{ "openapi": "3.0.1", "info": { "title": "All Forums Thread Scraper", "description": "A forum scraper that searches 21 sources from one keyword and returns 21-field discussion rows with complete Markdown content, titles, links, authors, dates, engagement, and source state. Covers forums, Q&A sites, aggregators, and developer communities in Japanese, Chinese, Korean, and Russian.", "version": "1.0", "x-build-id": "BSplbt9WbB0q7EzE3" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/agentx~all-forums-thread-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-agentx-all-forums-thread-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/agentx~all-forums-thread-scraper/runs": { "post": { "operationId": "runs-sync-agentx-all-forums-thread-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/agentx~all-forums-thread-scraper/run-sync": { "post": { "operationId": "run-sync-agentx-all-forums-thread-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "keyword", "max_results" ], "properties": { "keyword": { "title": "🔍 Keyword", "minLength": 1, "maxLength": 200, "type": "string", "description": "What the discussions should be about: a topic, a product, an error message, or a phrase. Every selected source is searched with the same words." }, "platforms": { "title": "🗂 Platforms", "type": "array", "description": "Which sources to read. Leave empty to read all 21. Each value chosen here is also what the row's platform field carries, so the Dataset filters on the same strings. Bing searches the open web, so it reaches forums that publish no API; the other twenty query each community's search surface. Where a source publishes engagement values, the row keeps its score, reply count, and timestamp; unavailable values stay empty. Seven sources cover Japanese, Chinese, Korean, and Russian developer communities.", "items": { "type": "string", "enum": [ "bing", "hacker_news", "stack_overflow", "super_user", "server_fault", "ask_ubuntu", "unix_linux", "lemmy_world", "programming_dev", "discourse_meta", "python_discuss", "rust_users", "openai_community", "obsidian_forum", "qiita", "zenn", "juejin", "segmentfault", "v2ex", "velog", "habr" ] } }, "max_results": { "title": "🔢 Max Results", "minimum": 1, "type": "integer", "description": "How many discussions to save from each source you select. Minimum 1 and no maximum, and every source gets the same budget, so eight sources at 25 return up to 200 rows. Every source is paged until your number is met or it runs out; Bing's open-web list runs out at roughly 16 to 60 results per keyword and Hacker News search at 1,000, while the community endpoints keep paging. A thread two sources both surface is saved once, against whichever source reached it first." } } }, "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 } } } } } } } } } }