{ "openapi": "3.0.1", "info": { "title": "YouTube Shorts Scraper With Transcripts & Captions", "description": "The Youtube Shorts Scraper extracts Shorts data including titles, views, likes, comments, creators, hashtags, and video links. Get clean JSON or CSV for trend analysis, content research, audience insights, and automation workflows at scale.", "version": "0.1", "x-build-id": "u4KShpdbnpcL4gask" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapio~youtube-shorts-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapio-youtube-shorts-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapio~youtube-shorts-scraper/runs": { "post": { "operationId": "runs-sync-scrapio-youtube-shorts-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapio~youtube-shorts-scraper/run-sync": { "post": { "operationId": "run-sync-scrapio-youtube-shorts-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "๐Ÿ“ Channels, handles or keywords", "type": "array", "description": "Sources to scrape Shorts from. Add one or more: channel handles (@MrBeast), usernames (mrbeast), full channel URLs (https://www.youtube.com/@MrBeast), or plain search keywords (e.g. cooking tips). Accepts a list of strings or a list of {\"url\": \"...\"} objects.", "default": [ "rainbowicecream9780" ], "items": { "type": "string" } }, "maxResults": { "title": "๐Ÿ”ข Max Shorts per source", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of Shorts to scrape per channel or keyword (1โ€“10,000). Higher = more transcripts, longer run.", "default": 10 }, "includeTranscript": { "title": "๐Ÿ“ Include transcript", "type": "boolean", "description": "Fetch each Short's transcript text from its caption track. Adds the transcript, transcriptStatus and transcriptLanguage fields to every row.", "default": true }, "transcriptFormat": { "title": "๐Ÿงพ Transcript format", "enum": [ "captions", "textWithTimestamps", "singleStringText" ], "type": "string", "description": "Shape of the transcript field. Captions = list of text lines; With timestamps = list of [m:ss] text lines; Single string = one joined paragraph (ideal for LLM prompts).", "default": "captions" }, "transcriptMode": { "title": "๐ŸŽฏ Transcript coverage mode", "enum": [ "standard", "aggressive" ], "type": "string", "description": "Standard = fetch the primary caption track only (fast). Aggressive = try every caption track plus a raw-timedtext fallback for higher coverage (slower).", "default": "standard" }, "publishedAfter": { "title": "๐Ÿ“… Only Shorts published after", "pattern": "^(\\d{4})-(0[1-9]|1[0-2])-(0[1-9]|[12]\\d|3[01])$|^(\\d+)\\s*(day|week|month|year)s?$", "type": "string", "description": "Filter by publish date. Use a date (YYYY-MM-DD) or relative time (e.g. 7 days, 2 weeks, 1 month, 1 year). Leave empty to include all Shorts." }, "sortOrder": { "title": "โ†•๏ธ Sort by", "enum": [ "newest", "popular", "oldest" ], "type": "string", "description": "Order of results: Newest first, Oldest first, or by Popularity (views).", "default": "newest" }, "proxyConfiguration": { "title": "๐ŸŒ Proxy configuration", "type": "object", "description": "Apify Proxy. Residential is required for transcript / caption-track recovery (YouTube serves caption tracks only to residential browser-fingerprint requests). Kept on by default.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "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 } } } } } } } } } }