NAiOS IconNAiOS Logo
Back to catalog

Importar sitio web

naios-web-importv0.1.0

Scan a website in a controlled manner, guided by AI, and ingest pages, catalog, and media into your Knowledge Base

Productividadwebscrapingimportknowledge-basesitemapcrawlerNAiOS Team
Features
5
Version
0.1.0
License
free
Services

Description

Assistant that discovers the structure of a website (sitemap-first, respecting robots.txt), extracts pages, product/service catalog, and media, displays an editable summary of what was obtained, and correctly ingests it into your Knowledge Base. Discovery and extraction are deterministic whenever possible (sitemaps, JSON-LD/schema.org, readability); AI guides classification and mapping to collections, with a limited budget.

Features (5)

Sitemap-first discovery

robots.txt + sitemaps (with lastmod) before crawling; BFS crawl only as a fallback

AI that guides, not crawls

Deterministic whenever possible; budgeted AI only for classification and mapping

Catalog and services

Extracts products/services from JSON-LD/schema.org; AI only where there is no structured data

Editable summary

Review and adjust what is ingested, with deduplication against your KB

Re-synchronization

Saves the scan recipe and re-synchronizes only what has changed (by lastmod)