{ "openapi": "3.0.1", "info": { "title": "Facebook Video Search Scraper - Description & Hashtags", "description": "Facebook Video Search Scraper extracts videos from Facebook search results, capturing titles, descriptions, URLs, views, reactions, comments, shares, and timestamps. Ideal for content research, trend analysis, competitor monitoring, and automating structured Facebook video data collection.", "version": "0.1", "x-build-id": "IuUe4uKm8b6ki4V1k" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/simpleapi~facebook-video-search-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-simpleapi-facebook-video-search-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/simpleapi~facebook-video-search-scraper/runs": { "post": { "operationId": "runs-sync-simpleapi-facebook-video-search-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/simpleapi~facebook-video-search-scraper/run-sync": { "post": { "operationId": "run-sync-simpleapi-facebook-video-search-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Keywords & topics (one per line)", "type": "array", "description": "One search phrase per line - for example `street food`, `cricket highlights`, `ev charging`. Each line is searched separately on Facebook Watch and every returned row is tagged with the keyword it came from. These are keywords, not URLs.", "items": { "type": "string" } }, "maxVideos": { "title": "Videos per keyword", "minimum": 1, "maximum": 1000, "type": "integer", "description": "How many videos to collect for each keyword, 1-1000. Facebook returns roughly 7-8 results per page, so larger numbers mean more pages and longer runs. Results are de-duplicated by video ID across pages and keywords.", "default": 10 }, "extractHashtags": { "title": "Extract hashtags", "type": "boolean", "description": "Read Facebook's own linkified hashtag entities out of the caption - each one gives a tag name, a browsable /hashtag/ URL and a stable tag ID. When Facebook returns no entity list for a caption, the tags are read from the text instead and `hashtagSource` says so.", "default": true }, "includeFullDescription": { "title": "Verify captions on the video page (adds hashtag IDs)", "type": "boolean", "description": "About 60% of results carry Facebook's own hashtag entity list in the search response. The rest are tile-shaped and carry caption text only. Turn this on to fetch those videos' own pages, which returns Facebook's hashtag entities - name, /hashtag/ URL and numeric ID - for 33 of 38 measured tile rows, and confirms the caption text (identical on 38/38, so it corrects nothing but proves nothing was cut). Costs one request per tile-shaped video. `descriptionStatus` records what happened per row.", "default": true }, "mustContainHashtags": { "title": "Keep only videos using these hashtags", "type": "array", "description": "Optional. One tag per line, with or without the leading `#`. A video is kept when it carries at least one of them, and `matchedRequiredHashtags` lists which ones matched. Leave empty to keep everything.", "default": [], "items": { "type": "string" } }, "includeMentionedPages": { "title": "Also collect tagged profiles and Pages", "type": "boolean", "description": "Off by default on purpose. Profile, Page and Group tags inside captions are rare - measured at 2 of 59 videos (3%) - and Facebook returns `name: null` on them, so only the short name, ID and URL are usable. Expect an empty array on almost every row.", "default": false }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Your selection is honoured: custom proxy URLs are tried first, then the Apify groups you pick, then Apify Residential as the final tier. Residential is the default because Facebook's search endpoint answers datacentre exits with a rate-limit error and zero results." } } }, "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 } } } } } } } } } }