{ "openapi": "3.0.1", "info": { "title": "Stack Overflow Scraper - Questions, Answers & Comments", "description": "Scrape questions, answers, and comments from Stack Overflow and the Stack Exchange network. Filter by tag, search, or user. Returns body, score, votes, accepted-answer flag. Built for AI/LLM training datasets, dev research, and tag-trend monitoring.", "version": "0.1", "x-build-id": "QGMFXNuUCR1IkRvGC" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/legend006~stackoverflow-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-legend006-stackoverflow-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/legend006~stackoverflow-scraper/runs": { "post": { "operationId": "runs-sync-legend006-stackoverflow-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/legend006~stackoverflow-scraper/run-sync": { "post": { "operationId": "run-sync-legend006-stackoverflow-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "site", "mode" ], "properties": { "site": { "title": "Site", "type": "string", "description": "Stack Exchange site short name. Default 'stackoverflow'. Examples: 'serverfault', 'superuser', 'math', 'askubuntu', 'unix', 'datascience'.", "default": "stackoverflow" }, "mode": { "title": "Scrape mode", "enum": [ "tag", "search", "user", "top" ], "type": "string", "description": "'tag' = questions by tag(s). 'search' = full-text search. 'user' = user's questions/answers. 'top' = top voted of period.", "default": "tag" }, "tags": { "title": "Tags", "type": "array", "description": "Tag names without '[' brackets, e.g. 'python', 'machine-learning'. Used in mode = tag.", "default": [ "python" ], "items": { "type": "string" } }, "searchQueries": { "title": "Search queries", "type": "array", "description": "Free-text search. Used in mode = search.", "default": [], "items": { "type": "string" } }, "userIds": { "title": "User IDs", "type": "array", "description": "Numeric Stack Exchange user IDs. Used in mode = user. Get from a profile URL: stackoverflow.com/users/{ID}/...", "default": [], "items": { "type": "string" } }, "sort": { "title": "Sort", "enum": [ "activity", "creation", "votes", "hot", "week", "month" ], "type": "string", "description": "Sort order. 'activity' / 'creation' / 'votes' / 'hot' / 'week' / 'month' (some sorts are mode-specific).", "default": "votes" }, "fromDate": { "title": "From date (ISO YYYY-MM-DD)", "type": "string", "description": "Optional lower bound on creation date." }, "toDate": { "title": "To date (ISO YYYY-MM-DD)", "type": "string", "description": "Optional upper bound on creation date." }, "minScore": { "title": "Minimum score", "minimum": 0, "type": "integer", "description": "Skip questions with score below this threshold (filters in code).", "default": 0 }, "includeAnswers": { "title": "Include answers", "type": "boolean", "description": "Fetch all answers for each question (slower, much richer).", "default": false }, "includeComments": { "title": "Include comments", "type": "boolean", "description": "Fetch comments on questions (and answers if includeAnswers is on).", "default": false }, "maxItems": { "title": "Max questions per target", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Cap per tag / per query / per user.", "default": 100 }, "apiKey": { "title": "Stack Exchange API key (optional)", "type": "string", "description": "Free key at https://stackapps.com/apps/oauth/register — boosts daily quota from 300 to 10,000 requests/day. Highly recommended for large scrapes." } } }, "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 } } } } } } } } } }