{ "openapi": "3.0.1", "info": { "title": "Website Content Text Extractor", "description": "Extract visible text content from websites as structured JSON blocks. Supports multi-URL batch processing, header/footer/cookie exclusion, and optional form extraction. Perfect for content analysis and translation workflows.", "version": "0.0", "x-build-id": "vYoeWug3oc8rSVJSG" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/smart-digital~website-content-text-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-smart-digital-website-content-text-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/smart-digital~website-content-text-extractor/runs": { "post": { "operationId": "runs-sync-smart-digital-website-content-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/smart-digital~website-content-text-extractor/run-sync": { "post": { "operationId": "run-sync-smart-digital-website-content-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrl": { "title": "Start URL", "type": "string", "description": "Single URL to extract text from (useful for quick tests). You can also use startUrls for multi-page runs. Leave empty if you only use startUrls.", "default": "" }, "startUrls": { "title": "URL List (Multiple URLs)", "type": "array", "description": "Liste d'URLs supplémentaires à traiter en masse dans un seul run (une URL par ligne). Les doublons et lignes vides sont ignorés. Utilisez ce champ pour traiter plusieurs pages en une seule exécution.", "items": { "type": "string", "minLength": 1 }, "default": [] }, "viewportType": { "title": "Viewport Type", "enum": [ "desktop", "mobile", "tablet", "custom" ], "type": "string", "description": "Choose a predefined viewport size or use custom dimensions", "default": "desktop" }, "viewportWidth": { "title": "Viewport Width (Custom)", "minimum": 320, "maximum": 3840, "type": "integer", "description": "Custom viewport width in pixels (only used when Viewport Type is 'custom')", "default": 1920 }, "viewportHeight": { "title": "Viewport Height (Custom)", "minimum": 568, "maximum": 2160, "type": "integer", "description": "Custom viewport height in pixels (only used when Viewport Type is 'custom')", "default": 1080 }, "excludeHeader": { "title": "Exclude Header", "type": "boolean", "description": "Exclude header and navigation elements. Compatible with WordPress, Shopify, Webflow, Drupal, Joomla and most CMS platforms. If this doesn't work for your site, use Exclude Selectors manually.", "default": false }, "excludeFooter": { "title": "Exclude Footer", "type": "boolean", "description": "Exclude footer elements. Compatible with WordPress, Shopify, Webflow, Drupal, Joomla and most CMS platforms. If this doesn't work for your site, use Exclude Selectors manually.", "default": false }, "excludeCookies": { "title": "Exclude Cookie Banners", "type": "boolean", "description": "Exclude cookie consent banners and GDPR notices. Compatible with Cookiebot, OneTrust, Iubenda and most cookie consent platforms.", "default": false }, "extractForms": { "title": "Extract Forms", "type": "boolean", "description": "Extract form content (labels, placeholders, values). When disabled, form elements are excluded from extraction. When enabled, form content is extracted including labels, placeholders, and input values.", "default": false }, "excludeSelectors": { "title": "Exclude Selectors", "type": "array", "description": "Additional CSS selectors for custom elements to exclude. Use this if Exclude Header/Footer options don't work for your site structure.", "items": { "type": "string" }, "default": [] }, "includeSelectors": { "title": "Include Selectors", "type": "array", "description": "CSS selectors to specifically include. If empty, all visible text is extracted.", "items": { "type": "string" }, "default": [] }, "minTextLength": { "title": "Minimum Text Length", "minimum": 0, "type": "integer", "description": "Minimum character length for text blocks to be included (default: 3)", "default": 3 }, "deduplicate": { "title": "Deduplicate Text", "type": "boolean", "description": "Remove duplicate text blocks (default: true)", "default": true }, "waitForSelector": { "title": "Wait For Selector", "type": "string", "description": "Optional CSS selector to wait for before extraction (e.g., '.main-content')", "default": "" }, "waitTimeout": { "title": "Wait Timeout", "minimum": 1000, "type": "integer", "description": "Timeout in milliseconds for waiting for selector (default: 30000)", "default": 30000 }, "removeEmptyBlocks": { "title": "Remove Empty Blocks", "type": "boolean", "description": "Remove empty or whitespace-only text blocks (default: true)", "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 } } }, "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 } } } } } } } } } }