Youtube Scraper
Pricing
$19.99/month + usage
Pricing
$19.99/month + usage
Rating
0.0
(0)
Developer
ScrapePilot
Actor stats
0
Bookmarked
2
Total users
0
Monthly active users
22 days ago
Last modified
Categories
Share
You can access the Youtube Scraper programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.1", "x-build-id": "pyDipCN6hLVlI2uq9" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapepilotapi~youtube-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapepilotapi-youtube-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/scrapepilotapi~youtube-scraper/runs": { "post": { "operationId": "runs-sync-scrapepilotapi-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/scrapepilotapi~youtube-scraper/run-sync": { "post": { "operationId": "run-sync-scrapepilotapi-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": { "searchTerms": { "title": "🔍 Search terms", "type": "array", "description": "Enter one or more YouTube search keywords (for example \"Crawlee\", \"fitness workout\"). The actor will run a full scrape for each term and collect matching videos, shorts, and streams.\n\n💬 For custom solutions or feature requests, contact us at dev.scraperengine@gmail.com", "items": { "type": "string" } }, "maxVideos": { "title": "🎞️ Maximum videos per search term", "minimum": 0, "maximum": 9999, "type": "integer", "description": "Set how many regular (non‑Shorts, non‑live) videos to scrape for each search term. Use 0 to skip long‑form videos completely and focus only on Shorts or streams.", "default": 10 }, "maxShorts": { "title": "📱 Maximum Shorts per search term", "minimum": 0, "maximum": 9999, "type": "integer", "description": "Control how many YouTube Shorts (vertical clips) to collect per keyword. Use 0 if you do not want to include Shorts in your dataset.", "default": 0 }, "maxStreams": { "title": "📡 Maximum streams per search term", "minimum": 0, "maximum": 9999, "type": "integer", "description": "Limit how many live or upcoming streams are scraped for each search term. Use 0 to ignore live content entirely.", "default": 0 }, "startUrls": { "title": "🔗 Direct URLs", "type": "array", "description": "Provide direct YouTube video, channel, playlist, or results page URLs to scrape without using search terms. This is ideal for monitoring specific assets.", "items": { "type": "string" } }, "downloadSubtitles": { "title": "💬 Download subtitles", "type": "boolean", "description": "Download video subtitles/transcripts when available. When enabled, the actor will try to fetch caption tracks and optionally full transcripts for each scraped video.", "default": false }, "saveSubtitlesToKvs": { "title": "🗄️ Save subtitles to key‑value store", "type": "boolean", "description": "When enabled, every downloaded transcript is stored in the default Apify key‑value store under its own key (e.g. \"transcript-VIDEO_ID\") so you can download large subtitle files separately from the main dataset.", "default": false }, "subtitlesLanguage": { "title": "🌐 Subtitle language", "enum": [ "en", "es", "fr", "de", "pt", "it", "ru", "ja", "ko", "zh", "ar", "hi", "bn", "tr", "pl", "nl", "sv", "id", "th", "vi" ], "type": "string", "description": "Choose the primary language for subtitles/transcripts (e.g. en, es, fr, de). The actor will look for this language first and fall back to available tracks where possible.", "default": "en" }, "preferAutoGenerated": { "title": "⚙️ Prefer automatically generated subtitles", "type": "boolean", "description": "If turned on, the actor will prefer auto‑generated subtitles over manually uploaded caption tracks. This can increase coverage for less localized videos at the cost of some accuracy.", "default": false }, "subtitlesFormat": { "title": "📄 Subtitle format", "enum": [ "srt", "text", "timestamp" ], "type": "string", "description": "Decide how transcripts should look in the output: classic SRT (with timestamps), simple plain text, or structured timestamped JSON that is easy to post‑process programmatically.", "default": "srt" }, "sortingOrder": { "title": "🧮 Sorting order", "enum": [ "", "relevance", "date", "viewCount", "rating" ], "type": "string", "description": "Sort the final dataset by relevance (original order), upload date, view count, or rating. Applied as post-processing for reliable results.", "default": "" }, "dateFilter": { "title": "🕒 Date filter", "enum": [ "", "hour", "today", "week", "month", "year" ], "type": "string", "description": "Apply YouTube’s built‑in \"Upload date\" filter: last hour, today, this week, this month, or this year — just like clicking the filter in the YouTube interface.", "default": "" }, "videoTypeFilter": { "title": "📂 Video type filter", "enum": [ "", "video", "channel", "playlist", "movie" ], "type": "string", "description": "Filter to only standard videos (exclude Shorts). Select 'video' to keep only long-form videos. Channel/playlist/movie apply when supported.", "default": "" }, "lengthFilter": { "title": "⏱️ Length filter", "enum": [ "", "short", "medium", "long" ], "type": "string", "description": "Use YouTube’s length presets to keep only short clips, medium‑length videos, or long‑form content over 20 minutes.", "default": "" }, "isHD": { "title": "📺 HD", "type": "boolean", "description": "Only include HD videos (720p or higher). The actor inspects YouTube's streaming formats to verify resolution before including the video.", "default": false }, "hasCC": { "title": "📝 Subtitles / CC", "type": "boolean", "description": "Only include videos that have at least one proper closed‑caption track (not just auto‑generated). Great for accessibility‑critical workflows.", "default": false }, "isCreativeCommons": { "title": "⚖️ Creative Commons", "type": "boolean", "description": "Filter for videos marked by YouTube as Creative Commons licensed. This can help discover content that is more remix‑friendly (always check final license conditions yourself).", "default": false }, "is3D": { "title": "🕶️ 3D", "type": "boolean", "description": "Keep only stereoscopic 3D videos that YouTube flags as special 3D content.", "default": false }, "isLive": { "title": "📺 Live only", "type": "boolean", "description": "Restrict results to live or live‑style content. Combine this with maxStreams to build focused dashboards of live events or streams.", "default": false }, "isPurchased": { "title": "💳 Purchased content", "type": "boolean", "description": "Best-effort filter for purchased/paid content. YouTube rarely exposes this in scraped data, so results may be limited. Use for niche use cases only.", "default": false }, "is4K": { "title": "🖥️ 4K only", "type": "boolean", "description": "Keep only videos that offer at least one 2160p (4K) stream in their available formats.", "default": false }, "is360": { "title": "🌐 360° video", "type": "boolean", "description": "Filter results down to immersive 360° videos (spherical / equirectangular projection) that can be explored in all directions.", "default": false }, "hasLocation": { "title": "📍 With location", "type": "boolean", "description": "Only keep videos where YouTube exposes explicit location metadata in the player response (for example city/country information).", "default": false }, "isHDR": { "title": "🌈 HDR only", "type": "boolean", "description": "Limit the dataset to High Dynamic Range (HDR) videos, detected from color information and HDR‑specific flags in the available formats.", "default": false }, "isVR180": { "title": "🥽 VR180 only", "type": "boolean", "description": "Filter for VR180 immersive content suitable for VR headsets when YouTube marks the video as VR180.", "default": false }, "publishedAfter": { "title": "📆 Scrape videos published after (date)", "pattern": "^(\\d{4})-(0[1-9]|1[0-2])-(0[1-9]|[12]\\d|3[01])$|^$", "type": "string", "description": "Only include videos published after this date. Pick a date in the calendar (absolute format YYYY-MM-DD). Leave empty to include all dates.", "default": "" }, "sortBy": { "title": "📊 Sort by (post‑processing)", "enum": [ "", "date", "viewCount", "likes" ], "type": "string", "description": "After scraping, optionally sort the final dataset by a chosen field (date, viewCount, or likes) so that the default dataset view is ordered exactly how you like it.", "default": "" }, "proxyConfiguration": { "title": "🛡️ Proxy configuration & anti‑blocking", "type": "object", "description": "Select the starting proxy setup for this actor. By default it uses no proxy and, if YouTube blocks the traffic, the actor automatically escalates to Apify datacenter proxy and then to residential proxy with up to 3 retries, locking onto residential for the rest of the run." } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Youtube Scraper from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: