{ "openapi": "3.0.1", "info": { "title": "Trade Fair Exhibitor Extractor", "description": "Extracts exhibitor companies from trade fair directories — name, country, website and a corporate email — and refuses to deliver rows it cannot verify. Rejects archived and cancelled events before crawling, and never passes off the fair organiser’s address as an exhibitor’s.", "version": "0.0", "x-build-id": "EO8JdhxbWKX1Jxlla" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/harunaakira~webscrape/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-harunaakira-webscrape", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/harunaakira~webscrape/runs": { "post": { "operationId": "runs-sync-harunaakira-webscrape", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/harunaakira~webscrape/run-sync": { "post": { "operationId": "run-sync-harunaakira-webscrape", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrls" ], "properties": { "startUrls": { "title": "Exhibitor pages", "type": "array", "description": "Exhibitor detail pages from a fair directory. Each page should show one company.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "fairName": { "title": "Fair name", "type": "string", "description": "Label used in the log and in the rejection record. Optional." }, "fairDateText": { "title": "Fair dates", "type": "string", "description": "Event dates as published by the organiser, e.g. \"15.09. - 18.09.2026\". If set, the fair is checked before any page is crawled — a past, cancelled or out-of-window event costs zero requests. Leave empty to skip the check." }, "targetMonth": { "title": "Target month", "type": "string", "description": "YYYY-MM. Fairs outside this month are rejected. Defaults to the current month." }, "country": { "title": "Country", "type": "string", "description": "Applied to every row when the directory does not publish a country per exhibitor." }, "roleMailboxesOnly": { "title": "Role mailboxes only", "type": "boolean", "description": "Accept only company addresses such as info@ or sales@, not named individuals. Safer under EU data-protection rules, but lowers yield by roughly 20 percentage points.", "default": true }, "allowBrandMatch": { "title": "Match across TLD variants", "type": "boolean", "description": "Treat wuerth.com and wuerth.de as the same company. Recovers large firms that publish one domain and send mail from another.", "default": true }, "organiserDomains": { "title": "Fair organiser domains", "type": "array", "description": "Hosts belonging to the fair itself. Any address from these is refused — exhibitor pages routinely expose the organiser's address instead of the exhibitor's. Defaults cover the major European venues.", "items": { "type": "string" } }, "maxRequestsPerCrawl": { "title": "Max requests per crawl", "minimum": 1, "type": "integer", "description": "Upper bound on pages fetched in one run.", "default": 100 }, "useProxy": { "title": "Use Apify Proxy", "type": "boolean", "description": "Route requests through Apify Proxy. Off by default — most fair directories do not require it.", "default": false } } }, "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 } } } } } } } } } }