{ "openapi": "3.0.1", "info": { "title": "Ai Web Intelligence", "description": "AI web crawler and scraper for clean Markdown, text, metadata, JSON-LD, PDFs, RAG chunks, screenshots, and structured web data. HTTP-first crawling with automatic browser fallback, built for AI agents, RAG pipelines, research, and knowledge bases.", "version": "0.0", "x-build-id": "RgcF7n4H7fCVsCezq" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/hakashi_katake~ai-web-intelligence/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-hakashi_katake-ai-web-intelligence", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/hakashi_katake~ai-web-intelligence/runs": { "post": { "operationId": "runs-sync-hakashi_katake-ai-web-intelligence", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/hakashi_katake~ai-web-intelligence/run-sync": { "post": { "operationId": "run-sync-hakashi_katake-ai-web-intelligence", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "One or more public HTTP(S) URLs where crawling starts.", "items": { "type": "object", "properties": { "url": { "title": "URL", "description": "Public HTTP(S) page where crawling starts.", "type": "string" } }, "required": [ "url" ] }, "default": [] }, "maxPages": { "title": "Maximum pages", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Hard cap on stored page records per run.", "default": 100 }, "maxDepth": { "title": "Maximum crawl depth", "minimum": 0, "maximum": 25, "type": "integer", "description": "Link distance from each start URL. Zero crawls only start URLs.", "default": 3 }, "includeSubdomains": { "title": "Include subdomains", "type": "boolean", "description": "Allow links on subdomains of the start URL’s registrable domain.", "default": false }, "includeUrlGlobs": { "title": "Include URL globs", "type": "array", "description": "Optional glob patterns that links must match.", "items": { "type": "string" }, "default": [] }, "excludeUrlGlobs": { "title": "Exclude URL globs", "type": "array", "description": "Optional glob patterns for URLs that must not be crawled.", "items": { "type": "string" }, "default": [] }, "discoverSitemaps": { "title": "Discover sitemap URLs", "type": "boolean", "description": "Read sitemap locations from robots.txt and common sitemap paths, then seed the crawl.", "default": false }, "useLlmsTxt": { "title": "Use llms.txt", "type": "boolean", "description": "Read root llms.txt files and enqueue linked public documentation URLs.", "default": false }, "renderingMode": { "title": "Rendering mode", "enum": [ "auto", "never", "always" ], "type": "string", "description": "Auto uses HTTP first and bounded browser fallback; never disables browser fallback; always renders every page in Playwright.", "default": "auto" }, "maxBrowserPages": { "title": "Maximum browser fallbacks", "minimum": 0, "maximum": 500, "type": "integer", "description": "Maximum pages that may be retried through Playwright in auto mode.", "default": 10 }, "includeHtml": { "title": "Include cleaned HTML", "type": "boolean", "description": "Include cleaned readable HTML. Disabled by default to reduce Dataset size.", "default": false }, "includeText": { "title": "Include plain text", "type": "boolean", "description": "Include normalized plain text extracted from the readable page content.", "default": true }, "includeMarkdown": { "title": "Include Markdown", "type": "boolean", "description": "Include structure-preserving Markdown extracted from the readable page content.", "default": true }, "includeMetadata": { "title": "Include metadata", "type": "boolean", "description": "Include title, description, author, language, canonical and date metadata.", "default": true }, "includeJsonLd": { "title": "Include JSON-LD", "type": "boolean", "description": "Parse valid JSON-LD script blocks when present.", "default": true }, "includeLinks": { "title": "Include links", "type": "boolean", "description": "Include normalized internal and external links found in readable content.", "default": true }, "includeImages": { "title": "Include image metadata", "type": "boolean", "description": "Include image URLs, alt text, title, width and height without downloading binaries.", "default": true }, "includeScreenshots": { "title": "Include screenshots", "type": "boolean", "description": "Save optional Playwright screenshots to Key-Value Store and return public URLs.", "default": false }, "screenshotFullPage": { "title": "Full-page screenshots", "type": "boolean", "description": "Capture full-page screenshots instead of the viewport.", "default": false }, "blockMedia": { "title": "Block media in browser mode", "type": "boolean", "description": "Abort image, font and media subrequests during browser rendering.", "default": true }, "blockAds": { "title": "Block common ad resources", "type": "boolean", "description": "Abort common advertising and analytics resource domains in browser mode.", "default": true }, "redactPii": { "title": "Redact obvious PII", "type": "boolean", "description": "Best-effort redaction of email, phone-like and SSN-shaped values in content and chunks.", "default": false }, "extractPdfText": { "title": "Extract PDF text", "type": "boolean", "description": "Extract text and basic metadata from PDF responses within the size limit.", "default": true }, "maxPdfBytes": { "title": "Maximum PDF size (bytes)", "minimum": 100000, "maximum": 50000000, "type": "integer", "description": "Hard limit for PDFs processed by the PDF parser.", "default": 10000000 }, "enableChunking": { "title": "Enable RAG chunks", "type": "boolean", "description": "Create token-based chunks from extracted text/Markdown.", "default": false }, "chunkSize": { "title": "Chunk size (tokens)", "minimum": 128, "maximum": 4096, "type": "integer", "description": "Target token count for optional RAG chunks.", "default": 512 }, "chunkOverlap": { "title": "Chunk overlap (tokens)", "minimum": 0, "maximum": 1024, "type": "integer", "description": "Token overlap between adjacent optional RAG chunks.", "default": 50 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip URLs disallowed by robots.txt. Enabled by default.", "default": true }, "sameDomainDelaySecs": { "title": "Same-domain delay (seconds)", "minimum": 0, "maximum": 30, "type": "number", "description": "Minimum delay between requests to the same domain.", "default": 0.25 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 180, "type": "integer", "description": "Maximum time allowed for one page request and extraction.", "default": 30 }, "maxRequestRetries": { "title": "Maximum request retries", "minimum": 0, "maximum": 5, "type": "integer", "description": "Bounded retries for transient HTTP or browser failures.", "default": 2 }, "maxResponseBytes": { "title": "Maximum response size (bytes)", "minimum": 100000, "maximum": 25000000, "type": "integer", "description": "Reject responses larger than this limit to prevent runaway memory/storage use.", "default": 5000000 }, "maxConcurrency": { "title": "HTTP concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum number of HTTP pages processed in parallel.", "default": 10 }, "snapshotStoreName": { "title": "Persistent snapshot store", "type": "string", "description": "Optional named Key-Value Store used for cross-run change detection.", "default": "" }, "enableChangeDetection": { "title": "Enable change detection", "type": "boolean", "description": "Compare content hashes with a prior snapshot and emit NEW/MODIFIED/REMOVED/UNCHANGED states.", "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 }, "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 } } } } } } } } } }