Universal Web Scraper - Extract Any URL
Pricing
$30.00 / 1,000 web scrape results
Pay-per-result web scraper with JS rendering, CSS selector / XPath / regex extraction, schema validation, retry on failure. Use for product catalogs, competitor pricing, news aggregation, lead generation. Fast (<2s/page), respects robots.txt by default.
You can access the Universal Web Scraper - Extract Any URL programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "1.0", "x-build-id": "Vq3oc9mhkcDnln8wG" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/lazymac~web-scraper-toolkit/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-lazymac-web-scraper-toolkit", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/lazymac~web-scraper-toolkit/runs": { "post": { "operationId": "runs-sync-lazymac-web-scraper-toolkit", "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/lazymac~web-scraper-toolkit/run-sync": { "post": { "operationId": "run-sync-lazymac-web-scraper-toolkit", "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 to Scrape", "type": "array", "description": "JSON array of URLs to scrape (maximum 10 per run). Each URL must be publicly accessible. Example: [\"https://example.com\", \"https://github.com\"]. Each URL is processed independently — if one fails, the others still succeed." }, "mode": { "title": "Extraction Mode", "enum": [ "full", "metadata", "links", "headlines", "images", "tables", "text", "custom" ], "type": "string", "description": "What data to extract from each page. 'full' returns metadata + headlines + links + images + tables. 'metadata' returns title, description, OG tags, canonical, language. 'links' returns all unique links with anchor text. 'headlines' returns H1, H2, H3 headings. 'images' returns all images with alt text. 'tables' parses HTML tables into structured rows. 'text' returns clean body text (no scripts/styles/nav/footer). 'custom' extracts elements matching a CSS selector.", "default": "full" }, "selector": { "title": "CSS Selector (for Custom Mode)", "type": "string", "description": "CSS selector for custom mode extraction. Supports all standard CSS selectors: element (div, p), class (.class-name), ID (#id), attribute ([href]), combinators (div > p, ul li), pseudo-classes (:first-child, :nth-of-type(2)). Only used when mode is 'custom'. Examples: '.article-title', '#main-content p', 'table.data-table tr td'." }, "timeout": { "title": "Request Timeout (ms)", "minimum": 1000, "maximum": 60000, "type": "integer", "description": "Maximum time in milliseconds to wait for each URL to respond. Default is 15000 (15 seconds). Increase for slow servers or large pages. Each URL is timed independently.", "default": 15000 }, "maxLinksPerPage": { "title": "Max Links Per Page", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Maximum number of links to extract per page in 'links' and 'full' modes. Default is 50 for full mode, unlimited for links mode. Set a lower value to limit output size.", "default": 500 }, "maxImagesPerPage": { "title": "Max Images Per Page", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Maximum number of images to extract per page in 'images' and 'full' modes. Default is 20 for full mode, unlimited for images mode. Set a lower value to limit output size.", "default": 200 }, "userAgent": { "title": "Custom User-Agent", "type": "string", "description": "Custom User-Agent header for HTTP requests. By default, uses a standard browser-like User-Agent. Set a custom value to simulate a specific bot or browser." }, "includeHtml": { "title": "Include Raw HTML", "type": "boolean", "description": "When enabled, includes the raw HTML of each matched element in custom mode, or the full page HTML in other modes. Useful for debugging. Disabled by default to keep output compact.", "default": false }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Apify proxy configuration. Use residential or datacenter proxies to avoid IP blocking. Format: {\"useApifyProxy\": true, \"apifyProxyGroups\": [\"RESIDENTIAL\"]}." } } }, "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 Scraper - Extract Any URL 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: