{ "openapi": "3.0.1", "info": { "title": "Facebook Page Posts Scraper: Media OCR Extraction", "description": "Facebook Page Posts Scraper: Extract page posts, captions, images, videos, engagement metrics, and text from media using OCR. Analyze visual content, identify keywords, monitor competitor activity, and build structured datasets for social media research and marketing insights.", "version": "0.2", "x-build-id": "Qk4JibqQCE0VF9Tbo" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapier~facebook-page-posts-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapier-facebook-page-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapier~facebook-page-posts-scraper/runs": { "post": { "operationId": "runs-sync-scrapier-facebook-page-posts-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapier~facebook-page-posts-scraper/run-sync": { "post": { "operationId": "run-sync-scrapier-facebook-page-posts-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "pagesToHarvest": { "title": "📚 Facebook pages to harvest media from", "type": "array", "description": "One asset source per line: a Facebook page link (full URL) or just its handle. Every post on these pages is scanned for media. Example: `https://www.facebook.com/RealMadrid/` or simply `RealMadrid`.", "items": { "type": "string" } }, "postsToScan": { "title": "🔎 Posts to scan per page", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Depth of the media sweep — how many recent posts to open and harvest assets from on each page (1–5000). Fewer = a fast skim; more = a deeper media crawl. Example: postsToScan=20 opens the 20 latest posts. Default 20." }, "includeMedia": { "title": "🖼️ Harvest media assets", "type": "boolean", "description": "When on, every scanned post is enriched with `images`, `imageVariants` and `videoVariants` — full-res images, each size variant, and every playable video URL plus its thumbnail. Turn off for a lean text-only crawl. Default true.", "default": true }, "mediaType": { "title": "📺 Asset kind to keep", "enum": [ "image", "video", "all" ], "type": "string", "description": "Narrow the harvest to one asset kind: images only, videos only, or every asset. Base media fields are always retained. Example: mediaType=video keeps only video variants. Default all.", "default": "all" }, "ocr": { "title": "🔤 Read on-image text (OCR, best-effort)", "type": "boolean", "description": "When on, run in-container OCR (tesseract) over each harvested post image and return the recognised words in `images[].ocrText`. Best-effort: images with no readable text return null (never fabricated). Slower. Default false.", "default": false }, "postedFrom": { "title": "🕐 Only posts published on/after", "type": "string", "description": "Lower time bound for the media sweep — a calendar date or relative like `7 days` / `2 weeks`. Posts older than this are skipped. Leave empty to harvest without a start bound." }, "postedUntil": { "title": "🕔 Only posts published on/before", "type": "string", "description": "Upper time bound for the media sweep — a calendar date or relative like `0 days` (through end of today). Posts newer than this are skipped. Leave empty to harvest without an end bound." }, "proxyConfiguration": { "title": "🌐 Apify Proxy (residential)", "type": "object", "description": "Apify Proxy (default): turn Use Apify Proxy on — traffic uses residential IPs only (UI group/type ignored; country still applies when set). Your own proxies: turn it off and add proxy URLs — the run tries yours first and falls back to Apify residential." } } }, "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 } } } } } } } } } }