{ "openapi": "3.0.1", "info": { "title": "YouTube Shorts Scraper: Sponsor Segments, Sentiment & Topics", "description": "YouTube Shorts Scraper extracts Shorts from any YouTube channel or search query. Capture video URLs, titles, creators, views, likes, comments, audio, and metadata. Ideal for trend research, content analysis, competitive tracking, and workflows needing structured YouTube Shorts data.", "version": "0.1", "x-build-id": "HW9p6NZsxIlvGRdBf" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/api-empire~youtube-shorts-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-api-empire-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/api-empire~youtube-shorts-scraper/runs": { "post": { "operationId": "runs-sync-api-empire-youtube-shorts-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/api-empire~youtube-shorts-scraper/run-sync": { "post": { "operationId": "run-sync-api-empire-youtube-shorts-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "📍 Channels or keywords (required)", "type": "array", "description": "Where to scrape Shorts from. Add one or more: channel handles (@MrBeast), usernames (mrbeast), full URLs (https://www.youtube.com/@MrBeast), or search keywords (e.g. funny shorts).", "default": [ "rainbowicecream9780" ], "items": { "type": "string" } }, "maxResults": { "title": "🔢 Max Shorts per channel", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of Shorts to scrape per channel or keyword. Ranges from 1 to 10,000. Higher = more data, longer run.", "default": 10 }, "includeSponsorSegments": { "title": "💸 Detect sponsor segments (SponsorBlock)", "type": "boolean", "description": "Look up community-submitted sponsor/self-promo/intro/outro segments from the public SponsorBlock database for each Short. Adds a sponsorSegments array with categories, timestamps and votes. Coverage is partial (~30-40% of videos have data); Shorts with no data return null.", "default": true }, "includeAnalytics": { "title": "🧠 Sentiment, keywords & topics", "type": "boolean", "description": "Run a keyless lexicon analyzer over each Short's title and description to produce a signed sentiment score (-5..+5), a sentiment label, extracted keywords, and topic categories. Useful for brand-safety screening and content classification.", "default": true }, "publishedAfter": { "title": "📅 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": "Lower date bound. Use a date (YYYY-MM-DD) or relative time (e.g. 7 days, 2 weeks, 1 month, 1 year). Leave empty for no lower bound." }, "publishedBefore": { "title": "📅 Only Shorts published before", "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": "Upper date bound. Use a date (YYYY-MM-DD) or relative time (e.g. 7 days, 1 month). Pairs with the lower bound above to capture an exact campaign window. Leave empty for no upper bound." }, "sortOrder": { "title": "↕️ Sort by", "enum": [ "newest", "popular", "oldest" ], "type": "string", "description": "Order of results: Newest first, Oldest first, or by Popularity (views).", "default": "newest" }, "proxyConfiguration": { "title": "🌐 Proxy configuration", "type": "object", "description": "Turn on Apify Proxy for more reliable scraping (useful in EU or restricted regions). Off = direct connection; works in most regions and for Apify QA." } } }, "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 } } } } } } } } } }