{ "openapi": "3.0.1", "info": { "title": "Website to Markdown Scraper", "description": "Crawl any website and turn its pages into clean Markdown — plus optional plain text, raw HTML and full-page screenshots. Built for LLM, RAG and AI training datasets.", "version": "1.0", "x-build-id": "P0s8LaRXvaq1U6RB1" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/receptional_blender~website-to-markdown-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-receptional_blender-website-to-markdown-scraper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/receptional_blender~website-to-markdown-scraper/runs": { "post": { "operationId": "runs-sync-receptional_blender-website-to-markdown-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/receptional_blender~website-to-markdown-scraper/run-sync": { "post": { "operationId": "run-sync-receptional_blender-website-to-markdown-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "type": "array", "description": "The web pages the scraper opens first. Each entry must be a full http:// or https:// address. Provide several to cover multiple pages or sites in one run. With \"Follow internal links\" enabled, the scraper also crawls same-domain links found on these pages, up to the page limit.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPages": { "title": "Maximum pages", "minimum": 1, "type": "integer", "description": "Upper bound on the total number of pages scraped in one run (across all start URLs). Begin with 1–5 to validate your settings, then raise it. Larger values crawl deeper but cost more compute and time. Most relevant when link-following is on.", "default": 5 }, "enqueue": { "title": "Follow internal links", "type": "boolean", "description": "When on, the scraper visits same-domain links discovered on each start page until the page limit is reached — the way to crawl a whole site. Turn it off to scrape only the exact URLs you supply (one record per URL).", "default": true }, "proxyConfig": { "title": "Proxy configuration", "type": "object", "description": "Proxy applied to every request. Keeping Apify Proxy on reduces blocking and rate limiting. You may pick specific groups or a country, or supply your own proxy URLs. Disabling proxy routes all traffic through a single datacenter IP, which many sites block.", "default": { "useApifyProxy": true } }, "screenshot": { "title": "Capture page screenshots", "type": "boolean", "description": "Save a full-page PNG of every page as a base64 data URI in the \"screenshot\" field. Handy for visual checks, but it enlarges each record and slows the run. Leave off if you only need text/Markdown.", "default": true }, "getText": { "title": "Include plain text", "type": "boolean", "description": "Also store each page's plain visible text in the \"textContent\" field. Markdown is produced either way — enable this only when you additionally want an unformatted text copy.", "default": false }, "getHtml": { "title": "Include raw HTML", "type": "boolean", "description": "Also store each page's full raw HTML in the \"htmlContent\" field. Useful when you want the original markup to parse yourself. This increases output size noticeably.", "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 } } }, "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 } } } } } } } } } }