The rapid growth of the Internet and the increasing demand for accuracy of information retrieval have made it important to develop the focused crawler based on intelligence. This paper presents a framework for the ontology-based focused crawler. We use domain ontology for the description of topic, use key words automatic indexing techniques to gain subject of Web Pages, and define a function for relevance computation based on domain ontology. Experiment results show that the ontology-based focused crawler can enhance the accuracy for extraction of topical information from Web Pages.
展开▼