Universal Web Extractor V8
Pricing
from $0.00005 / actor start
Beginner-friendly universal web extractor that converts web pages into clean, structured data on the first run. Export instantly to CSV, Excel, or JSON — no coding required.
Pricing
from $0.00005 / actor start
Rating
5.0
(1)
Developer
Leoncio Jr Coronado
Actor stats
0
Bookmarked
18
Total users
4
Monthly active users
6 days ago
Last modified
Categories
Share
You can access the Universal Web Extractor V8 programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.0", "x-build-id": "lvLIqslGnY462ZKhu" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/motivational_nickel~my-actor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-motivational_nickel-my-actor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/motivational_nickel~my-actor/runs": { "post": { "operationId": "runs-sync-motivational_nickel-my-actor", "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/motivational_nickel~my-actor/run-sync": { "post": { "operationId": "run-sync-motivational_nickel-my-actor", "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": [ "start_urls" ], "properties": { "start_urls": { "title": "Start URLs (Required)", "type": "array", "description": "Web pages where extraction will begin.", "items": { "type": "string" }, "default": [ "https://quotes.toscrape.com/" ] }, "simple_mode": { "title": "Simple Mode (Recommended)", "type": "boolean", "description": "Beginner-friendly mode. Automatically extracts page title, URL, and main text. Disable this to use advanced custom fields.", "default": true }, "fields": { "title": "Advanced: Custom Fields (CSS selectors)", "type": "array", "description": "Advanced users only. Format: name=css_selector (e.g. price=.price). Works only when Simple Mode is disabled.", "items": { "type": "string" }, "default": [] }, "link_selector": { "title": "Links to Follow (Pagination / Internal)", "type": "string", "description": "CSS selector for links to follow. Leave empty to disable link crawling.", "default": "a[href*='page']" }, "max_requests": { "title": "Max Pages to Crawl", "minimum": 1, "type": "integer", "description": "Maximum number of pages to extract before stopping.", "default": 5 }, "max_depth": { "title": "Link Depth (0 = Only start pages)", "minimum": 0, "type": "integer", "description": "How deep the crawler will follow links.", "default": 1 }, "use_playwright": { "title": "Use Playwright (JavaScript-heavy sites only)", "type": "boolean", "description": "Enable only if the website relies heavily on JavaScript (React, Vue, etc.).", "default": false }, "save_html_snapshot": { "title": "Save HTML Snapshot", "type": "boolean", "description": "Save the full HTML of each page visited.", "default": false }, "save_screenshot": { "title": "Save Screenshot (Playwright only)", "type": "boolean", "description": "Save a screenshot for each page (requires Playwright).", "default": false }, "proxy": { "title": "Proxy Configuration", "type": "object", "description": "Configure proxy usage for web requests. Apify Proxy is enabled by default for stability.", "properties": { "useApifyProxy": { "title": "Use Apify Proxy", "type": "boolean", "description": "Enable Apify Proxy for reliable IP rotation." }, "apifyProxyCountry": { "title": "Proxy Country", "type": "string", "description": "Optional country code (US, GB, AU). Leave empty for automatic routing." } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Universal Web Extractor V8 from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: