{ "openapi": "3.0.1", "info": { "title": "HelloPeter Scraper [$0.95/1K💰] | SA Reviews & TrustIndex", "description": "Scrape HelloPeter, South Africa's biggest review platform - business profiles, TrustIndex, star ratings, industry rankings, NPS, response time, contact details and individual consumer reviews.", "version": "1.9", "x-build-id": "SSncNEXu0L1EZI4zF" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ahmed_jasarevic~hellopeter-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ahmed_jasarevic-hellopeter-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/ahmed_jasarevic~hellopeter-scraper/runs": { "post": { "operationId": "runs-sync-ahmed_jasarevic-hellopeter-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/ahmed_jasarevic~hellopeter-scraper/run-sync": { "post": { "operationId": "run-sync-ahmed_jasarevic-hellopeter-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": "Business profile / industry / review URLs", "type": "array", "description": "Direct hellopeter.com URLs to scrape. Business profile pages look like https://www.hellopeter.com/dis-chem , industry ranking pages like https://www.hellopeter.com/industries/retail , and individual review pages like https://www.hellopeter.com/mtn/reviews/- . Discovery URLs (sitemap index, /api/search) are also accepted.", "items": { "type": "string" } }, "searchQueries": { "title": "Business search queries", "type": "array", "description": "Look up businesses by name through the public https://www.hellopeter.com/api/search?q= JSON endpoint, then scrape each matching profile. Example: [\"dis-chem\", \"capitec\", \" Vodacom\"].", "items": { "type": "string" } }, "businessSlugs": { "title": "Business slugs", "type": "array", "description": "Business slugs to scrape directly, e.g. [\"dis-chem\", \"mtn\", \"capitec-business\"]. Equivalent to visiting https://www.hellopeter.com/ .", "items": { "type": "string" } }, "industrySlugs": { "title": "Industry slugs", "type": "array", "description": "Industry pages to scrape for industry ranking leaderboards. Available slugs: https://www.hellopeter.com/industries/ . One row per ranked business is produced.", "items": { "type": "string" } }, "useSitemapDiscovery": { "title": "Discover businesses from the sitemap", "type": "boolean", "description": "When true, reads https://www.hellopeter.com/sitemaps/sitemap-index.xml and pulls business profile URLs from the business sitemaps. Combine with maxBusinesses to stay inside a sane budget.", "default": false }, "sitemapMaxSitemaps": { "title": "Max sitemaps to read", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many business sitemaps to read when sitemap discovery is enabled. Each sitemap holds 1,000 business URLs.", "default": 1 }, "maxBusinesses": { "title": "Max business profiles", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum number of business profile pages to scrape. Hard cap for safety.", "default": 20 }, "includeReviews": { "title": "Include reviews", "type": "boolean", "description": "Collect consumer reviews into the REVIEWS dataset. Switch on: the reviews server-rendered on each business profile are saved, and the newest weekly review sitemap is matched against the businesses in this run to pull their most recent reviews too - automatically, no extra setup. Switch off: only the BUSINESSES dataset is produced and no review pages are fetched.", "default": true }, "maxReviewsPerBusiness": { "title": "Max reviews per business", "minimum": 0, "maximum": 200, "type": "integer", "description": "Total number of reviews to collect for each business: the reviews HelloPeter server-renders on the profile page, plus extra reviews fetched from the newest weekly review sitemap. Every extra review costs one additional request. Set to 0 to collect businesses only, or to 8 to keep just the free profile-page reviews. Only used when includeReviews is true.", "default": 28 }, "maxIndustryPages": { "title": "Max industry leaderboard pages", "minimum": 1, "maximum": 25, "type": "integer", "description": "How many pages of the industry ranking leaderboard to follow. Each page lists 20 ranked businesses.", "default": 1 }, "maxRequestsPerCrawl": { "title": "Max total requests", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Safety cap on the total number of HTTP requests for the whole run.", "default": 200 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 25, "type": "integer", "description": "How many pages to fetch in parallel. Keep this modest.", "default": 8 }, "requestHandlerTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 10, "maximum": 180, "type": "integer", "description": "Per-request timeout.", "default": 60 }, "proxy": { "title": "Proxy configuration", "type": "object", "description": "Select proxies to be used by your crawler." } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }