Built by Metorial, the integration platform for agentic AI.
Ask a natural language question about any webpage and receive an AI-generated answer as plain text. The AI reads the page content and provides a direct answer without requiring HTML parsing. Useful for extracting specific insights, facts, or summaries from webpage content.
Fetch the full rendered HTML of any webpage. Supports JavaScript rendering via headless Chromium, proxy rotation, geo-targeting, device emulation, and custom headers. Use POST mode to submit form data or interact with target page APIs. Optionally execute custom JavaScript on the page before retrieving the HTML.
Retrieve the current WebScraping.AI account status including remaining API credits, credit reset time, and concurrency limits. Useful for monitoring usage and ensuring sufficient credits before running scraping tasks.
Extract HTML from specific page elements using CSS selectors. Supports single or multiple selectors to retrieve targeted portions of a webpage. Useful when you only need specific parts of a page like headings, prices, navigation, article content, or any element identifiable by CSS selector.
Extract visible text content from any webpage, stripped of HTML markup. Returns clean text ideal for feeding into LLMs, text analysis, or content processing pipelines. Supports plain text, JSON (with title, description, and content), or XML output formats. Can optionally include links found on the page.
Extract specific data fields from any webpage as structured JSON using AI. Define field names and natural language descriptions of what to extract, and the AI interprets the page to return the values. Works well for product details, articles, profiles, contact info, and similar structured content.