{ "openapi": "3.0.1", "info": { "title": "Facebook Posts Scraper with Linked Websites", "description": "Facebook Posts Scraper with Linked Websites Extract post text, dates, reactions, comments, shares, media, and more. Perfect for competitor research, content analysis, audience insights, and trend tracking. Turn Facebook data into actionable insights fast πŸš€", "version": "0.1", "x-build-id": "Yvic9VnVdOkHF3Ezq" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapemesh~facebook-posts-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapemesh-facebook-posts-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapemesh~facebook-posts-scraper/runs": { "post": { "operationId": "runs-sync-scrapemesh-facebook-posts-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapemesh~facebook-posts-scraper/run-sync": { "post": { "operationId": "run-sync-scrapemesh-facebook-posts-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "πŸ”— Facebook Page URLs or Usernames", "type": "array", "description": "πŸ“Œ **Required.** Enter one or more Facebook *page* targets.\n\nβ€’ **Full URL:** `https://www.facebook.com/nytimes/` or `https://www.facebook.com/Cristiano/`\nβ€’ **Username only:** `nytimes`, `Cristiano`, `iamsrk` β€” the actor will turn these into full URLs.\n\nYou can mix URLs and usernames. Each target is scraped in sequence (one page after another) to reduce rate limits. πŸ”„", "items": { "type": "string" } }, "maxPosts": { "title": "πŸ“Š Maximum Posts per Page", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "🎯 **Limit how many posts to collect *per target page*.**\n\nβ€’ Minimum: **1** β€” Maximum: **10,000**.\nβ€’ Default: **10** β€” Good for quick tests.\nβ€’ Increase for deeper timelines (e.g. 50–500). The actor stops once this count is reached for each page. πŸ›‘", "default": 10 }, "includeVideoTranscript": { "title": "πŸŽ₯ Include Video Transcripts", "type": "boolean", "description": "πŸ“ **Capture video captions & transcripts!**\n\nβ€’ **ON** ✨ β€” Extracts closed captions/transcripts from video & reel posts into the output.\nβ€’ **OFF** β€” Video posts still appear with metadata, but no transcript text.\n\nDefault: **OFF** for faster scraping. Turn **ON** when you need subtitle/caption data. 🎬", "default": false }, "timeoutMode": { "title": "⏱️ Timeout Mode", "enum": [ "auto", "manual" ], "type": "string", "description": "Choose how per-target timeout is determined. **Auto** scales timeout from requested post count. **Manual** uses your custom timeout value.", "default": "auto" }, "targetTimeoutSecs": { "title": "⏳ Per-Target Timeout (seconds)", "minimum": 60, "maximum": 72000, "type": "integer", "description": "Used only when Timeout Mode is set to **Manual**. The actor will stop a target when this time limit is reached.", "default": 1200 }, "oldestPostDateUnified": { "title": "πŸ“… Posts Newer Than (Start Date)", "type": "string", "description": "⏳ **Only include posts *after* this date.**\n\nβ€’ **Absolute:** Pick a calendar date (e.g. `2024-01-01`).\nβ€’ **Relative:** e.g. `7` days, `2` months, `1` year β€” counted backward from today.\n\nLeave empty to allow posts from any past date. Combines with \"Posts Older Than\" for a window. πŸ—“οΈ" }, "newestPostDate": { "title": "βŒ› Posts Older Than (End Date)", "type": "string", "description": "πŸ›‘ **Only include posts *before* this date.**\n\nβ€’ **Absolute:** e.g. `2024-12-31`.\nβ€’ **Relative:** e.g. `0` for β€œtoday” or a number of days/months/years ago.\n\nUse together with \"Posts Newer Than\" to scrape a precise date range. Leave empty for no end limit. πŸ“†" }, "proxyConfiguration": { "title": "🌐 Proxy Settings", "type": "object", "description": "πŸ›‘οΈ **Anti-block & reliability.**\n\nβ€’ The actor **prefers Apify Residential proxy** when available for higher success rates.\nβ€’ If residential isn’t set, it falls back to **Apify Datacenter** proxy.\nβ€’ You can optionally provide **custom proxy URLs** here as a fallback.\n\nNo proxy configuration is required for basic runs; the actor will use Apify proxy when possible. πŸ”’" }, "linkedPostsOnly": { "title": "πŸ”— Only posts that link somewhere", "type": "boolean", "description": "🎯 **Keep only posts that actually point somewhere off Facebook** β€” either a link card, or a link pasted into the post text. Posts with no destination are **dropped from the dataset**, so the download is this Page's outbound-link list instead of its whole feed.\n\n⚠️ Link yield depends on the Page. A news or affiliate Page posts links constantly; a video-first Page may post almost none, and on such a Page this switch can return very few rows. Turn it **OFF** to keep every post and simply leave the link fields empty where there is no link.", "default": true }, "destinationDomains": { "title": "🌍 Only these destination domains", "type": "array", "description": "🧭 **Keep only posts whose link points at one of these domains** β€” for example `nytimes.com`, `shopify.com`, `linktr.ee`. Leave it **empty to keep every post that links out**.\n\nMatched against the domain Facebook itself prints on the card **and** against the host of the destination URL, so `nytimes.com` also catches `www.nytimes.com`. Subdomains of a listed domain match too.", "default": [], "items": { "type": "string" } }, "includeInTextLinks": { "title": "✍️ Also read links pasted in the post text", "type": "boolean", "description": "πŸ“ **Also pull the links written into the caption**, not just the one attached as a preview card. Facebook stores those as marked ranges inside the post text, so posts that show no preview card still give up their destination.\n\nKeep this **ON** β€” it is what stops a Page that pastes its links into the caption from looking like a Page with no links at all.", "default": true } } }, "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 } } } } } } } } } }