oxylabs/oxylabs-ai-studio-js

Structured data gathering from any website using AI-powered scraper, crawler, and browser automation. Scraping and crawling with natural language prompts. Equip your LLM agents with fresh data. AI Studio JS SDK for intelligent web data gathering.

What it solves

This SDK provides a streamlined way for developers to integrate AI-powered web data extraction and navigation tools into JavaScript applications. It eliminates the need to manually handle complex API requests for scraping, crawling, and browsing, providing a structured interface for extracting structured data from the web using AI.

How it works

The SDK acts as a wrapper around the Oxylabs AI Studio API, allowing users to perform several AI-driven tasks:

  • AI-Scraper: Extracts data from a specific URL using a provided JSON schema or a natural language prompt to generate a schema.
  • AI-Crawler: Discovers and extracts data from multiple pages across a site based on user instructions.
  • Browser-Agent: An AI agent that can navigate a website (e.g., clicking and inputting text) and extract data based on a user prompt.
  • AI-Search: Performs web searches and can return content from the results using optimized endpoints for either real-time or polling-based responses.
  • AI-Map: Maps a website's structure to discover relevant URLs based on keywords or prompts.

Who it’s for

Developers building applications that require automated, AI-driven web data collection, structured data extraction, and autonomous web navigation.

Highlights

  • Schema-driven extraction: Supports JSON, CSV, and Markdown output formats with custom JSON schemas for structured data.
  • Autonomous navigation: The Browser-Agent can perform actions like clicking and inputting text before extracting data.
  • Crawl and Map: Tools for discovering URLs and mapping site structures at scale.
  • Geo-location simulation: Ability to simulate requests from specific countries to bypass regional restrictions.
  • JavaScript rendering: Support for rendering JavaScript to handle dynamic content on target pages.

Related

  • Project
  • Project
  • Project
  • Project
  • Project