{ "openapi": "3.0.1", "info": { "title": "Yelp Reviews Scraper — Owner Replies & Monitor", "description": "Scrape Yelp reviews into JSON: star ratings, full text, photos, reactions, and owner replies. Filter unanswered reviews and monitor new reviews with webhooks. A Yelp API alternative for Python, Node.js, and MCP.", "version": "0.1", "x-build-id": "YHlyTsiBQObr2A7Xh" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/crawloop~yelp-reviews-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-crawloop-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/crawloop~yelp-reviews-scraper/runs": { "post": { "operationId": "runs-sync-crawloop-yelp-reviews-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/crawloop~yelp-reviews-scraper/run-sync": { "post": { "operationId": "run-sync-crawloop-yelp-reviews-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "mode": { "title": "Mode", "enum": [ "reviews", "monitor" ], "type": "string", "description": "reviews = full/filtered scrape (optional business row); monitor = incremental new reviews + rating deltas with early-stop.", "default": "reviews" }, "startUrls": { "title": "Business page URLs", "type": "array", "description": "Yelp business page URLs, e.g. https://www.yelp.com/biz/gary-danko-san-francisco.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "businessAliases": { "title": "Business aliases", "type": "array", "description": "Yelp URL slugs such as gary-danko-san-francisco.", "items": { "type": "string" } }, "businessIds": { "title": "Encrypted business IDs", "type": "array", "description": "22-character Yelp encBizId values (e.g. cOcFMN_0nCqHHJ4KZhe5vA).", "items": { "type": "string" } }, "searchTerm": { "title": "Search term", "type": "string", "description": "Optional Yelp search query (e.g. pizza). Requires searchLocation. Discovered businesses are then scraped for reviews." }, "searchLocation": { "title": "Search location", "type": "string", "description": "City, neighborhood, or ZIP for searchTerm (e.g. San Francisco, CA)." }, "maxBusinessesPerSearch": { "title": "Max businesses per search", "minimum": 1, "maximum": 100, "type": "integer", "description": "Cap businesses expanded from searchTerm + searchLocation.", "default": 10 }, "maxSearchPages": { "title": "Max search pages", "minimum": 1, "maximum": 20, "type": "integer", "description": "Safety cap on Yelp search result pages (10 businesses per page).", "default": 3 }, "includeSearchAds": { "title": "Include sponsored search results", "type": "boolean", "description": "Keep Yelp ads when expanding searchTerm results.", "default": false }, "maxReviews": { "title": "Max reviews per business", "minimum": 0, "type": "integer", "description": "Cap reviews collected per business after filters. 0 = until pages run out (still bounded by maxPages).", "default": 100 }, "maxItems": { "title": "Max dataset items", "minimum": 0, "type": "integer", "description": "Hard cap on pushed dataset rows (all types). 0 = unlimited.", "default": 0 }, "maxPages": { "title": "Max review pages", "minimum": 1, "maximum": 500, "type": "integer", "description": "Safety cap on GraphQL review pages per business (10 reviews per page).", "default": 200 }, "sortOrder": { "title": "Review sort", "enum": [ "newest", "oldest", "recommended", "highest", "lowest", "elites" ], "type": "string", "description": "Yelp review sort. newest is best for monitoring and publishedAfter.", "default": "newest" }, "starRatings": { "title": "Star filter", "type": "array", "description": "Only keep these star ratings (1–5). Empty = all stars.", "items": { "type": "string", "enum": [ "5", "4", "3", "2", "1" ], "enumTitles": [ "5 stars", "4 stars", "3 stars", "2 stars", "1 star" ] } }, "publishedAfter": { "title": "Published after", "type": "string", "description": "Keep reviews on/after this date (YYYY-MM-DD) or period (7 days, 2 weeks, 1 month). Newest-first pagination stops when older reviews appear." }, "publishedBefore": { "title": "Published before", "type": "string", "description": "Keep reviews on/before this date (YYYY-MM-DD)." }, "reviewSearchQuery": { "title": "Search within reviews", "type": "string", "description": "Optional keyword passed to Yelp's review search (e.g. wait, parking, gluten)." }, "language": { "title": "Review language", "type": "string", "description": "Language code for the Yelp review feed (e.g. en, de, fr, es, ja). Default en.", "default": "en" }, "yelpDomain": { "title": "Yelp domain", "enum": [ "www.yelp.com", "www.yelp.ca", "www.yelp.co.uk", "www.yelp.com.au", "www.yelp.de", "www.yelp.fr", "www.yelp.it", "www.yelp.es", "www.yelp.nl", "www.yelp.ie", "www.yelp.at", "www.yelp.ch", "www.yelp.be", "www.yelp.se", "www.yelp.no", "www.yelp.dk", "www.yelp.fi", "www.yelp.pl", "www.yelp.pt", "www.yelp.cz", "www.yelp.com.mx", "www.yelp.com.br", "www.yelp.co.jp", "www.yelp.com.sg", "www.yelp.com.hk", "www.yelp.com.tw", "www.yelp.com.ph", "www.yelp.com.tr", "www.yelp.com.ar", "www.yelp.co.nz", "www.yelp.cl" ], "type": "string", "description": "Regional