Abstract
A large amount of on-line information resides on the invisible web - web pages generated dynamically from databases and other data sources hidden from the user. They are not indexed by a static URL but is generated when queries are asked via a search interface (we denote them as specialized search engines). In this paper we propose a system that is capable of automatically making use of these specialized engines to find information on the invisible web. We describe our overall architecture and process: from obtaining the search engines to picking the right engines to query. Experiments show that we can find information that is not found by the traditional search engines.