{ "openapi": "3.0.1", "info": { "title": "Youtube Comment Scrapper", "description": "Scrape comments on Youtube Video Pages. Just specify the video page urls to visit and how many comments you would like to collect.\nWe'll get all meaningful information: comment text, author, publication date, number of likes and replies and video+channel url and id", "version": "0.7", "x-build-id": "lX87DfKOWHJRTmwfv" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/deeper~youtube-comment-scrapper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-deeper-youtube-comment-scrapper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/deeper~youtube-comment-scrapper/runs": { "post": { "operationId": "runs-sync-deeper-youtube-comment-scrapper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/deeper~youtube-comment-scrapper/run-sync": { "post": { "operationId": "run-sync-deeper-youtube-comment-scrapper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "start_urls" ], "properties": { "start_urls": { "title": "Start URLs", "type": "array", "description": "URLs to start with. It could be either a channel url (we will collect info about the top videos on the channel) or a video url", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "details": { "title": "Scrap details for each video", "type": "boolean", "description": "Scrapping details allows to get the full video description, comment counts and view counts", "default": true }, "scrap_videos": { "title": "Scrap videos for the channel", "type": "boolean", "description": "Scrapping videos allows to get the videos from the channel", "default": true }, "scrap_shorts": { "title": "Scrap shorts for the channel", "type": "boolean", "description": "Scrapping shorts allows to get the short videos from the channel (currently, details and comments are not scrapped for shorts, so some fields will be empty like the publication date). Filtering by date is not applied to shorts.", "default": true }, "dateFilter": { "title": "Collect only video more recent than", "type": "string", "description": "Select a date cutoff to collect only video more recent than this one. In any case, the most recent video is always returned for every channel.", "default": "" }, "dateFilterTill": { "title": "Collect only video older than", "type": "string", "description": "Select an upper date cutoff to collect only videos published before this date. Combined with the 'since' date filter, this creates a date range filter.", "default": "" }, "max_videos": { "title": "Number of videos to scrap details for each channel", "minimum": 0, "maximum": 9999, "type": "integer", "description": "We will scrap the details (and possibly comments) of that amount of video found on the channel. Use low value to have run executing faster. Use 30 to get the first page data, use more to go back in time.", "default": 30 }, "max_comments": { "title": "Number of comments to retrieve for each video", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Keep scrolling the page down until we've reach at least that number of comments. This number is not strict, if we get more comments by scrolling the page, they will be returned as well. This is applicable only if 'details' is set to True.", "default": 20 }, "scrap_captions": { "title": "Scrap caption for each video", "type": "boolean", "description": "Scrapping caption allows to get the transcript of the video (there is one extra result by caption language loaded)", "default": false }, "caption_languages": { "title": "Caption language code to collect", "type": "array", "description": "List of caption languages to collect (i.e. : ['en','fr']), pass an empty array to collect all available languages", "items": { "type": "string" } } } }, "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 } } } } } } } } } }