Yelp host used when you pass aliases or IDs instead of full URLs.", "default": "www.yelp.com" }, "includeOwnerReplies": { "title": "Parse owner replies", "type": "boolean", "description": "Always parse public owner responses when present. Kept for compatibility; replies are included in the review row.", "default": true }, "onlyWithOwnerReply": { "title": "Only reviews with an owner reply", "type": "boolean", "description": "Keep reviews that have a public owner / manager response.", "default": false }, "onlyUnanswered": { "title": "Only unanswered reviews", "type": "boolean", "description": "Keep reviews with no public owner reply. Overrides onlyWithOwnerReply when both are set.", "default": false }, "includeReviewerProfile": { "title": "Include reviewer personal data", "type": "boolean", "description": "If off (default), reviewer name, location, counts, and photo are returned as null.", "default": false }, "includeBusinessProfile": { "title": "Emit business profile row", "type": "boolean", "description": "In reviews mode, also push a business row (name, rating, review count, address).", "default": true }, "includePhotos": { "title": "Include photo and video URLs", "type": "boolean", "description": "Keep photoUrls / videoUrls on review rows.", "default": true }, "concurrency": { "title": "Concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Parallel business workers. Keep moderate with residential proxies.", "default": 4 }, "requestDelaySecs": { "title": "Delay between requests (seconds)", "minimum": 0, "maximum": 5, "type": "number", "description": "Throttle between HTML/GraphQL calls on one worker.", "default": 0.6 }, "monitorStoreName": { "title": "Monitor KV store name", "type": "string", "description": "Named Key-Value Store for incremental state (per-business watermarks + seen review IDs).", "default": "yelp-monitor-store" }, "monitorBaselineOnly": { "title": "Monitor baseline only", "type": "boolean", "description": "First run: seed KV fingerprints and review watermarks without emitting deltas / webhooks.", "default": false }, "resetMonitorState": { "title": "Reset monitor state", "type": "boolean", "description": "Clear MONITOR_STATE in the named store before this run.", "default": false }, "monitorFetchReviews": { "title": "Monitor: fetch new reviews", "type": "boolean", "description": "In monitor mode, paginate newest reviews until early-stop.", "default": true }, "monitorMaxPages": { "title": "Monitor max pages", "minimum": 1, "maximum": 40, "type": "integer", "description": "Safety cap on review pages scanned per business in monitor mode.", "default": 5 }, "earlyStopAfterKnown": { "title": "Early-stop after N known reviews", "minimum": 1, "maximum": 40, "type": "integer", "description": "In monitor mode, stop pagination after this many consecutive already-seen or older reviews (newest-first).", "default": 5 }, "ratingDropThreshold": { "title": "Rating drop threshold", "minimum": 0, "type": "number", "description": "Emit rating_drop when the business star average falls by at least this amount.", "default": 0.1 }, "webhookUrl": { "title": "Webhook URL", "type": "string", "description": "Slack / Discord / custom HTTPS endpoint for monitor alerts (JSON POST)." }, "telegramToken": { "title": "Telegram Bot Token", "type": "string", "description": "Optional Telegram bot token for monitor alerts." }, "telegramChatId": { "title": "Telegram Chat ID", "type": "string", "description": "Telegram chat/user ID for alerts (requires token)." }, "notifyOnNewReviews": { "title": "Notify on new reviews", "type": "boolean", "description": "Send webhook/Telegram when a new review appears.", "default": true }, "notifyOnNegativeReviewsOnly": { "title": "Negative reviews only (≤2★)", "type": "boolean", "description": "If enabled, new-review notifications fire only for 1–2 star reviews.", "default": false }, "notifyOnUnansweredOnly": { "title": "Unanswered reviews only", "type": "boolean", "description": "If enabled, new-review notifications fire only when there is no owner reply.", "default": false }, "notifyOnRatingChange": { "title": "Notify on rating change", "type": "boolean", "description": "Send webhook/Telegram when the business star average moves beyond the threshold.", "default": true }, "notifyOnReviewCountChange": { "title": "Notify on review-count change", "type": "boolean", "description": "Send webhook/Telegram when the public review count changes.", "default": false }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Yelp blocks many datacenter IPs. Use Apify Residential proxies, preferably US.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ], "apifyProxyCountry": "US" } } } }, "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 } } } } } } } } } }