{ "openapi": "3.0.1", "info": { "title": "Website Content Crawler", "description": "Website Content Crawler SD - Website Content Crawler is a web crawling tool that extracts the main content of every page of a website as clean Markdown and text, with title, language and metadata, for LLMs, RAG, vector databases and search indexes.", "version": "1.0", "x-build-id": "AkAn1bCP9EgP5Gojs" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/neuro-scraper~website-content-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-neuro-scraper-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/neuro-scraper~website-content-crawler/runs": { "post": { "operationId": "runs-sync-neuro-scraper-website-content-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/neuro-scraper~website-content-crawler/run-sync": { "post": { "operationId": "run-sync-neuro-scraper-website-content-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Pages where the crawl starts, e.g. https://crawlee.dev/python/docs/guides or https://example.com. Links are followed inside the crawl scope below.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPages": { "title": "Max pages", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Maximum number of pages saved to the dataset (one row per page).", "default": 20 }, "maxCrawlDepth": { "title": "Max crawl depth", "minimum": 0, "maximum": 1000, "type": "integer", "description": "How many links away from a start URL the crawler may go. 0 = only the start URLs.", "default": 5 }, "crawlScope": { "title": "Crawl scope", "enum": [ "startUrlPath", "sameDomain", "sameDomainAndSubdomains" ], "type": "string", "description": "Which links are followed. 'Under the start URL path' (default): https://site.com/docs/ only follows https://site.com/docs/...; start from the homepage to crawl the whole site. 'Same domain': any page on the start URL's host (www. ignored). 'Domain and subdomains': also blog.site.com, docs.site.com... Include URL globs replace this setting.", "default": "startUrlPath" }, "includeUrlGlobs": { "title": "Include URL globs", "type": "array", "description": "Only follow links matching one of these globs (replaces the crawl scope). ** = anything, * = anything except '/'. Example: https://crawlee.dev/python/docs/**", "items": { "type": "string" } }, "excludeUrlGlobs": { "title": "Exclude URL globs", "type": "array", "description": "Never follow links matching these globs. Example: https://crawlee.dev/**/api/** or **/tag/**", "items": { "type": "string" } }, "useSitemaps": { "title": "Also use the site's sitemaps", "type": "boolean", "description": "Read the sitemaps listed in robots.txt (or /sitemap.xml) and queue their in-scope URLs, so pages that are not linked from the start page are found too.", "default": false }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip pages that the site's robots.txt disallows and honour its Crawl-delay (capped at 10 s). Turn off only for sites you are allowed to crawl.", "default": true }, "htmlTransformer": { "title": "Main content extraction", "enum": [ "trafilatura", "readability", "none" ], "type": "string", "description": "trafilatura (default) keeps the article/documentation text and drops menus, footers and cookie banners; it falls back to readability, then to the whole cleaned page, when it finds too little. 'readability' = Mozilla Readability port. 'none' = the whole page minus navigation, header, footer and banners.", "default": "trafilatura" }, "saveMarkdown": { "title": "Save Markdown", "type": "boolean", "description": "Add the main content as Markdown (headings, lists, tables, code blocks) in the 'markdown' field.", "default": true }, "saveText": { "title": "Save plain text", "type": "boolean", "description": "Add the main content as plain text in the 'text' field.", "default": true }, "saveHtml": { "title": "Save cleaned HTML", "type": "boolean", "description": "Add the main content as cleaned HTML in the 'html' field.", "default": false }, "keepMarkdownLinks": { "title": "Keep links in Markdown", "type": "boolean", "description": "Keep hyperlinks as [text](url) in the Markdown. Off = link text only (less noise for LLMs).", "default": false }, "requestDelayMs": { "title": "Delay between requests to one site (ms)", "minimum": 0, "maximum": 60000, "type": "integer", "description": "Pause between two requests to the same host. Pages of one site are fetched one at a time.", "default": 1000 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many pages are processed at once across different hosts (one host is always fetched one page at a time).", "default": 2 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify Proxy (datacenter by default). Choose RESIDENTIAL for sites that block datacenter IPs.", "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 }, "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 } } } } } } } } } }