{ "openapi": "3.0.1", "info": { "title": "Facebook Post & Comment Scraper for Pages, Groups and Profiles", "description": "Scrape public Facebook posts from pages, groups, and profiles with best-effort comment extraction. Collect post text, post IDs, permalinks, likes, shares, comment counts, profile data, media URLs, and comment samples. Built for Apify with fallback scraping and proxy suppor", "version": "0.0", "x-build-id": "HGagGy9l5sIx9J5xc" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/thescrapelab~Apify-Facebook-Post-Scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-thescrapelab-Apify-Facebook-Post-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/thescrapelab~Apify-Facebook-Post-Scraper/runs": { "post": { "operationId": "runs-sync-thescrapelab-Apify-Facebook-Post-Scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/thescrapelab~Apify-Facebook-Post-Scraper/run-sync": { "post": { "operationId": "run-sync-thescrapelab-Apify-Facebook-Post-Scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "Start URLs", "type": "array", "description": "Public Facebook page/group/profile URLs to scrape (backward-compatible field).", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "targets": { "title": "Targets (URL, page, or group name)", "type": "array", "description": "Use this field to pass Facebook URLs, page names, or group names (for example: NASA, Coca-Cola, groups/apify).", "items": { "type": "string" } }, "maxPosts": { "title": "Max posts per URL", "minimum": 1, "maximum": 500, "type": "integer", "description": "Maximum number of posts to output for each URL.", "default": 20 }, "maxScrollRounds": { "title": "Max scroll rounds (optional)", "minimum": 0, "maximum": 60, "type": "integer", "description": "Override automatic scrolling rounds for dynamic pages. Higher values may reveal more posts but increase runtime.", "default": 0 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many targets to scrape in parallel. Higher values are faster but require more container memory.", "default": 3 }, "performanceMode": { "title": "Performance mode", "enum": [ "fast", "balanced", "maxCoverage" ], "type": "string", "description": "Choose speed vs coverage tradeoff.", "default": "fast" }, "enrichmentMode": { "title": "Enrichment mode", "enum": [ "none", "basic", "deep" ], "type": "string", "description": "Add deeper post/page metadata in the same Actor run. Deep mode also extracts comment text samples from post permalinks (best-effort).", "default": "none" }, "maxEnrichedPosts": { "title": "Max enriched posts per URL", "minimum": 0, "maximum": 200, "type": "integer", "description": "How many collected posts per URL should get enrichment processing.", "default": 20 }, "maxCommentsPerPost": { "title": "Max comment samples per post", "minimum": 0, "maximum": 200, "type": "integer", "description": "Used in Deep enrichment mode to limit extracted comment text samples.", "default": 10 }, "maxCommentExpansionRounds": { "title": "Max comment expansion rounds", "minimum": 1, "maximum": 20, "type": "integer", "description": "Used in Deep enrichment mode to keep expanding comments and replies before extraction. Higher values may recover more comments but increase runtime.", "default": 6 }, "includeReplies": { "title": "Include replies", "type": "boolean", "description": "When enabled, Deep enrichment also clicks reply-expansion controls and includes visible replies in recovered comment samples.", "default": true }, "emitCommentItems": { "title": "Emit comment items", "type": "boolean", "description": "When enabled, extracted deep-mode comment samples are also pushed as separate dataset items with itemType=comment.", "default": false }, "failOnCommentBlock": { "title": "Fail when comments are blocked", "type": "boolean", "description": "In deep mode, fail the run when Facebook login-wall blocking prevents comment extraction for enriched posts.", "default": false }, "useMbasicFallback": { "title": "Use mbasic.facebook.com fallback", "type": "boolean", "description": "When enabled, the scraper will also try mbasic.facebook.com — Facebook's static HTML version that works without JavaScript. This greatly improves coverage for anonymous requests and on blocked IPs.", "default": true }, "sessionRotationOnBlock": { "title": "Rotate proxy session on block", "type": "boolean", "description": "When enabled and a proxy is configured, the scraper will automatically rotate to a fresh proxy session when Facebook returns a login-wall or access-denied response.", "default": true }, "facebookCookieHeader": { "title": "Facebook cookie header (optional)", "type": "string", "description": "Raw Cookie header from a logged-in Facebook browser session (for example c_user=...; xs=...). Improves coverage when Facebook blocks anonymous timelines." }, "proxyConfiguration": { "title": "Proxy configuration (optional)", "type": "object", "description": "Use Apify Proxy (preferably RESIDENTIAL) or custom proxies to reduce Facebook login-wall blocking." } } }, "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 } } } } } } } } } }