The Internet consists of web sites that employ different kinds of structures as the backbone of their build-up. However, users are browsing the web according to its content, regardless of the structure. In this paper we discuss the possibilities of applying ontologies in exploring the web sites’ structures and usage for producing viewing recommendations for the visitors. A special log system for capturing access data is introduced as well as techniques applied for data mining. Ontology of user profiles is constructed by exploiting the user locality model. Keywords. Web mining, web log, web ontology, recommender systems.