{ "openapi": "3.0.1", "info": { "title": "Website Contact Details Scraper", "description": "Extract emails, phone numbers, social media links, and addresses from any website. Supply one or more URLs and get structured contact data back in seconds.", "version": "0.1", "x-build-id": "ig5YFzymXBJKEH5Yr" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/jungle_synthesizer~website-contact-details-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-jungle_synthesizer-website-contact-details-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/jungle_synthesizer~website-contact-details-scraper/runs": { "post": { "operationId": "runs-sync-jungle_synthesizer-website-contact-details-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/jungle_synthesizer~website-contact-details-scraper/run-sync": { "post": { "operationId": "run-sync-jungle_synthesizer-website-contact-details-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrls" ], "properties": { "sp_intended_usage": { "title": "What is the intended usage of this data?", "minLength": 1, "type": "string", "description": "What will this data feed? E.g. lead lists, KYB checks, price tracking." }, "sp_improvement_suggestions": { "title": "How can we improve this crawler for you?", "minLength": 1, "type": "string", "description": "Provide any feedback or suggestions for improvements." }, "sp_contact": { "title": "Contact email (optional)", "minLength": 1, "type": "string", "description": "We'll personally help with your use case. No spam." }, "resumeCursor": { "title": "Resume cursor (continue a previous run)", "type": "string", "description": "Leave empty for a fresh crawl. To CONTINUE a previous run where it stopped — without paying again for records you already received — paste the `resumeCursor` value from that run's Output (the run's OUTPUT key). Resume promptly: the previous run's data expires with your account's retention window (free tier: your ~10 most recent runs)." }, "startUrls": { "title": "Start URLs", "type": "array", "description": "One or more website URLs to extract contact details from. The actor crawls each URL and discovers contact-related sub-pages automatically.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxItems": { "title": "Max Results", "type": "integer", "description": "Maximum number of result rows to return. This counts rows in the dataset, not pages crawled; to bound how many pages are fetched from each website use Max Pages Per Site. Default is 10.", "default": 10 }, "maxDepth": { "title": "Max Crawl Depth", "type": "integer", "description": "How many link-hops from the start URL to follow when discovering contact pages. 1 = only the start URL and pages linked directly from it. Default is 2.", "default": 2 }, "includeContactPages": { "title": "Deep-scan contact pages", "type": "boolean", "description": "When enabled, the actor also follows links to pages whose URL contains \"contact\", \"about\", \"team\", \"imprint\", or \"impressum\".", "default": true }, "extractFromAllPages": { "title": "Extract from all crawled pages", "type": "boolean", "description": "When enabled, also crawl and extract from non-contact pages linked from the start page, not just dedicated contact pages. The start page itself is always scanned. Useful for sites where emails appear in footers or sidebars on every page.", "default": false }, "maxCrawledPages": { "title": "Max Pages To Crawl", "minimum": 1, "type": "integer", "description": "Hard cap on the total number of pages (discovery + extraction) the crawler will fetch in this run, across every start URL combined. Leave empty for no cap. Use this to keep a large batch of start URLs cheap and fast — it bounds pages visited directly, independent of Max Crawl Depth (which bounds hops) and Max Results (which bounds saved records, not pages fetched)." }, "maxRequestsPerCrawl": { "title": "Max Requests Per Crawl", "minimum": 1, "type": "integer", "description": "Same cap as Max Pages To Crawl, under the name some callers already use for it — the total number of pages fetched in this run, across every start URL combined. Leave empty for no cap. If both Max Pages To Crawl and Max Requests Per Crawl are set, the lower of the two wins." }, "maxRequestsPerStartUrl": { "title": "Max Pages Per Site", "minimum": 1, "type": "integer", "description": "Maximum number of extra pages crawled from EACH start URL, on top of the start URL's own page (which is always fetched). Default is 5. Values above 20 are treated as 20. Composes with Max Pages To Crawl / Max Requests Per Crawl — a page is only fetched if every cap that is set still has room, so the strictest limit always wins.", "default": 5 } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }