{ "openapi": "3.0.1", "info": { "title": "Adaptive Website Lead Extractor", "description": "Crawl public business websites with Scrapling to extract emails, phones, social profiles, contact pages, automation gaps, and lead scores for CRM-ready outreach.", "version": "0.1", "x-build-id": "BECDTslymstuBaogY" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/solutionssmart~adaptive-website-lead-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-solutionssmart-adaptive-website-lead-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/solutionssmart~adaptive-website-lead-extractor/runs": { "post": { "operationId": "runs-sync-solutionssmart-adaptive-website-lead-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/solutionssmart~adaptive-website-lead-extractor/run-sync": { "post": { "operationId": "run-sync-solutionssmart-adaptive-website-lead-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Start URLs", "type": "array", "description": "Websites or domains to crawl. One lead intelligence record is produced for each domain.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPagesPerDomain": { "title": "Max pages per domain", "minimum": 1, "maximum": 200, "type": "integer", "description": "Hard limit for internal pages crawled per input domain.", "default": 20 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 25, "type": "integer", "description": "Maximum number of domains processed in parallel.", "default": 5 }, "useStealth": { "title": "Use stealth browser fetching", "type": "boolean", "description": "Use Scrapling's stealth browser fetcher. This is slower and intended for public pages that need JavaScript rendering; it does not perform aggressive bypassing.", "default": false }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Check robots.txt and skip disallowed paths for a generic crawler user agent.", "default": true }, "extractEmails": { "title": "Extract emails", "type": "boolean", "description": "Extract public email addresses from crawled pages.", "default": true }, "extractPhones": { "title": "Extract phone numbers", "type": "boolean", "description": "Extract conservative phone number candidates from crawled page text.", "default": true }, "extractSocialLinks": { "title": "Extract social links", "type": "boolean", "description": "Extract public social profile links for common platforms.", "default": true }, "extractContactPages": { "title": "Extract contact/about pages", "type": "boolean", "description": "Detect likely contact and about page URLs during the crawl.", "default": true }, "extractAutomationSignals": { "title": "Extract automation signals", "type": "boolean", "description": "Detect contact forms, booking tools, chat widgets, WhatsApp links, and similar public page signals.", "default": true }, "extractMedia": { "title": "Extract media assets", "type": "boolean", "description": "Discover public image, video, document, audio, archive, and embed URLs referenced by crawled pages. Files are not downloaded.", "default": false }, "extractImages": { "title": "Extract images", "type": "boolean", "description": "When media extraction is enabled, include image URLs from img, source, srcset, poster, and CSS url references.", "default": true }, "extractVideos": { "title": "Extract videos", "type": "boolean", "description": "When media extraction is enabled, include video file URLs and public video embeds such as YouTube, Vimeo, Wistia, Loom, and Vidyard.", "default": true }, "extractDocuments": { "title": "Extract documents", "type": "boolean", "description": "When media extraction is enabled, include document URLs such as PDF, DOCX, PPTX, XLSX, CSV, and text files.", "default": true }, "extractOtherMedia": { "title": "Extract other media", "type": "boolean", "description": "When media extraction is enabled, include audio, archive, and other recognized media file URLs.", "default": true }, "maxMediaPerDomain": { "title": "Max media assets per domain", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Maximum number of media asset URLs included in each domain output item.", "default": 100 }, "crawlSameDomainOnly": { "title": "Crawl same site host only", "type": "boolean", "description": "Restrict page crawling to the same normalized host as the input URL. For example, docs.example.com stays on docs.example.com.", "default": true }, "requestTimeoutSecs": { "title": "Request timeout", "minimum": 5, "maximum": 120, "type": "integer", "description": "Timeout per fetched page in seconds.", "default": 30 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional Apify Proxy configuration. Useful for geo-distributed public crawling when targets rate-limit datacenter traffic.", "default": { "useApifyProxy": 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 } } } } } } } } } }