{ "openapi": "3.0.1", "info": { "title": "Bark.com Directory Scraper – Listings & Profile URLs", "description": "Extract Bark.com business directory listings by category & location: company name, profile URL, rating, area & logo, deduped to one row per provider. Build B2B prospect lists or feed the profile URLs into a Bark Profile Scraper. Returns profiles & URLs, not contact info.", "version": "0.1", "x-build-id": "HdwUCmG9j7QeWGLkX" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapesage~bark-listing-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapesage-bark-listing-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapesage~bark-listing-scraper/runs": { "post": { "operationId": "runs-sync-scrapesage-bark-listing-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapesage~bark-listing-scraper/run-sync": { "post": { "operationId": "run-sync-scrapesage-bark-listing-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "country" ], "properties": { "country": { "title": "Country", "enum": [ "us", "gb", "ca", "au", "ie", "nz", "sg", "za", "de", "fr" ], "type": "string", "description": "Bark region to scrape. Determines which locale path (e.g. /en/us/) the actor harvests from the sitemap.", "default": "us" }, "categories": { "title": "Service categories", "type": "array", "description": "Bark category slugs, e.g. \"cleaners\", \"plumbers\", \"web-design\" (as they appear in a Bark URL: bark.com/en/us//). Don't worry about exact formatting — the actor auto-fixes capitalization, spaces (\"Web Design\" → \"web-design\"), and singular/plural (\"plumber\" → \"plumbers\"). Leave empty to scrape ALL categories (large — use the limits below).", "items": { "type": "string" } }, "state": { "title": "State / region (optional)", "type": "string", "description": "Optional regional filter using Bark's own slug for that country: US states (\"california\"), Canadian provinces (\"ontario\"), UK counties or big cities (\"greater-london\", \"berkshire\"), Australian states (\"new-south-wales\"). Note: \"england\" is NOT valid — the UK is split into counties, not nations. Easiest and most reliable: leave State AND City empty to sweep the entire country (all regions and cities)." }, "city": { "title": "City (optional — requires a State/region if set)", "type": "string", "description": "Restrict to a single city slug as it appears in Bark URLs, e.g. \"new-york-city\", \"los-angeles\". A city cannot be located without its state, so if you fill this in you MUST also fill in State/region (.../plumbers/california/los-angeles/). Leave empty to cover all cities." }, "includeNationalAndState": { "title": "Include national & state listing pages", "type": "boolean", "description": "When true, also pull providers from the national category page and state pages (max coverage). When false, only city pages are scraped (deepest local long-tail). Either way results are deduplicated per provider. Default: true.", "default": true }, "maxItems": { "title": "Max unique providers", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Hard cap on the number of UNIQUE providers scraped (and charged) in a single run. The primary cost guard. Duplicates are never charged. Default: 1000.", "default": 1000 }, "maxListingPages": { "title": "Max listing pages to scan", "minimum": 1, "maximum": 200000, "type": "integer", "description": "Safety cap on how many directory listing pages the actor fetches during a run. Pairs with Max unique providers to bound a run's size and cost. Default: 2000.", "default": 2000 }, "maxConcurrency": { "title": "Max concurrent requests", "minimum": 1, "maximum": 10, "type": "integer", "description": "Maximum parallel requests. Higher is faster; lower is gentler on the target site. Default: 5.", "default": 5 }, "minRequestDelayMs": { "title": "Minimum delay between requests (ms)", "minimum": 0, "type": "integer", "description": "Minimum wait time before each request (jittered up to +3 seconds). Default: 2000.", "default": 2000 }, "maxRequestRetries": { "title": "Max retries per request", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many times to retry a failed request with a fresh session/IP before giving up. Default: 5.", "default": 5 }, "useBrowserFallback": { "title": "Enable headless browser fallback", "type": "boolean", "description": "When true, the crawler may auto-promote a request to a headless Chromium browser if it can't be parsed via HTTP. Bark listing pages are server-rendered, so this rarely fires — leave on for resilience, disable for strictly HTTP-only runs.", "default": true }, "debugRenderPath": { "title": "Debug: tag records with rendering path", "type": "boolean", "description": "Diagnostic only. When true, every record gets a `_renderedBy` field ('http' / 'browser' / 'unknown') so you can verify the cheap HTTP path is being used. Off by default to keep output clean.", "default": false }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify Proxy configuration. Default is automatic (datacenter) proxy — tested reliable on Bark at the default concurrency, and cheaper/faster. If a large or high-concurrency run starts returning blocked or empty pages, switch to the Residential group.", "default": { "useApifyProxy": 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 } } } } } } } } } }