{ "openapi": "3.0.1", "info": { "title": "Website Markdown Crawler - Content & Change Tracking", "description": "Crawl public HTML within a website section. Export Markdown, text, source URLs and change hashes, with page limits and a URL-level coverage report.", "version": "1.0", "x-build-id": "b13LVcjRdL4Nt58tQ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/benthepythondev~website-markdown-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-benthepythondev-website-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/benthepythondev~website-markdown-crawler/runs": { "post": { "operationId": "runs-sync-benthepythondev-website-markdown-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/benthepythondev~website-markdown-crawler/run-sync": { "post": { "operationId": "run-sync-benthepythondev-website-markdown-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "One to twenty public HTTP(S) URL strings. Follow links only within these origins and path subtrees. Supply the final HTTPS URL when possible.", "default": [ "https://docs.python.org/3/tutorial/" ], "items": { "type": "string" } }, "maxPages": { "title": "Maximum pages to attempt", "minimum": 1, "maximum": 200, "type": "integer", "description": "Stop after this many queued page attempts, including skipped pages. Exported pages cannot exceed this limit. Default ten.", "default": 10 }, "maxDepth": { "title": "Maximum link depth", "minimum": 0, "maximum": 5, "type": "integer", "description": "Zero fetches only the supplied URLs; one also follows their links. Applies within each start URL subtree.", "default": 2 }, "contentSelector": { "title": "Content CSS selector", "type": "string", "description": "Optional CSS selector matching exactly one content element. Zero or multiple matches fail visibly. Otherwise selects main, a main role, a single article, or body.", "default": "" }, "excludeSelectors": { "title": "Remove these CSS selectors", "type": "array", "description": "Optional selectors to remove within the content, such as .cookie-banner. Navigation, scripts, styles, footers and sidebars are removed by default.", "default": [], "items": { "type": "string" } }, "previousHashes": { "title": "Previous URL hashes", "type": "object", "description": "Optional map of final page URLs to previous content_hash values. Matching pages still produce a charged metadata row with unchanged status and null Markdown/text. Keep the same extraction settings for comparisons.", "default": {} }, "renderJavaScript": { "title": "Render JavaScript", "type": "boolean", "description": "Run Chromium for public same-origin JavaScript content. Only checked GET resources are supplied; no login, cross-origin resources, forms, media, WebSockets or access challenges. HTTP remains the default.", "default": false }, "waitForSelector": { "title": "Wait for content selector", "type": "string", "description": "Optional CSS selector to wait up to ten seconds for after page load. Requires JavaScript rendering. Without it, capture one second after load. Use contentSelector separately to choose the exported content.", "default": "" } } }, "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 } } } } } } } } } }