{
"openapi": "3.0.1",
"info": {
"title": "StackOverflow Scraper ยท Questions, Answers, Tags & Users",
"description": "Stack Overflow Scraper (StackOverflow Scraper) to scrape questions, answers, tags, user profiles, and developer Q&A datasets across Stack Overflow and Stack Exchange sites. Filter by tag, query, score, date, and accepted answers. No login or API key required.",
"version": "1.0",
"x-build-id": "6HsHtOicGAdQ7MkU2"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/reapx~stackoverflow-scraper/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-reapx-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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/reapx~stackoverflow-scraper/runs": {
"post": {
"operationId": "runs-sync-reapx-stackoverflow-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/reapx~stackoverflow-scraper/run-sync": {
"post": {
"operationId": "run-sync-reapx-stackoverflow-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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",
"properties": {
"dataset": {
"title": "What to scrape",
"enum": [
"questions",
"answers",
"tags",
"users"
],
"type": "string",
"description": "Which Stack Exchange collection to read. Each returns a different kind of row, keyed by its own Stack Exchange identifier.
Options: questions, answers, tags, users."
},
"site": {
"title": "Stack Exchange site",
"type": "string",
"description": "Which site to read. Defaults to Stack Overflow; any Stack Exchange site key works, e.g. serverfault, superuser, askubuntu, math, unix, dba.
Leave this field empty to skip this filter."
},
"maxItems": {
"title": "Max items",
"minimum": 1,
"maximum": 2500,
"type": "integer",
"description": "Hard cap on how many rows the run returns. This is also your cost cap: you are charged once per item returned. The API serves at most 2,500 items for one query.
The higher the number, the longer the run takes and the more you are charged, because you pay per row returned."
},
"sortBy": {
"title": "Sort by",
"enum": [
"activity",
"votes",
"creation",
"relevance",
"popular",
"name",
"reputation",
"modified"
],
"type": "string",
"description": "Ordering. Questions accept activity, votes, creation and relevance; answers accept activity, votes and creation; tags accept popular, activity and name; users accept reputation, creation, name and modified. An unsupported value falls back to the dataset's default.
Options: activity, votes, creation, relevance, popular, name."
},
"order": {
"title": "Direction",
"enum": [
"desc",
"asc"
],
"type": "string",
"description": "Descending gives the highest or newest first.
Options: desc, asc."
},
"query": {
"title": "Full-text search",
"type": "string",
"description": "Free-text search across question titles and bodies. Pair it with sort \"Best match\" for relevance ranking.
Leave this field empty to skip this filter."
},
"titleContains": {
"title": "Title contains",
"type": "string",
"description": "Match text in the question title only, which is far more precise than a body search.
Leave this field empty to skip this filter."
},
"tagged": {
"title": "Tagged with all of",
"type": "array",
"description": "Only questions carrying every one of these tags. Use the exact Stack Overflow tag spelling, e.g. python, pandas, machine-learning.
Leave this field empty to include every option.",
"items": {
"type": "string"
}
},
"notTagged": {
"title": "Not tagged with",
"type": "array",
"description": "Exclude questions carrying any of these tags.
Leave this field empty to include every option.",
"items": {
"type": "string"
}
},
"minScore": {
"title": "Minimum score",
"type": "integer",
"description": "Only items at or above this vote score. Requires sort \"Votes / score\", which is how the API applies a floor."
},
"minAnswers": {
"title": "Minimum answers",
"minimum": 1,
"type": "integer",
"description": "Only questions with at least this many answers."
},
"acceptedOnly": {
"title": "Has an accepted answer",
"type": "boolean",
"description": "Only questions where the asker accepted an answer - the solved set."
},
"unansweredOnly": {
"title": "Unanswered only",
"type": "boolean",
"description": "Only questions with no answers and nothing accepted - where the gaps are."
},
"closedOnly": {
"title": "Closed questions only",
"type": "boolean",
"description": "Only questions the community has closed."
},
"user": {
"title": "Author user ID",
"type": "integer",
"description": "Only questions asked by this Stack Exchange user ID."
},
"tagNameContains": {
"title": "Tag name contains",
"type": "string",
"description": "Only tags whose name contains this text. Applies when scraping tags.
Leave this field empty to skip this filter."
},
"userNameContains": {
"title": "Display name contains",
"type": "string",
"description": "Only users whose display name contains this text. Applies when scraping users.
Leave this field empty to skip this filter."
},
"minReputation": {
"title": "Minimum reputation",
"type": "integer",
"description": "Only users at or above this reputation. Requires sort \"Reputation\"."
},
"lastNDays": {
"title": "In the last N days",
"minimum": 1,
"maximum": 20000,
"type": "integer",
"description": "Rolling window on the creation date. Ignored if you set an explicit \"From date\".
The higher the number, the longer the run takes and the more you are charged, because you pay per row returned."
},
"dateFrom": {
"title": "From date",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"type": "string",
"description": "Earliest creation date, YYYY-MM-DD."
},
"dateTo": {
"title": "To date",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"type": "string",
"description": "Latest creation date, YYYY-MM-DD."
},
"includeBody": {
"title": "Include the full body text",
"type": "boolean",
"description": "Add the question or answer body as both plain text and original HTML. Off by default to keep rows small."
},
"includeAnswers": {
"title": "Include answers with each question",
"type": "boolean",
"description": "Attach every answer to each question row, highest score first, with author and accepted flag. Applies when scraping questions. Costs one extra request per 100 questions."
},
"apiKey": {
"title": "Stack Apps API key (optional)",
"type": "string",
"description": "Optional and free from stackapps.com/apps/oauth/register. Without one, Stack Exchange allows 300 requests per day per IP; with one, 10,000. Only needed for very large or frequent runs.
Leave this field empty to skip this filter."
}
}
},
"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
}
}
}
}
}
}
}
}
}
}