{ "openapi": "3.0.1", "info": { "title": "SourceLens: Website to Markdown & JSON", "description": "Turn any public webpage into clean, LLM-ready Markdown or structured JSON with CSS selectors. Optional same-site crawling, robots.txt aware, pay only for pages that succeed.", "version": "1.1", "x-build-id": "kWh9H7VrCnC4cYdxJ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/onsq~sourcelens/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-onsq-sourcelens", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/onsq~sourcelens/runs": { "post": { "operationId": "runs-sync-onsq-sourcelens", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/onsq~sourcelens/run-sync": { "post": { "operationId": "run-sync-onsq-sourcelens", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "urls" ], "properties": { "urls": { "title": "URLs", "type": "array", "description": "Public webpages to extract, up to 1,000 per run. Missing https:// is added for you and #anchors are ignored.", "items": { "type": "string" } }, "mode": { "title": "Output", "enum": [ "markdown", "selectors" ], "type": "string", "description": "Markdown returns the main content of each page as clean Markdown. CSS selectors return only the fields you define below.", "default": "markdown" }, "fields": { "title": "Fields to extract (CSS selectors mode)", "type": "array", "description": "Each field needs a name and a CSS selector. Optional: attribute (text by default, html, href, src or any attribute name) and multiple (true returns every match as a list).", "items": { "type": "object" } }, "maxCrawlDepth": { "title": "Crawl depth", "minimum": 0, "maximum": 10, "type": "integer", "description": "0 extracts only the URLs above. 1 also follows links found on those pages, 2 follows links on those pages too, and so on. Crawling stays on the same website.", "default": 0 }, "maxCrawlPages": { "title": "Max pages discovered by crawling", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Upper limit on extra pages added by crawling, on top of your start URLs. Only used when crawl depth is above 0.", "default": 100 }, "includeUrlPattern": { "title": "Only follow links matching", "type": "string", "description": "Optional regular expression. Example: /blog/ follows only blog pages." }, "excludeUrlPattern": { "title": "Never follow links matching", "type": "string", "description": "Optional regular expression. Example: /(login|cart|tag)/" }, "maxChars": { "title": "Max Markdown characters per page", "minimum": 1000, "maximum": 500000, "type": "integer", "description": "Longer pages are cut off and marked truncated.", "default": 100000 }, "concurrency": { "title": "Parallel requests", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many pages to fetch at the same time.", "default": 5 }, "timeoutSeconds": { "title": "Page timeout", "minimum": 5, "maximum": 60, "type": "integer", "description": "Give up on a page after this many seconds. One automatic retry is made for timeouts and temporary server errors.", "default": 30 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip pages that the website's robots.txt asks crawlers not to visit.", "default": true } } }, "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 } } } } } } } } } }