Abstract
With the huge information on the Web, Web mining is a new research paradigm which draws great attention from many communities. At present there is no concrete agreement about Web
mining. It needs more discussion among the researchers in order to define what it is exactly it is. Meanwhile, the development of Web mining system will promote its research in turn. In this paper we present a preliminary discussion about Web mining, including the relationship between information mining and retrieval on the Web, he definition, the taxonomy and the function of Web mining. In addition, Web-TMS, a prototype of Web text mining system, was designed. HTML documents on the Web can be effectively mined using Web-TMS is a multi-agent system.