{ "openapi": "3.0.1", "info": { "title": "Website Content Crawler (Anti-Bot) - $1.20 / 1000 Pages", "description": "Crawl any website, even behind Cloudflare, DataDome, PerimeterX or Akamai, and get clean Markdown and text of every page for LLMs, RAG and AI agents. Main-content extraction, URL globs, sitemaps, depth and page limits. $1.20 per 1000 pages; failed pages are free.", "version": "0.1", "x-build-id": "Bfk45HtYmSt7JpfjF" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapeunblocker~website-content-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapeunblocker-website-content-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/scrapeunblocker~website-content-crawler/runs": { "post": { "operationId": "runs-sync-scrapeunblocker-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/scrapeunblocker~website-content-crawler/run-sync": { "post": { "operationId": "run-sync-scrapeunblocker-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", "properties": { "startUrls": { "title": "Start URLs", "type": "array", "description": "One or more URLs to start crawling from. By default the crawler follows links to pages under the start URL's path only: https://example.com/docs/ crawls /docs/... and nothing else on the site.", "default": [ { "url": "https://docs.python.org/3/tutorial/" } ], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxCrawlPages": { "title": "Max pages", "minimum": 1, "maximum": 100000, "type": "integer", "description": "The most pages to load in this run, start URLs included. Pages that fail are counted but not billed.", "default": 100 }, "maxCrawlDepth": { "title": "Max crawling depth", "minimum": 0, "type": "integer", "description": "How many links away from a start URL to go. 0 = only the start URLs, 1 = start URLs and the pages they link to.", "default": 20 }, "useSitemaps": { "title": "Load URLs from sitemaps", "type": "boolean", "description": "Also read the site's sitemap (robots.txt Sitemap entries, else /sitemap.xml) and add its URLs that fall in the crawl scope. Finds pages that are not linked from the start URL.", "default": false }, "includeUrlGlobs": { "title": "Include URL patterns (globs)", "type": "array", "description": "Crawl only links matching these patterns, e.g. https://example.com/blog/**. Setting this replaces the default rule of staying under the start URL's path. ** matches anything, * anything within one path segment.", "default": [], "items": { "type": "object", "required": [ "glob" ], "properties": { "glob": { "type": "string", "title": "Glob of a web page" } } } }, "excludeUrlGlobs": { "title": "Exclude URL patterns (globs)", "type": "array", "description": "Never crawl links matching these patterns, e.g. https://example.com/**/tag/** or **?page=*.", "default": [], "items": { "type": "object", "required": [ "glob" ], "properties": { "glob": { "type": "string", "title": "Glob of a web page" } } } }, "keepUrlFragments": { "title": "URL #fragments identify unique pages", "type": "boolean", "description": "Treat page.html#a and page.html#b as different pages. Leave off unless the site is a single-page app routed by #fragments.", "default": false }, "ignoreCanonicalUrl": { "title": "Ignore canonical URLs", "type": "boolean", "description": "By default a page whose canonical URL was already crawled is skipped as a duplicate (not billed). Turn this on if the site sets one canonical URL for many different pages.", "default": false }, "outputFormats": { "title": "Output formats", "type": "array", "description": "What to save for every page: Markdown (headings, lists, tables, links, code blocks), plain text, and/or the cleaned HTML of the content.", "items": { "type": "string", "enum": [ "markdown", "text", "html" ], "enumTitles": [ "Markdown", "Plain text", "Cleaned HTML" ] }, "default": [ "markdown", "text" ] }, "htmlTransformer": { "title": "Content extraction", "enum": [ "readableText", "none" ], "type": "string", "description": "Main content keeps the article or documentation body and drops menus, sidebars and footers. Whole page keeps everything except the removed elements.", "default": "readableText" }, "removeElementsCssSelector": { "title": "Remove HTML elements (CSS selector)", "type": "string", "description": "Elements to delete before the content is extracted, e.g. nav, footer, .sidebar, #comments.", "default": "nav, footer, script, style, noscript, svg, img[src^='data:'],\n[role=\"alert\"],\n[role=\"banner\"],\n[role=\"dialog\"],\n[role=\"alertdialog\"],\n[role=\"region\"][aria-label*=\"skip\" i],\n[aria-modal=\"true\"]" }, "keepElementsCssSelector": { "title": "Keep only HTML elements (CSS selector)", "type": "string", "description": "Optional: keep only the elements matching this selector, e.g. article or .post-content. Pages where nothing matches are kept whole." }, "removeCookieWarnings": { "title": "Remove cookie warnings", "type": "boolean", "description": "Drop cookie consent banners (OneTrust, Cookiebot, Usercentrics, Didomi, Quantcast and common generic ones) from the content.", "default": true }, "waitForSelector": { "title": "Wait for selector", "type": "string", "description": "Optional CSS selector to wait for before the page is captured (up to 15 s), for pages that load their content with JavaScript, e.g. .article-body." }, "proxyCountry": { "title": "Proxy country", "type": "string", "description": "Optional exit-IP country (ISO-2, e.g. US, DE) for sites that show different content by country. Leave empty: the exit is chosen automatically, which is the most reliable." }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many pages to load at the same time (1-10). Lower it for small sites that slow down under load.", "default": 5 }, "requestTimeoutSecs": { "title": "Page request timeout", "minimum": 30, "maximum": 200, "type": "integer", "description": "How long to wait for one page. Most pages take a few seconds; pages behind a hard anti-bot challenge can take a minute or more.", "default": 150 }, "maxRequestRetries": { "title": "Max retries", "minimum": 0, "maximum": 5, "type": "integer", "description": "How many times to retry a page after a server error or timeout. Pages that do not exist (404) are not retried.", "default": 2 } } }, "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 } } } } } } } } } }