{ "openapi": "3.0.1", "info": { "title": "Website Reviews, Comments & Testimonials Scraper", "description": "Turn allowed public website reviews, testimonials, comments, and forum posts into clean feedback intelligence for competitor research, reputation monitoring, and voice-of-customer analysis.", "version": "1.0", "x-build-id": "tO3bDLwhrXVeTYyQl" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/thescrapelab~universal-public-feedback-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-thescrapelab-universal-public-feedback-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/thescrapelab~universal-public-feedback-scraper/runs": { "post": { "operationId": "runs-sync-thescrapelab-universal-public-feedback-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/thescrapelab~universal-public-feedback-scraper/run-sync": { "post": { "operationId": "run-sync-thescrapelab-universal-public-feedback-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrls" ], "properties": { "startUrls": { "title": "Start URLs", "minItems": 1, "maxItems": 100, "type": "array", "description": "Public HTTP(S) pages containing reviews, comments, testimonials, or discussion posts. Private, login-protected, paywalled, and CAPTCHA-protected pages are skipped.", "items": { "type": "object", "properties": { "url": { "title": "URL", "type": "string", "description": "A public HTTP(S) URL.", "pattern": "^https?://[^\\s]+$", "minLength": 8, "maxLength": 4096 } }, "required": [ "url" ], "additionalProperties": false } }, "contentTypes": { "title": "What to collect", "minItems": 1, "uniqueItems": true, "type": "array", "description": "Choose the public feedback types you want in the dataset.", "items": { "type": "string", "enum": [ "review", "comment", "post", "testimonial" ], "enumTitles": [ "Reviews", "Comments", "Forum posts", "Testimonials" ] }, "default": [ "review", "comment", "post", "testimonial" ] }, "includeReplies": { "title": "Include public replies", "type": "boolean", "description": "Include publicly visible replies when the source exposes them.", "default": true }, "maxItemsPerUrl": { "title": "Items per URL", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum feedback items to save for each starting URL, including any discovered pages.", "default": 100 }, "maxPagesPerUrl": { "title": "Pages per URL", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum public pages to visit for each starting URL, including the first page.", "default": 10 }, "useLlmFallback": { "title": "Use AI fallback for unfamiliar layouts", "type": "boolean", "description": "Use OpenRouter only when standard extraction cannot confidently find feedback. The AI discovers selectors; it never writes or invents feedback text.", "default": true }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Honor robots.txt allow/disallow rules. Keep enabled unless you control the target and have a clear reason to change it.", "default": true }, "proxyConfiguration": { "title": "Proxy configuration (API compatibility)", "type": "object", "description": "Accepted for API compatibility. This release uses guarded direct egress and records a warning instead of routing through a remote proxy." }, "maxConcurrency": { "title": "Crawl speed", "minimum": 1, "maximum": 5, "type": "integer", "description": "Maximum number of pages processed at the same time. Per-domain pacing and robots.txt can reduce the actual speed.", "default": 2 }, "dryRun": { "title": "Preview only", "type": "boolean", "description": "Check what can be extracted and review the run summary without saving feedback items to the dataset.", "default": 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 } } }, "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 } } } } } } } } } }