{ "openapi": "3.0.1", "info": { "title": "Local Review Snippet Extractor", "description": "Extract visible review snippets, ratings, dates, reviewer display names, source pages, and common review themes from public local business pages", "version": "1.0", "x-build-id": "J15yqoQBWW2G8M7GE" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/junipr~local-review-snippet-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-junipr-local-review-snippet-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/junipr~local-review-snippet-extractor/runs": { "post": { "operationId": "runs-sync-junipr-local-review-snippet-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/junipr~local-review-snippet-extractor/run-sync": { "post": { "operationId": "run-sync-junipr-local-review-snippet-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "startUrls": { "title": "Review page URLs", "type": "array", "description": "Public business or review pages containing visible review snippets.", "items": { "type": "string" }, "default": [ "https://example.com/" ] }, "sitemapUrls": { "title": "Sitemap URLs", "type": "array", "description": "Optional public sitemap URLs for user-selected review sources.", "items": { "type": "string" }, "default": [] }, "htmlInputs": { "title": "HTML snapshots", "type": "array", "description": "Optional source-backed public review page snapshots.", "items": { "type": "object", "required": [ "html" ], "properties": { "sourceId": { "type": "string", "title": "Source ID", "description": "Source ID value for htmlInputs." }, "sourceUrl": { "type": "string", "title": "Source URL", "description": "Source URL value for htmlInputs." }, "title": { "type": "string", "title": "Title", "description": "Title value for htmlInputs." }, "html": { "type": "string", "title": "HTML", "description": "HTML value for htmlInputs." }, "sourceType": { "type": "string", "title": "Source Type", "description": "Source Type value for htmlInputs." }, "httpStatus": { "type": "integer", "title": "Http Status", "description": "Http Status value for htmlInputs." } }, "additionalProperties": true }, "default": [] }, "allowedDomains": { "title": "Allowed domains", "type": "array", "description": "Optional domain allowlist for supplied URLs.", "items": { "type": "string" }, "default": [] }, "maxPages": { "title": "Maximum pages", "minimum": 1, "maximum": 25, "type": "integer", "description": "Maximum pages fetched or analyzed.", "default": 1 }, "maxDepth": { "title": "Maximum crawl depth", "minimum": 0, "maximum": 1, "type": "integer", "description": "Reserved discovery depth; supplied URL mode does not crawl arbitrary review-site links.", "default": 0 }, "maxSources": { "title": "Maximum review sources", "minimum": 1, "maximum": 25, "type": "integer", "description": "Maximum supplied review pages fetched.", "default": 5 }, "includeEvidence": { "title": "Include evidence", "type": "boolean", "description": "Include visible review text excerpts in output rows.", "default": true }, "includeRawSnapshots": { "title": "Include raw snapshots", "type": "boolean", "description": "Reserve raw snapshots in run artifacts when enabled.", "default": false }, "requestDelayMs": { "title": "Request delay", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Delay between public HTTP requests in milliseconds.", "default": 250 }, "timeoutMs": { "title": "Request timeout", "minimum": 1000, "maximum": 60000, "type": "integer", "description": "Per-request timeout in milliseconds.", "default": 15000 }, "userAgentMode": { "title": "User agent mode", "enum": [ "standard", "compatibility" ], "type": "string", "description": "Normal HTTP user-agent profile.", "default": "standard" }, "reviewPageUrls": { "title": "Additional review URLs", "type": "array", "description": "Additional public review pages merged with startUrls.", "items": { "type": "string" }, "default": [] }, "businessName": { "title": "Business name", "type": "string", "description": "Optional public business name used to label extracted snippets.", "default": "" }, "minRating": { "title": "Minimum rating", "minimum": 1, "maximum": 5, "type": "number", "description": "Exclude review snippets with a lower visible rating; unrated visible snippets remain eligible.", "default": 1 }, "maxReviewsPerPage": { "title": "Maximum reviews per page", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum visible snippets emitted from each source page.", "default": 10 }, "extractThemes": { "title": "Extract themes", "type": "boolean", "description": "Assign transparent keyword-based themes from observed review text.", "default": true }, "includeReviewerDisplayNames": { "title": "Include reviewer display names", "type": "boolean", "description": "Include only display names already visible on the public source page.", "default": true }, "maxChargeUsd": { "title": "Maximum charge", "minimum": 0, "maximum": 100, "type": "number", "description": "Maximum estimated PPE spend before a graceful stop.", "default": 15 }, "includeReport": { "title": "Generate reports", "type": "boolean", "description": "Write review evidence and theme reports to key-value storage.", "default": 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 } } } } } } } } } }