{ "openapi": "3.0.1", "info": { "title": "Italian Companies Data Scraper", "description": "Extract Italian company data by category from aziende.it. Get company name, revenue range, ATECO code, location and optional VAT, address, postal code and employees. Ideal for market research, CRM prep, BI datasets and B2B analysis.", "version": "0.0", "x-build-id": "Use8gYKXhbtitbzbb" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ayrtondavoli97~italy-companies-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ayrtondavoli97-italy-companies-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/ayrtondavoli97~italy-companies-scraper/runs": { "post": { "operationId": "runs-sync-ayrtondavoli97-italy-companies-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/ayrtondavoli97~italy-companies-scraper/run-sync": { "post": { "operationId": "run-sync-ayrtondavoli97-italy-companies-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "category", "maxItems" ], "properties": { "category": { "title": "Business category", "type": "string", "description": "Choose the main Italian business category to scrape. Validated categories: informatica, software, consulenza, marketing, edilizia, immobiliare, turismo, trasporti.", "default": "informatica" }, "categories": { "title": "Additional categories", "type": "array", "description": "Optional extra validated categories to merge into the same dataset. Example: software, consulenza, marketing. Leave empty for a single-category run.", "default": [], "items": { "type": "string" } }, "maxItemsPerCategory": { "title": "Maximum results per category", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Optional category-level limit. Use it when scraping multiple categories and you want a balanced dataset, for example 1000 companies per category. Set to 0 to use only the overall Maximum results limit.", "default": 0 }, "maxItems": { "title": "Maximum results", "minimum": 1, "maximum": 500000, "type": "integer", "description": "Maximum number of companies to save overall. Listing-only runs are fast. Full-detail runs are slower because each company detail page must be opened.", "default": 5000 }, "includeDetails": { "title": "Include company details", "type": "boolean", "description": "Enable this to enrich each company with VAT number, address, postal code and employee range when available. Detail enrichment is slower: based on current tests, about 100 companies with details are pushed to the dataset in roughly 1 minute. For large full-detail runs, increase the Actor run timeout and memory in Run options.", "default": false }, "includeWebsiteContacts": { "title": "Try website contact enrichment", "type": "boolean", "description": "Optional advanced enrichment. If a real company website is found, the Actor can try to inspect it for public emails, PEC and phone numbers. This slows runs down and often returns few results because aziende.it rarely exposes company websites.", "default": false }, "allCategories": { "title": "Scrape all validated categories", "type": "boolean", "description": "When enabled, the Actor runs all validated preset categories. Recommended with Maximum results per category to keep the dataset balanced.", "default": false }, "startUrls": { "title": "Advanced category URLs", "type": "array", "description": "Optional. Add specific aziende.it category URLs if you want to bypass the simple category presets.", "default": [], "items": { "type": "string" } }, "proxyConfig": { "title": "Proxy", "type": "object", "description": "Apify proxy configuration.", "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 } } } } } } } } } }