berrycrawl

Berrycrawl is a web data API designed for AI agents. It converts live web content into structured, agent-ready data through focused endpoints that handle scraping, crawling, searching, screenshot capture, document parsing, and data extraction.

The service addresses the challenges of turning raw web pages into usable information without the overhead of managing browsers, proxies, or custom parsers. Users can point to a website to retrieve its complete public brand profile, including logos, colors, fonts, and social links. Separate endpoints support scraping page content, capturing clean screenshots that remove cookie banners, overlays, and chat widgets while loading lazy content and stitching tall pages, and parsing documents. Site mapping and crawling features discover URLs from sitemaps and links, then execute bounded crawls with controls for depth, concurrency, deduplication, and webhooks. Web search capabilities use advanced operators to locate current sources and return relevant page content within the same workflow. Data extraction accepts a JSON schema or description to produce structured JSON output from single pages or batches of URLs, with support for asynchronous jobs.

It is delivered as a unified API with endpoints such as POST /api/v1/brand. The platform emphasizes one focused service for live web content, discovery, extraction, and company intelligence. New users receive 100 free credits with no card required.