{ "openapi": "3.0.1", "info": { "title": "Website to Markdown Crawler", "description": "Crawls a public website and saves clean Markdown for AI tools, docs and content audits. Same-site pages only, with robots.txt checked on every URL, heading-aware chunks, repeated boilerplate removed, and an optional change-only recrawl.", "version": "0.1", "x-build-id": "KAK84cHBdrhokl3MH" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/vizellie~website-to-markdown-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-vizellie-website-to-markdown-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/vizellie~website-to-markdown-crawler/runs": { "post": { "operationId": "runs-sync-vizellie-website-to-markdown-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/vizellie~website-to-markdown-crawler/run-sync": { "post": { "operationId": "run-sync-vizellie-website-to-markdown-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Public http or https pages to start from. The crawl stays on those hosts. Use a site you own, or a site whose robots.txt allows WebsiteToMarkdownCrawler. At most 10 start URLs. Private addresses are blocked.", "items": { "type": "string" } }, "maxDepth": { "title": "Max depth", "minimum": 0, "maximum": 5, "type": "integer", "description": "How many links away from a start URL to follow. 0 reads the start URLs only. The ceiling is 5.", "default": 2 }, "maxPages": { "title": "Max pages", "minimum": 1, "maximum": 50, "type": "integer", "description": "Most pages fetched in one run, from 1 to 50. The sample uses 10. URLs past the cap are not fetched and are not charged.", "default": 10 }, "includePatterns": { "title": "Include URL patterns", "type": "array", "description": "Optional patterns. When this list is not empty, a URL path must match one of them. Use * as a wildcard. The sample keeps the Python tutorial. robots.txt, sitemap.xml and llms.txt are still read.", "items": { "type": "string" } }, "excludePatterns": { "title": "Exclude URL patterns", "type": "array", "description": "Optional patterns. A matching URL is out of scope and is not charged. * is a wildcard.", "items": { "type": "string" } }, "concurrency": { "title": "Concurrency", "minimum": 1, "maximum": 4, "type": "integer", "description": "How many fetches to run at once, from 1 to 4. Requests to the same host are still spaced out, and a crawl-delay is honoured up to 5 seconds.", "default": 2 }, "chunkSize": { "title": "Chunk size", "minimum": 100, "maximum": 2000, "type": "integer", "description": "Target size of a chunk, in estimated tokens. The ceiling is 2000. A heading starts a new chunk when the current one is already full.", "default": 500 }, "chunkOverlap": { "title": "Chunk overlap", "minimum": 0, "maximum": 400, "type": "integer", "description": "Estimated tokens repeated at the start of the next chunk when a long section is split. The overlap is kept at or below half the chunk size.", "default": 40 }, "changesOnly": { "title": "Changes only", "type": "boolean", "description": "When on, compare this crawl with the snapshot in the state store and return only added, changed or removed pages. Unchanged pages are not charged. Leave this off for a full crawl. The default run does not open a named store.", "default": false }, "stateStoreName": { "title": "State store name", "type": "string", "description": "Named key-value store for the snapshot. Used only when Changes only is on. Letters, digits and hyphens. Leave empty to use website-markdown-state. If this token cannot open that store, the run uses the default store and still finishes." }, "extractPdfs": { "title": "PDF text", "type": "boolean", "description": "Also read linked PDF files on the same site when they contain a text layer. Scanned pages are skipped. Each file is capped at 2 MB.", "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 } } } } } } } } } }