{ "openapi": "3.0.1", "info": { "title": "Youtube Scraper Pro", "description": "Full‑fidelity YouTube data extractor for videos, Shorts, live streams, and channels. Built on Apify + Puppeteer for reliable, scalable web scraping that returns complete metadata, engagement stats, caption tracks for transcripts, hashtags/keywords, description links, and channel insights — fast.", "version": "3.1", "x-build-id": "NMRuXm6mw9VcKXYxZ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/coregent~youtube-scraper-pro/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-coregent-youtube-scraper-pro", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/coregent~youtube-scraper-pro/runs": { "post": { "operationId": "runs-sync-coregent-youtube-scraper-pro", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/coregent~youtube-scraper-pro/run-sync": { "post": { "operationId": "run-sync-coregent-youtube-scraper-pro", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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, Channels, Playlists & Discovery", "type": "array", "description": "Discovery sources — each entry is auto-detected as one of: (1) a search keyword (e.g. \"ai automation tutorial\"); (2) a channel — URL, @handle, /channel/UC…, /c/…, /user/…, or a bare channel ID (UC…); (3) a playlist — URL (…?list=…) or a bare playlist ID (PL…, UU…); (4) a video URL or 11-char video ID — treated as a SEED (its owning channel is found and that channel's videos are returned, not just the one video); (5) a hashtag — #tag or a youtube.com/hashtag/ URL. Each source is capped by \"Max videos per source\". To fetch a single video by itself, use the \"YouTube URLs or IDs\" field instead.", "items": { "type": "string" }, "default": [] }, "startUrls": { "title": "YouTube URLs or IDs", "type": "array", "description": "Direct YouTube videos to scrape — one output record per entry, for that video only (no channel expansion, exempt from the Filters below). Accepts full URLs (https://www.youtube.com/watch?v=…, https://youtu.be/…, /shorts/…) or bare 11-character video IDs (e.g. dQw4w9WgXcQ). Channel/playlist/keyword entries here are skipped — put those in the Discovery field above.", "items": { "type": "string" }, "default": [] }, "maxResultsPerQuery": { "title": "Max videos per source", "minimum": 1, "type": "integer", "description": "Maximum videos to take from EACH discovery source (keyword, hashtag, channel, playlist, or seed-video channel) before filtering. Does not apply to the YouTube URLs/IDs field (one video each).", "default": 10 }, "maxItems": { "title": "Max results (whole run)", "minimum": 0, "type": "integer", "description": "Global cap on the total number of results saved across the entire run — your spend ceiling. 0 means no global limit (each source is still capped by 'Max videos per source'). Applied after filtering and sorting.", "default": 0 }, "contentType": { "title": "Content type", "enum": [ "all", "videos", "shorts", "live" ], "type": "string", "description": "Filter discovered results by content type. Shorts are detected by duration (≤ 60s); live from broadcast status. Does not affect videos listed in YouTube URLs/IDs.", "default": "all" }, "videoDuration": { "title": "Duration", "enum": [ "all", "short", "medium", "long" ], "type": "string", "description": "Filter by video length: short (< 4 min), medium (4–20 min), long (> 20 min).", "default": "all" }, "sortBy": { "title": "Sort results by", "enum": [ "relevance", "date", "views" ], "type": "string", "description": "Order of results. 'Relevance' keeps discovery order (keyword search relevance / channel newest-first). 'Date' and 'Views' sort the discovered set before the total cap is applied.", "default": "relevance" }, "uploadDate": { "title": "Upload date filter", "enum": [ "any", "hour", "today", "week", "month", "year" ], "type": "string", "description": "Relative published-date filter, applied to ALL discovered sources. Combined with From/To Date below (the stricter bound wins).", "default": "any" }, "titleFilter": { "title": "Title filter (optional)", "type": "string", "description": "Comma-separated keywords. Keep only results whose title contains at least one of them (OR logic, case-insensitive). Leave empty to disable.", "default": "" }, "getTrending": { "title": "Include trending videos", "type": "boolean", "description": "Also add the region's trending (\"most popular\") videos as a source (via the official YouTube Data API). Requires an API key. Uses the Country setting; capped by YouTube. These rows are marked provenance.source = \"trending\".", "default": false }, "dateFrom": { "title": "From Date", "type": "string", "description": "Only include videos published on or after this date (YYYY-MM-DD). Applies to ALL discovered sources. Leave empty to disable.", "default": "" }, "dateTo": { "title": "To Date", "type": "string", "description": "Only include videos published on or before this date (YYYY-MM-DD). Applies to ALL discovered sources. Leave empty to disable.", "default": "" }, "regionCode": { "title": "Country", "enum": [ "US", "GB", "CA", "AU", "IE", "NZ", "DE", "FR", "ES", "IT", "NL", "PL", "SE", "TR", "RU", "UA", "IN", "ID", "JP", "KR", "VN", "TH", "PH", "MY", "SG", "HK", "TW", "BR", "MX", "AR", "CO", "CL", "NG", "ZA", "EG", "SA", "AE" ], "type": "string", "description": "Country for localization (ISO 3166-1 alpha-2). Also selects the category list used for the category name.", "default": "US" }, "language": { "title": "Language", "enum": [ "en", "es", "de", "fr", "pt", "it", "nl", "pl", "sv", "tr", "ru", "uk", "ja", "ko", "zh", "hi", "id", "vi", "th", "ar" ], "type": "string", "description": "Preferred language (IETF BCP-47). Limited effect in API mode.", "default": "en" }, "outputMode": { "title": "Output format", "enum": [ "rich", "analyticsFlat" ], "type": "string", "description": "How each record is shaped. 'Rich' keeps nested objects (channel, features, provenance). 'Analytics-flat' flattens them into top-level columns (channel_name, features_isHD, …) and joins keyword/hashtag arrays — easier for Google Sheets, Excel, and BI tools.", "default": "rich" }, "includeTranscript": { "title": "Include Transcript", "type": "boolean", "description": "Extract captions for each result and fill the `subtitles` array (otherwise it stays empty). Each entry has the caption text, a `type`, the `language`, and a link to the file in the run's key-value store. Adds ~1-2 seconds per video; about 60-80% of videos have captions available. Billed as a separate `transcript` pay-per-event charge, only for videos where a subtitle is actually delivered.", "default": false }, "subtitleFormats": { "title": "Subtitle formats (select one or more)", "type": "array", "description": "Which subtitle format(s) to include in each `subtitles` entry — pick one or more. 'SRT' and 'VTT' keep timestamps (SubRip / WebVTT); 'Plain text' is the spoken text only; 'JSON' is an array of `{ start, dur, text }` segments. All are derived from one caption fetch (no extra API cost per format). Only used when Include Transcript is enabled.", "items": { "type": "string", "enum": [ "srt", "vtt", "txt", "json" ], "enumTitles": [ "SRT (timestamped)", "VTT (WebVTT)", "Plain text", "JSON (segments)" ] }, "default": [ "srt" ] }, "transcriptLanguage": { "title": "Transcript Language", "enum": [ "", "en", "es", "fr", "de", "pt", "ru", "ja", "ko", "zh", "zh-TW", "ar", "hi", "it", "nl", "tr", "pl", "sv", "id", "vi", "uk" ], "type": "string", "description": "Preferred caption language. Auto-detect uses the first available track. Only used when Include Transcript is enabled.", "default": "" } } }, "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 } } } } } } } } } }