{ "openapi": "3.0.1", "info": { "title": "YouTube Scraper — Videos, Channels, Playlists, Comments", "description": "Scrapes YouTube search results, video details, channels, playlists and comments — views, likes, descriptions, durations, subscriber counts and full comment threads. No login or API key. Does not download video or transcripts (YouTube gates those behind a browser-only token).", "version": "0.1", "x-build-id": "OVR95OjZTJqnMBfYA" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapyx~youtube-data-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapyx-youtube-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapyx~youtube-data-scraper/runs": { "post": { "operationId": "runs-sync-scrapyx-youtube-data-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapyx~youtube-data-scraper/run-sync": { "post": { "operationId": "run-sync-scrapyx-youtube-data-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "mode": { "title": "What to scrape", "enum": [ "search", "video", "channel", "playlist", "comments" ], "type": "string", "description": "Decides what your `queries` mean and what rows you get back.\n\n• **Search** — search terms → video results\n• **Video details** — video IDs/URLs → one rich row each (views, likes, description, channel)\n• **Channel** — channel IDs/@handles/URLs → a channel row plus its videos, shorts or live streams\n• **Playlist** — playlist IDs/URLs → a playlist row plus its videos\n• **Comments** — video IDs/URLs → comment rows", "default": "search" }, "queries": { "title": "Queries / URLs", "type": "array", "description": "One entry per thing to scrape. What goes here depends on the mode:\n\n• **Search** — plain search terms, e.g. `python tutorial`\n• **Video details / Comments** — an 11-character video ID or any video URL (`watch?v=`, `youtu.be/`, `/shorts/`, `/embed/`, `/live/`)\n• **Channel** — a `UC…` channel ID, an `@handle`, or a channel URL (legacy `/c/` and `/user/` URLs work too)\n• **Playlist** — a playlist ID (`PL…`, `UU…`, …) or any URL with a `list=` parameter", "default": [], "items": { "type": "string" } }, "maxItems": { "title": "Max results per query", "minimum": 0, "type": "integer", "description": "Videos per search/channel/playlist, or comments per video. Set to 0 for as many as YouTube will page through. Results are paged in chunks (search ~12–14, channel 30, comments 20), so the actual count lands on a chunk boundary at or above your number.", "default": 50 }, "channelTab": { "title": "Channel tab", "enum": [ "videos", "shorts", "streams" ], "type": "string", "description": "Which tab to read in Channel mode. Note that **Shorts carry no publish date and no duration** — YouTube's shorts shelf simply doesn't include them, so those fields come back empty (and the run says so in its summary row).", "default": "videos" }, "searchFilter": { "title": "Search filter", "enum": [ "", "video", "channel", "playlist", "movie", "today", "this_week", "this_month" ], "type": "string", "description": "Optional filter for Search mode, matching YouTube's own filter chips. Leave blank for unfiltered results.", "default": "" }, "commentSort": { "title": "Comment sort", "enum": [ "top", "newest" ], "type": "string", "description": "Order for Comments mode: YouTube's own \"Top comments\" ranking, or newest first.", "default": "top" }, "includeChannelVideos": { "title": "Include the channel's videos", "type": "boolean", "description": "In Channel mode, also page through the selected tab. Turn this off to fetch only the channel profile row (title, description, subscriber count, avatar, banner) — one request instead of many.", "default": true }, "language": { "title": "Language (hl)", "type": "string", "description": "Interface language for titles and metadata YouTube localises, as an ISO code — `en`, `es`, `id`, `de`.", "default": "en" }, "country": { "title": "Country (gl)", "type": "string", "description": "Country context as a two-letter code — `US`, `GB`, `ID`. Affects which results YouTube considers relevant.", "default": "US" }, "maxConcurrency": { "title": "Max concurrent requests", "minimum": 1, "maximum": 16, "type": "integer", "description": "Upper bound on requests in flight at once, across all queries. Keep this modest: YouTube answers a hot IP with a rate-limit interstitial rather than a clean error.", "default": 4 }, "minRequestInterval": { "title": "Minimum seconds between request starts", "minimum": 0, "maximum": 30, "type": "number", "description": "The honest speed control — it paces request starts without tying up a worker. Raise it (0.5–2) if the log shows rate-limit warnings; once this cap binds, extra concurrency buys nothing.", "default": 0.25 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Off by default — these endpoints answer a datacenter IP fine. Enable it if you scrape heavily and start seeing rate-limit warnings, or if you need results from a specific country.", "default": { "useApifyProxy": false } } } }, "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 } } } } } } } } } }