Direct the crawler to what matters
Crawl specific domains or URL patterns on demand. Seed URLs and watch them get indexed into the knowledge graph — companies, people, products, and locations extracted automatically.
Key capabilities
Domain-Targeted Crawling
Point the crawler at specific domains or URL patterns. Focus crawl effort on the sites most relevant to your research or monitoring needs.
Data Type Hunting
Hunt for specific entity types — companies, products, people, or locations. The crawler prioritizes pages likely to contain the data you need.
Seed URL Injection
Submit individual URLs or bulk lists directly into the crawl queue. Seeds get processed, entities extracted, and results appear in the knowledge graph.
Crawl Scope Control
Configure crawl depth, follow rules, and politeness settings. Control how deep and wide the crawler goes for each domain or URL pattern.
How it works
Submit seed URLs
Paste individual URLs or upload a list. Each seed enters the crawl queue and gets prioritized based on your topic configuration.
Configure scope
Set crawl depth, domain boundaries, and politeness rules. Choose which entity types to prioritize and how aggressively to follow links.
Watch entities appear
As pages are crawled, entities are extracted in real time. Monitor progress on the crawler dashboard and see new entities flow into the graph.
Start crawling on your terms
Submit seeds, set your scope, and watch the knowledge graph grow.