{ "openapi": "3.0.1", "info": { "title": "Website Content Crawler Pro — Markdown for AI & RAG", "description": "Crawl any website into clean Markdown or text for LLMs, RAG and AI. HTTP + JS-browser modes, main-content (readability) extraction, sitemaps, URL glob filters, cookie-banner removal and CSS selectors. No login, no API key.", "version": "1.0", "x-build-id": "zfGsc1hvgaiav0FrF" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/hipersoft~web-content-crawler-pro/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-hipersoft-web-content-crawler-pro", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/hipersoft~web-content-crawler-pro/runs": { "post": { "operationId": "runs-sync-hipersoft-web-content-crawler-pro", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/hipersoft~web-content-crawler-pro/run-sync": { "post": { "operationId": "run-sync-hipersoft-web-content-crawler-pro", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "Start URLs", "type": "array", "description": "URLs to crawl. One per line.", "items": { "type": "string" } }, "startUrls": { "title": "Start URLs (request objects)", "type": "array", "description": "Advanced: start URLs as request objects.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "crawlerType": { "title": "Crawler type", "enum": [ "http", "browser" ], "type": "string", "description": "http = fast, no JavaScript. browser = full Chromium for JS/SPA sites.", "default": "http" }, "crawl": { "title": "Follow links", "type": "boolean", "description": "Crawl internal links from the start URLs (otherwise only the given URLs).", "default": false }, "maxCrawlPages": { "title": "Max pages", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Maximum pages to crawl in total.", "default": 50 }, "maxCrawlDepth": { "title": "Max depth", "minimum": 0, "type": "integer", "description": "How many link-hops from a start URL to follow.", "default": 3 }, "sameDomainOnly": { "title": "Same domain only", "type": "boolean", "description": "Only follow links on the same domain as the start URL.", "default": true }, "includeUrlGlobs": { "title": "Include URL globs", "type": "array", "description": "Only crawl URLs matching these glob patterns, e.g. https://site.com/docs/**.", "items": { "type": "string" } }, "excludeUrlGlobs": { "title": "Exclude URL globs", "type": "array", "description": "Skip URLs matching these glob patterns.", "items": { "type": "string" } }, "useSitemaps": { "title": "Use sitemaps", "type": "boolean", "description": "Seed the crawl from each site's sitemap.xml.", "default": false }, "saveMarkdown": { "title": "Save Markdown", "type": "boolean", "description": "Output clean Markdown (ideal for LLMs/RAG).", "default": true }, "saveText": { "title": "Save plain text", "type": "boolean", "description": "Output plain text.", "default": true }, "saveHtml": { "title": "Save HTML", "type": "boolean", "description": "Include the cleaned content HTML.", "default": false }, "saveLinks": { "title": "Save links", "type": "boolean", "description": "Include the list of links found on each page.", "default": false }, "htmlTransformer": { "title": "Content extraction", "enum": [ "readability", "none" ], "type": "string", "description": "readability = extract the main article (strip nav/ads). none = keep the whole page body.", "default": "readability" }, "removeElementsCssSelector": { "title": "Remove elements (CSS)", "type": "string", "description": "CSS selector of elements to strip before extraction (e.g. nav, footer, .ads)." }, "keepElementsCssSelector": { "title": "Keep only (CSS)", "type": "string", "description": "If set, keep only content inside this CSS selector." }, "removeCookieWarnings": { "title": "Remove cookie banners", "type": "boolean", "description": "Strip common cookie/consent banners.", "default": true }, "dynamicContentWaitSecs": { "title": "Dynamic content wait (s)", "minimum": 0, "maximum": 30, "type": "integer", "description": "Browser mode: wait this many seconds for JS content to load.", "default": 0 }, "waitForSelector": { "title": "Wait for selector", "type": "string", "description": "Browser mode: wait until this CSS selector appears." }, "textMaxChars": { "title": "Max chars per page", "minimum": 0, "type": "integer", "description": "Truncate each page's text/markdown to this many characters (0 = no limit).", "default": 0 }, "maxConcurrency": { "title": "Concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Max pages crawled in parallel.", "default": 10 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Proxy configuration.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } }