{ "openapi": "3.0.1", "info": { "title": "YouTube Channel Scraper - Videos, Playlists, Comments, Stats", "description": "Channel, playlist and video data from YouTube: titles, views, likes, duration, publish dates and comments. Search is NOT available from Apify - YouTube answers 302 to its datacenter addresses, measured three runs in a row - so this Actor works from channel, playlist and video addresses instead.", "version": "0.1", "x-build-id": "fSGfDdDNmP1xKe7ar" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/snow_leo_data~youtube-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-snow_leo_data-youtube-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/snow_leo_data~youtube-scraper/runs": { "post": { "operationId": "runs-sync-snow_leo_data-youtube-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/snow_leo_data~youtube-scraper/run-sync": { "post": { "operationId": "run-sync-snow_leo_data-youtube-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "searchQueries": { "title": "🔍 Search terms", "type": "array", "description": "One YouTube search per line. A plain search stops at 289 videos per term - YouTube itself stops handing out the next page there. Turn on Deep search below to go past it. Note: YouTube refuses search requests coming from Apify's datacenter addresses (measured: HTTP 302 on three runs in a row), so search returns nothing here. Channel, playlist and video addresses in Start URLs do work.", "default": [], "items": { "type": "string" } }, "startUrls": { "title": "🔗 YouTube URLs", "type": "array", "description": "Video, channel, @handle or playlist addresses. Bare IDs work too: a video ID, a UC... channel ID or a PL... playlist ID.", "default": [ "https://www.youtube.com/@NASA" ], "items": { "type": "string" } }, "searchFor": { "title": "Search for", "enum": [ "videos", "shorts", "live", "channels", "playlists" ], "type": "string", "description": "What the search terms should return. Shorts are a separate listing on YouTube's side: asking for videos excludes them and asking for shorts excludes regular videos.", "default": "videos" }, "deepSearch": { "title": "🚀 Deep search (go past YouTube's 289-video ceiling)", "type": "boolean", "description": "Only affects keyword search, which does not work from Apify's datacenter addresses (YouTube answers HTTP 302; measured three runs in a row). Leave it off unless you run this Actor somewhere else. Runs the same term as up to 64 separate searches - four sort orders x four upload windows x four durations - and merges them. Measured on 'excavator repair': 289 videos without it, 3860 with it, 13.4x more. Costs more requests, so raise 'Max results per search term' to match. That 13.4x figure was measured off-platform and is NOT reachable from a run here.", "default": false }, "maxResultsPerQuery": { "title": "Max results per search term", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stop collecting a term after this many rows. Also the per-tab limit for a channel and the per-playlist limit.", "default": 100 }, "sortBy": { "title": "Sort by", "enum": [ "relevance", "date", "views", "rating" ], "type": "string", "description": "Handed to YouTube itself, so it filters before you are charged for a row.", "default": "relevance" }, "uploadDate": { "title": "Uploaded within", "enum": [ "any", "hour", "today", "week", "month", "year" ], "type": "string", "description": "Handed to YouTube inside the request. Non-matching videos never reach your dataset and never reach your bill.", "default": "any" }, "videoDuration": { "title": "Duration", "enum": [ "any", "short", "medium", "long" ], "type": "string", "description": "YouTube's own duration buckets. Shorts carry no duration at all, so this filter and a Shorts search cannot be combined.", "default": "any" }, "features": { "title": "Must have", "type": "array", "description": "YouTube's own feature filters. Several may be combined.", "items": { "type": "string", "enum": [ "hd", "is4k", "subtitles", "creativeCommons", "live", "is360", "vr180", "is3d", "hdr", "location", "purchased" ], "enumTitles": [ "HD", "4K", "Subtitles / CC", "Creative Commons", "Live", "360°", "VR180", "3D", "HDR", "Location", "Purchased" ] }, "default": [] }, "channelTabs": { "title": "Channel tabs to read", "type": "array", "description": "Only used for channel and @handle addresses.", "items": { "type": "string", "enum": [ "videos", "shorts", "live", "playlists" ], "enumTitles": [ "Videos", "Shorts", "Live", "Playlists" ] }, "default": [ "videos" ] }, "includeVideoDetails": { "title": "Fetch full video details", "type": "boolean", "description": "Opens