{ "openapi": "3.0.1", "info": { "title": "GoodFirms B2B Companies & Software Scraper", "description": "Extract B2B agency listings (web dev, mobile, marketing, design, blockchain, AI) and software products (CRM, PM, HR…) from GoodFirms.co — with hourly rates, employees, hourly rate, services, ratings, verified reviews, and contact data. No API key required.", "version": "0.0", "x-build-id": "EuqAzZp3hgXzAH5Zb" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/haketa~goodfirms-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-haketa-goodfirms-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/haketa~goodfirms-scraper/runs": { "post": { "operationId": "runs-sync-haketa-goodfirms-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/haketa~goodfirms-scraper/run-sync": { "post": { "operationId": "run-sync-haketa-goodfirms-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Scraping Mode", "enum": [ "auto", "companies", "software" ], "type": "string", "description": "What to scrape. 'companies' = B2B agencies (web dev, mobile, marketing…). 'software' = SaaS products (CRM, PM…). 'auto' = infer from each startUrl.", "default": "auto" }, "startUrls": { "title": "Start URLs", "type": "array", "description": "Any GoodFirms URL — service category (/companies/web-development-agency), company detail (/company/), software category (/crm-software), or software detail (/software/). Mixed types OK.", "default": [], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "serviceCategorySlugs": { "title": "Service Category Slugs (companies mode)", "type": "array", "description": "Discover companies from these service categories. Examples: web-development-agency, mobile-app-development, digital-marketing-agency, blockchain-development, ai-development, ecommerce-development, software-development.", "default": [], "items": { "type": "string" } }, "countrySlugs": { "title": "Country / Region Slugs (companies mode)", "type": "array", "description": "Limit company discovery to these countries or states/cities. Examples: us, in, gb, ua, ca, california, denver, orange-county. If empty, scrapes the global category page.", "default": [], "items": { "type": "string" } }, "softwareCategorySlugs": { "title": "Software Category Slugs (software mode)", "type": "array", "description": "Discover software from these category pages. Examples: crm-software, project-management-software, accounting-software, hr-software.", "default": [], "items": { "type": "string" } }, "companySlugs": { "title": "Individual Company Slugs", "type": "array", "description": "Scrape these specific company profiles directly. Slug is the part after /company/ in the URL.", "default": [], "items": { "type": "string" } }, "softwareSlugs": { "title": "Individual Software Slugs", "type": "array", "description": "Scrape these specific software product pages directly. Slug is the part after /software/.", "default": [], "items": { "type": "string" } }, "employeesFilter": { "title": "Employees Range Filter", "enum": [ "", "2-9", "10-49", "50-249", "250-999", "1000-9999", "10000+" ], "type": "string", "description": "Restrict company listings to this employee range. Maps to GoodFirms employees[] filter.", "default": "" }, "hourlyRateFilter": { "title": "Hourly Rate Filter (USD)", "enum": [ "", "<25", "25-49", "50-99", "100-149", "150-199", "200+" ], "type": "string", "description": "Restrict company listings to this hourly rate bracket. Maps to GoodFirms rate[] filter.", "default": "" }, "minReviews": { "title": "Minimum Reviews", "minimum": 0, "type": "integer", "description": "Filter listings to companies with at least N reviews (server-side via reviews=N).", "default": 0 }, "scrapeReviews": { "title": "Scrape Reviews", "type": "boolean", "description": "Fetch verified client reviews (rating, body, reviewer, project cost/duration). Costs more requests.", "default": false }, "scrapeProfileDetails": { "title": "Scrape Full Profile Details", "type": "boolean", "description": "Visit each company/software detail page to extract richer data (services breakdown, portfolio counts, contact info). Disable for fast list-only scraping.", "default": true }, "maxRecords": { "title": "Max Records", "minimum": 0, "type": "integer", "description": "Maximum records to push. Set to 0 for unlimited.", "default": 100 }, "maxPagesPerCategory": { "title": "Max Pages Per Category", "minimum": 1, "type": "integer", "description": "Pagination cap for each category/country page (≈10 listings per page).", "default": 5 }, "requestDelay": { "title": "Request Delay (ms)", "minimum": 0, "type": "integer", "description": "Delay between requests. Higher = friendlier to GoodFirms / Cloudflare.", "default": 1200 }, "maxConcurrency": { "title": "Max Concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Parallel request count. Keep low (1–3) to avoid Cloudflare challenges.", "default": 2 }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Proxy configuration. Default: DATACENTER (cheap, fast — passes GoodFirms's Cloudflare basic check in most cases). If you see persistent 403s in the log, switch to RESIDENTIAL." } } }, "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 } } } } } } } } } }