacenter proxies are usually blocked." } } }, "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 } } } } } } } } } }