{ "openapi": "3.0.1", "info": { "title": "HardwareZone SG Forum Scraper", "description": "Scrape HardwareZone, Singapore's largest tech and lifestyle forum. Board mode returns one row per thread; thread mode returns every reply. Filter from newest replies, keywords, bulk input.", "version": "0.0", "x-build-id": "PshStN4eoyBROErRt" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/lexac94~hardwarezone-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-lexac94-hardwarezone-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/lexac94~hardwarezone-scraper/runs": { "post": { "operationId": "runs-sync-lexac94-hardwarezone-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/lexac94~hardwarezone-scraper/run-sync": { "post": { "operationId": "run-sync-lexac94-hardwarezone-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "🎯 Mode", "enum": [ "forum", "thread" ], "type": "string", "description": "Board threads returns one row per thread from a board's listing pages and never opens a thread. Full thread returns the thread's opening post plus one row per reply.", "default": "forum" }, "forumIds": { "title": "Board IDs", "maxItems": 50, "type": "array", "description": "HardwareZone board IDs — the {id} in forums/{slug}.{id}/. e.g. 234 (Chill-out / Hangout Den), 323 (Android User Group). Must be a board that lists threads, not a category that lists sub-forums: 16 and 9 are categories and return nothing.", "items": { "type": "string" }, "default": [] }, "keywords": { "title": "Title keyword filter", "maxItems": 50, "type": "array", "description": "Optional. Keeps only threads whose title contains at least one keyword (case-insensitive). Leave empty for no filtering.", "items": { "type": "string" }, "default": [] }, "excludeKeywords": { "title": "Exclude these words", "maxItems": 50, "type": "array", "description": "Drops any thread whose title contains one of these words, even if it also matches the filter above. Useful for stripping out spam and off-topic threads.", "items": { "type": "string" }, "default": [] }, "matchWholeWords": { "title": "Match whole words only", "type": "boolean", "description": "Off, a keyword matches anywhere in the title, so \"vivo\" also matches \"vivoX300\". On, it must appear as its own word. Applies to both fields above.", "default": false }, "threadIds": { "title": "Thread IDs", "maxItems": 100, "type": "array", "description": "HardwareZone thread IDs — the {id} in threads/{slug}.{id}/, e.g. 7147770.", "items": { "type": "string" }, "default": [] }, "threadUrls": { "title": "Thread URLs", "maxItems": 100, "type": "array", "description": "Full HardwareZone thread URLs, e.g. https://forums.hardwarezone.com.sg/threads/vivo-x300-series.7147770/. The thread ID is extracted automatically.", "items": { "type": "string" }, "default": [] }, "maxPagesPerThread": { "title": "Max pages per thread", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Caps how many pages of replies to walk per thread, counting back from the NEWEST page. 0 means unlimited — be careful: HWZ megathreads run to 500+ pages. Replies are always returned newest first.", "default": 0 }, "bulkInput": { "title": "Bulk paste", "type": "string", "description": "One item per line (press Enter for a new line, no quotes or commas). Treated as board IDs, thread IDs, or thread URLs depending on the current mode. Fastest way is to paste a column straight from Google Sheets or Excel.", "default": "" }, "maxItems": { "title": "Max items", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Board threads mode: max threads per board. Full thread mode: max threads to scrape — replies within a thread are not limited by this, use Max pages per thread instead.", "default": 50 }, "dateFrom": { "title": "Only items since this time", "type": "string", "description": "Formats: 3d, 12h, 2w, or MM/DD/YY. Leave empty for no filtering. Board threads mode: filters threads by the newer of post time and last reply time, and stops paging early — pinned threads are exempt from both. Full thread mode: filters replies by post time; because threads are walked newest-first this stops as soon as a page falls past the cutoff, so pulling the last 2 years of a thread started in 2008 costs a few pages, not all of them. The thread's opening post is always returned.", "default": "" }, "proxyConfiguration": { "title": "Proxy (Apify datacenter proxy on by default)", "type": "object", "description": "Without a proxy your run shares the platform's egress IPs with every other run, so HardwareZone rate-limits you (429s, missing pages). HTML responses are small, so proxy bandwidth cost is negligible. Turn it off only for local testing.", "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 } } } } } } } } } }