{ "openapi": "3.0.1", "info": { "title": "IFA Berlin Exhibitor Data Scraper", "description": "Scrapes everything from each ifa-berlin.com exhibitor page: profile, contacts, products, events, all images and links, meta and JSON-LD. Downloads image files and raw HTML. Auto-reads URLs from ifa-berlin-links-scraper's last run.", "version": "0.1", "x-build-id": "EMvSfXsgAre7iONcJ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/outspoken_strategy~ifa-berlin-data-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-outspoken_strategy-ifa-berlin-data-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/outspoken_strategy~ifa-berlin-data-scraper/runs": { "post": { "operationId": "runs-sync-outspoken_strategy-ifa-berlin-data-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/outspoken_strategy~ifa-berlin-data-scraper/run-sync": { "post": { "operationId": "run-sync-outspoken_strategy-ifa-berlin-data-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Exhibitor URLs", "type": "array", "description": "Add the exhibitor page URLs you want to scrape — click Add, or use Bulk edit to paste many at once (one per line). These always take priority. Leave empty only if you want the actor to automatically use all URLs from the links scraper's last run.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "linksDatasetId": { "title": "Links dataset ID", "type": "string", "description": "ID of a dataset produced by ifa-berlin-links-scraper. Every item's `url` field is scraped. Takes priority over the automatic last-run lookup." }, "linksActor": { "title": "Links actor", "type": "string", "description": "When no start URLs and no dataset ID are given, the dataset of this actor's most recent successful run is used automatically — so you can chain the two actors without copying IDs.", "default": "outspoken_strategy/ifa-berlin-links-scraper" }, "downloadImages": { "title": "Download image files", "type": "boolean", "description": "Download every content image (logos, product photos, event logos) into the run's key-value store, not just record their URLs. True = leave nothing behind.", "default": true }, "saveHtml": { "title": "Save raw HTML", "type": "boolean", "description": "Also store each page's full raw HTML in the key-value store, so nothing is ever lost even if the extraction misses a future field.", "default": true }, "maxResults": { "title": "Max results", "minimum": 0, "type": "integer", "description": "Scrape at most this many exhibitor pages. 0 = no limit (scrape all). Useful for cheap test runs.", "default": 0 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum number of pages fetched in parallel.", "default": 10 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy settings. Defaults to Apify datacenter proxies with IP rotation.", "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 } } } } } } } } } }