{ "openapi": "3.0.1", "info": { "title": "Web Page Reader - Clean Text, Markdown and Links", "description": "Read public web pages into clean text and Markdown with links, metadata and JSON-LD. HTTP first, headless browser only when the page needs JavaScript. One result per URL, failures included.", "version": "0.0", "x-build-id": "YaLeJKAF9jUaeQsjd" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/leadproof~web-page-reader/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-leadproof-web-page-reader", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/leadproof~web-page-reader/runs": { "post": { "operationId": "runs-sync-leadproof-web-page-reader", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/leadproof~web-page-reader/run-sync": { "post": { "operationId": "run-sync-leadproof-web-page-reader", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "maxItems": 5000, "type": "array", "description": "Pages to read: strings or objects {\"url\": \"...\", \"id\": \"your-row-id\"}. Up to 5,000 per run. Repeated URLs are read once and returned once per row, each with its own inputId, and charged once. The example reads one static page and one JavaScript-rendered page." }, "renderMode": { "title": "Render mode", "enum": [ "auto", "http", "browser" ], "type": "string", "description": "auto: plain HTTP first, headless browser only when the page is a JavaScript shell, has almost no text, or answers with a bot challenge. http: never start a browser (cheapest). browser: always render in Chromium.", "default": "auto" }, "contentScope": { "title": "Content scope", "enum": [ "auto", "main", "page" ], "type": "string", "description": "auto: main content, widened to header/footer when the main region is nearly empty (short contact pages). main: main content only. page: whole page minus navigation and cookie banners (keeps footer contact details).", "default": "auto" }, "includeHtml": { "title": "Include HTML", "type": "boolean", "description": "Add the fetched or rendered HTML to each result, cut at the HTML size limit. Off by default: it makes results much larger.", "default": false }, "maxHtmlKb": { "title": "HTML size limit (KB)", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Maximum size of the html field when Include HTML is on.", "default": 1000 }, "maxLinks": { "title": "Maximum links per page", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Unique links kept per page (navigation included). 0 returns an empty list.", "default": 1000 }, "maxContentChars": { "title": "Text limit per page (characters)", "minimum": 1000, "maximum": 5000000, "type": "integer", "description": "text and markdown are each cut at this length (status partial, warning text_truncated). Records are also kept under the 9 MB dataset item limit.", "default": 1000000 }, "maxConcurrency": { "title": "Pages in parallel", "minimum": 1, "maximum": 20, "type": "integer", "description": "Pages read at the same time across all hosts.", "default": 5 }, "maxBrowserConcurrency": { "title": "Browser pages in parallel", "minimum": 1, "maximum": 5, "type": "integer", "description": "Browser tabs open at the same time. Each needs roughly 150-300 MB of memory.", "default": 2 }, "maxConcurrencyPerHost": { "title": "Parallel requests per host", "minimum": 1, "maximum": 8, "type": "integer", "description": "Politeness limit for pages on the same host name.", "default": 2 }, "hostDelayMs": { "title": "Delay between requests to one host (ms)", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Minimum time between request starts on the same host name.", "default": 250 }, "pageTimeoutSecs": { "title": "Page time limit (seconds)", "minimum": 5, "maximum": 180, "type": "integer", "description": "Wall-clock limit per page, HTTP and browser attempts included.", "default": 45 }, "maxPageSizeKb": { "title": "Page size limit (KB)", "minimum": 10, "maximum": 20000, "type": "integer", "description": "Larger documents are truncated and returned with status partial.", "default": 5000 }, "maxRedirects": { "title": "Maximum redirects", "minimum": 0, "maximum": 10, "type": "integer", "description": "Redirect hops per page (meta refresh included).", "default": 5 }, "minTextLength": { "title": "Browser fallback text threshold", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Auto mode: an HTTP result with less extracted text than this (in characters) is retried in the browser.", "default": 100 }, "browserFallbackOnChallenge": { "title": "Try the browser on bot challenges", "type": "boolean", "description": "Auto mode: when the HTTP response is a bot challenge page, try once in the browser. It does not solve CAPTCHAs.", "default": true }, "removeSelectors": { "title": "Extra CSS selectors to remove", "maxItems": 50, "type": "array", "description": "Elements removed before extraction, in addition to scripts, navigation and cookie banners.", "items": { "type": "string" } }, "acceptLanguage": { "title": "Accept-Language", "type": "string", "description": "Language preference sent to sites.", "default": "en-US,en;q=0.9" } } }, "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 } } } } } } } } } }