{ "openapi": "3.0.1", "info": { "title": "Web Page Markdown Scraper", "description": "Turn supplied public JavaScript-rendered page URLs into clean Markdown and text with source metadata and content hashes for recurring RAG ingestion.", "version": "0.1", "x-build-id": "aZp0Ui8dttn18NyCE" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/automation-lab~rendered-web-page-rag-context/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-automation-lab-rendered-web-page-rag-context", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/automation-lab~rendered-web-page-rag-context/runs": { "post": { "operationId": "runs-sync-automation-lab-rendered-web-page-rag-context", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/automation-lab~rendered-web-page-rag-context/run-sync": { "post": { "operationId": "run-sync-automation-lab-rendered-web-page-rag-context", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "pageUrls" ], "properties": { "pageUrls": { "title": "Public page URLs", "minItems": 1, "maxItems": 20, "type": "array", "description": "Supply 1–20 anonymous public page URL strings: HTTP on port 80 or HTTPS on port 443 only. Request objects, methods, headers, sessions and custom code are unsupported. Fragments are removed and identical normalized URLs deduplicated in order. Private/reserved networks, IPv6 and cross-protocol or nonstandard ports are rejected, including redirects and subresources.", "items": { "type": "string" } }, "maxItems": { "title": "Maximum pages", "minimum": 1, "maximum": 20, "type": "integer", "description": "Global maximum unique supplied pages to process, in input order after deduplication. Default 3, range 1–20; zero/unlimited is unsupported. No links are followed. A failed page stops the run; any saved rows are partial.", "default": 3 }, "pageTimeoutSecs": { "title": "Page attempt timeout (seconds)", "minimum": 5, "maximum": 15, "type": "integer", "description": "Maximum browser lifetime per attempt, default 15 seconds, range 5–15. A transient network/timeout/429/selected 5xx failure gets one fresh-context retry. Challenges, login and invalid content are not retried.", "default": 15 }, "maxContentChars": { "title": "Content character limit", "minimum": 1000, "maximum": 100000, "type": "integer", "description": "Maximum returned characters separately for Markdown and normalized text per page. Default 50000, range 1000–100000. Longer content is clipped with truncated=true. SHA-256 is calculated from the returned text, not the raw DOM or timestamp.", "default": 50000 }, "waitForSelector": { "title": "Optional rendered-content CSS selector", "type": "string", "description": "Optional CSS selector (maximum 300 characters) that must become visible before extraction; it controls readiness, not content selection. Without it, wait for bounded network idle and nonempty body. No scrolling or clicking is performed; content rendered later may be absent.", "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 }, "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 } } } } } } } } } }