{ "openapi": "3.0.1", "info": { "title": "Headless Browser HTML Scraper", "description": "Render any URL in a real headless browser and return the fully-rendered HTML, the page text, or a selected area by CSS selector. Scroll for lazy content, wait for elements, and capture screenshots. A browserless-style HTML API on Apify.", "version": "0.1", "x-build-id": "JB3gbz3xb8oq4vGJe" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/patel_dev_automation~browserless-html-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-patel_dev_automation-browserless-html-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/patel_dev_automation~browserless-html-scraper/runs": { "post": { "operationId": "runs-sync-patel_dev_automation-browserless-html-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/patel_dev_automation~browserless-html-scraper/run-sync": { "post": { "operationId": "run-sync-patel_dev_automation-browserless-html-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "urls" ], "properties": { "urls": { "title": "URLs", "type": "array", "description": "One or more URLs to open in a real headless browser and scrape. JavaScript is fully rendered.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "selector": { "title": "Selected area (CSS selector)", "type": "string", "description": "Optional. A CSS selector for the area you want to extract (like browserless /scrape). Every matching element is returned with its HTML, text, attributes, and position. Leave empty to just get the full page HTML." }, "scrollToBottom": { "title": "Scroll to bottom (load lazy content)", "type": "boolean", "description": "Scroll the page down with real wheel events to trigger infinite-scroll / lazy-loaded content before scraping.", "default": false }, "maxScrolls": { "title": "Max scroll rounds", "minimum": 1, "type": "integer", "description": "Maximum scroll iterations when 'Scroll to bottom' is on. Stops early when the page stops growing.", "default": 15 }, "waitForSelector": { "title": "Wait for selector", "type": "string", "description": "Optional. Wait until this CSS selector appears before scraping (up to 30s)." }, "waitUntil": { "title": "Wait until (page load event)", "enum": [ "domcontentloaded", "load", "networkidle" ], "type": "string", "description": "When to consider navigation finished.", "default": "domcontentloaded" }, "waitMs": { "title": "Extra wait (ms)", "minimum": 0, "type": "integer", "description": "Optional fixed wait after the page loads, in milliseconds (max 60000).", "default": 0 }, "blockResources": { "title": "Block resource types", "type": "array", "description": "Resource types to block to speed up loading and cut bandwidth. Blocking 'image'/'stylesheet' can break layout-dependent lazy scrolling on some sites.", "items": { "type": "string", "enum": [ "image", "media", "font", "stylesheet" ], "enumTitles": [ "Images", "Media (video/audio)", "Fonts", "Stylesheets (CSS)" ] }, "default": [ "media", "font" ] }, "returnFullHtml": { "title": "Return full page HTML", "type": "boolean", "description": "Include the full rendered page HTML in the output (like browserless /content).", "default": true }, "returnText": { "title": "Return page text", "type": "boolean", "description": "Include the page's visible text (innerText) in the output.", "default": true }, "includeScreenshot": { "title": "Capture full-page screenshot", "type": "boolean", "description": "Take a full-page JPEG screenshot, store it, and return its URL in the output.", "default": false }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy to route requests through. Apify Proxy (datacenter) by default; switch to Residential for bot-protected sites.", "default": { "useApifyProxy": 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 } } }, "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 } } } } } } } } } }