{ "openapi": "3.0.1", "info": { "title": "Web Page Text Scraper – Clean Text & Links", "description": "Scrape any web page as clean text: the full visible prose, with scripts, navigation, headers, footers, booking widgets and cookie banners stripped out. Discover mode also returns every same-site link with its anchor text. JavaScript is rendered only when a page needs it.", "version": "0.1", "x-build-id": "5W2FFwIgFJIooTIZ0" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/simple.actors~page-text-reader/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-simple.actors-page-text-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/simple.actors~page-text-reader/runs": { "post": { "operationId": "runs-sync-simple.actors-page-text-reader", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/simple.actors~page-text-reader/run-sync": { "post": { "operationId": "run-sync-simple.actors-page-text-reader", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "startUrls": { "title": "Pages to read (URL editor)", "type": "array", "description": "The addresses to read, one per entry. In discover mode these are entry pages — usually a site's home page — and each row comes back with the page's text plus the same-site links found on it. In text mode they are the specific pages you want read.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "urls": { "title": "Pages to read (plain list, bare hosts OK)", "type": "array", "description": "The same thing as \"Pages to read\", as a plain list of addresses — easier to paste from your own records, and it accepts a bare host such as example.com. Both inputs are read; giving either one is enough.", "items": { "type": "string" } }, "mode": { "title": "Mode: discover links, or read text only", "enum": [ "discover", "text" ], "type": "string", "description": "\"discover\" reads the page and lists every link to the same site, each with the words that were clickable — use it first, to find out which of a site's pages is worth reading. \"text\" reads the pages you name and returns their text alone. The rows have the same shape either way; only \"links\" is added by discover.", "default": "discover" }, "renderJs": { "title": "When to run the page's JavaScript", "enum": [ "auto", "always", "never" ], "type": "string", "description": "\"auto\" reads the served HTML and only opens a browser when that HTML turns out not to hold the page — the right setting for almost everyone, and the cheapest. \"always\" opens a browser for every page: slower and dearer, worth it only if you know your sites build themselves in the browser. \"never\" refuses the browser entirely, so a site that needs one comes back as an error row rather than as an empty page.", "default": "auto" }, "maxTextLength": { "title": "Longest text to return (safety net)", "minimum": 500, "maximum": 50000, "type": "integer", "description": "A safety net, not a trim. Text is returned in full — a typical page runs 1,200 to 7,000 characters, far below this — and a page that does exceed it is cut at a word and marked with textTruncated: true, so a shortened answer can never pass for a complete one.", "default": 50000 }, "includeHtml": { "title": "Also return the raw HTML", "type": "boolean", "description": "Adds the page's own markup to each row as `html`, beside the cleaned text — for a caller who would rather run their own extractor. Off by default: the markup is often a hundred times the size of the text, which makes every row slow to read back for anyone who did not ask for it.", "default": false }, "proxy": { "title": "Proxy (datacenter is usually enough)", "type": "object", "description": "Defaults to Apify's datacenter proxy, which is included in every plan and is enough for almost every site. Switch to residential if a site answers you with a challenge page — every retry already lands on a different address, so a challenge that survives that is usually about the address pool rather than the request.", "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 } } } } } } } } } }