each video page for the exact view count, like count, comment count, full description, tags, category and the publication date to the second. One extra request per video.", "default": false }, "includeComments": { "title": "Fetch comments", "type": "boolean", "description": "Adds one row per comment, with author, likes, replies and a direct link. Comments are rows too, so they count towards Max rows.", "default": false }, "maxCommentsPerVideo": { "title": "Comments per video", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Comments to take from each video, newest or top first depending on the order below. Zero switches comments off.", "default": 20 }, "commentsSortBy": { "title": "Comment order", "enum": [ "top", "newest" ], "type": "string", "description": "Top comments are the ones YouTube ranks highest; newest first is the raw chronological feed.", "default": "top" }, "titleContains": { "title": "Title contains any of", "type": "array", "description": "Case-insensitive. A row whose title is unknown is kept, not dropped - the count of such rows is in the REPORT record.", "default": [], "items": { "type": "string" } }, "channelContains": { "title": "Channel name contains", "type": "string", "description": "Case-insensitive substring of the channel name. A row whose channel is unknown is kept, not dropped.", "default": "" }, "minViews": { "title": "Minimum views", "type": "integer", "description": "Rows with fewer views are dropped before they are written. A row with no view count is kept, not dropped." }, "maxViews": { "title": "Maximum views", "type": "integer", "description": "Rows with more views are dropped before they are written. A row with no view count is kept, not dropped." }, "minDurationSeconds": { "title": "Minimum duration", "type": "integer", "description": "Rows shorter than this are dropped before they are written. Shorts and channels carry no duration, so they are kept, not dropped." }, "maxDurationSeconds": { "title": "Maximum duration", "type": "integer", "description": "Rows longer than this are dropped before they are written. Shorts and channels carry no duration, so they are kept, not dropped." }, "publishedAfter": { "title": "Published after", "type": "string", "description": "YYYY-MM-DD. Search listings carry only '4 years ago', so the date used is an estimate unless 'Fetch full video details' is on.", "default": "" }, "publishedBefore": { "title": "Published before", "type": "string", "description": "YYYY-MM-DD.", "default": "" }, "onlyNew": { "title": "Only new and changed rows", "type": "boolean", "description": "Remembers what earlier runs delivered in a named key-value store and writes only what is new or changed. Scheduled runs stop paying for the same rows twice.", "default": false }, "emitUnchanged": { "title": "Emit unchanged rows too", "type": "boolean", "description": "Brings back the rows that have not changed as well, marked UNCHANGED, when you want a full snapshot rather than a diff.", "default": false }, "maxItems": { "title": "Max rows", "type": "integer", "description": "Hard stop on delivered rows, comments included. Zero means no limit." }, "compactOutput": { "title": "Compact output", "type": "boolean", "description": "Fifteen decision-making columns instead of all of them. Handy for AI agents and small files.", "default": false }, "dropEmptyFields": { "title": "Drop empty fields", "type": "boolean", "description": "Removes null cells from every row entirely, instead of returning them empty. Smaller files, fewer tokens for an AI agent.", "default": false }, "language": { "title": "Language (hl)", "type": "string", "description": "Two-letter interface language. It changes the wording YouTube returns, such as '4 years ago'.", "default": "en" }, "country": { "title": "Country (gl)", "type": "string", "description": "Two-letter country code. YouTube ranks and filters results per country.", "default": "US" }, "concurrency": { "title": "Parallel detail requests", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many video or channel pages are opened at the same time. Higher is faster and more likely to make YouTube ask you to slow down.", "default": 4 }, "inputDatasetId": { "title": "Read URLs from a dataset", "type": "string", "description": "Dataset ID of another Actor's output. Its rows feed YouTube URLs into this run.", "default": "" }, "urlField": { "title": "Field holding the URL", "type": "string", "description": "Which column of that dataset holds the YouTube address.", "default": "url" } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }