{
"openapi": "3.0.1",
"info": {
"title": "Yelp Reviews Scraper — Unlimited Reviews + AI Analysis",
"description": "Scrape unlimited Yelp reviews past the 3-review page cap — reviewer name, rating, date, full text, photos and owner replies. Feed it a business URL or a search term plus city. Optional AI pain-point teardown turns the reviews into ranked complaint themes. No login or API key. Clean JSON or CSV.",
"version": "0.0",
"x-build-id": "5jKOIvtSM1EdM9at8"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/memo23~yelp-reviews-scraper/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-memo23-yelp-reviews-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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/memo23~yelp-reviews-scraper/runs": {
"post": {
"operationId": "runs-sync-memo23-yelp-reviews-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/memo23~yelp-reviews-scraper/run-sync": {
"post": {
"operationId": "run-sync-memo23-yelp-reviews-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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",
"properties": {
"startUrls": {
"title": "Yelp business URLs",
"type": "array",
"description": "Paste one or more Yelp business page URLs to pull their reviews directly — the fastest path when you already know the businesses.",
"items": {
"type": "string"
}
},
"searchTerms": {
"title": "Or search a category",
"type": "array",
"description": "Find businesses by category, then scrape the reviews of everything found — e.g. \"plumbers\". Needs the location field below. Leave empty when using business URLs.",
"items": {
"type": "string"
}
},
"searchLocation": {
"title": "Search location",
"type": "string",
"description": "City or region for the category search above, e.g. \"Chicago, IL\". Ignored when you supply business URLs."
},
"searchSortBy": {
"title": "Sort search results by",
"enum": [
"",
"rating",
"review_count"
],
"type": "string",
"description": "Result ordering for generated searches. Applies to **Search terms** only.",
"default": ""
},
"scrapeReviews": {
"title": "Scrape reviews",
"type": "boolean",
"description": "Pull the full review list for every business found. Yelp only shows 3 reviews per page to anonymous visitors; this walks the full set.",
"default": true
},
"maxReviews": {
"title": "Max reviews per business",
"type": "integer",
"description": "Upper bound per business. Lower it to control cost on businesses with thousands of reviews.",
"default": 200
},
"reviewInsights": {
"title": "📊 Review insights",
"type": "boolean",
"description": "Adds a computed summary per business: rating distribution, recent-vs-lifetime trend, and most-repeated phrases. Billed per business.",
"default": false
},
"painPointAnalysis": {
"title": "🤖 AI pain-point analysis",
"type": "boolean",
"description": "Runs an LLM teardown of the collected reviews and returns ranked complaint themes with supporting quotes. Paid plans only, billed per business.",
"default": false
},
"maxItems": {
"title": "Maximum number of items OR limit the results per crawl",
"type": "integer",
"description": "Maximum number of items that will be scraped. One item = one business row. Default: 1000 — set a lower cap (e.g. 50) for test runs.",
"default": 1000
},
"useCachedData": {
"title": "Use cached data (faster, cheaper)",
"type": "boolean",
"description": "When enabled (default), business and search pages that were already scraped recently are served from a shared cache instead of being re-fetched — noticeably faster and cheaper. Cached rows are marked with servedFromCache: true and a dataAsOf timestamp so you always know how fresh the data is. Reviews (when enabled) are always fetched fresh. Turn this off to force every page to be scraped live.",
"default": true
},
"maxCacheAgeDays": {
"title": "Max cache age (days)",
"minimum": 0,
"type": "integer",
"description": "Freshness limit for cached pages. A cached record older than this many days is re-scraped live. Set 0 to always bypass the cache and fetch everything fresh. Leave empty to use sensible defaults (business details ~21 days, search listings ~14 days). Only applies when Use cached data is enabled."
},
"maxConcurrency": {
"title": "Max Concurrency",
"minimum": 1,
"maximum": 20,
"type": "integer",
"description": "Maximum number of pages that can be processed at the same time (max 20). When Fetch full business details is enabled, the effective value is additionally capped to what the run's memory can sustain (about 10 at 1024MB) to prevent out-of-memory failures.",
"default": 20
},
"minConcurrency": {
"title": "Min Concurrency",
"type": "integer",
"description": "Minimum number of pages that will be processed at the same time.",
"default": 1
},
"maxRequestRetries": {
"title": "Max Request Retries",
"type": "integer",
"description": "Number of times the crawler will retry a failed request before giving up.",
"default": 100
},
"proxy": {
"title": "Proxy configuration (optional override)",
"type": "object",
"description": "Leave empty — the actor already routes all traffic through its own built-in residential proxy at no extra cost to you. Only set this if you want to use your own proxies.
Heads-up: selecting Apify's RESIDENTIAL group here will make the run fail before it starts unless your account has that add-on enabled."
},
"proxyProviders": {
"title": "Proxy providers (preference order)",
"type": "array",
"description": "Paying users only. Preference list of providers from the shared proxy-pool KV store. First usable provider wins; add fallbacks like ['evomi','decodo'] for resilience. Rotation is centralised — credentials are updated in the KV store, not in this input. Defaults to ['evomi'].",
"items": {
"type": "string"
},
"default": [
"evomi"
]
}
}
},
"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
}
}
}
}
}
}
}
}
}
}