{ "openapi": "3.0.1", "info": { "title": "Website Content Crawler", "description": "Crawl any website and extract clean, LLM-ready Markdown for RAG pipelines, vector databases and AI agents. Boilerplate, navigation and cookie banners removed. No browser, no login.", "version": "0.1", "x-build-id": "b1eDhqgrjq9NWaOrl" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/myagizm~website-content-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-myagizm-website-content-crawler", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/myagizm~website-content-crawler/runs": { "post": { "operationId": "runs-sync-myagizm-website-content-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/myagizm~website-content-crawler/run-sync": { "post": { "operationId": "run-sync-myagizm-website-content-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 pages to start crawling from. The crawler follows links found on these pages, breadth-first, until it hits the page or depth limit.", "items": { "type": "string" } }, "maxPages": { "title": "Max pages", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Hard cap on how many pages are crawled and stored. You are billed per stored page, so this is also your budget cap.", "default": 50 }, "maxCrawlDepth": { "title": "Max crawl depth", "minimum": 0, "maximum": 20, "type": "integer", "description": "How many link hops away from the start URLs to go. 0 = only the start URLs themselves, 1 = start URLs plus pages they link to, and so on.", "default": 3 }, "crawlScope": { "title": "Crawl scope", "enum": [ "domain", "subdomains", "anywhere" ], "type": "string", "description": "Which links are allowed to be followed. 'Same domain' stays on the exact hostname, 'Include subdomains' also follows blog./docs. style subdomains, 'Anywhere' follows external links too (use with care).", "default": "domain" }, "includeUrlGlobs": { "title": "Include URL globs", "type": "array", "description": "If set, ONLY URLs matching one of these glob patterns are crawled, e.g. **/blog/** or https://example.com/docs/*. Leave empty to allow everything in scope.", "default": [], "items": { "type": "string" } }, "excludeUrlGlobs": { "title": "Exclude URL globs", "type": "array", "description": "URLs matching any of these glob patterns are skipped, e.g. **/tag/** or **/*.pdf. Applied after the include list.", "default": [], "items": { "type": "string" } }, "minWordCount": { "title": "Minimum word count", "minimum": 0, "type": "integer", "description": "Pages with fewer words than this after boilerplate removal are dropped and not billed. Useful for skipping login, tag and pagination stubs.", "default": 0 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Honour the site's robots.txt disallow rules. Strongly recommended; turn off only for sites you own or are authorised to crawl.", "default": true }, "outputFormat": { "title": "Output format", "enum": [ "markdown", "text", "html" ], "type": "string", "description": "Shape of the extracted page content. Markdown keeps headings, links and code blocks and is the best default for LLM/RAG pipelines. Text is plain prose. HTML returns the cleaned main-content HTML.", "default": "markdown" }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many pages are fetched in parallel. Lower this if the target site rate-limits you.", "default": 5 }, "includeLinks": { "title": "Include outgoing links", "type": "boolean", "description": "Add a links array to every item listing all URLs found on that page. Useful for building site maps or link graphs.", "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 } } }, "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 } } } } } } } } } }