Discourse Community Scraper
Pricing
from $1.00 / 1,000 dataset items
Go to Apify Store
Discourse Community Scraper
Generalised scraper for any Discourse-based community forum (topics, posts, categories, search) via Discourse's JSON API.
Discourse Community Scraper
Pricing
from $1.00 / 1,000 dataset items
Generalised scraper for any Discourse-based community forum (topics, posts, categories, search) via Discourse's JSON API.
You can access the Discourse Community Scraper programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.1", "x-build-id": "lI36toMRY0NFGnEd3" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/rl1987~discourse-community-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-rl1987-discourse-community-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/rl1987~discourse-community-scraper/runs": { "post": { "operationId": "runs-sync-rl1987-discourse-community-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/rl1987~discourse-community-scraper/run-sync": { "post": { "operationId": "run-sync-rl1987-discourse-community-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": [ "forumUrl", "mode" ], "properties": { "forumUrl": { "title": "Forum URL", "type": "string", "description": "Base URL of any Discourse-powered forum, e.g. https://community.n8n.io" }, "mode": { "title": "Mode", "enum": [ "categories", "latest", "top", "category", "search", "topicUrls" ], "type": "string", "description": "What to crawl. 'categories' lists the forum's categories/sections (use this to discover a categorySlug for mode=category). 'latest'/'top' pull the site-wide topic list, 'category' pulls one category, 'search' pulls search results, 'topicUrls' scrapes only the topics you list.", "default": "latest" }, "categorySlug": { "title": "Category slug/path", "type": "string", "description": "Required when mode=category. E.g. 'questions' or 'questions/12' (slug or slug/id) as it appears in the category URL." }, "searchQuery": { "title": "Search query", "type": "string", "description": "Required when mode=search. Uses Discourse's /search.json endpoint (supports its query filters, e.g. 'order:latest #category')." }, "topicUrls": { "title": "Topic URLs", "type": "array", "description": "Required when mode=topicUrls. Direct URLs to Discourse topics.", "default": [], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "includePosts": { "title": "Include full posts", "type": "boolean", "description": "If true, fetch every topic's full post stream (original post + all replies) in addition to the topic metadata. If false, only topic-level metadata is scraped (much faster, fewer requests).", "default": true }, "maxTopics": { "title": "Max topics", "minimum": 0, "type": "integer", "description": "Maximum number of topics to scrape. 0 = unlimited.", "default": 100 }, "maxPostsPerTopic": { "title": "Max posts per topic", "minimum": 0, "type": "integer", "description": "Maximum number of posts to fetch per topic (only used when includePosts is true). 0 = unlimited.", "default": 0 }, "requestDelaySecs": { "title": "Delay between requests (seconds)", "minimum": 0, "type": "integer", "description": "Polite delay between outgoing API requests to avoid overloading the forum.", "default": 1 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Maximum number of concurrent HTTP requests.", "default": 3 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy settings. Recommended if scraping many pages to avoid rate limiting.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Discourse Community Scraper from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: