{ "openapi": "3.0.1", "info": { "title": "๐Ÿ”ฅ YouTube Scraper โ€“ Transcripts, Dislikes & Heatmaps", "description": "YouTube scraper with full transcripts, the most-replayed heatmap, likes AND dislikes, channel profiles with social links, and bulk channel/search scraping โ€” plus chain modes: viral-DNA (heatmap x transcript), niche-map (the algorithm's related-video graph), and gap-finder (demand vs supply).", "version": "0.1", "x-build-id": "l0bpoZXILVPi5EqIa" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/yumitori~youtube-intel/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-yumitori-youtube-intel", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/yumitori~youtube-intel/runs": { "post": { "operationId": "runs-sync-yumitori-youtube-intel", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/yumitori~youtube-intel/run-sync": { "post": { "operationId": "run-sync-yumitori-youtube-intel", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "inputs" ], "properties": { "mode": { "title": "Mode", "enum": [ "auto", "video", "channel", "channel-bulk", "search", "hashtag", "viral-dna", "niche-map", "gap-finder", "demand" ], "type": "string", "description": "Leave on Auto โ€” it figures out each input for you (video URL โ†’ that video ยท @handle โ†’ the channel's top videos ยท search term โ†’ results ยท #tag โ†’ hashtag). Only change it to force a mode or run a chain-insight mode.", "default": "auto" }, "inputs": { "title": "What to scrape", "maxItems": 200, "uniqueItems": true, "type": "array", "description": "Paste any mix โ€” one per line: video URLs, channel @handles or URLs, search terms, or #hashtags. It auto-detects each one.", "items": { "type": "string" } }, "maxVideos": { "title": "Max videos (per channel / search / hashtag)", "minimum": 1, "maximum": 1000, "type": "integer", "description": "How many videos to return when the input is a channel, search, or hashtag โ€” highest-viewed first. (A single video URL always returns just that one video.)", "default": 30 }, "includeTranscript": { "title": "Include transcripts", "type": "boolean", "description": "Full multi-language transcripts. โš ๏ธ Needs the Residential proxy (the default, below) to work on EVERY video โ€” small / low-view videos are gated without it.", "default": true }, "includeComments": { "title": "Include comments", "type": "boolean", "description": "Top comments with like / reply counts, verified & creator flags, and the โ˜… creator-hearted signal (which comments the creator personally amplified).", "default": false }, "proxyConfiguration": { "title": "Proxy โ€” keep RESIDENTIAL on for transcripts", "type": "object", "description": "IMPORTANT for transcripts: YouTube gates less-popular / low-view videos on shared datacenter IPs, blanking the transcript. A RESIDENTIAL proxy behaves like a home IP so nothing gets gated โ€” that's why it's the default. Only scraping popular/big-channel videos? Switch to No proxy to save cost." }, "enrichTop": { "title": "How many videos to deep-dive", "minimum": 0, "maximum": 200, "type": "integer", "description": "For channel/search/hashtag: how many of the returned videos get the FULL deep-dive (transcript, heatmap, comments). The rest get title/views/channel only. 0 = list only (cheapest).", "default": 5 }, "enrichBy": { "title": "Deep-dive which videos", "enum": [ "hottest", "latest" ], "type": "string", "description": "For channel/search/hashtag: pick which videos get the full deep-dive.", "default": "hottest" }, "bulkTranscripts": { "title": "Transcript on ALL listed videos", "type": "boolean", "description": "Add a transcript to every returned video, not just the deep-dived ones (cheap; needs Residential proxy).", "default": false }, "includeNeighbors": { "title": "Include related videos", "type": "boolean", "description": "Video mode: add the ~20 videos YouTube recommends next.", "default": true }, "commentsLimit": { "title": "Max comments per video", "minimum": 1, "maximum": 500, "type": "integer", "description": "How many top comments to pull when Include comments is on.", "default": 50 }, "tab": { "title": "Channel tab", "enum": [ "videos", "shorts", "streams" ], "type": "string", "description": "For channel modes: which catalog โ€” long-form Videos, Shorts, or past Streams.", "default": "videos" }, "momentsPerVideo": { "title": "Moments per video (viral-dna)", "minimum": 1, "maximum": 10, "type": "integer", "description": "viral-dna: how many most-replayed moments to extract per video.", "default": 2 }, "crawlDepth": { "title": "Crawl depth (niche-map)", "minimum": 1, "maximum": 3, "type": "integer", "description": "niche-map: hops through the related-video graph (2 is plenty; 3 explodes).", "default": 2 }, "crawlWidth": { "title": "Crawl width (niche-map)", "minimum": 2, "maximum": 20, "type": "integer", "description": "niche-map: neighbors followed per node.", "default": 8 }, "country": { "title": "Country (gap-finder)", "type": "string", "description": "gap-finder: gl code for search demand.", "default": "US" }, "countries": { "title": "Countries (demand)", "type": "array", "description": "demand: gl codes to compare demand across.", "default": [ "US", "GB", "DE", "JP", "BR" ], "items": { "type": "string" } }, "maxQueries": { "title": "Max queries (gap-finder)", "minimum": 1, "maximum": 50, "type": "integer", "description": "gap-finder: autocomplete suggestions to check supply for.", "default": 12 } } }, "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 } } } } } } } } } }