{ "openapi": "3.0.1", "info": { "title": "Discourse Scraper: Topics, Posts, Users & Search", "description": "Scrape any Discourse forum via the public REST API. Latest / top topics, category topics, full topic + posts, user profiles + activity, full-text search. No browser, no proxies, no auth. Pay only per result item.", "version": "0.1", "x-build-id": "I0BlXuAc0mm4qqj1s" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/perconey~discourse-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-perconey-discourse-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/perconey~discourse-scraper/runs": { "post": { "operationId": "runs-sync-perconey-discourse-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/perconey~discourse-scraper/run-sync": { "post": { "operationId": "run-sync-perconey-discourse-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "action" ], "properties": { "action": { "title": "What do you want to scrape?", "enum": [ "getLatest", "getTop", "getCategories", "getCategoryTopics", "getTopicDetail", "getUserProfile", "getUserActivity", "searchPosts" ], "type": "string", "description": "Pick the action. getLatest / getTop / getCategories work without queries. getCategoryTopics needs a category slug. getTopicDetail needs a numeric topic id. getUserProfile / getUserActivity need a username. searchPosts needs a query.", "default": "getLatest" }, "instance": { "title": "Discourse instance URL", "type": "string", "description": "Base URL of the Discourse forum. Examples: https://discuss.huggingface.co, https://forum.djangoproject.com, https://discuss.python.org, https://meta.discourse.org.", "default": "https://discuss.huggingface.co" }, "queries": { "title": "Queries", "type": "array", "description": "One entry per query. getCategoryTopics: category slug (e.g. 'beginners') or 'slug/id' if known. getTopicDetail: numeric topic id (e.g. 175977). getUserProfile / getUserActivity: username (e.g. julien-c). searchPosts: free-text.", "items": { "type": "string" } }, "maxItems": { "title": "Max items per query", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Stop after this many items. Latest / top / category feeds paginate 30 per page. Topic detail returns posts in chunks of 20.", "default": 30 }, "topPeriod": { "title": "Period for getTop", "enum": [ "all", "yearly", "quarterly", "monthly", "weekly", "daily" ], "type": "string", "description": "Discourse 'top' period selector. Default is the forum's configured default (usually weekly or monthly)." } } }, "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 } } } } } } } } } }