{ "openapi": "3.0.1", "info": { "title": "YouTube Shorts Data Scraper", "description": "YouTube Shorts Data Scraper extracts YouTube Shorts metadata by channel or keyword. Fast, concurrent, and low-bandwidth scraping with real-time dataset streaming for analytics, research, lead generation, and content discovery.", "version": "0.1", "x-build-id": "jZxx2YhkAp0fmGM5G" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/code-node-tools~yt-shorts-data-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-code-node-tools-yt-shorts-data-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/code-node-tools~yt-shorts-data-scraper/runs": { "post": { "operationId": "runs-sync-code-node-tools-yt-shorts-data-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/code-node-tools~yt-shorts-data-scraper/run-sync": { "post": { "operationId": "run-sync-code-node-tools-yt-shorts-data-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "channels": { "title": "Name(s) of the channel", "type": "array", "description": "Enter a username of a channel (without @ sign) or a link to it (e.g. https://www.youtube.com/c/Apify). Required unless 'searchTerm' is provided.", "items": { "type": "string" } }, "searchTerm": { "title": "Search term", "type": "string", "description": "Search YouTube for Shorts matching this term. If provided, 'channels' is not required. Best-effort: results are filtered to short-form videos (<= 180s)." }, "maxResultsShorts": { "title": "Maximum number of shorts per search term", "minimum": 1, "maximum": 999999, "type": "integer", "description": "Limit the number of Shorts videos you want to crawl from the channel (or per search term).", "default": 3 }, "oldestPostDate": { "title": "Scrape shorts published after [date]", "type": "string", "description": "Only posts uploaded after or on this date will be scraped. Alternatively, specify how old the scraped videos should be in days. Putting 1 day will get you only today's posts, 2 days - yesterday's and today's, and so on. Note: if you select this, the sorting parameter is auto-reset to NEWEST." }, "sortChannelShortsBy": { "title": "Sort shorts by", "enum": [ "NEWEST", "POPULAR", "OLDEST" ], "type": "string", "description": "Maps to the three sorting buttons on the top of the channel shorts page. Ignored for search-term runs.", "default": "NEWEST" }, "liteMode": { "title": "Lite mode (minimize bandwidth)", "type": "boolean", "description": "Skip the per-video detail pass and return only lightweight metadata (id, url, title, views, thumbnail) from the cheap flat listing. Dramatically reduces proxy bandwidth and cost, at the expense of fields like description, likes, exact upload date and tags.", "default": false }, "maxConcurrency": { "title": "Max concurrency", "minimum": 5, "maximum": 18, "type": "integer", "description": "Number of videos to extract metadata for in parallel. Higher is faster but uses more resources and may trigger rate limiting.", "default": 10 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy settings. Residential proxies are strongly recommended for YouTube (datacenter IPs are usually blocked). Residential costs more bandwidth, so switch to datacenter only if it works for your targets.", "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 } } } } } } } } } }