{ "openapi": "3.0.1", "info": { "title": "Stack Overflow Scraper", "description": "Stack Overflow Scraper is a Python tool designed to extract Q&A data, accepted answers, vote counts, code snippets, and user profiles from Stack Overflow. It exports structured developer knowledge into clean CSV or JSON formats for research and AI model training.", "version": "0.0", "x-build-id": "xNhB6QGREFZvubREn" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/real-estate-api~Stack-Overflow-Scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-real-estate-api-Stack-Overflow-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/real-estate-api~Stack-Overflow-Scraper/runs": { "post": { "operationId": "runs-sync-real-estate-api-Stack-Overflow-Scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/real-estate-api~Stack-Overflow-Scraper/run-sync": { "post": { "operationId": "run-sync-real-estate-api-Stack-Overflow-Scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "mode" ], "properties": { "mode": { "title": "What to scrape", "enum": [ "questions", "search", "answers", "tags", "users", "sites" ], "type": "string", "description": "Questions by tag, advanced question search, answers for question ids, tags, users, or the list of Stack Exchange sites.", "default": "search" }, "site": { "title": "Site", "type": "string", "description": "api_site_parameter, e.g. stackoverflow, superuser, serverfault, askubuntu, math, datascience. Ignored for the sites list.", "default": "stackoverflow" }, "query": { "title": "Search query", "type": "string", "description": "Keyword query for search mode. Sent as q to /search/advanced." }, "tags": { "title": "Tags (all must match)", "type": "array", "description": "Tags that must all match. Used as tagged on questions and search. One tag per line.", "items": { "type": "string" } }, "titleContains": { "title": "Title contains", "type": "string", "description": "Search mode only. Keep questions whose title contains this text." }, "acceptedOnly": { "title": "Only questions with accepted answer", "type": "boolean", "description": "Search mode only. When checked, only questions with an accepted answer are returned.", "default": false }, "minAnswers": { "title": "Min answers", "minimum": 0, "type": "integer", "description": "Search mode only. Minimum number of answers a question must have." }, "sort": { "title": "Sort", "enum": [ "activity", "creation", "votes", "relevance", "popular", "reputation" ], "type": "string", "description": "relevance: search only; popular: tags; reputation: users. A sort the endpoint does not accept is replaced with that mode's usual sort.", "default": "activity" }, "fromDate": { "title": "From date", "type": "string", "description": "Oldest creation date for questions and search, inclusive. Sent as a Unix timestamp." }, "toDate": { "title": "To date", "type": "string", "description": "Newest creation date for questions and search, inclusive. Sent as a Unix timestamp." }, "questionIds": { "title": "Question IDs or URLs (answers mode)", "type": "array", "description": "Answers mode. Numeric question ids or stackoverflow.com/questions/ID URLs. Up to 100 ids are sent per request.", "items": { "type": "string" } }, "userIds": { "title": "User IDs or profile URLs (users mode)", "type": "array", "description": "Users mode. Numeric user ids or /users/ID profile URLs. When this list is set, name search is skipped.", "items": { "type": "string" } }, "nameContains": { "title": "Name contains (tags/users)", "type": "string", "description": "Partial name for tags (inname) or users (inname). Leave empty to list by the selected sort." }, "includeBody": { "title": "Include full body", "type": "boolean", "description": "Request filter=withbody and store the question or answer body. Turn off to keep rows smaller.", "default": true }, "includeAnswers": { "title": "Fetch answers for each question", "type": "boolean", "description": "Questions and search only. Batches up to 100 question ids per /questions/{ids}/answers call and nests the answers on each question.", "default": false }, "bodyFormat": { "title": "Body format", "enum": [ "markdown", "text", "html" ], "type": "string", "description": "How to store the body: Markdown, plain text, or the original HTML.", "default": "markdown" }, "maxItems": { "title": "Max results (total)", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Free cap 10,000. Without an API key Stack Exchange allows about 300 requests/day per IP (100 items each).", "default": 200 }, "timeoutSecs": { "title": "Run timeout (seconds)", "minimum": 1, "maximum": 3600, "type": "integer", "description": "Stop the run after this many seconds and write a timeout error row. Default 300. Maximum 3600.", "default": 300 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 1, "maximum": 300, "type": "integer", "description": "How long to wait for one Stack Exchange response. Default 30 seconds.", "default": 30 }, "apiKey": { "title": "Stack Apps API key (optional)", "type": "string", "description": "Optional Stack Apps key. It is sent only on the request and is never written to the dataset or the repo. A key raises the daily quota from about 300 requests per IP to 10,000." }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional proxy for Stack Exchange requests. Leave this off unless an IP has used its daily quota. The API allows calls with no proxy.", "default": { "useApifyProxy": false } } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }