{ "openapi": "3.0.1", "info": { "title": "Website Intelligence API", "description": "Crawl any public website and turn it into AI-ready intelligence. Extract screenshots, Markdown, HTML, metadata, links, PDFs, compliance evidence, RAG chunks, and structured JSON for sales research, audits, website snapshots, and automation.", "version": "0.0", "x-build-id": "cJ2iHjsBVrcxZgaAn" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ladra~Website-Intelligence-API/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ladra-Website-Intelligence-API", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/ladra~Website-Intelligence-API/runs": { "post": { "operationId": "runs-sync-ladra-Website-Intelligence-API", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/ladra~Website-Intelligence-API/run-sync": { "post": { "operationId": "run-sync-ladra-Website-Intelligence-API", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrl": { "title": "Start URL", "type": "string", "description": "The website URL where crawling starts. Legacy alias for url." }, "url": { "title": "URL", "type": "string", "description": "Website URL for the v2 extract API shape. If startUrl is omitted, this value is used." }, "intent": { "title": "Intent", "enum": [ "website_snapshot", "rag", "sales_research", "documentation", "ecommerce", "compliance", "website_clone" ], "type": "string", "description": "High-level extraction intent. Existing low-level options can still override this preset.", "default": "website_snapshot" }, "mode": { "title": "Mode", "enum": [ "snapshot", "rag", "ux_audit", "compliance_evidence" ], "type": "string", "description": "Snapshot mode controls defaults and summary outputs.", "default": "snapshot" }, "qualityMode": { "title": "Quality mode", "enum": [ "fast", "balanced", "complete" ], "type": "string", "description": "Preset for speed and output depth. Fast favors text outputs, balanced captures desktop screenshots, complete enables richer report defaults.", "default": "balanced" }, "crawlStrategy": { "title": "Crawl strategy", "enum": [ "auto", "sitemap", "links", "manual_only", "compliance_first" ], "type": "string", "description": "Controls how URLs are selected. Compliance-first prioritizes legal, security, trust, status, contact, and support pages.", "default": "auto" }, "maxPages": { "title": "Max pages", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum number of pages to capture.", "default": 25 }, "crawlDepth": { "title": "Crawl depth", "minimum": 0, "maximum": 10, "type": "integer", "description": "Maximum link depth from the start URL.", "default": 2 }, "sameDomainOnly": { "title": "Same domain only", "type": "boolean", "description": "Only crawl URLs on the start URL hostname.", "default": true }, "useSitemap": { "title": "Use sitemap", "type": "boolean", "description": "Seed the crawler with URLs from sitemap.xml when available.", "default": true }, "urls": { "title": "Manual URLs", "type": "array", "description": "Optional explicit URLs to capture in addition to the start URL. These bypass include URL patterns but still respect same-domain, asset, and robots filters.", "items": { "type": "string" } }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Read robots.txt, use its sitemap declarations, and skip disallowed URLs.", "default": true }, "maxSitemapUrls": { "title": "Max sitemap URLs", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Maximum URLs to collect from sitemap files before applying max page limits.", "default": 5000 }, "includeUrlPatterns": { "title": "Include URL patterns", "type": "array", "description": "Optional path or URL fragments that URLs must match.", "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Exclude URL patterns", "type": "array", "description": "Optional path or URL fragments to skip.", "items": { "type": "string" }, "default": [ "/cart", "/checkout", "/account", "/wp-admin" ] }, "includeScreenshots": { "title": "Include screenshots", "type": "boolean", "description": "Capture desktop full-page screenshots.", "default": true }, "includeMobileScreenshots": { "title": "Include mobile screenshots", "type": "boolean", "description": "Capture an additional mobile full-page screenshot.", "default": false }, "includeLightModeScreenshots": { "title": "Include light mode screenshots", "type": "boolean", "description": "Capture additional screenshots after forcing the page to light color scheme.", "default": false }, "includeDarkModeScreenshots": { "title": "Include dark mode screenshots", "type": "boolean", "description": "Capture additional screenshots after forcing the page to dark color scheme.", "default": false }, "screenshotFullPage": { "title": "Full-page screenshots", "type": "boolean", "description": "Capture full-page screenshots. Disable to capture only the visible viewport.", "default": true }, "includeScreenshotThumbnails": { "title": "Include screenshot thumbnails", "type": "boolean", "description": "Create viewport thumbnail images for each captured screenshot variant.", "default": false }, "includeHtml": { "title": "Include HTML", "type": "boolean", "description": "Save rendered page HTML files.", "default": false }, "includeMarkdown": { "title": "Include Markdown", "type": "boolean", "description": "Extract readable page content and save it as Markdown.", "default": true }, "includePdf": { "title": "Include PDF", "type": "boolean", "description": "Capture each page as a PDF when supported.", "default": false }, "includeMetadata": { "title": "Include metadata", "type": "boolean", "description": "Extract titles, descriptions, headings, links, CTAs, hashes, and page type.", "default": true }, "includeRagChunks": { "title": "Include RAG chunks", "type": "boolean", "description": "Create simple AI-ready text chunks from Markdown.", "default": false }, "enableAiAnalysis": { "title": "Enable AI analysis", "type": "boolean", "description": "Run optional AI-style page analysis tasks such as webpage summaries and CTA highlighting.", "default": false }, "aiProvider": { "title": "AI provider", "enum": [ "heuristic", "openai" ], "type": "string", "description": "Choose heuristic local analysis or OpenAI Responses API analysis.", "default": "heuristic" }, "aiTasks": { "title": "AI tasks", "type": "array", "description": "AI tasks to run. Supported values: summarize_page, highlight_cta.", "items": { "type": "string" }, "default": [] }, "aiPrompt": { "title": "AI prompt", "type": "string", "description": "Optional natural-language prompt, for example: Highlight the CTA, or Summarize this webpage." }, "aiModel": { "title": "OpenAI model", "type": "string", "description": "OpenAI model used when AI provider is OpenAI.", "default": "gpt-5.5" }, "openaiApiKey": { "title": "OpenAI API key", "type": "string", "description": "Optional OpenAI API key. If omitted, the Actor uses the OPENAI_API_KEY environment variable." }, "aiMaxInputChars": { "title": "AI max input characters", "minimum": 1000, "maximum": 50000, "type": "integer", "description": "Maximum page text characters sent to the AI provider per page.", "default": 12000 }, "removeCookieBanners": { "title": "Remove cookie banners", "type": "boolean", "description": "Attempt to accept, reject, close, or remove common cookie consent overlays before capture.", "default": true }, "removePopups": { "title": "Remove popups", "type": "boolean", "description": "Attempt to close or remove common modal, popup, newsletter, and overlay elements before capture.", "default": true }, "detectBrokenLinks": { "title": "Detect broken links", "type": "boolean", "description": "Check links found on captured pages and report failed or HTTP 4xx/5xx links.", "default": false }, "checkExternalLinks": { "title": "Check external links", "type": "boolean", "description": "When broken-link detection is enabled, also check outbound external links.", "default": false }, "maxLinksToCheckPerPage": { "title": "Max links to check per page", "minimum": 0, "maximum": 500, "type": "integer", "description": "Caps broken-link checks per captured page.", "default": 50 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Requested maximum pages to crawl at the same time. The resource profile controls how strictly this is capped.", "default": 1 }, "resourceProfile": { "title": "Resource profile", "enum": [ "safe", "speed", "manual" ], "type": "string", "description": "Controls how aggressively the Actor manages memory and concurrency. Safe caps heavy runs conservatively, speed allows more concurrency, and manual honors maxConcurrency with warnings.", "default": "safe" }, "assetLoading": { "title": "Asset loading", "enum": [ "auto", "full", "block_heavy" ], "type": "string", "description": "Controls image, media, and font requests. Auto blocks heavy assets only for text-only runs, full loads all assets, and block heavy blocks them even if screenshots are enabled.", "default": "auto" }, "includeZipArchive": { "title": "Include ZIP archive", "type": "boolean", "description": "Create a ZIP archive containing generated screenshots, Markdown, JSON, CSV, and summary files.", "default": false }, "enableChangeDetection": { "title": "Enable change detection", "type": "boolean", "description": "Compare this run against a previous snapshot provided as JSON input or URL.", "default": false }, "previousSnapshot": { "title": "Previous snapshot JSON", "type": "object", "description": "Previous dataset export or object containing pages/items/capturedPages for hash-based comparison." }, "previousSnapshotUrl": { "title": "Previous snapshot URL", "type": "string", "description": "Optional URL returning previous snapshot JSON for hash-based comparison." }, "webhookUrl": { "title": "Webhook URL", "type": "string", "description": "Optional endpoint that receives a POST when the snapshot completes." }, "enableVisualDiff": { "title": "Enable visual diff", "type": "boolean", "description": "Compare current desktop screenshots against previous snapshot screenshot URLs.", "default": false }, "visualDiffThreshold": { "title": "Visual diff threshold", "minimum": 0, "maximum": 1, "type": "number", "description": "Pixelmatch threshold from 0 to 1. Lower values are more sensitive.", "default": 0.1 }, "includeAuditReport": { "title": "Include audit PDF report", "type": "boolean", "description": "Generate audit-report.html and audit-report.pdf summary files.", "default": false }, "detectCompliancePages": { "title": "Detect compliance pages", "type": "boolean", "description": "Classify privacy, legal, security, trust, and related pages.", "default": true }, "detectMissingPages": { "title": "Detect missing recommended pages", "type": "boolean", "description": "Create a missing-page checklist in compliance evidence mode.", "default": true }, "waitUntil": { "title": "Wait until", "enum": [ "load", "domcontentloaded", "networkidle" ], "type": "string", "description": "Page load state to wait for before capture.", "default": "networkidle" }, "advanced": { "title": "Advanced options", "type": "object", "description": "Optional lower-level overrides for intent presets, such as includePdf, includeScreenshots, waitUntil, resourceProfile, assetLoading, maxConcurrency, enableVisualDiff, and enableChangeDetection." } } }, "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 } } } } } } } } } }