{ "openapi": "3.0.1", "info": { "title": "Website Crawler - Site Pages to Markdown and Text", "description": "Crawl one public website within page, depth and time limits: clean text, Markdown, links and metadata per page, plus a coverage report. Private build under development.", "version": "0.0", "x-build-id": "Ute69lfhjtO3nQ8bu" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/leadproof~website-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-leadproof-website-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/leadproof~website-crawler/runs": { "post": { "operationId": "runs-sync-leadproof-website-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/leadproof~website-crawler/run-sync": { "post": { "operationId": "run-sync-leadproof-website-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "minItems": 1, "maxItems": 100, "type": "array", "description": "Where the crawl starts. The crawl stays on these hosts (www and the bare domain count as the same site). Add an optional id per URL to find its row in the output.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPages": { "title": "Maximum pages", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum page reads, including failed ones. The crawl stops scheduling at this number and reports how many discovered URLs were left.", "default": 50 }, "maxDepth": { "title": "Maximum link depth", "minimum": 0, "maximum": 50, "type": "integer", "description": "Link hops from a start URL (start = 0, pages from the sitemap = 1). 0 reads only the start URLs.", "default": 5 }, "includeSubdomains": { "title": "Include subdomains", "type": "boolean", "description": "Also crawl subdomains of each start host (for example blog.example.com when starting at example.com). Parent and sibling domains are never crawled.", "default": false }, "useSitemaps": { "title": "Use sitemaps", "type": "boolean", "description": "Also discover pages from the site's sitemaps (robots.txt Sitemap lines, else /sitemap.xml). Nested sitemap indexes are followed up to 3 levels.", "default": true }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Follow the site's robots.txt rules and Crawl-delay (RFC 9309). Turn off only for sites you own or may crawl regardless.", "default": true }, "includeUrlPatterns": { "title": "Only crawl URLs matching", "maxItems": 50, "type": "array", "description": "Glob patterns matched against full URLs. ** matches anything, * matches anything except /. Example: https://example.com/blog/**. Empty = every URL in scope. Start URLs are always read.", "default": [], "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Never crawl URLs matching", "maxItems": 50, "type": "array", "description": "Glob patterns for URLs to skip, same syntax. Example: https://example.com/tag/**.", "default": [], "items": { "type": "string" } }, "renderMode": { "title": "Rendering", "enum": [ "auto", "http", "browser" ], "type": "string", "description": "auto: read over HTTP and open a headless browser only when the page is a JavaScript shell, has almost no text or is a bot-challenge page. http: never use a browser (cheapest). browser: render every page (slowest, needs more memory).", "default": "auto" }, "maxConcurrency": { "title": "Concurrent page reads", "minimum": 1, "maximum": 20, "type": "integer", "description": "Pages read at the same time across all hosts.", "default": 5 }, "maxRequestsPerMinute": { "title": "Requests per minute per host", "minimum": 1, "maximum": 600, "type": "integer", "description": "Politeness limit per host (robots.txt, sitemaps and pages). A longer robots.txt Crawl-delay wins.", "default": 60 }, "maxCrawlSeconds": { "title": "Maximum crawl time (seconds)", "minimum": 30, "maximum": 86400, "type": "integer", "description": "Wall-clock budget. When it runs out no new page starts; pages already loading finish and the partial crawl is reported.", "default": 3600 }, "pageTimeoutSeconds": { "title": "Page timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Maximum time for one page read.", "default": 30 }, "maxPageSizeKb": { "title": "Maximum page size (KB)", "minimum": 100, "maximum": 20000, "type": "integer", "description": "Larger pages are cut at this size and marked partial.", "default": 5000 }, "maxUrlsPerPattern": { "title": "Maximum URLs per URL pattern", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Protects against calendars and filter combinations: URLs that differ only in numbers, dates, IDs or query values share a pattern, and each pattern gets at most this many URLs.", "default": 200 }, "maxDiscoveredUrls": { "title": "Maximum tracked URLs", "minimum": 100, "maximum": 20000, "type": "integer", "description": "Cap on distinct in-scope URLs the crawl keeps track of (queued, read or skipped). Further URLs are counted but not tracked.", "default": 5000 }, "maxSitemapUrls": { "title": "Maximum URLs taken from sitemaps", "minimum": 0, "maximum": 20000, "type": "integer", "description": "Cap on page URLs taken from sitemaps. 0 disables sitemaps.", "default": 5000 }, "maxSitemapFiles": { "title": "Maximum sitemap files", "minimum": 1, "maximum": 200, "type": "integer", "description": "Cap on sitemap files downloaded, indexes included.", "default": 20 }, "includeHtml": { "title": "Include raw HTML", "type": "boolean", "description": "Add the page HTML (up to 1 MB per page) to each item. Makes the dataset much larger.", "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 } } } } } } } } } }